KG/PersonRelationKnowledgeGraph
1
0
Fork 0
Code Issues Pull Requests Packages Projects Releases Wiki Activity

添加备注信息

Browse Source
This commit is contained in:
lhy_in_blcu@126.com 2018-11-28 19:50:44 +08:00
parent 81d6fa1b42
commit 3395134e3c
2 changed files with 56 additions and 18 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

56
README.md
View File

@ -37,12 +37,64 @@ ChinesePersonRelationGraph, person relationship extraction based on nlp methods.
# 人物关系基础知识库 # 人物关系基础知识库
# 刘备人物关系网 1,收集人名词典
2,基于人名词典,采集搜狗人物关系图谱数据库
1# 刘备人物关系网
![image](https://github.com/liuhuanyong/ChinesePersonRelationGraph/blob/master/image/rel_graph1.png) ![image](https://github.com/liuhuanyong/ChinesePersonRelationGraph/blob/master/image/rel_graph1.png)
# 韩寒人物关系网 2# 韩寒人物关系网
![image](https://github.com/liuhuanyong/ChinesePersonRelationGraph/blob/master/image/rel_graph2.png) ![image](https://github.com/liuhuanyong/ChinesePersonRelationGraph/blob/master/image/rel_graph2.png)
3,人物关系数据库规模
|项目|数量|
|:--:|:--:|
|人物|11024|
|关系对|35995|
|关系类型|1144|
4,人物关系60%
关系类型 频次 频率 累加频率
搭档 4692 0.1303478164240471 0.1303478164240471
好友 3771 0.10476164018224247 0.23510945660628957
队友 1758 0.04883875986220691 0.2839482164684965
朋友 1681 0.04669963329258806 0.3306478497610846
丈夫 1431 0.03975441715746194 0.3704022669185465
妻子 1198 0.03328147571952439 0.4036837426380709
师傅 986 0.02739193243693744 0.4310756750750083
儿子 972 0.027003000333370376 0.4580786754083787
母亲 922 0.02561395710634515 0.4836926325147239
同学 698 0.01939104344927214 0.5030836759639961
弟弟 678 0.01883542615846205 0.5219191021224581
女儿 609 0.01691854650516724 0.5388376486276253
前女友 594 0.016501833537059675 0.555339482164685
哥哥 580 0.01611290143349261 0.5714523835981776
合作 573 0.01591843538170908 0.5873708189798867
前男友 573 0.01591843538170908 0.6032892543615959
# 回标语料构建
目录地址:EventMonitor
运行方式:cd EventMonitor , scrapy crawl eventspider
#

18
collect_person_rel.py
View File

@ -83,7 +83,7 @@ class PersonSpider:
history_names = [i.strip() for i in open('history_person_names.txt') if len(i.strip()) > 1] history_names = [i.strip() for i in open('history_person_names.txt') if len(i.strip()) > 1]
star_names = [i.strip() for i in open('star_person_names.txt') if len(i.strip()) > 1] star_names = [i.strip() for i in open('star_person_names.txt') if len(i.strip()) > 1]
name_dict = { name_dict = {
# 'star': star_names, 'star': star_names,
'history': history_names, 'history': history_names,
} }
for label, names in name_dict.items(): for label, names in name_dict.items():
@ -194,20 +194,6 @@ class PersonSpider:
if __name__ == '__main__': if __name__ == '__main__':
handler = PersonSpider() handler = PersonSpider()
# handler.spider('张学友') handler.spider_main()
# while 1:
# query = input('entere an person to spider:')
# res = handler.spider(query)
# print(res)
# handler.update_data()
# iteration = 10
# while(iteration):
# # handler.read_persons()
# handler.update_data()
# print(iteration)
# iteration -= 1
# handler.read_persons()
handler.modify_data()