Want to achieve:
For a fixed format of Chinese resume, information extraction, the final output to the corresponding field for the JSON format

Great god you have better ideas, we can discuss communication
Don't want to use regular expressions to achieve completely, later period maintenance cost is too high

CodePudding user response:

Mainly to the laws of your own information

CodePudding user response:

In addition to the similar "names", "degree", "work experience" the title, other information also have no law, great god can provide the train of thought about upstairs?

CodePudding user response:

The a Chinese resume, information extraction, the final output to the corresponding field for the JSON format

Recruit interns artificial processing,

CodePudding user response:

The

refer to the original poster guo2312668 response:

want to accomplish:
For a fixed format of Chinese resume, information extraction, the final output to the corresponding field for the JSON format

Great god you have better ideas, we can discuss communication
Don't want to use regular expressions to achieve completely, later period maintenance cost is too high

The building Lord, how are you, solve the problem?

CodePudding user response:

You can use NLP processing try

First section clause, then participle

Keyword extraction: artificial maintenance keywords and similar words (email: email, email, mail, email), to extract the keywords from the result of a paragraph of word segmentation, extracting information

CodePudding user response:

Jieba collocation of machine learning can be broken, but you this cost is a bit high

CodePudding user response:

Use NLP processing is ok that we use is spacy library

CodePudding user response:

The

reference 7 building small leaf response:

use NLP processing is better that we use is spacy library

Spacy how to deal with the Chinese?