Resume data automatic labeling method, system, medium and equipment
By constructing a tagging system and a large language model for automatic annotation of historical data, the problem of ineffective utilization of equipment and component historical data in the power industry has been solved, and automatic structuring of historical data and continuous updating of fault knowledge have been achieved.
Patent Information
- Application Number
- CN202511013194.3
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- Filing Date
- 2025-07-22
- Publication Date
- 2025-11-11
AI Technical Summary
In the power industry, the history data of equipment components is not effectively stored and utilized, making it difficult to solidify and pass on expert experience, and hindering the automatic history analysis and extraction and utilization of fault knowledge.
A tagging system is constructed, which obtains resume data through a large language model and extracts fault knowledge. If a match is found, a new tag is added; if no match is found, a new tag is generated, thus realizing automatic labeling of resume data.
It has achieved automatic structuring and standardization of resume data, established a continuous update mechanism for the fault knowledge base, solved the data silo problem, and improved the efficiency of fault knowledge extraction and utilization.