Resume information extraction method and system based on deep learning

An information extraction and deep learning technology, applied in the field of resume information extraction methods and systems based on deep learning, can solve problems such as time-consuming and labor-intensive, missing keywords, limited feature selection and corpus, and achieve good generalization ability , the effect of strong representational ability

Pending Publication Date: 2021-11-30
的卢技术有限公司
View PDF0 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0004] The traditional named entity extraction technology is based on the Chinese keyword matching method. This technology needs to build the keyword thesaurus required in the system. The disadvantage is that some keywords may be missed and it is time-consuming and labor-intensive.
Statistical methods, such as conditional random fields and hidden Markov models, do not need to build a thesaurus compared to keyword matching, but they are limited by the selection of features and corpus

Method used

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
View more

Image

Smart Image Click on the blue labels to locate them in the text.
Viewing Examples
Smart Image
  • Resume information extraction method and system based on deep learning
  • Resume information extraction method and system based on deep learning
  • Resume information extraction method and system based on deep learning

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0032] refer to figure 1 , which is the overall flowchart of a method for extracting resume information based on deep learning proposed in this embodiment. The current entity extraction technology is mainly based on the Chinese keyword matching method, and it is necessary to build the keyword thesaurus required in the system , in the face of a large amount of data, there are cases of missing keywords, or limited by the selection of features and corpus, and this method is also time-consuming and labor-intensive, and the extraction is not accurate and comprehensive enough.

[0033] In order to solve the above problems, this embodiment can well deal with complex semi-structured data in the resume by applying the method of deep learning to the extraction of resume information.

[0034] Specifically, this embodiment proposes a method for extracting resume information based on deep learning, including:

[0035] S1: Collect the Chinese corpus of resumes as training data. It should ...

Embodiment 2

[0052] refer to figure 2 , which is a schematic diagram of the overall structure of a resume information extraction system based on deep learning proposed in this embodiment. The method for extracting resume information based on deep learning proposed in the above embodiment can be realized by relying on this embodiment. The system includes collecting Module 100, extraction module 200.

[0053] Wherein, the collection module 100 is used to collect and construct training data; the extraction module 200 constructs a neural network model according to the data collected by the collection module 100, and extracts information based on the neural network model.

[0054] Further, the collection module 100 includes that the real-time data collection unit 101 obtains the resume information on the major recruitment websites in real time; the historical data storage unit 102 stores the historical extraction results, and the historical data storage unit 102 includes a labeling module M fo...

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to view more

PUM

No PUM Login to view more

Abstract

The invention discloses a resume information extraction method and system based on deep learning. The method comprises the following steps: collecting Chinese corpora of resumes, and taking the Chinese corpora as training data; constructing a neural network model according to information of the Chinese corpora; training the constructed neural network model through the training data until convergence; and inputting resumes into the neural network for information extraction. The method and the system have the beneficial effects that complex semi-structured data in resumes can be well dealt with when the method provided by the invention is used for extracting resume information; due to the fact that deep learning has strong characterization capabilities, features can be well extracted; and meanwhile, the method also has good generalization ability and is suitable for information extraction.

Description

technical field [0001] The present invention relates to the technical field of natural language processing, in particular to a method and system for extracting resume information based on deep learning. Background technique [0002] In recent years, with the rapid development of the Internet and the information industry, a large amount of unstructured data and semi-structured data can be obtained from the Internet. Using crawler technology, a large amount of resume text information can be obtained from the Internet. Since resumes contain a lot of data content, how to quickly integrate the data in resumes and populate them into the database as a resource for talent screening is very important for many companies. [0003] For resume information, the main data information to be extracted includes name, phone number, age, gender, graduate school, education background, and occupations that have been engaged. The information is extracted and stored in the database as a prelimina...

Claims

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to view more

Application Information

Patent Timeline
no application Login to view more
IPC IPC(8): G06F16/35G06F40/295G06N3/04G06N3/08
CPCG06F16/353G06F40/295G06N3/08G06N3/044G06N3/045
Inventor 张晋
Owner 的卢技术有限公司
Who we serve
  • R&D Engineer
  • R&D Manager
  • IP Professional
Why Eureka
  • Industry Leading Data Capabilities
  • Powerful AI technology
  • Patent DNA Extraction
Social media
Try Eureka
PatSnap group products

Browse by: Latest US Patents, China's latest patents, Technical Efficacy Thesaurus, Application Domain, Technology Topic.

© 2024 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap