|
@@ -2519,7 +2519,7 @@ class DocChannel():
|
|
113: '业主采购'
|
|
113: '业主采购'
|
|
}
|
|
}
|
|
if original_docchannel in not_extract_dic:
|
|
if original_docchannel in not_extract_dic:
|
|
- return {'docchannel': {'docchannel':'', 'doctype':not_extract_dic[original_docchannel]}}
|
|
|
|
|
|
+ return {'docchannel': {'docchannel':'', 'doctype':not_extract_dic[original_docchannel], "original_docchannel_id": str(original_docchannel)}}
|
|
if web_source_no in ['02104-7']:
|
|
if web_source_no in ['02104-7']:
|
|
return {'docchannel': {'docchannel':'', 'doctype':'采招数据'}}
|
|
return {'docchannel': {'docchannel':'', 'doctype':'采招数据'}}
|
|
|
|
|
|
@@ -2534,7 +2534,7 @@ class DocChannel():
|
|
data_content, data_title = self.predict_process(docid='', doctitle=title[-50:], dochtmlcon=content) # 标题最多取50字
|
|
data_content, data_title = self.predict_process(docid='', doctitle=title[-50:], dochtmlcon=content) # 标题最多取50字
|
|
text_len = len(data_content[0]) if len(data_content[0])<self.sequen_len else self.sequen_len
|
|
text_len = len(data_content[0]) if len(data_content[0])<self.sequen_len else self.sequen_len
|
|
title_len = len(data_title[0]) if len(data_title[0])<self.title_len else self.title_len
|
|
title_len = len(data_title[0]) if len(data_title[0])<self.title_len else self.title_len
|
|
- result = {'docchannel': {'docchannel':'', 'doctype':''}}
|
|
|
|
|
|
+ result = {'docchannel': {'docchannel':'', 'doctype':'', "original_docchannel_id": str(original_docchannel)}}
|
|
|
|
|
|
array_content = embedding(data_content, shape=(len(data_content), self.sequen_len, 128))
|
|
array_content = embedding(data_content, shape=(len(data_content), self.sequen_len, 128))
|
|
array_title = embedding(data_title, shape=(len(data_title), self.title_len, 128))
|
|
array_title = embedding(data_title, shape=(len(data_title), self.title_len, 128))
|