增加问题模板第几个

final/ByRules/app.py

@@ -26,7 +26,6 @@ app = Flask(__name__)
 # DATA_FOLDER = resource_path("final/Json/json_data")
 
 
-
 BASE_DIR = os.path.dirname(os.path.abspath(__file__))
 TEMPLATE_FOLDER = os.path.join(BASE_DIR, "templatesJson")
 DATA_FOLDER = os.path.join(BASE_DIR, "..", "Json", "json_data")
@@ -36,7 +35,6 @@ MAPPING_FOLDER = os.path.join(BASE_DIR, "..", "Json", "sjgxys")
 MAPPING_FILE = os.path.join(MAPPING_FOLDER, "sjgxys.json")
 
 
-
 @app.route('/process_query', methods=['POST'])
 def process_query_route():
     data = request.get_json()
@@ -116,7 +114,7 @@ def process_query_route():
         elif result['type'] == 'topN':
             topN = result["conditions"]['rank']
             del result["conditions"]['rank']
-            print(topN)
+            # print(topN)
             final_value = find_top_n_by_value(folder_path=DATA_FOLDER,
                                               file_name=result["dataJsonName"],
                                               value_key=result['value_key'],
@@ -137,6 +135,36 @@ def process_query_route():
                 "play": result["play"]
             }
             return jsonify(response)
+        # TopN
+        elif result['type'] == 'rank':
+            rank = result["conditions"]['rank2']
+            del result["conditions"]['rank2']
+            # print(topN)
+            final_value = find_top_n_by_value(folder_path=DATA_FOLDER,
+                                              file_name=result["dataJsonName"],
+                                              value_key=result['value_key'],
+                                              name_key=result['name_key'],
+                                              mapping_file=MAPPING_FILE,
+                                              conditions=result["conditions"],
+                                              top_n=rank,  # 查前3高
+                                              descending=True
+                                              )
+            # keys = [result['name_key'], result['value_key']]
+            contentResult = final_value[rank - 1]
+            # 构造需要填充的列表
+            fillResult = [rank, contentResult[result['name_key']]]
+            final_content = fill_template_auto(result['content'], fillResult)
+            response = {
+                "rank": rank,
+                "content": final_content,
+                "content_text": result["content"],
+                "raw_result": final_value,
+                "conditions": result["conditions"],
+                "name": result["name"],
+                "play": result["play"],
+                "qcode": result["qcode"]
+            }
+            return jsonify(response)
     except Exception as e:
         return jsonify({"error": str(e)}), 500
 

final/ByRules/similarity_answer_json.py

@@ -52,7 +52,8 @@ template_dict = {
     "23": ["省间交易当年参与交易的家次有多少？"],
     "24": ["某年送出电量前五名是谁？"],
     "25": ["某年受入电量前五名是谁？"],
-    "26": ["某年送出电量第五名是谁？"],
+    "26": ["某年受入电量第五名是谁？"],
+    "27": ["某年送出电量第五名是谁？"],
 }
 # 将地点映射成相应的代码
 def map_location_to_unit(location: str) -> str:
@@ -269,9 +270,32 @@ def extract_time_location(question: str) -> Tuple[List[Dict], List[str]]:
         # print(f"匹配到的排名为：{rank}")
     else:
         rank = None
-        print("未匹配到排名")
+        # print("未匹配到排名")
 
-    return time_results, locations, rank
+
+
+    # 匹配“第五”或“top 5”等形式
+    rank_match2 = re.search(r'(第\s*)(\d+|[一二两三四五六七八九十])\s*(名)', question, re.IGNORECASE)
+
+    # rank_match = re.search(
+    #     r'(前|top\s*|第\s*)(\d+|[一二三四五六七八九十])\s*(名)?',
+    #     question,
+    #     re.IGNORECASE
+    # )
+
+    if rank_match2:
+        rank_str = rank_match2.group(2)
+        if rank_str.isdigit():
+            rank2 = int(rank_str)
+        else:
+            rank2 = chinese_digit_map.get(rank_str, None)
+
+        # print(f"匹配到的排名为：{rank}")
+    else:
+        rank2 = None
+        # print("未匹配到排名")
+
+    return time_results, locations, rank, rank2
 
 # 先用 extract_time_location 判断问句包含哪类时间信息，然后只对结构匹配的模板子集做余弦匹配。
 # def classify_by_time_type(query, time_info):
@@ -282,7 +306,7 @@ def extract_time_location(question: str) -> Tuple[List[Dict], List[str]]:
 def classify_by_time_type(query, time_info):
     if not time_info:
         # 无时间信息时，返回指定模板 19-23
-        return ['19', '20', '21', '22', '23', '17.1', '17.2', '17.3', '17.4', '18.1', '18.2', '18.3', '18.4','24','25']
+        return ['19', '20', '21', '22', '23', '17.1', '17.2', '17.3', '17.4', '18.1', '18.2', '18.3', '18.4','24','25','26','27']
 
     time = time_info[0]
 
@@ -296,17 +320,17 @@ def classify_by_time_type(query, time_info):
 
     # 情况 3：仅 year，全年
     if 'year' in time and 'month' not in time:
-        return ['1','8.1','8.2','8.3','8.4','9.1','9.2','9.3','9.4','9.5','9.6','9.7','9.8','9.9','9.10','9.11','9.12','9.13','9.14','9.15','9.16','9.17','16.1','16.2','21','22','23','24','25']  # 某年全年累计交易电量
+        return ['1','8.1','8.2','8.3','8.4','9.1','9.2','9.3','9.4','9.5','9.6','9.7','9.8','9.9','9.10','9.11','9.12','9.13','9.14','9.15','9.16','9.17','16.1','16.2','21','22','23','24','25','26','27']  # 某年全年累计交易电量
 def match_template_with_time_filter(query, template_dict, tokenizer, extract_time_location_func):
     """
     先基于时间信息筛选候选模板，再进行TF-IDF匹配。
     """
     # 提取时间
-    time_info, _, _ = extract_time_location_func(query)
-    print(time_info)
+    time_info, _, _, _ = extract_time_location_func(query)
+    # print(time_info)
     # 通过时间判断候选模板 key
     candidate_keys = classify_by_time_type(query, time_info)
-    print(candidate_keys)
+    # print(candidate_keys)
     # 构造候选子模板字典
     filtered_template_dict = {k: template_dict[k] for k in candidate_keys}
     # 使用你原来的 TF-IDF 匹配函数
@@ -377,7 +401,7 @@ def load_template_info(matched_key, json_folder):
     return data
 def process_query(query, template_dict, json_folder, tokenizer=jieba_tokenizer):
     # 提取条件
-    time_info, location_info, rank_info = extract_time_location(query)
+    time_info, location_info, rank_info, rank_info2 = extract_time_location(query)
 
     conditions = {}
     # 匹配模板
@@ -427,6 +451,10 @@ def process_query(query, template_dict, json_folder, tokenizer=jieba_tokenizer):
 
     if rank_info:
         conditions['rank'] = rank_info
+
+    if rank_info2:
+        conditions['rank2'] = rank_info2
+
     # 查询模板json
     template_info = load_template_info(matched_key, json_folder)
     # 模板的关键词
@@ -447,6 +475,8 @@ def process_query(query, template_dict, json_folder, tokenizer=jieba_tokenizer):
     content = template_info.get("content", "")
     # 动作类型
     play = template_info.get("play", "")
+    # 问题序号
+    qcode = template_info.get("qcode", "")
     return {
         "matched_key": matched_key,
         "matched_template": best_sentence,
@@ -462,8 +492,8 @@ def process_query(query, template_dict, json_folder, tokenizer=jieba_tokenizer):
         "play": play,
         "find_max": find_max,
         "value_key": value_key,
-        "name_key": name_key
-
+        "name_key": name_key,
+        "qcode": qcode
     }
 # 查询类
 def smart_find_value(folder_path, file_name, conditions: dict, target_key: str):
@@ -528,26 +558,28 @@ def find_key_recursively(data, target_key):
 
 # query = "2023年省间交易电量新能源交易电量是多少？？"
 # query = "今年1月到2023年2月累计交易电量是多少?"
+# query = "2024年送出电量第二名是谁?"
+query = "2024年7月、8月、12月交易电量的平均值是多少?"
+
+json_folder = "templatesJson"
+
 #
-# json_folder = "templatesJson"
 #
-# #
-# #
-# result = process_query(query, template_dict, json_folder)
+result = process_query(query, template_dict, json_folder)
 #
-# # print(result)
-# print(result['content'])
-# print("匹配的模板 key：", result["matched_key"])
-# print("最相似的模板句：", result["matched_template"])
-# print("相似度分数：", result["similarity_score"])
-# print("类型：", result["type"])
-# print("关键词：", result["keywords"])
-# print("查询字段：", result["target"])
-# print("模型名字", result["name"])
-# print("条件", result["conditions"])
-# print("返回的内容是：", result["content"])
-# print("问句是：", result["query"])
-# print("动作是：", result["play"])
+print(result)
+print(result['content'])
+print("匹配的模板 key：", result["matched_key"])
+print("最相似的模板句：", result["matched_template"])
+print("相似度分数：", result["similarity_score"])
+print("类型：", result["type"])
+print("关键词：", result["keywords"])
+print("查询字段：", result["target"])
+print("模型名字", result["name"])
+print("条件", result["conditions"])
+print("返回的内容是：", result["content"])
+print("问句是：", result["query"])
+print("动作是：", result["play"])
 
 # query = "当月送出均价最高的是哪个省？？"
 # query = ("2025年送出电量前五名是谁？？")

final/ByRules/templatesJson/26.json

@@ -1,11 +1,11 @@
 {
   "dataJsonName": "sjjy1_B05_output",
-  "type": "topN",
+  "type": "rank",
   "value_key": "受入电量",
   "name_key": "单位",
-  "top_n": 5,
-  "content": "送出电量排名分别为：&",
+  "rank": 1,
+  "content": "第&名是：&",
   "play": "讲述文本",
   "name": "省间交易",
-  "qcode": "25"
+  "qcode": "26"
 }

final/ByRules/templatesJson/27.json

@@ -0,0 +1,11 @@
+{
+  "dataJsonName": "sjjy1_B04_output",
+  "type": "rank",
+  "value_key": "送出电量",
+  "name_key": "单位",
+  "rank": 1,
+  "content": "第&名是：&",
+  "play": "讲述文本",
+  "name": "省间交易",
+  "qcode": "27"
+}