|
@@ -4107,8 +4107,8 @@ def getProjectContacts(list_entity, list_sentence):
|
|
|
# project_contacts "项目联系人"提取
|
|
# project_contacts "项目联系人"提取
|
|
|
temp_person_entitys = [ent for ent in list_entity if ent.entity_type=='person' and ent.label in [1,2,3]]
|
|
temp_person_entitys = [ent for ent in list_entity if ent.entity_type=='person' and ent.label in [1,2,3]]
|
|
|
temp_person_entitys = sorted(temp_person_entitys,key=lambda x:(x.sentence_index,x.wordOffset_begin))
|
|
temp_person_entitys = sorted(temp_person_entitys,key=lambda x:(x.sentence_index,x.wordOffset_begin))
|
|
|
- project_contacts_patterns = ['项目.?联系[人方]', '项目.?负责人']
|
|
|
|
|
- project_contacts_patterns_prob = [0.9, 0.8]
|
|
|
|
|
|
|
+ project_contacts_patterns = ['项目.?联系[人方]','项目.?联系.?方式', '项目.?负责人']
|
|
|
|
|
+ project_contacts_patterns_prob = [0.9, 0.85, 0.8]
|
|
|
project_contacts_patterns_res = []
|
|
project_contacts_patterns_res = []
|
|
|
for ent in temp_person_entitys:
|
|
for ent in temp_person_entitys:
|
|
|
sent_idx = ent.sentence_index
|
|
sent_idx = ent.sentence_index
|
|
@@ -4116,7 +4116,7 @@ def getProjectContacts(list_entity, list_sentence):
|
|
|
# word_end = ent.wordOffset_end
|
|
# word_end = ent.wordOffset_end
|
|
|
in_att = ent.in_attachment
|
|
in_att = ent.in_attachment
|
|
|
if word_begin >= 5: # > len('项目联系人')
|
|
if word_begin >= 5: # > len('项目联系人')
|
|
|
- left_text = list_sentence[sent_idx].sentence_text[max(0, word_begin - 10):word_begin]
|
|
|
|
|
|
|
+ left_text = list_sentence[sent_idx].sentence_text[max(0, word_begin - 15):word_begin]
|
|
|
# print('left_text', left_text)
|
|
# print('left_text', left_text)
|
|
|
for pattern, prob in zip(project_contacts_patterns, project_contacts_patterns_prob):
|
|
for pattern, prob in zip(project_contacts_patterns, project_contacts_patterns_prob):
|
|
|
if re.search(pattern, left_text):
|
|
if re.search(pattern, left_text):
|
