附件文本无法识别的问题

BiddingKG/app.py

@@ -73,63 +73,65 @@ class MyProcessor(allspark.BaseProcessor):
         data_res = ""
         try:
             if "content" in data:
-                log("get request of doc_id:%s"%(_doc_id))
-                k = str(uuid.uuid4())
-                cost_time = dict()
                 content = data['content']
-                start_time = time.time()
-                list_articles,list_sentences,list_entitys,_cost_time = Preprocessing.get_preprocessed([[k,content,"",_doc_id,_title]],useselffool=True)
-                log("get preprocessed done of doc_id%s"%(_doc_id))
-                cost_time["preprocess"] = time.time()-start_time
-                cost_time.update(_cost_time)
-                '''
-                for articles in list_articles:
-                    print(articles.content)
-                    
-                '''
-                start_time = time.time()
-                codeName = self.codeNamePredict.predict(list_sentences,list_entitys=list_entitys)
-                log("get codename done of doc_id%s"%(_doc_id))
-                cost_time["codename"] = time.time()-start_time
-
-                start_time = time.time()
-                self.premPredict.predict(list_sentences,list_entitys)
-
-                self.premPredict.predict(list_sentences,list_entitys)
-                log("get prem done of doc_id%s"%(_doc_id))
-                cost_time["prem"] = time.time()-start_time
-                start_time = time.time()
-                self.roleRulePredict.predict(list_articles,list_sentences, list_entitys,codeName)
+                data_res  = predict(_doc_id,content,_title)
+                # log("get request of doc_id:%s"%(_doc_id))
+                # k = str(uuid.uuid4())
+                # cost_time = dict()
+                #
+                # start_time = time.time()
+                # list_articles,list_sentences,list_entitys,_cost_time = Preprocessing.get_preprocessed([[k,content,"",_doc_id,_title]],useselffool=True)
+                # log("get preprocessed done of doc_id%s"%(_doc_id))
+                # cost_time["preprocess"] = time.time()-start_time
+                # cost_time.update(_cost_time)
+                # '''
+                # for articles in list_articles:
+                #     print(articles.content)
+                #
+                # '''
+                # start_time = time.time()
+                # codeName = self.codeNamePredict.predict(list_sentences,list_entitys=list_entitys)
+                # log("get codename done of doc_id%s"%(_doc_id))
+                # cost_time["codename"] = time.time()-start_time
+                #
+                # start_time = time.time()
+                # self.premPredict.predict(list_sentences,list_entitys)
+                #
+                # self.premPredict.predict(list_sentences,list_entitys)
+                # log("get prem done of doc_id%s"%(_doc_id))
+                # cost_time["prem"] = time.time()-start_time
+                # start_time = time.time()
                 # self.roleRulePredict.predict(list_articles,list_sentences, list_entitys,codeName)
-                cost_time["rule"] = time.time()-start_time
-                start_time = time.time()
-                self.epcPredict.predict(list_sentences,list_entitys)
-                log("get epc done of doc_id%s"%(_doc_id))
-                cost_time["person"] = time.time()-start_time
-                start_time = time.time()
-                entityLink.link_entitys(list_entitys)
-                '''
-                for list_entity in list_entitys:
-                    for _entity in list_entity:
-                        for _ent in _entity.linked_entitys:
-                            print(_entity.entity_text,_ent.entity_text)
-                '''
-                prem = getAttributes.getPREMs(list_sentences,list_entitys,list_articles)
-                log("get attributes done of doc_id%s"%(_doc_id))
-                cost_time["attrs"] = time.time()-start_time
-
-
-                '''
-                
-                
-                for entitys in list_entitys:
-                    for entity in entitys:
-                        print(entity.entity_text,entity.entity_type,entity.sentence_index,entity.begin_index,entity.label,entity.values)
-                '''
-                #print(prem)
-                data_res = predict(docid)
-                data_res["cost_time"] = cost_time
-                data_res["success"] = True
+                # # self.roleRulePredict.predict(list_articles,list_sentences, list_entitys,codeName)
+                # cost_time["rule"] = time.time()-start_time
+                # start_time = time.time()
+                # self.epcPredict.predict(list_sentences,list_entitys)
+                # log("get epc done of doc_id%s"%(_doc_id))
+                # cost_time["person"] = time.time()-start_time
+                # start_time = time.time()
+                # entityLink.link_entitys(list_entitys)
+                # '''
+                # for list_entity in list_entitys:
+                #     for _entity in list_entity:
+                #         for _ent in _entity.linked_entitys:
+                #             print(_entity.entity_text,_ent.entity_text)
+                # '''
+                # prem = getAttributes.getPREMs(list_sentences,list_entitys,list_articles)
+                # log("get attributes done of doc_id%s"%(_doc_id))
+                # cost_time["attrs"] = time.time()-start_time
+                #
+                #
+                # '''
+                #
+                #
+                # for entitys in list_entitys:
+                #     for entity in entitys:
+                #         print(entity.entity_text,entity.entity_type,entity.sentence_index,entity.begin_index,entity.label,entity.values)
+                # '''
+                # #print(prem)
+                # data_res = predict(docid)
+                # data_res["cost_time"] = cost_time
+                # data_res["success"] = True
                 #return json.dumps(Preprocessing.union_result(codeName, prem)[0][1],cls=MyEncoder,sort_keys=True,indent=4,ensure_ascii=False)
             else:
                 data_res = {"success":False,"msg":"content not passed"}

BiddingKG/dl/interface/predictor.py

@@ -1884,13 +1884,13 @@ def save_money_model():
             model = models.load_model(model_file,custom_objects={'precision':precision,'recall':recall,'f1_score':f1_score})
             model.summary()
             print(model.weights)
-            # tf.saved_model.simple_save(sess,
-            #                            "./money_savedmodel2/",
-            #                            inputs = {"input0":model.input[0],
-            #                                      "input1":model.input[1],
-            #                                      "input2":model.input[2]},
-            #                            outputs = {"outputs":model.output}
-            #                            )
+            tf.saved_model.simple_save(sess,
+                                       "./money_savedmodel2/",
+                                       inputs = {"input0":model.input[0],
+                                                 "input1":model.input[1],
+                                                 "input2":model.input[2]},
+                                       outputs = {"outputs":model.output}
+                                       )
     
 
 def save_person_model():