work history information extraction method based on a double-layer BiLSTM-CRF

A technology of information extraction and work, applied in neural learning methods, digital data information retrieval, instruments, etc., can solve the problem of low extraction rate, and achieve the effect of improving extraction performance, enriching entity information, and good presentation effect.

Active Publication Date: 2019-04-19
SUN YAT SEN UNIV +1
View PDF3 Cites 10 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

However, this method separates the connection between entities, resulting in a low extraction rate

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
  • work history information extraction method based on a double-layer BiLSTM-CRF
  • work history information extraction method based on a double-layer BiLSTM-CRF
  • work history information extraction method based on a double-layer BiLSTM-CRF

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0071] A method for extracting work history information based on a two-layer BiLSTM-CRF provided in this embodiment, such as figure 1 , including the following steps:

[0072] S1: Preprocessing of work history information;

[0073] S2: Split the work history information into work history according to time, and preprocess the work history;

[0074] S3: Use the two-layer BiLSTM-CRF model to extract the information entities of work experience;

[0075] S4: further processing the information entity extracted in S3;

[0076] S5: Organize information.

[0077] The preprocessing of work history information in step S1 includes extracting information other than work location, organizational department and position.

[0078] The work experience in step S2 is a sentence including the work location, organizational department and position.

[0079] The double-layer BiLSTM-CRF model in step S3, such as image 3 As shown, specifically:

[0080] Including the first BiLSTM-CRF model and...

Embodiment 2

[0130] A system for extracting work history information based on a two-layer BiLSTM-CRF provided in this embodiment, such as Figure 4 , including preprocessing module, extraction module, disambiguation module, association module and perfection module, among which:

[0131] The preprocessing module completes the preprocessing of the work history information, splits the work history information into work experience according to time, and preprocesses the work history, and its output terminal is connected to the input terminal of the extraction module;

[0132] The extraction module uses the double-layer BiLSTM-CRF model to extract the information entity of the work experience, and its output is connected to the input of the disambiguation module;

[0133] The disambiguation module completes the calculation of the information entity using the disambiguation algorithm, modifies the entity, and its output terminal is connected to the input terminal of the association module;

[0...

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 work history information extraction method based on a double-layer BiLSTM-CRF which comprises the following steps: S1, preprocessing work history information; S2, according to the time division work history information as work experience, preprocessing the work experience; S3: utilizing double-layer BiLSTM-CRF model extracts the information entity of the work experience;S4, further processing the information entity extracted in the step S3; S5, arranging information. A Double-layer BiLSTM model is used in the invention so that the CRF model can better extract the information entity in the work experience. The problem that information extraction is difficult due to factors such as information entity intersection and Chinese information entity irregularity is better solved. Besides, a traditional information extraction task is divided into a plurality of sub-tasks, a disambiguation module and an association module are added, high aggregation and low coupling are achieved, extraction can be conducted concurrently, the extraction performance is improved, the context relation can be fully utilized, and entity information is enriched. The information extractiontask can be better completed, and a better presentation effect is obtained.

Description

technical field [0001] The present invention relates to the field of automatic information extraction, and more specifically, relates to a method for extracting work history information based on a two-layer BiLSTM-CRF. Background technique [0002] Work history is very important for getting to know a person. However, due to the relatively large amount of information in the resume, the readability is low and the speed of obtaining information is slow. If the resume can be structured and the information in the text can be extracted, the speed and quality of information acquisition can be greatly improved, and it can also provide a data basis for subsequent analysis. [0003] It is very difficult to extract the information entities of the work experience in the work history. Including the location of work, organizational department, job title, etc. On the one hand, the difficulty comes from the irregularity of location, organizational department, position, etc., and the flex...

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
Patent Type & Authority Applications(China)
IPC IPC(8): G06F16/332G06F17/27G06Q10/10G06N3/04G06N3/08
CPCG06N3/08G06Q10/105G06F40/295G06N3/045
Inventor 林创伟赖韩江印鉴高静
Owner SUN YAT SEN UNIV
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