更新检测模型

chatgpt_detector_model_predict.py

@@ -20,6 +20,7 @@ import uuid
 import time
 import json
 import docx2txt
+from datetime import datetime
 
 
 pool = redis.ConnectionPool(host='localhost', port=63179, max_connections=100, db=12, password="zhicheng123*")
@@ -32,7 +33,8 @@ batch_size = 32
 # model_name = "AIGC_detector_zhv2"
 # model_name = "drop_aigc_model_2"
 # model_name = "drop_aigc_model_3"
-model_name = "/home/majiahui/project/models-llm/aigc_check_10"
+# model_name = "/home/majiahui/project/models-llm/aigc_check_10"
+model_name = "/home/majiahui/project/models-llm/weipu_aigc_512_3"
 
 
 tokenizer = AutoTokenizer.from_pretrained(model_name)
@@ -124,14 +126,14 @@ def main(content_list: list):
         reference_bool = is_reference_sentence(content_list[i])
 
         if reference_bool == False:
-            if res["robot"] > 0.8:
+            if res["robot"] > 0.9:
                 for _ in range(len(content_list[i])):
                     gpt_score_list.append(res["robot"])
                 gpt_score_sentence_list.append(res["robot"])
                 sim_word += len(content_list[i])
                 gpt_content.append(
                     "<em class=\"similar\" id='score_{}'>".format(str(i)) + content_list[i] + "\n" + "</em>")
-            elif 0.8 >= res["robot"] > 0.3:
+            elif 0.9 >= res["robot"] > 0.5:
                 for _ in range(len(content_list[i])):
                     gpt_score_list.append(res["robot"])
                 gpt_score_sentence_list.append(res["robot"])
@@ -208,7 +210,14 @@ def classify():  # 调用模型，设置最大batch_size
             }
 
             return_text = {"resilt": resilt, "probabilities": None, "status_code": 200}
-            load_result_path = "./new_data_logs/{}.json".format(queue_uuid)
+
+            # 查询增加日期
+            date_str = datetime.now().strftime("%Y-%m-%d")
+            dir_path = "./new_data_logs/{}/".format(date_str)
+            # 检查并创建目录（如果不存在）
+            os.makedirs(dir_path, exist_ok=True)
+            load_result_path = dir_path + '{}.json'.format(id_)
+            # load_result_path = "./new_data_logs/{}.json".format(query_id)
 
             print("query_id: ", queue_uuid)
             print("load_result_path: ", load_result_path)