推荐系统
Change-Id: I49b9205568f1ccf88b32b08511aff8b0bea8d1bd
diff --git a/rhj/backend/app/models/recall/hot_recall.py b/rhj/backend/app/models/recall/hot_recall.py
new file mode 100644
index 0000000..dbc716c
--- /dev/null
+++ b/rhj/backend/app/models/recall/hot_recall.py
@@ -0,0 +1,163 @@
+import pymysql
+from typing import List, Tuple, Dict
+import numpy as np
+
+class HotRecall:
+ """
+ 热度召回算法实现
+ 基于物品的热度（热度分数、交互次数等）进行召回
+ """
+
+ def __init__(self, db_config: dict):
+ """
+ 初始化热度召回模型
+
+ Args:
+ db_config: 数据库配置
+ """
+ self.db_config = db_config
+ self.hot_items = []
+
+ def _calculate_heat_scores(self):
+ """计算物品热度分数"""
+ conn = pymysql.connect(**self.db_config)
+ try:
+ cursor = conn.cursor()
+
+ # 综合考虑多个热度指标
+ cursor.execute("""
+ SELECT
+ p.id,
+ p.heat,
+ COUNT(DISTINCT CASE WHEN b.type = 'like' THEN b.user_id END) as like_count,
+ COUNT(DISTINCT CASE WHEN b.type = 'favorite' THEN b.user_id END) as favorite_count,
+ COUNT(DISTINCT CASE WHEN b.type = 'comment' THEN b.user_id END) as comment_count,
+ COUNT(DISTINCT CASE WHEN b.type = 'view' THEN b.user_id END) as view_count,
+ COUNT(DISTINCT CASE WHEN b.type = 'share' THEN b.user_id END) as share_count,
+ DATEDIFF(NOW(), p.created_at) as days_since_created
+ FROM posts p
+ LEFT JOIN behaviors b ON p.id = b.post_id
+ WHERE p.status = 'published'
+ GROUP BY p.id, p.heat, p.created_at
+ """)
+
+ results = cursor.fetchall()
+
+ # 计算综合热度分数
+ items_with_scores = []
+ for row in results:
+ post_id, heat, like_count, favorite_count, comment_count, view_count, share_count, days_since_created = row
+
+ # 处理None值
+ heat = heat or 0
+ like_count = like_count or 0
+ favorite_count = favorite_count or 0
+ comment_count = comment_count or 0
+ view_count = view_count or 0
+ share_count = share_count or 0
+ days_since_created = days_since_created or 0
+
+ # 综合热度分数计算
+ # 基础热度 + 加权的用户行为 + 时间衰减
+ behavior_score = (
+ like_count * 1.0 +
+ favorite_count * 2.0 +
+ comment_count * 3.0 +
+ view_count * 0.1 +
+ share_count * 5.0
+ )
+
+ # 时间衰减因子（越新的内容热度越高）
+ time_decay = np.exp(-days_since_created / 30.0) # 30天半衰期
+
+ # 最终热度分数
+ final_score = (heat * 0.3 + behavior_score * 0.7) * time_decay
+
+ items_with_scores.append((post_id, final_score))
+
+ # 按热度排序
+ self.hot_items = sorted(items_with_scores, key=lambda x: x[1], reverse=True)
+
+ finally:
+ cursor.close()
+ conn.close()
+
+ def train(self):
+ """训练热度召回模型"""
+ print("开始计算热度分数...")
+ self._calculate_heat_scores()
+ print(f"热度召回模型训练完成，共{len(self.hot_items)}个物品")
+
+ def recall(self, user_id: int, num_items: int = 50) -> List[Tuple[int, float]]:
+ """
+ 为用户召回热门物品
+
+ Args:
+ user_id: 用户ID
+ num_items: 召回物品数量
+
+ Returns:
+ List of (item_id, score) tuples
+ """
+ # 如果尚未训练，先进行训练
+ if not hasattr(self, 'hot_items') or not self.hot_items:
+ self.train()
+
+ # 获取用户已交互的物品，避免重复推荐
+ conn = pymysql.connect(**self.db_config)
+ try:
+ cursor = conn.cursor()
+ cursor.execute("""
+ SELECT DISTINCT post_id
+ FROM behaviors
+ WHERE user_id = %s AND type IN ('like', 'favorite', 'comment')
+ """, (user_id,))
+
+ user_interacted_items = set(row[0] for row in cursor.fetchall())
+
+ finally:
+ cursor.close()
+ conn.close()
+
+ # 过滤掉用户已交互的物品
+ filtered_items = [
+ (item_id, score) for item_id, score in self.hot_items
+ if item_id not in user_interacted_items
+ ]
+
+ # 如果过滤后没有足够的候选，放宽条件：只过滤强交互（like, favorite, comment）
+ if len(filtered_items) < num_items:
+ print(f"热度召回：过滤后候选不足（{len(filtered_items)}），放宽过滤条件")
+ conn = pymysql.connect(**self.db_config)
+ try:
+ cursor = conn.cursor()
+ cursor.execute("""
+ SELECT DISTINCT post_id
+ FROM behaviors
+ WHERE user_id = %s AND type IN ('like', 'favorite', 'comment')
+ """, (user_id,))
+
+ strong_interacted_items = set(row[0] for row in cursor.fetchall())
+
+ finally:
+ cursor.close()
+ conn.close()
+
+ filtered_items = [
+ (item_id, score) for item_id, score in self.hot_items
+ if item_id not in strong_interacted_items
+ ]
+
+ return filtered_items[:num_items]
+
+ def get_top_hot_items(self, num_items: int = 100) -> List[Tuple[int, float]]:
+ """
+ 获取全局热门物品（不考虑用户个性化）
+
+ Args:
+ num_items: 返回物品数量
+
+ Returns:
+ List of (item_id, score) tuples
+ """
+ return self.hot_items[:num_items]