TASK：系统sketch推荐接口新用户处理；

app/api/api_recommendation.py

@@ -31,6 +31,15 @@ async def startup_event():
     scheduler.start()
     logger.info("定时任务已启动")
 
+def get_random_recommendations(category: str, num: int) -> List[str]:
+    """全品类随机推荐"""
+    all_iids = list(matrix_data["iid_to_sketch"].keys())
+    # 优先从当前品类选择
+    category_iids = matrix_data["category_to_iids"].get(category, all_iids)
+    # 确保不超出实际数量
+    sample_size = min(num, len(category_iids))
+    sampled = np.random.choice(category_iids, size=sample_size, replace=False)
+    return [matrix_data["iid_to_sketch"][iid] for iid in sampled]
 
 @router.get("/recommend/{user_id}/{category}/{num_recommendations}", response_model=List[str])
 async def get_recommendations(user_id: int, category: str, num_recommendations: int = 10):
@@ -46,6 +55,14 @@ async def get_recommendations(user_id: int, category: str, num_recommendations:
     try:
         start_time = time.time()
         cache_key = (user_id, category)
+        # === 新增：用户存在性检查 ===
+        user_exists_inter = user_id in matrix_data["user_index_interaction"]
+        user_exists_feat = user_id in matrix_data["user_index_feature"]
+
+        # 任一矩阵不存在用户则返回随机推荐
+        if not (user_exists_inter and user_exists_feat):
+            logger.info(f"用户 {user_id} 数据不完整，触发随机推荐")
+            return get_random_recommendations(category, num_recommendations)
 
         # 检查缓存
         if cache_key in matrix_data["cached_scores"]:
@@ -100,7 +117,7 @@ async def get_recommendations(user_id: int, category: str, num_recommendations:
             exps = np.exp(scale)
             return exps / np.sum(exps)
 
-        probs = calibrated_softmax(scores, 0.07)
+        probs = calibrated_softmax(scores, 0.09)
 
         chosen_indices = np.random.choice(
             len(valid_sketch_idxs),