diff --git a/api/app/cache/__init__.py b/api/app/cache/__init__.py
index a79d4cb2..748ce8ae 100644
--- a/api/app/cache/__init__.py
+++ b/api/app/cache/__init__.py
@@ -2,10 +2,7 @@
 Cache 缓存模块
 
 提供各种缓存功能的统一入口
+注意：隐性记忆和情绪建议已迁移到数据库存储，不再使用Redis缓存
 """
-from .memory import EmotionMemoryCache, ImplicitMemoryCache
 
-__all__ = [
-    "EmotionMemoryCache",
-    "ImplicitMemoryCache",
-]
+__all__ = []
diff --git a/api/app/cache/memory/__init__.py b/api/app/cache/memory/__init__.py
index 4ada3153..35f45aad 100644
--- a/api/app/cache/memory/__init__.py
+++ b/api/app/cache/memory/__init__.py
@@ -2,11 +2,7 @@
 Memory 缓存模块
 
 提供记忆系统相关的缓存功能
+注意：隐性记忆和情绪建议已迁移到数据库存储，不再使用Redis缓存
 """
-from .emotion_memory import EmotionMemoryCache
-from .implicit_memory import ImplicitMemoryCache
 
-__all__ = [
-    "EmotionMemoryCache",
-    "ImplicitMemoryCache",
-]
+__all__ = []
diff --git a/api/app/cache/memory/emotion_memory.py b/api/app/cache/memory/emotion_memory.py
deleted file mode 100644
index 45ea90de..00000000
--- a/api/app/cache/memory/emotion_memory.py
+++ /dev/null
@@ -1,134 +0,0 @@
-"""
-Emotion Suggestions Cache
-
-情绪个性化建议缓存模块
-用于缓存用户的情绪个性化建议数据
-"""
-import json
-import logging
-from typing import Optional, Dict, Any
-from datetime import datetime
-
-from app.aioRedis import aio_redis
-
-logger = logging.getLogger(__name__)
-
-
-class EmotionMemoryCache:
-    """情绪建议缓存类"""
-    
-    # Key 前缀
-    PREFIX = "cache:memory:emotion_memory"
-    
-    @classmethod
-    def _get_key(cls, *parts: str) -> str:
-        """生成 Redis key
-        
-        Args:
-            *parts: key 的各个部分
-            
-        Returns:
-            完整的 Redis key
-        """
-        return ":".join([cls.PREFIX] + list(parts))
-    
-    @classmethod
-    async def set_emotion_suggestions(
-        cls,
-        user_id: str,
-        suggestions_data: Dict[str, Any],
-        expire: int = 86400
-    ) -> bool:
-        """设置用户情绪建议缓存
-        
-        Args:
-            user_id: 用户ID（end_user_id）
-            suggestions_data: 建议数据字典，包含：
-                - health_summary: 健康状态摘要
-                - suggestions: 建议列表
-                - generated_at: 生成时间（可选）
-            expire: 过期时间（秒），默认24小时（86400秒）
-            
-        Returns:
-            是否设置成功
-        """
-        try:
-            key = cls._get_key("suggestions", user_id)
-            
-            # 添加生成时间戳
-            if "generated_at" not in suggestions_data:
-                suggestions_data["generated_at"] = datetime.now().isoformat()
-            
-            # 添加缓存标记
-            suggestions_data["cached"] = True
-            
-            value = json.dumps(suggestions_data, ensure_ascii=False)
-            await aio_redis.set(key, value, ex=expire)
-            logger.info(f"设置情绪建议缓存成功: {key}, 过期时间: {expire}秒")
-            return True
-        except Exception as e:
-            logger.error(f"设置情绪建议缓存失败: {e}", exc_info=True)
-            return False
-    
-    @classmethod
-    async def get_emotion_suggestions(cls, user_id: str) -> Optional[Dict[str, Any]]:
-        """获取用户情绪建议缓存
-        
-        Args:
-            user_id: 用户ID（end_user_id）
-            
-        Returns:
-            建议数据字典，如果不存在或已过期返回 None
-        """
-        try:
-            key = cls._get_key("suggestions", user_id)
-            value = await aio_redis.get(key)
-            
-            if value:
-                data = json.loads(value)
-                logger.info(f"成功获取情绪建议缓存: {key}")
-                return data
-            
-            logger.info(f"情绪建议缓存不存在或已过期: {key}")
-            return None
-        except Exception as e:
-            logger.error(f"获取情绪建议缓存失败: {e}", exc_info=True)
-            return None
-    
-    @classmethod
-    async def delete_emotion_suggestions(cls, user_id: str) -> bool:
-        """删除用户情绪建议缓存
-        
-        Args:
-            user_id: 用户ID（end_user_id）
-            
-        Returns:
-            是否删除成功
-        """
-        try:
-            key = cls._get_key("suggestions", user_id)
-            result = await aio_redis.delete(key)
-            logger.info(f"删除情绪建议缓存: {key}, 结果: {result}")
-            return result > 0
-        except Exception as e:
-            logger.error(f"删除情绪建议缓存失败: {e}", exc_info=True)
-            return False
-    
-    @classmethod
-    async def get_suggestions_ttl(cls, user_id: str) -> int:
-        """获取情绪建议缓存的剩余过期时间
-        
-        Args:
-            user_id: 用户ID（end_user_id）
-            
-        Returns:
-            剩余秒数，-1表示永不过期，-2表示key不存在
-        """
-        try:
-            key = cls._get_key("suggestions", user_id)
-            ttl = await aio_redis.ttl(key)
-            logger.debug(f"情绪建议缓存TTL: {key} = {ttl}秒")
-            return ttl
-        except Exception as e:
-            logger.error(f"获取情绪建议缓存TTL失败: {e}")
-            return -2
diff --git a/api/app/cache/memory/implicit_memory.py b/api/app/cache/memory/implicit_memory.py
deleted file mode 100644
index 21f08e9a..00000000
--- a/api/app/cache/memory/implicit_memory.py
+++ /dev/null
@@ -1,136 +0,0 @@
-"""
-Implicit Memory Profile Cache
-
-隐式记忆用户画像缓存模块
-用于缓存用户的完整画像数据（偏好标签、四维画像、兴趣领域、行为习惯）
-"""
-import json
-import logging
-from typing import Optional, Dict, Any
-from datetime import datetime
-
-from app.aioRedis import aio_redis
-
-logger = logging.getLogger(__name__)
-
-
-class ImplicitMemoryCache:
-    """隐式记忆用户画像缓存类"""
-    
-    # Key 前缀
-    PREFIX = "cache:memory:implicit_memory"
-    
-    @classmethod
-    def _get_key(cls, *parts: str) -> str:
-        """生成 Redis key
-        
-        Args:
-            *parts: key 的各个部分
-            
-        Returns:
-            完整的 Redis key
-        """
-        return ":".join([cls.PREFIX] + list(parts))
-    
-    @classmethod
-    async def set_user_profile(
-        cls,
-        user_id: str,
-        profile_data: Dict[str, Any],
-        expire: int = 86400
-    ) -> bool:
-        """设置用户完整画像缓存
-        
-        Args:
-            user_id: 用户ID（end_user_id）
-            profile_data: 画像数据字典，包含：
-                - preferences: 偏好标签列表
-                - portrait: 四维画像对象
-                - interest_areas: 兴趣领域分布对象
-                - habits: 行为习惯列表
-                - generated_at: 生成时间（可选）
-            expire: 过期时间（秒），默认24小时（86400秒）
-            
-        Returns:
-            是否设置成功
-        """
-        try:
-            key = cls._get_key("profile", user_id)
-            
-            # 添加生成时间戳
-            if "generated_at" not in profile_data:
-                profile_data["generated_at"] = datetime.now().isoformat()
-            
-            # 添加缓存标记
-            profile_data["cached"] = True
-            
-            value = json.dumps(profile_data, ensure_ascii=False)
-            await aio_redis.set(key, value, ex=expire)
-            logger.info(f"设置用户画像缓存成功: {key}, 过期时间: {expire}秒")
-            return True
-        except Exception as e:
-            logger.error(f"设置用户画像缓存失败: {e}", exc_info=True)
-            return False
-    
-    @classmethod
-    async def get_user_profile(cls, user_id: str) -> Optional[Dict[str, Any]]:
-        """获取用户完整画像缓存
-        
-        Args:
-            user_id: 用户ID（end_user_id）
-            
-        Returns:
-            画像数据字典，如果不存在或已过期返回 None
-        """
-        try:
-            key = cls._get_key("profile", user_id)
-            value = await aio_redis.get(key)
-            
-            if value:
-                data = json.loads(value)
-                logger.info(f"成功获取用户画像缓存: {key}")
-                return data
-            
-            logger.info(f"用户画像缓存不存在或已过期: {key}")
-            return None
-        except Exception as e:
-            logger.error(f"获取用户画像缓存失败: {e}", exc_info=True)
-            return None
-    
-    @classmethod
-    async def delete_user_profile(cls, user_id: str) -> bool:
-        """删除用户完整画像缓存
-        
-        Args:
-            user_id: 用户ID（end_user_id）
-            
-        Returns:
-            是否删除成功
-        """
-        try:
-            key = cls._get_key("profile", user_id)
-            result = await aio_redis.delete(key)
-            logger.info(f"删除用户画像缓存: {key}, 结果: {result}")
-            return result > 0
-        except Exception as e:
-            logger.error(f"删除用户画像缓存失败: {e}", exc_info=True)
-            return False
-    
-    @classmethod
-    async def get_profile_ttl(cls, user_id: str) -> int:
-        """获取用户画像缓存的剩余过期时间
-        
-        Args:
-            user_id: 用户ID（end_user_id）
-            
-        Returns:
-            剩余秒数，-1表示永不过期，-2表示key不存在
-        """
-        try:
-            key = cls._get_key("profile", user_id)
-            ttl = await aio_redis.ttl(key)
-            logger.debug(f"用户画像缓存TTL: {key} = {ttl}秒")
-            return ttl
-        except Exception as e:
-            logger.error(f"获取用户画像缓存TTL失败: {e}")
-            return -2
diff --git a/api/app/celery_app.py b/api/app/celery_app.py
index 8ef44975..ba294651 100644
--- a/api/app/celery_app.py
+++ b/api/app/celery_app.py
@@ -4,6 +4,7 @@ from datetime import timedelta
 from urllib.parse import quote
 
 from celery import Celery
+from celery.schedules import crontab
 
 from app.core.config import settings
 
@@ -82,7 +83,8 @@ celery_app.conf.update(
         'app.tasks.workspace_reflection_task': {'queue': 'periodic_tasks'},
         'app.tasks.regenerate_memory_cache': {'queue': 'periodic_tasks'},
         'app.tasks.run_forgetting_cycle_task': {'queue': 'periodic_tasks'},
-        'app.controllers.memory_storage_controller.search_all': {'queue': 'periodic_tasks'},
+        'app.tasks.write_all_workspaces_memory_task': {'queue': 'periodic_tasks'},
+        'app.tasks.update_implicit_emotions_storage': {'queue': 'periodic_tasks'},
     },
 )
 
@@ -92,9 +94,12 @@ celery_app.autodiscover_tasks(['app'])
 # Celery Beat schedule for periodic tasks
 memory_increment_schedule = timedelta(hours=settings.MEMORY_INCREMENT_INTERVAL_HOURS)
 memory_cache_regeneration_schedule = timedelta(hours=settings.MEMORY_CACHE_REGENERATION_HOURS)
-# 这个30秒的设计不合理
-workspace_reflection_schedule = timedelta(seconds=30)  # 每30秒运行一次settings.REFLECTION_INTERVAL_TIME
-forgetting_cycle_schedule = timedelta(hours=24)  # 每24小时运行一次遗忘周期
+workspace_reflection_schedule = timedelta(seconds=settings.WORKSPACE_REFLECTION_INTERVAL_SECONDS)
+forgetting_cycle_schedule = timedelta(hours=settings.FORGETTING_CYCLE_INTERVAL_HOURS)
+implicit_emotions_update_schedule = crontab(
+    hour=settings.IMPLICIT_EMOTIONS_UPDATE_HOUR,
+    minute=settings.IMPLICIT_EMOTIONS_UPDATE_MINUTE,
+)
 
 #构建定时任务配置
 beat_schedule_config = {
@@ -115,16 +120,16 @@ beat_schedule_config = {
             "config_id": None,  # 使用默认配置，可以通过环境变量配置
         },
     },
+    "write-all-workspaces-memory": {
+        "task": "app.tasks.write_all_workspaces_memory_task",
+        "schedule": memory_increment_schedule,
+        "args": (),
+    },
+    "update-implicit-emotions-storage": {
+        "task": "app.tasks.update_implicit_emotions_storage",
+        "schedule": implicit_emotions_update_schedule,
+        "args": (),
+    },
 }
 
-#如果配置了默认工作空间ID，则添加记忆总量统计任务
-if settings.DEFAULT_WORKSPACE_ID:
-    beat_schedule_config["write-total-memory"] = {
-        "task": "app.controllers.memory_storage_controller.search_all",
-        "schedule": memory_increment_schedule,
-        "kwargs": {
-            "workspace_id": settings.DEFAULT_WORKSPACE_ID,
-        },
-    }
-
 celery_app.conf.beat_schedule = beat_schedule_config
diff --git a/api/app/controllers/emotion_controller.py b/api/app/controllers/emotion_controller.py
index eb2436d2..8cfc5014 100644
--- a/api/app/controllers/emotion_controller.py
+++ b/api/app/controllers/emotion_controller.py
@@ -208,14 +208,64 @@ async def get_emotion_health(
 
 
 
+# @router.post("/check-data", response_model=ApiResponse)
+# async def check_emotion_data_exists(
+#     request: EmotionSuggestionsRequest,
+#     db: Session = Depends(get_db),
+#     current_user: User = Depends(get_current_user),
+# ):
+#     """检查用户情绪建议数据是否存在
+
+#     Args:
+#         request: 包含 end_user_id
+#         db: 数据库会话
+#         current_user: 当前用户
+
+#     Returns:
+#         数据存在状态
+#     """
+#     try:
+#         api_logger.info(
+#             f"检查用户情绪建议数据是否存在: {request.end_user_id}",
+#             extra={"end_user_id": request.end_user_id}
+#         )
+
+#         # 从数据库获取建议
+#         data = await emotion_service.get_cached_suggestions(
+#             end_user_id=request.end_user_id,
+#             db=db
+#         )
+
+#         if data is None:
+#             api_logger.info(f"用户 {request.end_user_id} 的情绪建议数据不存在")
+#             return fail(
+#                 BizCode.NOT_FOUND,
+#                 "情绪建议数据不存在，请点击右上角刷新进行初始化",
+#                 {"exists": False}
+#             )
+
+#         api_logger.info(f"用户 {request.end_user_id} 的情绪建议数据存在")
+#         return success(data={"exists": True}, msg="情绪建议数据已存在")
+
+#     except Exception as e:
+#         api_logger.error(
+#             f"检查情绪建议数据失败: {str(e)}",
+#             extra={"end_user_id": request.end_user_id},
+#             exc_info=True
+#         )
+#         raise HTTPException(
+#             status_code=status.HTTP_500_INTERNAL_SERVER_ERROR,
+#             detail=f"检查情绪建议数据失败: {str(e)}"
+#         )
+
+
 @router.post("/suggestions", response_model=ApiResponse)
 async def get_emotion_suggestions(
     request: EmotionSuggestionsRequest,
-    language_type: str = Header(default=None, alias="X-Language-Type"),
     db: Session = Depends(get_db),
     current_user: User = Depends(get_current_user),
 ):
-    """获取个性化情绪建议（从缓存读取）
+    """获取个性化情绪建议（从数据库读取）
 
     Args:
         request: 包含 end_user_id 和可选的 config_id
@@ -223,77 +273,42 @@ async def get_emotion_suggestions(
         current_user: 当前用户
 
     Returns:
-        缓存的个性化情绪建议响应
+        存储的个性化情绪建议响应
     """
     try:
-        # 使用集中化的语言校验
-        language = get_language_from_header(language_type)
-        
         api_logger.info(
-            f"用户 {current_user.username} 请求获取个性化情绪建议（缓存）",
+            f"用户 {current_user.username} 请求获取个性化情绪建议",
             extra={
                 "end_user_id": request.end_user_id,
                 "config_id": request.config_id
             }
         )
 
-        # 从缓存获取建议
+        # 从数据库获取建议
         data = await emotion_service.get_cached_suggestions(
             end_user_id=request.end_user_id,
             db=db
         )
 
         if data is None:
-            # 缓存不存在或已过期，自动触发生成
             api_logger.info(
-                f"用户 {request.end_user_id} 的建议缓存不存在或已过期，自动生成新建议",
+                f"用户 {request.end_user_id} 的建议数据不存在",
                 extra={"end_user_id": request.end_user_id}
             )
-            try:
-                data = await emotion_service.generate_emotion_suggestions(
-                    end_user_id=request.end_user_id,
-                    db=db,
-                    language=language
-                )
-                # 保存到缓存
-                await emotion_service.save_suggestions_cache(
-                    end_user_id=request.end_user_id,
-                    suggestions_data=data,
-                    db=db,
-                    expires_hours=24
-                )
-            except (ValueError, KeyError) as gen_e:
-                # 预期内的业务异常：配置缺失、数据格式问题等
-                api_logger.warning(
-                    f"自动生成建议失败（业务异常）: {str(gen_e)}",
-                    extra={"end_user_id": request.end_user_id}
-                )
-                return fail(
-                    BizCode.NOT_FOUND,
-                    f"自动生成建议失败: {str(gen_e)}",
-                    ""
-                )
-            except Exception as gen_e:
-                # 非预期异常：记录完整 traceback 便于排查
-                api_logger.error(
-                    f"自动生成建议时发生未预期异常: {str(gen_e)}",
-                    extra={"end_user_id": request.end_user_id},
-                    exc_info=True
-                )
-                raise HTTPException(
-                    status_code=status.HTTP_500_INTERNAL_SERVER_ERROR,
-                    detail=f"生成建议时发生内部错误: {str(gen_e)}"
-                )
+            return success(
+                data={"exists": False},
+                msg="情绪建议数据不存在，请点击右上角刷新进行初始化"
+            )
 
         api_logger.info(
-            "个性化建议获取成功（缓存）",
+            "个性化建议获取成功",
             extra={
                 "end_user_id": request.end_user_id,
                 "suggestions_count": len(data.get("suggestions", []))
             }
         )
 
-        return success(data=data, msg="个性化建议获取成功（缓存）")
+        return success(data=data, msg="个性化建议获取成功")
 
     except Exception as e:
         api_logger.error(
@@ -314,7 +329,7 @@ async def generate_emotion_suggestions(
     db: Session = Depends(get_db),
     current_user: User = Depends(get_current_user),
 ):
-    """生成个性化情绪建议（调用LLM并缓存）
+    """生成个性化情绪建议（调用LLM并保存到数据库）
 
     Args:
         request: 包含 end_user_id
@@ -342,12 +357,11 @@ async def generate_emotion_suggestions(
             language=language
         )
 
-        # 保存到缓存
+        # 保存到数据库
         await emotion_service.save_suggestions_cache(
             end_user_id=request.end_user_id,
             suggestions_data=data,
-            db=db,
-            expires_hours=24
+            db=db
         )
 
         api_logger.info(
@@ -369,4 +383,4 @@ async def generate_emotion_suggestions(
         raise HTTPException(
             status_code=status.HTTP_500_INTERNAL_SERVER_ERROR,
             detail=f"生成个性化建议失败: {str(e)}"
-        )
+        )
\ No newline at end of file
diff --git a/api/app/controllers/implicit_memory_controller.py b/api/app/controllers/implicit_memory_controller.py
index 96e437d6..76a87c5f 100644
--- a/api/app/controllers/implicit_memory_controller.py
+++ b/api/app/controllers/implicit_memory_controller.py
@@ -122,6 +122,48 @@ def validate_confidence_threshold(threshold: float) -> None:
         raise ValueError("confidence_threshold must be between 0.0 and 1.0")
 
 
+@router.get("/check-data/{end_user_id}", response_model=ApiResponse)
+@cur_workspace_access_guard()
+async def check_user_data_exists(
+    end_user_id: str,
+    db: Session = Depends(get_db),
+    current_user: User = Depends(get_current_user)
+) -> ApiResponse:
+    """
+    检查用户画像数据是否存在
+    
+    Args:
+        end_user_id: 目标用户ID
+        
+    Returns:
+        数据存在状态
+    """
+    api_logger.info(f"检查用户画像数据是否存在: {end_user_id}")
+    
+    try:
+        # Validate inputs
+        validate_user_id(end_user_id)
+        
+        # Create service with user-specific config
+        service = ImplicitMemoryService(db=db, end_user_id=end_user_id)
+        
+        # Get cached profile
+        cached_profile = await service.get_cached_profile(end_user_id=end_user_id, db=db)
+        
+        if cached_profile is None:
+            api_logger.info(f"用户 {end_user_id} 的画像数据不存在")
+            return success(
+                data={"exists": False},
+                msg="画像数据不存在，请点击右上角刷新进行初始化"
+            )
+        
+        api_logger.info(f"用户 {end_user_id} 的画像数据存在")
+        return success(data={"exists": True}, msg="画像数据已存在")
+        
+    except Exception as e:
+        return handle_implicit_memory_error(e, "检查画像数据", end_user_id)
+
+
 @router.get("/preferences/{end_user_id}", response_model=ApiResponse)
 @cur_workspace_access_guard()
 async def get_preference_tags(
@@ -159,12 +201,8 @@ async def get_preference_tags(
         cached_profile = await service.get_cached_profile(end_user_id=end_user_id, db=db)
         
         if cached_profile is None:
-            api_logger.info(f"用户 {end_user_id} 的画像缓存不存在或已过期")
-            return fail(
-                BizCode.NOT_FOUND,
-                "画像缓存不存在或已过期，请右上角刷新生成新画像",
-                ""
-            )
+            api_logger.info(f"用户 {end_user_id} 的画像数据不存在")
+            return fail(BizCode.NOT_FOUND, "", "")
         
         # Extract preferences from cache
         preferences = cached_profile.get("preferences", [])
@@ -230,12 +268,8 @@ async def get_dimension_portrait(
         cached_profile = await service.get_cached_profile(end_user_id=end_user_id, db=db)
         
         if cached_profile is None:
-            api_logger.info(f"用户 {end_user_id} 的画像缓存不存在或已过期")
-            return fail(
-                BizCode.NOT_FOUND,
-                "画像缓存不存在或已过期，请右上角刷新生成新画像",
-                ""
-            )
+            api_logger.info(f"用户 {end_user_id} 的画像数据不存在")
+            return fail(BizCode.NOT_FOUND, "", "")
         
         # Extract portrait from cache
         portrait = cached_profile.get("portrait", {})
@@ -278,12 +312,8 @@ async def get_interest_area_distribution(
         cached_profile = await service.get_cached_profile(end_user_id=end_user_id, db=db)
         
         if cached_profile is None:
-            api_logger.info(f"用户 {end_user_id} 的画像缓存不存在或已过期")
-            return fail(
-                BizCode.NOT_FOUND,
-                "画像缓存不存在或已过期，请右上角刷新生成新画像",
-                ""
-            )
+            api_logger.info(f"用户 {end_user_id} 的画像数据不存在")
+            return fail(BizCode.NOT_FOUND, "", "")
         
         # Extract interest areas from cache
         interest_areas = cached_profile.get("interest_areas", {})
@@ -330,12 +360,8 @@ async def get_behavior_habits(
         cached_profile = await service.get_cached_profile(end_user_id=end_user_id, db=db)
         
         if cached_profile is None:
-            api_logger.info(f"用户 {end_user_id} 的画像缓存不存在或已过期")
-            return fail(
-                BizCode.NOT_FOUND,
-                "画像缓存不存在或已过期，请右上角刷新生成新画像",
-                ""
-            )
+            api_logger.info(f"用户 {end_user_id} 的画像数据不存在")
+            return fail(BizCode.NOT_FOUND, "", "")
         
         # Extract habits from cache
         habits = cached_profile.get("habits", [])
diff --git a/api/app/controllers/memory_agent_controller.py b/api/app/controllers/memory_agent_controller.py
index 0e632fcc..b88e65ff 100644
--- a/api/app/controllers/memory_agent_controller.py
+++ b/api/app/controllers/memory_agent_controller.py
@@ -633,12 +633,11 @@ async def get_knowledge_type_stats_api(
     current_user: User = Depends(get_current_user)
 ):
     """
-    统计当前空间下各知识库类型的数量，包含 General | Web | Third-party | Folder | memory。
+    统计当前空间下各知识库类型的数量，包含 General | Web | Third-party | Folder。
     会对缺失类型补 0，返回字典形式。
     可选按状态过滤。
     - 知识库类型根据当前用户的 current_workspace_id 过滤
-    - memory 是 Neo4j 中 Chunk 的数量，根据 end_user_id (end_user_id) 过滤
-    - 如果用户没有当前工作空间或未提供 end_user_id，对应的统计返回 0
+    - 如果用户没有当前工作空间，对应的统计返回 0
     """
     api_logger.info(f"Knowledge type stats requested for workspace_id: {current_user.current_workspace_id}, end_user_id: {end_user_id}")
     try:
diff --git a/api/app/controllers/memory_dashboard_controller.py b/api/app/controllers/memory_dashboard_controller.py
index 88684a39..475d184e 100644
--- a/api/app/controllers/memory_dashboard_controller.py
+++ b/api/app/controllers/memory_dashboard_controller.py
@@ -9,6 +9,7 @@ from app.schemas.response_schema import ApiResponse
 
 from app.services import memory_dashboard_service, memory_storage_service, workspace_service
 from app.services.memory_agent_service import get_end_users_connected_configs_batch
+from app.services.app_statistics_service import AppStatisticsService
 from app.core.logging_config import get_api_logger
 
 # 获取API专用日志器
@@ -469,6 +470,8 @@ async def get_chunk_insight(
 @router.get("/dashboard_data", response_model=ApiResponse)
 async def dashboard_data(
     end_user_id: Optional[str] = Query(None, description="可选的用户ID"),
+    start_date: Optional[int] = Query(None, description="开始时间戳（毫秒）"),
+    end_date: Optional[int] = Query(None, description="结束时间戳（毫秒）"),
     db: Session = Depends(get_db),
     current_user: User = Depends(get_current_user),
 ):
@@ -503,6 +506,15 @@ async def dashboard_data(
     workspace_id = current_user.current_workspace_id
     api_logger.info(f"用户 {current_user.username} 请求获取工作空间 {workspace_id} 的dashboard整合数据")
     
+    # 如果没有提供时间范围，默认使用最近30天
+    if start_date is None or end_date is None:
+        from datetime import datetime, timedelta
+        end_dt = datetime.now()
+        start_dt = end_dt - timedelta(days=30)
+        end_date = int(end_dt.timestamp() * 1000)
+        start_date = int(start_dt.timestamp() * 1000)
+        api_logger.info(f"使用默认时间范围: {start_dt} 到 {end_dt}")
+    
     # 获取 storage_type，如果为 None 则使用默认值
     storage_type = workspace_service.get_workspace_storage_type(
         db=db,
@@ -563,17 +575,22 @@ async def dashboard_data(
             except Exception as e:
                 api_logger.warning(f"获取知识库类型统计失败: {str(e)}")
             
-            # 3. 获取API调用增量（total_api_call，转换为整数）
+            # 3. 获取API调用统计（total_api_call）
             try:
-                api_increment = memory_dashboard_service.get_workspace_api_increment(
-                    db=db,
+                # 使用 AppStatisticsService 获取真实的API调用统计
+                app_stats_service = AppStatisticsService(db)
+                api_stats = app_stats_service.get_workspace_api_statistics(
                     workspace_id=workspace_id,
-                    current_user=current_user
+                    start_date=start_date,
+                    end_date=end_date
                 )
-                neo4j_data["total_api_call"] = api_increment
-                api_logger.info(f"成功获取API调用增量: {neo4j_data['total_api_call']}")
+                # 计算总调用次数
+                total_api_calls = sum(item.get("total_calls", 0) for item in api_stats)
+                neo4j_data["total_api_call"] = total_api_calls
+                api_logger.info(f"成功获取API调用统计: {neo4j_data['total_api_call']}")
             except Exception as e:
-                api_logger.warning(f"获取API调用增量失败: {str(e)}")
+                api_logger.error(f"获取API调用统计失败: {str(e)}")
+                neo4j_data["total_api_call"] = 0
             
             result["neo4j_data"] = neo4j_data
             api_logger.info("成功获取neo4j_data")
@@ -602,10 +619,23 @@ async def dashboard_data(
                 total_kb = memory_dashboard_service.get_rag_total_kb(db, current_user)
                 rag_data["total_knowledge"] = total_kb
                 
-                # total_api_call: 固定值
-                rag_data["total_api_call"] = 1024
+                # total_api_call: 使用 AppStatisticsService 获取真实的API调用统计
+                try:
+                    app_stats_service = AppStatisticsService(db)
+                    api_stats = app_stats_service.get_workspace_api_statistics(
+                        workspace_id=workspace_id,
+                        start_date=start_date,
+                        end_date=end_date
+                    )
+                    # 计算总调用次数
+                    total_api_calls = sum(item.get("total_calls", 0) for item in api_stats)
+                    rag_data["total_api_call"] = total_api_calls
+                    api_logger.info(f"成功获取RAG模式API调用统计: {rag_data['total_api_call']}")
+                except Exception as e:
+                    api_logger.warning(f"获取RAG模式API调用统计失败，使用默认值: {str(e)}")
+                    rag_data["total_api_call"] = 0
                 
-                api_logger.info(f"成功获取RAG相关数据: memory={total_chunk}, app={len(apps_orm)}, knowledge={total_kb}")
+                api_logger.info(f"成功获取RAG相关数据: memory={total_chunk}, app={len(apps_orm)}, knowledge={total_kb}, api_calls={rag_data['total_api_call']}")
             except Exception as e:
                 api_logger.warning(f"获取RAG相关数据失败: {str(e)}")
             
diff --git a/api/app/core/config.py b/api/app/core/config.py
index 3a0c97b4..7392d29a 100644
--- a/api/app/core/config.py
+++ b/api/app/core/config.py
@@ -202,13 +202,20 @@ class Settings:
     REFLECTION_INTERVAL_SECONDS: float = float(os.getenv("REFLECTION_INTERVAL_SECONDS", "300"))
     HEALTH_CHECK_SECONDS: float = float(os.getenv("HEALTH_CHECK_SECONDS", "600"))
     MEMORY_INCREMENT_INTERVAL_HOURS: float = float(os.getenv("MEMORY_INCREMENT_INTERVAL_HOURS", "24"))
-    DEFAULT_WORKSPACE_ID: Optional[str] = os.getenv("DEFAULT_WORKSPACE_ID", None)
     REFLECTION_INTERVAL_TIME: Optional[str] = int(os.getenv("REFLECTION_INTERVAL_TIME", 30))
 
     # Memory Cache Regeneration Configuration
     MEMORY_CACHE_REGENERATION_HOURS: int = int(os.getenv("MEMORY_CACHE_REGENERATION_HOURS", "24"))
 
-    # Memory Module Configuration (internal)
+    # Periodic Task Schedule Configuration
+    # workspace_reflection: 每隔多少秒执行一次
+    WORKSPACE_REFLECTION_INTERVAL_SECONDS: int = int(os.getenv("WORKSPACE_REFLECTION_INTERVAL_SECONDS", "30"))
+    # forgetting_cycle: 每隔多少小时执行一次
+    FORGETTING_CYCLE_INTERVAL_HOURS: int = int(os.getenv("FORGETTING_CYCLE_INTERVAL_HOURS", "24"))
+    # implicit_emotions_update: 每天几点执行（小时，0-23）
+    IMPLICIT_EMOTIONS_UPDATE_HOUR: int = int(os.getenv("IMPLICIT_EMOTIONS_UPDATE_HOUR", "2"))
+    # implicit_emotions_update: 每天几分执行（分钟，0-59）
+    IMPLICIT_EMOTIONS_UPDATE_MINUTE: int = int(os.getenv("IMPLICIT_EMOTIONS_UPDATE_MINUTE", "0"))    # Memory Module Configuration (internal)
     MEMORY_OUTPUT_DIR: str = os.getenv("MEMORY_OUTPUT_DIR", "logs/memory-output")
     MEMORY_CONFIG_DIR: str = os.getenv("MEMORY_CONFIG_DIR", "app/core/memory")
 
diff --git a/api/app/models/__init__.py b/api/app/models/__init__.py
index b1b723e9..c6098a6d 100644
--- a/api/app/models/__init__.py
+++ b/api/app/models/__init__.py
@@ -35,6 +35,7 @@ from .ontology_scene import OntologyScene
 from .ontology_class import OntologyClass
 from .ontology_scene import OntologyScene
 from .ontology_class import OntologyClass
+from .implicit_emotions_storage_model import ImplicitEmotionsStorage
 
 __all__ = [
     "Tenants",
@@ -90,5 +91,6 @@ __all__ = [
     "MemoryPerceptualModel",
     "ModelBase",
     "LoadBalanceStrategy",
-    "Skill"
+    "Skill",
+    "ImplicitEmotionsStorage"
 ]
diff --git a/api/app/models/implicit_emotions_storage_model.py b/api/app/models/implicit_emotions_storage_model.py
new file mode 100644
index 00000000..cf654950
--- /dev/null
+++ b/api/app/models/implicit_emotions_storage_model.py
@@ -0,0 +1,45 @@
+"""
+Implicit Emotions Storage Model
+
+数据库模型：存储用户的隐性记忆画像和情绪建议数据
+替代原有的Redis缓存方式
+"""
+import uuid
+from datetime import datetime
+from sqlalchemy import Column, String, Text, DateTime, Index
+from sqlalchemy.dialects.postgresql import UUID, JSONB
+from app.db import Base
+
+
+class ImplicitEmotionsStorage(Base):
+    """隐性记忆和情绪存储表"""
+    
+    __tablename__ = "implicit_emotions_storage"
+    
+    # 主键
+    id = Column(UUID(as_uuid=True), primary_key=True, default=uuid.uuid4, comment="主键ID")
+    
+    # 用户标识（unique=True会自动创建唯一索引）
+    end_user_id = Column(String(255), nullable=False, unique=True, comment="终端用户ID")
+    
+    # 隐性记忆画像数据（JSON格式）
+    implicit_profile = Column(JSONB, nullable=True, comment="隐性记忆用户画像数据")
+    
+    # 情绪建议数据（JSON格式）
+    emotion_suggestions = Column(JSONB, nullable=True, comment="情绪个性化建议数据")
+    
+    # 时间戳
+    created_at = Column(DateTime, nullable=False, default=datetime.utcnow, comment="创建时间")
+    updated_at = Column(DateTime, nullable=False, default=datetime.utcnow, onupdate=datetime.utcnow, comment="更新时间")
+    
+    # 数据生成时间（用于业务逻辑）
+    implicit_generated_at = Column(DateTime, nullable=True, comment="隐性记忆画像生成时间")
+    emotion_generated_at = Column(DateTime, nullable=True, comment="情绪建议生成时间")
+    
+    # 索引（只为updated_at创建索引，end_user_id的unique约束已自动创建索引）
+    __table_args__ = (
+        Index('idx_updated_at', 'updated_at'),
+    )
+    
+    def __repr__(self):
+        return f"<ImplicitEmotionsStorage(id={self.id}, end_user_id={self.end_user_id})>"
diff --git a/api/app/repositories/implicit_emotions_storage_repository.py b/api/app/repositories/implicit_emotions_storage_repository.py
new file mode 100644
index 00000000..97405ab6
--- /dev/null
+++ b/api/app/repositories/implicit_emotions_storage_repository.py
@@ -0,0 +1,169 @@
+"""
+Implicit Emotions Storage Repository
+
+数据访问层：处理隐性记忆和情绪数据的数据库操作
+事务由调用方控制，仓储层只使用 flush/refresh
+"""
+import logging
+from datetime import datetime, date, timezone, timedelta
+from typing import Optional, Generator
+from sqlalchemy.orm import Session
+from sqlalchemy import select, not_, exists
+
+from app.models.implicit_emotions_storage_model import ImplicitEmotionsStorage
+from app.models.end_user_model import EndUser
+
+logger = logging.getLogger(__name__)
+
+
+class ImplicitEmotionsStorageRepository:
+    """隐性记忆和情绪存储仓储类"""
+
+    def __init__(self, db: Session):
+        self.db = db
+
+    def get_by_end_user_id(self, end_user_id: str) -> Optional[ImplicitEmotionsStorage]:
+        """根据终端用户ID获取存储记录"""
+        try:
+            stmt = select(ImplicitEmotionsStorage).where(
+                ImplicitEmotionsStorage.end_user_id == end_user_id
+            )
+            return self.db.execute(stmt).scalar_one_or_none()
+        except Exception as e:
+            logger.error(f"获取用户存储记录失败: end_user_id={end_user_id}, error={e}")
+            return None
+
+    def create(self, end_user_id: str) -> ImplicitEmotionsStorage:
+        """创建新的存储记录（事务由调用方提交）"""
+        storage = ImplicitEmotionsStorage(
+            end_user_id=end_user_id,
+            created_at=datetime.utcnow(),
+            updated_at=datetime.utcnow()
+        )
+        self.db.add(storage)
+        self.db.flush()
+        self.db.refresh(storage)
+        logger.info(f"创建用户存储记录成功: end_user_id={end_user_id}")
+        return storage
+
+    def update_implicit_profile(
+        self,
+        end_user_id: str,
+        profile_data: dict
+    ) -> ImplicitEmotionsStorage:
+        """更新隐性记忆画像数据（事务由调用方提交）"""
+        storage = self.get_by_end_user_id(end_user_id)
+        if storage is None:
+            storage = self.create(end_user_id)
+
+        storage.implicit_profile = profile_data
+        storage.implicit_generated_at = datetime.utcnow()
+        storage.updated_at = datetime.utcnow()
+
+        self.db.flush()
+        self.db.refresh(storage)
+        logger.info(f"更新隐性记忆画像成功: end_user_id={end_user_id}")
+        return storage
+
+    def update_emotion_suggestions(
+        self,
+        end_user_id: str,
+        suggestions_data: dict
+    ) -> ImplicitEmotionsStorage:
+        """更新情绪建议数据（事务由调用方提交）"""
+        storage = self.get_by_end_user_id(end_user_id)
+        if storage is None:
+            storage = self.create(end_user_id)
+
+        storage.emotion_suggestions = suggestions_data
+        storage.emotion_generated_at = datetime.utcnow()
+        storage.updated_at = datetime.utcnow()
+
+        self.db.flush()
+        self.db.refresh(storage)
+        logger.info(f"更新情绪建议成功: end_user_id={end_user_id}")
+        return storage
+
+    def get_all_user_ids(self, batch_size: int = 100) -> Generator[str, None, None]:
+        """分批次获取所有已存储数据的用户ID（避免大数据量内存溢出）
+
+        Args:
+            batch_size: 每批次加载的数量，默认100
+
+        Yields:
+            用户ID字符串
+        """
+        offset = 0
+        while True:
+            try:
+                stmt = (
+                    select(ImplicitEmotionsStorage.end_user_id)
+                    .order_by(ImplicitEmotionsStorage.end_user_id)
+                    .limit(batch_size)
+                    .offset(offset)
+                )
+                batch = self.db.execute(stmt).scalars().all()
+                if not batch:
+                    break
+                yield from batch
+                offset += batch_size
+            except Exception as e:
+                logger.error(f"分批获取用户ID失败: offset={offset}, error={e}")
+                break
+
+    def get_new_user_ids_today(self, batch_size: int = 100) -> Generator[str, None, None]:
+        """分批次获取当天新增的、尚未初始化隐性记忆和情绪建议数据的用户ID
+
+        查询逻辑：end_users 表中 created_at 为今天，且在 implicit_emotions_storage 中没有对应记录。
+        没有对应记录意味着隐性记忆画像和情绪建议均未初始化，需要对这批用户执行首次初始化。
+        end_users.id（UUID）转为字符串后与 implicit_emotions_storage.end_user_id（String）对比。
+
+        Args:
+            batch_size: 每批次加载的数量，默认100
+
+        Yields:
+            用户ID字符串
+        """
+        from sqlalchemy import cast, String as SAString
+        CST = timezone(timedelta(hours=8))
+        now_cst = datetime.now(CST)
+        today_start = now_cst.replace(hour=0, minute=0, second=0, microsecond=0).astimezone(timezone.utc).replace(tzinfo=None)
+        tomorrow_start = today_start + timedelta(days=1)
+        offset = 0
+        while True:
+            try:
+                stmt = (
+                    select(EndUser.id)
+                    .where(
+                        EndUser.created_at >= today_start,
+                        EndUser.created_at < tomorrow_start,
+                        not_(
+                            exists(
+                                select(ImplicitEmotionsStorage.end_user_id).where(
+                                    ImplicitEmotionsStorage.end_user_id == cast(EndUser.id, SAString)
+                                )
+                            )
+                        )
+                    )
+                    .order_by(EndUser.id)
+                    .limit(batch_size)
+                    .offset(offset)
+                )
+                batch = self.db.execute(stmt).scalars().all()
+                if not batch:
+                    break
+                yield from (str(uid) for uid in batch)
+                offset += batch_size
+            except Exception as e:
+                logger.error(f"分批获取当天新增用户ID失败: offset={offset}, error={e}")
+                break
+
+    def delete_by_end_user_id(self, end_user_id: str) -> bool:
+        """删除用户的存储记录（事务由调用方提交）"""
+        storage = self.get_by_end_user_id(end_user_id)
+        if storage:
+            self.db.delete(storage)
+            self.db.flush()
+            logger.info(f"删除用户存储记录成功: end_user_id={end_user_id}")
+            return True
+        return False
diff --git a/api/app/services/emotion_analytics_service.py b/api/app/services/emotion_analytics_service.py
index 89e3cab9..c226348e 100644
--- a/api/app/services/emotion_analytics_service.py
+++ b/api/app/services/emotion_analytics_service.py
@@ -843,32 +843,33 @@ class EmotionAnalyticsService:
             end_user_id: str,
             db: Session,
     ) -> Optional[Dict[str, Any]]:
-        """从 Redis 缓存获取个性化情绪建议
+        """从数据库获取个性化情绪建议
 
         Args:
             end_user_id: 宿主ID（用户组ID）
-            db: 数据库会话（保留参数以保持接口兼容性）
+            db: 数据库会话
 
         Returns:
-            Dict: 缓存的建议数据，如果不存在或已过期返回 None
+            Dict: 存储的建议数据，如果不存在返回 None
         """
         try:
-            from app.cache.memory.emotion_memory import EmotionMemoryCache
+            from app.repositories.implicit_emotions_storage_repository import ImplicitEmotionsStorageRepository
 
-            logger.info(f"尝试从 Redis 缓存获取情绪建议: user={end_user_id}")
+            logger.info(f"尝试从数据库获取情绪建议: user={end_user_id}")
 
-            # 从 Redis 获取缓存
-            cached_data = await EmotionMemoryCache.get_emotion_suggestions(end_user_id)
+            # 从数据库获取存储记录
+            repo = ImplicitEmotionsStorageRepository(db)
+            storage = repo.get_by_end_user_id(end_user_id)
 
-            if cached_data is None:
-                logger.info(f"用户 {end_user_id} 的建议缓存不存在或已过期")
+            if storage is None or storage.emotion_suggestions is None:
+                logger.info(f"用户 {end_user_id} 的建议数据不存在")
                 return None
 
-            logger.info(f"成功从 Redis 缓存获取建议: user={end_user_id}")
-            return cached_data
+            logger.info(f"成功从数据库获取建议: user={end_user_id}")
+            return storage.emotion_suggestions
 
         except Exception as e:
-            logger.error(f"从 Redis 缓存获取建议失败: {str(e)}", exc_info=True)
+            logger.error(f"从数据库获取建议失败: {str(e)}", exc_info=True)
             return None
 
     async def save_suggestions_cache(
@@ -876,36 +877,27 @@ class EmotionAnalyticsService:
             end_user_id: str,
             suggestions_data: Dict[str, Any],
             db: Session,
-            expires_hours: int = 24
+            expires_hours: int = 24  # 参数保留以保持接口兼容性
     ) -> None:
-        """保存建议到 Redis 缓存
+        """保存建议到数据库
 
         Args:
             end_user_id: 宿主ID（用户组ID）
             suggestions_data: 建议数据
-            db: 数据库会话（保留参数以保持接口兼容性）
-            expires_hours: 过期时间（小时），默认24小时
+            db: 数据库会话
+            expires_hours: 保留参数（兼容性）
         """
         try:
-            from app.cache.memory.emotion_memory import EmotionMemoryCache
+            from app.repositories.implicit_emotions_storage_repository import ImplicitEmotionsStorageRepository
 
-            logger.info(f"保存建议到 Redis 缓存: user={end_user_id}, expires={expires_hours}小时")
+            logger.info(f"保存建议到数据库: user={end_user_id}")
 
-            # 计算过期时间（秒）
-            expire_seconds = expires_hours * 3600
+            repo = ImplicitEmotionsStorageRepository(db)
+            repo.update_emotion_suggestions(end_user_id, suggestions_data)
+            db.commit()
 
-            # 保存到 Redis
-            success = await EmotionMemoryCache.set_emotion_suggestions(
-                user_id=end_user_id,
-                suggestions_data=suggestions_data,
-                expire=expire_seconds
-            )
-
-            if success:
-                logger.info(f"建议缓存保存成功: user={end_user_id}")
-            else:
-                logger.warning(f"建议缓存保存失败: user={end_user_id}")
+            logger.info(f"建议保存成功: user={end_user_id}")
 
         except Exception as e:
-            logger.error(f"保存建议缓存失败: {str(e)}", exc_info=True)
-            # 不抛出异常，缓存失败不应影响主流程
\ No newline at end of file
+            db.rollback()
+            logger.error(f"保存建议失败: {str(e)}", exc_info=True)
\ No newline at end of file
diff --git a/api/app/services/implicit_memory_service.py b/api/app/services/implicit_memory_service.py
index 34ebe880..4bd11deb 100644
--- a/api/app/services/implicit_memory_service.py
+++ b/api/app/services/implicit_memory_service.py
@@ -422,32 +422,33 @@ class ImplicitMemoryService:
         end_user_id: str,
         db: Session
     ) -> Optional[dict]:
-        """从 Redis 缓存获取完整用户画像
+        """从数据库获取完整用户画像
         
         Args:
             end_user_id: 终端用户ID
-            db: 数据库会话（保留参数以保持接口兼容性）
+            db: 数据库会话
             
         Returns:
-            Dict: 缓存的画像数据，如果不存在或已过期返回 None
+            Dict: 存储的画像数据，如果不存在返回 None
         """
         try:
-            from app.cache.memory.implicit_memory import ImplicitMemoryCache
+            from app.repositories.implicit_emotions_storage_repository import ImplicitEmotionsStorageRepository
             
-            logger.info(f"尝试从 Redis 缓存获取用户画像: user={end_user_id}")
+            logger.info(f"尝试从数据库获取用户画像: user={end_user_id}")
             
-            # 从 Redis 获取缓存
-            cached_data = await ImplicitMemoryCache.get_user_profile(end_user_id)
+            # 从数据库获取存储记录
+            repo = ImplicitEmotionsStorageRepository(db)
+            storage = repo.get_by_end_user_id(end_user_id)
             
-            if cached_data is None:
-                logger.info(f"用户 {end_user_id} 的画像缓存不存在或已过期")
+            if storage is None or storage.implicit_profile is None:
+                logger.info(f"用户 {end_user_id} 的画像数据不存在")
                 return None
             
-            logger.info(f"成功从 Redis 缓存获取用户画像: user={end_user_id}")
-            return cached_data
+            logger.info(f"成功从数据库获取用户画像: user={end_user_id}")
+            return storage.implicit_profile
             
         except Exception as e:
-            logger.error(f"从 Redis 缓存获取用户画像失败: {str(e)}", exc_info=True)
+            logger.error(f"从数据库获取用户画像失败: {str(e)}", exc_info=True)
             return None
     
     async def save_profile_cache(
@@ -455,36 +456,27 @@ class ImplicitMemoryService:
         end_user_id: str,
         profile_data: dict,
         db: Session,
-        expires_hours: int = 168  # 默认7天
+        expires_hours: int = 168  # 参数保留以保持接口兼容性
     ) -> None:
-        """保存用户画像到 Redis 缓存
+        """保存用户画像到数据库
         
         Args:
             end_user_id: 终端用户ID
             profile_data: 画像数据
-            db: 数据库会话（保留参数以保持接口兼容性）
-            expires_hours: 过期时间（小时），默认168小时（7天）
+            db: 数据库会话
+            expires_hours: 保留参数（兼容性）
         """
         try:
-            from app.cache.memory.implicit_memory import ImplicitMemoryCache
+            from app.repositories.implicit_emotions_storage_repository import ImplicitEmotionsStorageRepository
             
-            logger.info(f"保存用户画像到 Redis 缓存: user={end_user_id}, expires={expires_hours}小时")
+            logger.info(f"保存用户画像到数据库: user={end_user_id}")
             
-            # 计算过期时间（秒）
-            expire_seconds = expires_hours * 3600
+            repo = ImplicitEmotionsStorageRepository(db)
+            repo.update_implicit_profile(end_user_id, profile_data)
+            db.commit()
             
-            # 保存到 Redis
-            success = await ImplicitMemoryCache.set_user_profile(
-                user_id=end_user_id,
-                profile_data=profile_data,
-                expire=expire_seconds
-            )
-            
-            if success:
-                logger.info(f"用户画像缓存保存成功: user={end_user_id}")
-            else:
-                logger.warning(f"用户画像缓存保存失败: user={end_user_id}")
+            logger.info(f"用户画像保存成功: user={end_user_id}")
             
         except Exception as e:
-            logger.error(f"保存用户画像缓存失败: {str(e)}", exc_info=True)
-            # 不抛出异常，缓存失败不应影响主流程
+            db.rollback()
+            logger.error(f"保存用户画像失败: {str(e)}", exc_info=True)
diff --git a/api/app/services/memory_agent_service.py b/api/app/services/memory_agent_service.py
index da8a8e06..1f3667a6 100644
--- a/api/app/services/memory_agent_service.py
+++ b/api/app/services/memory_agent_service.py
@@ -816,11 +816,10 @@ class MemoryAgentService:
         """
         统计知识库类型分布，包含：
         1. PostgreSQL 中的知识库类型：General, Web, Third-party, Folder（根据 workspace_id 过滤）
-        2. Neo4j 中的 memory 类型（仅统计 Chunk 数量，根据 end_user_id/end_user_id 过滤）
-        3. total: 所有类型的总和
+        2. total: 所有类型的总和
 
         参数：
-        - end_user_id: 用户组ID（可选，未提供时 memory 统计为 0）
+        - end_user_id: 用户组ID（可选，保留参数以保持接口兼容性）
         - only_active: 是否仅统计有效记录
         - current_workspace_id: 当前工作空间ID（可选，未提供时知识库统计为 0）
         - db: 数据库会话
@@ -831,7 +830,6 @@ class MemoryAgentService:
             "Web": count,
             "Third-party": count,
             "Folder": count,
-            "memory": chunk_count,
             "total": sum_of_all
         }
         """
@@ -878,51 +876,8 @@ class MemoryAgentService:
             logger.error(f"知识库类型统计失败: {e}")
             raise Exception(f"知识库类型统计失败: {e}")
 
-        # 2. 统计 Neo4j 中的 memory 总量（统计当前空间下所有宿主的 Chunk 总数）
-        try:
-            if current_workspace_id:
-                # 获取当前空间下的所有宿主
-                from app.repositories import app_repository, end_user_repository
-                from app.schemas.app_schema import App as AppSchema
-                from app.schemas.end_user_schema import EndUser as EndUserSchema
-
-                # 查询应用并转换为 Pydantic 模型
-                apps_orm = app_repository.get_apps_by_workspace_id(db, current_workspace_id)
-                apps = [AppSchema.model_validate(h) for h in apps_orm]
-                app_ids = [app.id for app in apps]
-
-                # 获取所有宿主
-                end_users = []
-                for app_id in app_ids:
-                    end_user_orm_list = end_user_repository.get_end_users_by_app_id(db, app_id)
-                    end_users.extend(h for h in end_user_orm_list)
-
-                # 统计所有宿主的 Chunk 总数
-                total_chunks = 0
-                for end_user in end_users:
-                    end_user_id_str = str(end_user.id)
-                    memory_query = """
-                    MATCH (n:Chunk) WHERE n.end_user_id = $end_user_id RETURN count(n) AS Count
-                    """
-                    neo4j_result = await _neo4j_connector.execute_query(
-                        memory_query,
-                        end_user_id=end_user_id_str,
-                    )
-                    chunk_count = neo4j_result[0]["Count"] if neo4j_result else 0
-                    total_chunks += chunk_count
-                    logger.debug(f"EndUser {end_user_id_str} Chunk数量: {chunk_count}")
-
-                result["memory"] = total_chunks
-                logger.info(f"Neo4j memory统计成功: 总Chunk数={total_chunks}, 宿主数={len(end_users)}")
-            else:
-                # 没有 workspace_id 时，返回 0
-                result["memory"] = 0
-                logger.info("未提供 workspace_id，memory 统计为 0")
-
-        except Exception as e:
-            logger.error(f"Neo4j memory统计失败: {e}", exc_info=True)
-            # 如果 Neo4j 查询失败，memory 设为 0
-            result["memory"] = 0
+        # 2. 统计 Neo4j 中的 memory 总量已移除
+        # memory 字段不再返回
 
         # 3. 计算知识库类型总和（不包括 memory）
         result["total"] = (
diff --git a/api/app/tasks.py b/api/app/tasks.py
index d408a0da..ae533489 100644
--- a/api/app/tasks.py
+++ b/api/app/tasks.py
@@ -1304,6 +1304,203 @@ def write_total_memory_task(workspace_id: str) -> Dict[str, Any]:
             "workspace_id": workspace_id,
             "elapsed_time": elapsed_time,
         }
+@celery_app.task(
+    name="app.tasks.write_all_workspaces_memory_task",
+    bind=True,
+    ignore_result=False,
+    max_retries=3,
+    acks_late=True,
+    time_limit=3600,
+    soft_time_limit=3300,
+)
+def write_all_workspaces_memory_task(self) -> Dict[str, Any]:
+    """定时任务：遍历所有工作空间，统计并写入记忆增量
+
+    此任务会：
+    1. 查询所有活跃的工作空间
+    2. 对每个工作空间统计记忆总量
+    3. 将统计结果写入 memory_increments 表
+
+    Returns:
+        包含任务执行结果的字典
+    """
+    start_time = time.time()
+
+    async def _run() -> Dict[str, Any]:
+        from app.core.logging_config import get_api_logger
+        from app.models.workspace_model import Workspace
+        from app.models.app_model import App
+        from app.models.end_user_model import EndUser
+        from app.repositories.memory_increment_repository import write_memory_increment
+        from app.services.memory_storage_service import search_all
+
+        api_logger = get_api_logger()
+
+        with get_db_context() as db:
+            try:
+                # 获取所有活跃的工作空间
+                workspaces = db.query(Workspace).filter(
+                    Workspace.is_active.is_(True)
+                ).all()
+
+                if not workspaces:
+                    api_logger.warning("没有找到活跃的工作空间")
+                    return {
+                        "status": "SUCCESS",
+                        "message": "没有找到活跃的工作空间",
+                        "workspace_count": 0,
+                        "workspace_results": []
+                    }
+
+                api_logger.info(f"开始统计 {len(workspaces)} 个工作空间的记忆增量")
+                all_workspace_results = []
+
+                # 遍历每个工作空间
+                for workspace in workspaces:
+                    workspace_id = workspace.id
+                    api_logger.info(f"开始处理工作空间: {workspace.name} (ID: {workspace_id})")
+
+                    try:
+                        # 1. 查询当前workspace下的所有app（仅未删除的）
+                        apps = db.query(App).filter(
+                            App.workspace_id == workspace_id,
+                            App.is_active.is_(True)
+                        ).all()
+
+                        if not apps:
+                            # 如果没有app，总量为0
+                            memory_increment = write_memory_increment(
+                                db=db,
+                                workspace_id=workspace_id,
+                                total_num=0
+                            )
+                            all_workspace_results.append({
+                                "workspace_id": str(workspace_id),
+                                "workspace_name": workspace.name,
+                                "status": "SUCCESS",
+                                "total_num": 0,
+                                "end_user_count": 0,
+                                "memory_increment_id": str(memory_increment.id),
+                                "created_at": memory_increment.created_at.isoformat(),
+                            })
+                            api_logger.info(f"工作空间 {workspace.name} 没有应用，记录总量为0")
+                            continue
+
+                        # 2. 查询所有app下的end_user_id（去重）
+                        app_ids = [app.id for app in apps]
+                        end_users = db.query(EndUser.id).filter(
+                            EndUser.app_id.in_(app_ids)
+                        ).distinct().all()
+
+                        # 3. 遍历所有end_user，查询每个宿主的记忆总量并累加
+                        total_num = 0
+                        end_user_details = []
+
+                        for (end_user_id,) in end_users:
+                            try:
+                                # 调用 search_all 接口查询该宿主的总量
+                                result = await search_all(str(end_user_id))
+                                user_total = result.get("total", 0)
+                                total_num += user_total
+                                end_user_details.append({
+                                    "end_user_id": str(end_user_id),
+                                    "total": user_total
+                                })
+                            except Exception as e:
+                                # 记录单个用户查询失败，但继续处理其他用户
+                                api_logger.warning(f"查询用户 {end_user_id} 记忆失败: {str(e)}")
+                                end_user_details.append({
+                                    "end_user_id": str(end_user_id),
+                                    "total": 0,
+                                    "error": str(e)
+                                })
+
+                        # 4. 写入数据库
+                        memory_increment = write_memory_increment(
+                            db=db,
+                            workspace_id=workspace_id,
+                            total_num=total_num
+                        )
+
+                        all_workspace_results.append({
+                            "workspace_id": str(workspace_id),
+                            "workspace_name": workspace.name,
+                            "status": "SUCCESS",
+                            "total_num": total_num,
+                            "end_user_count": len(end_users),
+                            "memory_increment_id": str(memory_increment.id),
+                            "created_at": memory_increment.created_at.isoformat(),
+                        })
+
+                        api_logger.info(
+                            f"工作空间 {workspace.name} 统计完成: 总量={total_num}, 用户数={len(end_users)}"
+                        )
+
+                    except Exception as e:
+                        db.rollback()  # 回滚失败的事务，允许继续处理下一个工作空间
+                        api_logger.error(f"处理工作空间 {workspace.name} (ID: {workspace_id}) 失败: {str(e)}")
+                        all_workspace_results.append({
+                            "workspace_id": str(workspace_id),
+                            "workspace_name": workspace.name,
+                            "status": "FAILURE",
+                            "error": str(e),
+                            "total_num": 0,
+                            "end_user_count": 0,
+                        })
+
+                total_memory = sum(r.get("total_num", 0) for r in all_workspace_results)
+                success_count = sum(1 for r in all_workspace_results if r.get("status") == "SUCCESS")
+
+                return {
+                    "status": "SUCCESS",
+                    "message": f"成功处理 {success_count}/{len(workspaces)} 个工作空间，总记忆量: {total_memory}",
+                    "workspace_count": len(workspaces),
+                    "success_count": success_count,
+                    "total_memory": total_memory,
+                    "workspace_results": all_workspace_results
+                }
+
+            except Exception as e:
+                api_logger.error(f"记忆增量统计任务执行失败: {str(e)}")
+                return {
+                    "status": "FAILURE",
+                    "error": str(e),
+                    "workspace_count": 0,
+                    "workspace_results": []
+                }
+
+    try:
+        # 使用 nest_asyncio 来避免事件循环冲突
+        try:
+            import nest_asyncio
+            nest_asyncio.apply()
+        except ImportError:
+            pass
+
+        # 尝试获取现有事件循环，如果不存在则创建新的
+        try:
+            loop = asyncio.get_event_loop()
+            if loop.is_closed():
+                loop = asyncio.new_event_loop()
+                asyncio.set_event_loop(loop)
+        except RuntimeError:
+            loop = asyncio.new_event_loop()
+            asyncio.set_event_loop(loop)
+
+        result = loop.run_until_complete(_run())
+        elapsed_time = time.time() - start_time
+        result["elapsed_time"] = elapsed_time
+        result["task_id"] = self.request.id
+
+        return result
+    except Exception as e:
+        elapsed_time = time.time() - start_time
+        return {
+            "status": "FAILURE",
+            "error": str(e),
+            "elapsed_time": elapsed_time,
+            "task_id": self.request.id
+        }
 
 
 @celery_app.task(
@@ -1924,4 +2121,307 @@ def run_forgetting_cycle_task(self, config_id: Optional[uuid.UUID] = None) -> Di
 #             "config_id": config_id,
 #             "elapsed_time": elapsed_time,
 #             "task_id": self.request.id
-#         }
\ No newline at end of file
+#         }
+
+
+# =============================================================================
+# 隐性记忆和情绪数据更新定时任务
+# =============================================================================
+
+@celery_app.task(
+    name="app.tasks.update_implicit_emotions_storage",
+    bind=True,
+    ignore_result=True,
+    max_retries=0,
+    acks_late=False,
+    time_limit=7200,  # 2小时硬超时
+    soft_time_limit=6900,  # 1小时55分钟软超时
+)
+def update_implicit_emotions_storage(self) -> Dict[str, Any]:
+    """定时任务：更新所有用户的隐性记忆画像和情绪建议数据
+
+    遍历数据库中所有已存在数据的用户，为每个用户重新生成隐性记忆画像和情绪建议。
+    实现错误隔离，单个用户失败不影响其他用户的处理。
+
+    Returns:
+        包含任务执行结果的字典，包括：
+        - status: 任务状态 (SUCCESS/FAILURE)
+        - message: 执行消息
+        - total_users: 总用户数
+        - successful_implicit: 成功更新隐性记忆的用户数
+        - successful_emotion: 成功更新情绪建议的用户数
+        - failed: 失败的用户数
+        - user_results: 每个用户的详细结果
+        - elapsed_time: 执行耗时（秒）
+        - task_id: 任务ID
+    """
+    start_time = time.time()
+
+    async def _run() -> Dict[str, Any]:
+        from app.core.logging_config import get_logger
+        from app.repositories.implicit_emotions_storage_repository import ImplicitEmotionsStorageRepository
+        from app.models.implicit_emotions_storage_model import ImplicitEmotionsStorage
+        from sqlalchemy import select, func
+        from app.services.implicit_memory_service import ImplicitMemoryService
+        from app.services.emotion_analytics_service import EmotionAnalyticsService
+
+        logger = get_logger(__name__)
+        logger.info("开始执行隐性记忆和情绪数据更新定时任务")
+
+        total_users = 0
+        successful_implicit = 0
+        successful_emotion = 0
+        failed = 0
+        user_results = []
+
+        with get_db_context() as db:
+            try:
+                # 获取所有已存储数据的用户ID（分批次处理）
+                repo = ImplicitEmotionsStorageRepository(db)
+                
+                # 先统计总数用于日志
+                from sqlalchemy import func
+                total_users = db.execute(
+                    select(func.count()).select_from(ImplicitEmotionsStorage)
+                ).scalar() or 0
+                logger.info(f"找到 {total_users} 个需要更新的用户")
+
+                # 遍历每个用户并更新数据（分批次，避免一次性加载所有ID）
+                for end_user_id in repo.get_all_user_ids(batch_size=100):
+                    logger.info(f"开始处理用户: {end_user_id}")
+                    user_start_time = time.time()
+                    
+                    implicit_success = False
+                    emotion_success = False
+                    errors = []
+
+                    try:
+                        # 更新隐性记忆画像
+                        try:
+                            implicit_service = ImplicitMemoryService(db=db, end_user_id=end_user_id)
+                            profile_data = await implicit_service.generate_complete_profile(user_id=end_user_id)
+                            await implicit_service.save_profile_cache(
+                                end_user_id=end_user_id,
+                                profile_data=profile_data,
+                                db=db
+                            )
+                            implicit_success = True
+                            logger.info(f"成功更新用户 {end_user_id} 的隐性记忆画像")
+                        except Exception as e:
+                            error_msg = f"隐性记忆更新失败: {str(e)}"
+                            errors.append(error_msg)
+                            logger.error(f"用户 {end_user_id} {error_msg}")
+
+                        # 更新情绪建议
+                        try:
+                            emotion_service = EmotionAnalyticsService()
+                            suggestions_data = await emotion_service.generate_emotion_suggestions(
+                                end_user_id=end_user_id,
+                                db=db,
+                                language="zh"
+                            )
+                            await emotion_service.save_suggestions_cache(
+                                end_user_id=end_user_id,
+                                suggestions_data=suggestions_data,
+                                db=db
+                            )
+                            emotion_success = True
+                            logger.info(f"成功更新用户 {end_user_id} 的情绪建议")
+                        except Exception as e:
+                            error_msg = f"情绪建议更新失败: {str(e)}"
+                            errors.append(error_msg)
+                            logger.error(f"用户 {end_user_id} {error_msg}")
+
+                        # 统计结果
+                        if implicit_success:
+                            successful_implicit += 1
+                        if emotion_success:
+                            successful_emotion += 1
+                        if not implicit_success and not emotion_success:
+                            failed += 1
+
+                        user_elapsed = time.time() - user_start_time
+                        
+                        # 记录用户处理结果
+                        user_result = {
+                            "end_user_id": end_user_id,
+                            "implicit_success": implicit_success,
+                            "emotion_success": emotion_success,
+                            "errors": errors,
+                            "elapsed_time": user_elapsed
+                        }
+                        user_results.append(user_result)
+
+                        logger.info(
+                            f"用户 {end_user_id} 处理完成: "
+                            f"隐性记忆={'成功' if implicit_success else '失败'}, "
+                            f"情绪建议={'成功' if emotion_success else '失败'}, "
+                            f"耗时={user_elapsed:.2f}秒"
+                        )
+
+                    except Exception as e:
+                        # 单个用户失败不影响其他用户（错误隔离）
+                        failed += 1
+                        user_elapsed = time.time() - user_start_time
+                        error_info = {
+                            "end_user_id": end_user_id,
+                            "implicit_success": False,
+                            "emotion_success": False,
+                            "errors": [str(e)],
+                            "elapsed_time": user_elapsed
+                        }
+                        user_results.append(error_info)
+                        logger.error(f"处理用户 {end_user_id} 时出错: {str(e)}")
+
+                # ---- 处理增量用户（当天新增、尚未初始化的用户）----
+                new_users_initialized = 0
+                new_users_failed = 0
+                logger.info("开始处理当天新增的增量用户初始化")
+
+                for end_user_id in repo.get_new_user_ids_today(batch_size=100):
+                    logger.info(f"开始初始化新用户: {end_user_id}")
+                    user_start_time = time.time()
+                    implicit_success = False
+                    emotion_success = False
+                    errors = []
+
+                    try:
+                        try:
+                            implicit_service = ImplicitMemoryService(db=db, end_user_id=end_user_id)
+                            profile_data = await implicit_service.generate_complete_profile(user_id=end_user_id)
+                            await implicit_service.save_profile_cache(
+                                end_user_id=end_user_id,
+                                profile_data=profile_data,
+                                db=db
+                            )
+                            implicit_success = True
+                            logger.info(f"成功初始化新用户 {end_user_id} 的隐性记忆画像")
+                        except Exception as e:
+                            error_msg = f"隐性记忆初始化失败: {str(e)}"
+                            errors.append(error_msg)
+                            logger.error(f"新用户 {end_user_id} {error_msg}")
+
+                        try:
+                            emotion_service = EmotionAnalyticsService()
+                            suggestions_data = await emotion_service.generate_emotion_suggestions(
+                                end_user_id=end_user_id,
+                                db=db,
+                                language="zh"
+                            )
+                            await emotion_service.save_suggestions_cache(
+                                end_user_id=end_user_id,
+                                suggestions_data=suggestions_data,
+                                db=db
+                            )
+                            emotion_success = True
+                            logger.info(f"成功初始化新用户 {end_user_id} 的情绪建议")
+                        except Exception as e:
+                            error_msg = f"情绪建议初始化失败: {str(e)}"
+                            errors.append(error_msg)
+                            logger.error(f"新用户 {end_user_id} {error_msg}")
+
+                        if implicit_success or emotion_success:
+                            new_users_initialized += 1
+                        else:
+                            new_users_failed += 1
+
+                        user_elapsed = time.time() - user_start_time
+                        user_results.append({
+                            "end_user_id": end_user_id,
+                            "type": "init",
+                            "implicit_success": implicit_success,
+                            "emotion_success": emotion_success,
+                            "errors": errors,
+                            "elapsed_time": user_elapsed
+                        })
+
+                    except Exception as e:
+                        new_users_failed += 1
+                        user_elapsed = time.time() - user_start_time
+                        user_results.append({
+                            "end_user_id": end_user_id,
+                            "type": "init",
+                            "implicit_success": False,
+                            "emotion_success": False,
+                            "errors": [str(e)],
+                            "elapsed_time": user_elapsed
+                        })
+                        logger.error(f"初始化新用户 {end_user_id} 时出错: {str(e)}")
+
+                logger.info(
+                    f"增量用户初始化完成: 成功={new_users_initialized}, 失败={new_users_failed}"
+                )
+                # ---- 增量用户处理结束 ----
+
+                # 记录总体统计信息
+                logger.info(
+                    f"隐性记忆和情绪数据更新定时任务完成: "
+                    f"存量用户总数={total_users}, "
+                    f"隐性记忆成功={successful_implicit}, "
+                    f"情绪建议成功={successful_emotion}, "
+                    f"存量失败={failed}, "
+                    f"增量初始化成功={new_users_initialized}, "
+                    f"增量初始化失败={new_users_failed}"
+                )
+
+                return {
+                    "status": "SUCCESS",
+                    "message": (
+                        f"存量用户 {total_users} 个，隐性记忆 {successful_implicit} 个成功，情绪建议 {successful_emotion} 个成功；"
+                        f"增量新用户初始化 {new_users_initialized} 个成功，{new_users_failed} 个失败"
+                    ),
+                    "total_users": total_users,
+                    "successful_implicit": successful_implicit,
+                    "successful_emotion": successful_emotion,
+                    "failed": failed,
+                    "new_users_initialized": new_users_initialized,
+                    "new_users_failed": new_users_failed,
+                    "user_results": user_results[:50]  # 只保留前50个用户的详细结果
+                }
+
+            except Exception as e:
+                logger.error(f"隐性记忆和情绪数据更新定时任务执行失败: {str(e)}")
+                return {
+                    "status": "FAILURE",
+                    "error": str(e),
+                    "total_users": total_users,
+                    "successful_implicit": successful_implicit,
+                    "successful_emotion": successful_emotion,
+                    "failed": failed,
+                    "new_users_initialized": 0,
+                    "new_users_failed": 0,
+                    "user_results": user_results[:50]
+                }
+
+    try:
+        # 使用 nest_asyncio 来避免事件循环冲突
+        try:
+            import nest_asyncio
+            nest_asyncio.apply()
+        except ImportError:
+            pass
+
+        # 尝试获取现有事件循环，如果不存在则创建新的
+        try:
+            loop = asyncio.get_event_loop()
+            if loop.is_closed():
+                loop = asyncio.new_event_loop()
+                asyncio.set_event_loop(loop)
+        except RuntimeError:
+            loop = asyncio.new_event_loop()
+            asyncio.set_event_loop(loop)
+
+        result = loop.run_until_complete(_run())
+        elapsed_time = time.time() - start_time
+        result["elapsed_time"] = elapsed_time
+        result["task_id"] = self.request.id
+
+        return result
+    except Exception as e:
+        elapsed_time = time.time() - start_time
+        return {
+            "status": "FAILURE",
+            "error": str(e),
+            "elapsed_time": elapsed_time,
+            "task_id": self.request.id
+        }
diff --git a/redbear-mem-benchmark b/redbear-mem-benchmark
index 4b0257bb..8494e824 160000
--- a/redbear-mem-benchmark
+++ b/redbear-mem-benchmark
@@ -1 +1 @@
-Subproject commit 4b0257bb4e7dc384b2aaf849b0bd6eae4b39835d
+Subproject commit 8494e82498cb99c70ac67a64a544ff872432363a
diff --git a/web/src/api/memory.ts b/web/src/api/memory.ts
index 987ef358..cb917ec1 100644
--- a/web/src/api/memory.ts
+++ b/web/src/api/memory.ts
@@ -1,8 +1,8 @@
 /*
  * @Author: ZhaoYing 
  * @Date: 2026-02-03 14:00:06 
- * @Last Modified by:   ZhaoYing 
- * @Last Modified time: 2026-02-03 14:00:06 
+ * @Last Modified by: ZhaoYing
+ * @Last Modified time: 2026-03-03 14:58:32
  */
 import { request } from '@/utils/request'
 import type {
@@ -163,9 +163,14 @@ export const getImplicitInterestAreas = (end_user_id: string) => {
 export const getImplicitHabits = (end_user_id: string) => {
   return request.get(`/memory/implicit-memory/habits/${end_user_id}`)
 }
+// Implicit Memory - Generate user portrait
 export const generateProfile = (end_user_id: string) => {
   return request.post(`/memory/implicit-memory/generate_profile`, { end_user_id })
 }
+// Implicit Memory - Check if data exists
+export const implicitCheckData = (end_user_id: string) => {
+  return request.get(`/memory/implicit-memory/check-data/${end_user_id}`)
+}
 // Short-term memory
 export const getShortTerm = (end_user_id: string) => {
   return request.get(`/memory/short/short_term`, { end_user_id })
diff --git a/web/src/i18n/en.ts b/web/src/i18n/en.ts
index f2b4eaa4..352fc4b6 100644
--- a/web/src/i18n/en.ts
+++ b/web/src/i18n/en.ts
@@ -2276,6 +2276,7 @@ Memory Bear: After the rebellion, regional warlordism intensified for several re
       suggestions: 'Personalized Suggestions',
       suggestionLoading: 'Your personalized suggestions are being generated',
       item: 'item',
+      noData: 'Emotion suggestion data does not exist, please click the refresh button to initialize',
     },
     reflectionEngine: {
       reflectionEngineConfig: 'Reflection Engine Configuration',
@@ -2522,7 +2523,8 @@ Memory Bear: After the rebellion, regional warlordism intensified for several re
       context_details: 'Preference Details',
       supporting_evidence: 'Preference Source',
       specific_examples: 'Source',
-      wordEmpty: 'Click on a node in the left chart to view preference details'
+      wordEmpty: 'Click on a node in the left chart to view preference details',
+      noData: 'Portrait data does not exist, please click the refresh button to initialize',
     },
     shortTermDetail: {
       title: 'Short-term memory is the "workbench" of the AI system, connecting instant conversations with long-term knowledge bases. Through real-time capture, deep retrieval, intelligent extraction and filtering transformation, temporary unstructured information is converted into valuable long-term knowledge.',
diff --git a/web/src/i18n/zh.ts b/web/src/i18n/zh.ts
index e2e7082a..92f0710c 100644
--- a/web/src/i18n/zh.ts
+++ b/web/src/i18n/zh.ts
@@ -2272,6 +2272,7 @@ export const zh = {
       suggestions: '个性化建议',
       suggestionLoading: '您的个性化建议正在生成中',
       item: '个',
+      noData: '情绪建议数据不存在，请点击刷新按钮进行初始化',
     },
     reflectionEngine: {
       reflectionEngineConfig: '反思引擎配置',
@@ -2518,7 +2519,8 @@ export const zh = {
       context_details: '偏好详情',
       supporting_evidence: '偏好来源',
       specific_examples: '来源',
-      wordEmpty: '点击左侧图表中的节点查看偏好详情'
+      wordEmpty: '点击左侧图表中的节点查看偏好详情',
+      noData: '画像数据不存在，请点击刷新按钮进行初始化',
     },
     shortTermDetail: {
       title: '短期记忆是AI系统的"工作台"，连接即时对话与长期知识库。通过实时捕获、深度检索、智能提取和筛选转化，将临时的非结构化信息转化为有价值的长期知识。',
diff --git a/web/src/views/UserMemoryDetail/components/Suggestions.tsx b/web/src/views/UserMemoryDetail/components/Suggestions.tsx
index 55bfbf14..3b7c1800 100644
--- a/web/src/views/UserMemoryDetail/components/Suggestions.tsx
+++ b/web/src/views/UserMemoryDetail/components/Suggestions.tsx
@@ -1,12 +1,13 @@
 /*
  * @Author: ZhaoYing 
  * @Date: 2026-02-03 18:31:50 
- * @Last Modified by:   ZhaoYing 
- * @Last Modified time: 2026-02-03 18:31:50 
+ * @Last Modified by: ZhaoYing
+ * @Last Modified time: 2026-03-04 16:22:03
  */
-import { useEffect, useState, forwardRef, useImperativeHandle } from 'react'
+import { useEffect, useState, useRef, forwardRef, useImperativeHandle } from 'react'
 import { useTranslation } from 'react-i18next'
 import { useParams } from 'react-router-dom'
+import { App } from 'antd'
 
 import Empty from '@/components/Empty'
 import RbCard from '@/components/RbCard/Card'
@@ -20,6 +21,7 @@ import RbAlert from '@/components/RbAlert'
  * @property {Array} suggestions - List of suggestions with actionable steps
  */
 interface Suggestions {
+  exists?: boolean;
   health_summary: string;
   suggestions: Array<{
     type: string;
@@ -35,14 +37,17 @@ interface Suggestions {
  * Displays emotional health suggestions with actionable steps
  * Shows health summary and prioritized recommendations
  */
-const Suggestions = forwardRef<{ handleRefresh: () => void; }>((_props, ref) => {
+const Suggestions = forwardRef<{ handleRefresh: () => void; }, { refresh: () => void; }>(({ refresh }, ref) => {
   const { t } = useTranslation()
   const { id } = useParams()
+  const { modal } = App.useApp()
   const [loading, setLoading] = useState(false)
   const [suggestions, setSuggestions] = useState<Suggestions | null>(null)
+  const modalInstanceRef = useRef<{ destroy: () => void } | null>(null)
 
   useEffect(() => {
     getSuggestionData()
+    return () => modalInstanceRef.current?.destroy()
   }, [id])
 
   const getSuggestionData = () => {
@@ -52,7 +57,18 @@ const Suggestions = forwardRef<{ handleRefresh: () => void; }>((_props, ref) =>
     setLoading(true)
     getEmotionSuggestions(id)
       .then((res) => {
-        setSuggestions(res as Suggestions)
+        const response = res as Suggestions
+        if (!response.exists && (!response.suggestions || !response.suggestions?.length)) {
+          modalInstanceRef.current = modal.warning({
+            title: t('statementDetail.noData'),
+            okText: t('common.refresh'),
+            onOk: () => {
+              refresh()
+            }
+          })
+        } else {
+          setSuggestions(res as Suggestions)
+        }
       })
       .finally(() => {
         setLoading(false)
diff --git a/web/src/views/UserMemoryDetail/pages/ImplicitDetail.tsx b/web/src/views/UserMemoryDetail/pages/ImplicitDetail.tsx
index dfe5c1ee..46286fff 100644
--- a/web/src/views/UserMemoryDetail/pages/ImplicitDetail.tsx
+++ b/web/src/views/UserMemoryDetail/pages/ImplicitDetail.tsx
@@ -1,6 +1,12 @@
-import { forwardRef, useImperativeHandle, useRef } from 'react'
+/*
+ * @Author: ZhaoYing 
+ * @Date: 2026-01-08 19:46:02 
+ * @Last Modified by: ZhaoYing
+ * @Last Modified time: 2026-03-04 16:26:55
+ */
+import { forwardRef, useImperativeHandle, useRef, useEffect } from 'react'
 import { useTranslation } from 'react-i18next'
-import { Row, Col } from 'antd'
+import { Row, Col, App } from 'antd'
 import { useParams } from 'react-router-dom'
 
 import Preferences from '../components/Preferences'
@@ -9,16 +15,44 @@ import InterestAreas from '../components/InterestAreas'
 import Habits from '../components/Habits'
 import {
   generateProfile,
+  implicitCheckData,
 } from '@/api/memory'
 
-const ImplicitDetail = forwardRef<{ handleRefresh: () => void; }>((_props, ref) => {
+/**
+ * ImplicitDetail Component - Displays user's implicit memory profile
+ * Shows unconscious preferences, personality traits, interests and habits
+ */
+const ImplicitDetail = forwardRef<{ handleRefresh: () => void; }, { refresh: () => void; }>(({
+  refresh
+}, ref) => {
   const { t } = useTranslation()
   const { id } = useParams()
+  const { modal } = App.useApp()
   const preferencesRef = useRef<{ handleRefresh: () => void; }>(null)
   const portraitRef = useRef<{ handleRefresh: () => void; }>(null)
   const interestAreasRef = useRef<{ handleRefresh: () => void; }>(null)
   const habitsRef = useRef<{ handleRefresh: () => void; }>(null)
+  
+  // Check if implicit data exists, prompt user to initialize if not
+  useEffect(() => {
+    if (!id) return
+    let modalInstance: { destroy: () => void } | null = null
+    implicitCheckData(id)
+      .then(res => {
+        if (!(res as { exists: boolean }).exists) {
+          modalInstance = modal.warning({
+            title: t('implicitDetail.noData'),
+            okText: t('common.refresh'),
+            onOk: () => {
+              refresh()
+            }
+          })
+        }
+      })
+    return () => modalInstance?.destroy()
+  }, [id])
 
+  // Refresh all implicit memory components by regenerating profile
   const handleRefresh = () => {
     if (!id) {
       return Promise.resolve()
diff --git a/web/src/views/UserMemoryDetail/pages/StatementDetail.tsx b/web/src/views/UserMemoryDetail/pages/StatementDetail.tsx
index 72d35c60..cddf95ad 100644
--- a/web/src/views/UserMemoryDetail/pages/StatementDetail.tsx
+++ b/web/src/views/UserMemoryDetail/pages/StatementDetail.tsx
@@ -1,3 +1,9 @@
+/*
+ * @Author: ZhaoYing 
+ * @Date: 2025-12-19 16:54:52 
+ * @Last Modified by: ZhaoYing
+ * @Last Modified time: 2026-03-04 16:28:00
+ */
 import { forwardRef, useImperativeHandle, useRef } from 'react'
 import { Row, Col, Space } from 'antd';
 import { useParams } from 'react-router-dom'
@@ -9,9 +15,17 @@ import Suggestions from '../components/Suggestions'
 import { generateSuggestions } from '@/api/memory'
 
 
-const StatementDetail = forwardRef((_props, ref) => {
+/**
+ * StatementDetail - Displays emotional memory analysis for a user
+ * Shows word cloud, emotion tags, health index, and personalized suggestions
+ */
+const StatementDetail = forwardRef<{ handleRefresh: () => void },{ refresh: () => void; }>(({
+  refresh
+}, ref) => {
   const { id } = useParams()
   const suggestionsRef = useRef<{ handleRefresh: () => void; }>(null)
+
+  // Regenerate suggestions and refresh the Suggestions child component
   const handleRefresh = () => {
     if (!id) {
       return Promise.resolve()
@@ -41,7 +55,7 @@ const StatementDetail = forwardRef((_props, ref) => {
         </Space>
       </Col>
       <Col span={12}>
-        <Suggestions ref={suggestionsRef} />
+        <Suggestions ref={suggestionsRef} refresh={refresh} />
       </Col>
     </Row>
   )
diff --git a/web/src/views/UserMemoryDetail/pages/index.tsx b/web/src/views/UserMemoryDetail/pages/index.tsx
index c5dea163..71cada89 100644
--- a/web/src/views/UserMemoryDetail/pages/index.tsx
+++ b/web/src/views/UserMemoryDetail/pages/index.tsx
@@ -1,8 +1,13 @@
+/*
+ * @Author: ZhaoYing 
+ * @Date: 2026-01-07 20:37:34 
+ * @Last Modified by:   ZhaoYing 
+ * @Last Modified time: 2026-03-04 16:27:14 
+ */
 import { type FC, useEffect, useState, useMemo, useRef } from 'react'
 import { useParams, useNavigate } from 'react-router-dom'
 import { useTranslation } from 'react-i18next'
 import { Dropdown, Button } from 'antd'
-import { LoadingOutlined } from '@ant-design/icons';
 
 import PageHeader from '../components/PageHeader'
 import StatementDetail from './StatementDetail'
@@ -19,11 +24,16 @@ import {
 import refreshIcon from '@/assets/images/refresh_hover.svg'
 import GraphDetail from './GraphDetail'
 
+/**
+ * Detail page for user memory - renders different memory type views
+ * based on the `type` route param
+ */
 const Detail: FC = () => {
   const { t } = useTranslation()
   const { id, type } = useParams()
   const navigate = useNavigate()
   const [name, setName] = useState<string>('')
+  // Refs for child components that support imperative refresh
   const forgetDetailRef = useRef<{ handleRefresh: () => void }>(null)
   const statementDetailRef = useRef<{ handleRefresh: () => void }>(null)
   const implicitDetailRef = useRef<{ handleRefresh: () => void }>(null)
@@ -33,6 +43,7 @@ const Detail: FC = () => {
     getData()
   }, [id])
   
+  // Fetch end user profile to display the user's name in the header
   const getData = () => {
     if (!id) return
     getEndUserProfile(id).then((res) => {
@@ -40,15 +51,21 @@ const Detail: FC = () => {
       setName(response.other_name || response.id) 
     })
   }
+
+  // Build dropdown menu items for switching between memory types
   const items = useMemo(() => {
     return ['PERCEPTUAL_MEMORY', 'WORKING_MEMORY', 'EMOTIONAL_MEMORY', 'SHORT_TERM_MEMORY', 'IMPLICIT_MEMORY', 'EPISODIC_MEMORY', 'EXPLICIT_MEMORY', 'FORGET_MEMORY']
       .map(key => ({ key, label: t(`userMemory.${key}`) }))
   }, [t])
+
+  // Navigate to the selected memory type detail page
   const onClick = ({ key }: { key: string }) => {
     navigate(`/user-memory/detail/${id}/${key}`, { replace: true })
   }
 
   const [loading, setLoading] = useState(false)
+
+  // Trigger refresh on the active memory type's child component
   const handleRefresh = () => {
     setLoading(true)
     let response: any = null
@@ -64,6 +81,7 @@ const Detail: FC = () => {
         break
     }
 
+    // If the child returns a Promise, wait for it before clearing loading state
     if (response instanceof Promise) {
       response.finally(() => {
         setLoading(false)
@@ -99,9 +117,9 @@ const Detail: FC = () => {
           </Button>}
       />
       <div className="rb:h-[calc(100vh-64px)] rb:overflow-y-auto rb:py-3 rb:px-4">
-        {type === 'EMOTIONAL_MEMORY' && <StatementDetail ref={statementDetailRef} />}
+        {type === 'EMOTIONAL_MEMORY' && <StatementDetail ref={statementDetailRef} refresh={handleRefresh} />}
         {type === 'FORGET_MEMORY' && <ForgetDetail ref={forgetDetailRef} />}
-        {type === 'IMPLICIT_MEMORY' && <ImplicitDetail ref={implicitDetailRef} />}
+        {type === 'IMPLICIT_MEMORY' && <ImplicitDetail ref={implicitDetailRef} refresh={handleRefresh} />}
         {type === 'SHORT_TERM_MEMORY' && <ShortTermDetail />}
         {type === 'PERCEPTUAL_MEMORY' && <PerceptualDetail />}
         {type === 'EPISODIC_MEMORY' && <EpisodicDetail />}
diff --git a/web/src/views/Workflow/components/Chat/Chat.tsx b/web/src/views/Workflow/components/Chat/Chat.tsx
index 895ade24..4b7ffc2a 100644
--- a/web/src/views/Workflow/components/Chat/Chat.tsx
+++ b/web/src/views/Workflow/components/Chat/Chat.tsx
@@ -2,7 +2,7 @@
  * @Author: ZhaoYing 
  * @Date: 2026-02-06 21:10:56 
  * @Last Modified by: ZhaoYing
- * @Last Modified time: 2026-02-27 09:58:30
+ * @Last Modified time: 2026-02-24 17:55:08
  */
 /**
  * Workflow Chat Component