fix：修改log,说明更清楚

src/chat/focus_chat/info_processors/relationship_processor.py

@@ -23,10 +23,8 @@ def init_prompt():
 
 你和别人的关系信息是，请从这些信息中提取出你和别人的关系的原文：
 {relation_prompt}
-请只从上面这些信息中提取出。
+请只从上面这些信息中提取出内容。
 
-
-现在是{time_now}，你正在上网，和qq群里的网友们聊天，以下是正在进行的聊天内容：
 {chat_observe_info}
 
 现在请你根据现有的信息，总结你和群里的人的关系

src/chat/normal_chat/normal_chat.py

@@ -387,7 +387,10 @@ class NormalChat:
             if not response_set or (
                 self.enable_planner and self.action_type not in ["no_action", "change_to_focus_chat"]
             ):
+                if not response_set:
                     logger.info(f"[{self.stream_name}] 模型未生成回复内容")
+                elif self.enable_planner and self.action_type not in ["no_action", "change_to_focus_chat"]:
+                    logger.info(f"[{self.stream_name}] 模型选择其他动作")
                 # 如果模型未生成回复，移除思考消息
                 container = await message_manager.get_container(self.stream_id)  # 使用 self.stream_id
                 for msg in container.messages[:]:
@@ -443,7 +446,7 @@ class NormalChat:
                             logger.warning(f"[{self.stream_name}] 没有设置切换到focus聊天模式的回调函数，无法执行切换")
                         return
                     else:
-                        # await self._check_switch_to_focus()
+                        await self._check_switch_to_focus()
                         pass
 
             info_catcher.done_catch()

src/chat/normal_chat/normal_chat_generator.py

@@ -57,7 +57,7 @@ class NormalChatGenerator:
         )
 
         if model_response:
-            logger.debug(f"{global_config.bot.nickname}的原始回复是：{model_response}")
+            logger.debug(f"{global_config.bot.nickname}的备选回复是：{model_response}")
             model_response = process_llm_response(model_response)
 
             return model_response

src/person_info/relationship_manager.py

@@ -13,6 +13,9 @@ from json_repair import repair_json
 from datetime import datetime
 from difflib import SequenceMatcher
 import ast
+import jieba
+from sklearn.feature_extraction.text import TfidfVectorizer
+from sklearn.metrics.pairwise import cosine_similarity
 
 logger = get_logger("relation")
 
@@ -119,6 +122,8 @@ class RelationshipManager:
             person_id = person_info_manager.get_person_id(person[0], person[1])
 
         person_name = await person_info_manager.get_value(person_id, "person_name")
+        if not person_name or person_name == "none":
+            return ""
         impression = await person_info_manager.get_value(person_id, "impression")
         interaction = await person_info_manager.get_value(person_id, "interaction")
         points = await person_info_manager.get_value(person_id, "points") or []
@@ -324,8 +329,8 @@ class RelationshipManager:
                 
                 # 在现有points中查找相似的点
                 for i, existing_point in enumerate(current_points):
-                    similarity = SequenceMatcher(None, new_point[0], existing_point[0]).ratio()
+                    # 使用组合的相似度检查方法
-                    if similarity > 0.8:
+                    if self.check_similarity(new_point[0], existing_point[0]):
                         similar_points.append(existing_point)
                         similar_indices.append(i)
                 
@@ -355,7 +360,7 @@ class RelationshipManager:
             current_points = points_list
 
 # 如果points超过30条，按权重随机选择多余的条目移动到forgotten_points
-        if len(current_points) > 5:
+        if len(current_points) > 10:
             # 获取现有forgotten_points
             forgotten_points = await person_info_manager.get_value(person_id, "forgotten_points") or []
             if isinstance(forgotten_points, str):
@@ -576,5 +581,56 @@ class RelationshipManager:
             self.logger.error(f"计算时间权重失败: {e}")
             return 0.5  # 发生错误时返回中等权重
 
+    def tfidf_similarity(self, s1, s2):
+        """
+        使用 TF-IDF 和余弦相似度计算两个句子的相似性。
+        """
+        # 1. 使用 jieba 进行分词
+        s1_words = " ".join(jieba.cut(s1))
+        s2_words = " ".join(jieba.cut(s2))
+        
+        # 2. 将两句话放入一个列表中
+        corpus = [s1_words, s2_words]
+        
+        # 3. 创建 TF-IDF 向量化器并进行计算
+        try:
+            vectorizer = TfidfVectorizer()
+            tfidf_matrix = vectorizer.fit_transform(corpus)
+        except ValueError:
+            # 如果句子完全由停用词组成，或者为空，可能会报错
+            return 0.0
+
+        # 4. 计算余弦相似度
+        similarity_matrix = cosine_similarity(tfidf_matrix)
+        
+        # 返回 s1 和 s2 的相似度
+        return similarity_matrix[0, 1]
+
+    def sequence_similarity(self, s1, s2):
+        """
+        使用 SequenceMatcher 计算两个句子的相似性。
+        """
+        return SequenceMatcher(None, s1, s2).ratio()
+
+    def check_similarity(self, text1, text2, tfidf_threshold=0.5, seq_threshold=0.6):
+        """
+        使用两种方法检查文本相似度，只要其中一种方法达到阈值就认为是相似的。
+        
+        Args:
+            text1: 第一个文本
+            text2: 第二个文本
+            tfidf_threshold: TF-IDF相似度阈值
+            seq_threshold: SequenceMatcher相似度阈值
+            
+        Returns:
+            bool: 如果任一方法达到阈值则返回True
+        """
+        # 计算两种相似度
+        tfidf_sim = self.tfidf_similarity(text1, text2)
+        seq_sim = self.sequence_similarity(text1, text2)
+        
+        # 只要其中一种方法达到阈值就认为是相似的
+        return tfidf_sim > tfidf_threshold or seq_sim > seq_threshold
+
 
 relationship_manager = RelationshipManager()

tests/test_sentence_similarity.py

@@ -0,0 +1,156 @@
+import time
+import unittest
+import jieba
+from difflib import SequenceMatcher
+from sklearn.feature_extraction.text import TfidfVectorizer
+from sklearn.metrics.pairwise import cosine_similarity
+
+def tfidf_similarity(s1, s2):
+    """
+    使用 TF-IDF 和余弦相似度计算两个句子的相似性。
+    """
+    # 1. 使用 jieba 进行分词
+    s1_words = " ".join(jieba.cut(s1))
+    s2_words = " ".join(jieba.cut(s2))
+    
+    # 2. 将两句话放入一个列表中
+    corpus = [s1_words, s2_words]
+    
+    # 3. 创建 TF-IDF 向量化器并进行计算
+    try:
+        vectorizer = TfidfVectorizer()
+        tfidf_matrix = vectorizer.fit_transform(corpus)
+    except ValueError:
+        # 如果句子完全由停用词组成，或者为空，可能会报错
+        return 0.0
+
+    # 4. 计算余弦相似度
+    similarity_matrix = cosine_similarity(tfidf_matrix)
+    
+    # 返回 s1 和 s2 的相似度
+    return similarity_matrix[0, 1]
+
+def sequence_similarity(s1, s2):
+    """
+    使用 SequenceMatcher 计算两个句子的相似性。
+    """
+    return SequenceMatcher(None, s1, s2).ratio()
+
+class TestSentenceSimilarity(unittest.TestCase):
+    def test_similarity_comparison(self):
+        """比较不同相似度计算方法的结果"""
+        test_cases = [
+            {
+                "sentence1": "今天天气怎么样",
+                "sentence2": "今天气候如何",
+                "expected_similar": True
+            },
+            {
+                "sentence1": "今天天气怎么样",
+                "sentence2": "我今天要去吃麦当劳",
+                "expected_similar": False
+            },
+            {
+                "sentence1": "我今天要去吃麦当劳",
+                "sentence2": "肯德基和麦当劳哪家好吃",
+                "expected_similar": True
+            },
+            {
+                "sentence1": "Vindemiatrix提到昨天三个无赖杀穿交界地",
+                "sentence2": "Vindemiatrix昨天用三个无赖角色杀穿了游戏中的交界地",
+                "expected_similar": True
+            },
+            {
+                "sentence1": "tc_魔法士解释了之前templateinfo的with用法和现在的单独逻辑发送的区别",
+                "sentence2": "tc_魔法士解释了templateinfo的用法，包括它是一个字典，key是prompt的名字，value是prompt的内容，格式是只支持大括号的fstring",
+                "expected_similar": False
+            },
+            {
+                "sentence1": "YXH_XianYu分享了一张舰娘街机游戏的图片，并提到'玩舰娘街机的董不懂'",
+                "sentence2": "YXH_XianYu对街机游戏表现出兴趣，并分享了玩舰娘街机的经历",
+                "expected_similar": True
+            },
+            {
+                "sentence1": "YXH_XianYu在考虑入坑明日方舟，犹豫是否要从零开荒或使用初始号",
+                "sentence2": "YXH_XianYu考虑入坑明日方舟，倾向于从零开荒或初始号开荒",
+                "expected_similar": True
+            },
+            {
+                "sentence1": "YXH_XianYu提到秋叶原好多人在玩maimai",
+                "sentence2": "YXH_XianYu对学园偶像的付费石头机制表示惊讶",
+                "expected_similar": False
+            }
+        ]
+
+        print("\n相似度计算方法比较:")
+        for i, case in enumerate(test_cases, 1):
+            print(f"\n测试用例 {i}:")
+            print(f"句子1: {case['sentence1']}")
+            print(f"句子2: {case['sentence2']}")
+
+            # TF-IDF 相似度
+            start_time = time.time()
+            tfidf_sim = tfidf_similarity(case['sentence1'], case['sentence2'])
+            tfidf_time = time.time() - start_time
+
+            # SequenceMatcher 相似度
+            start_time = time.time()
+            seq_sim = sequence_similarity(case['sentence1'], case['sentence2'])
+            seq_time = time.time() - start_time
+
+            print(f"TF-IDF相似度: {tfidf_sim:.4f} (耗时: {tfidf_time:.4f}秒)")
+            print(f"SequenceMatcher相似度: {seq_sim:.4f} (耗时: {seq_time:.4f}秒)")
+
+    def test_batch_processing(self):
+        """测试批量处理性能"""
+        sentences = [
+            "人工智能正在改变世界",
+            "AI技术发展迅速",
+            "机器学习是人工智能的一个分支",
+            "深度学习在图像识别领域取得了突破",
+            "自然语言处理技术越来越成熟"
+        ]
+
+        print("\n批量处理测试:")
+        
+        # TF-IDF 批量处理
+        start_time = time.time()
+        tfidf_matrix = []
+        for i in range(len(sentences)):
+            row = []
+            for j in range(len(sentences)):
+                similarity = tfidf_similarity(sentences[i], sentences[j])
+                row.append(similarity)
+            tfidf_matrix.append(row)
+        tfidf_time = time.time() - start_time
+
+        # SequenceMatcher 批量处理
+        start_time = time.time()
+        seq_matrix = []
+        for i in range(len(sentences)):
+            row = []
+            for j in range(len(sentences)):
+                similarity = sequence_similarity(sentences[i], sentences[j])
+                row.append(similarity)
+            seq_matrix.append(row)
+        seq_time = time.time() - start_time
+
+        print(f"TF-IDF批量处理 {len(sentences)} 个句子耗时: {tfidf_time:.4f}秒")
+        print(f"SequenceMatcher批量处理 {len(sentences)} 个句子耗时: {seq_time:.4f}秒")
+
+        # 打印TF-IDF相似度矩阵
+        print("\nTF-IDF相似度矩阵:")
+        for row in tfidf_matrix:
+            for similarity in row:
+                print(f"{similarity:.4f}", end="\t")
+            print()
+
+        # 打印SequenceMatcher相似度矩阵
+        print("\nSequenceMatcher相似度矩阵:")
+        for row in seq_matrix:
+            for similarity in row:
+                print(f"{similarity:.4f}", end="\t")
+            print()
+
+if __name__ == '__main__':
+    unittest.main(verbosity=2)