Chinese resume multi-entity recognition method based on BERT-BiLSTM-CRF combined model

By using the BERT-BiLSTM-CRF model, combined with a pre-trained language model and a bidirectional long short-term memory network, the problems of entity type ambiguity and inaccurate boundary localization in Chinese resumes were solved, achieving high-precision multi-entity recognition and improving the recognition effect.

CN122334248APending Publication Date: 2026-07-03JINBAOXIN SOCIAL SECURITY CARD TECH CO LTD
0 Cites 0 Cited by

Patent Information

Authority / Receiving Office
CN · China
Patent Type
Applications(China)
Current Assignee / Owner
JINBAOXIN SOCIAL SECURITY CARD TECH CO LTD
Filing Date
2026-04-13
Publication Date
2026-07-03

AI Technical Summary

Technical Problem

Existing technologies for processing Chinese resumes suffer from problems such as ambiguity in entity types, insufficient capture of long-distance dependencies, and inaccurate entity boundary localization, resulting in low recognition accuracy and recall.

Method used

The BERT-BiLSTM-CRF joint model is adopted. A deep semantic vector sequence is generated by a pre-trained language model and offset mapping information is recorded. A bidirectional long short-term memory network is combined to capture long-distance contextual dependencies. A conditional random field layer is used for decoding, and entity boundaries are aligned based on the offset mapping information to achieve high-precision entity recognition.

Benefits of technology

It improves the accuracy and recall of entity recognition in Chinese resumes, accurately distinguishes entity types, solves the problem of entity boundary positioning offset, and meets the strict requirements of downstream applications for location information.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure CN122334248A_ABST
    Figure CN122334248A_ABST
Patent Text Reader

Abstract

This invention discloses a multi-entity recognition method for Chinese resumes based on a BERT-BiLSTM-CRF joint model, belonging to the field of natural language processing and information extraction technology. The method performs deep semantic encoding on the original resume text using a pre-trained language model and generates offset mapping information. Then, it utilizes a bidirectional long short-term memory network to capture long-distance contextual dependencies in the text, enhancing sequence features. Next, it performs global decoding based on label transfer rules through a conditional random field layer to obtain the optimal word-level entity label sequence. Finally, based on the offset mapping information, the sequence is mapped and merged into a character-level entity recognition result. This invention effectively solves the problems of entity type ambiguity, insufficient capture of long-distance dependencies, and inaccurate entity boundary localization in Chinese resume parsing, and can accurately jointly identify multiple key entities in the three modules of educational background, work experience, and job expectations.
Need to check novelty before this filing date? Find Prior Art