Semantic matching method and system for knowledge retrieval and question answering of power transformer

Abstract

The invention discloses a semantic matching method and system for knowledge retrieval and question answering of a power transformer, and belongs to the technical field of power transformer equipment. According to an existing semantic matching method, retrieval / question and answer semantics of base-level operation inspection personnel are difficult to accurately recognize, and the operation inspection efficiency of the base-level operation inspection personnel is affected. According to the semantic matching method for knowledge retrieval and question answering of the power transformer, a corpus enhancement model based on a small sample transformer question sentence template is constructed, and enhancement of a transformer corpus text and data enhancement are realized in combination with a transformer knowledge graph and a synonym word library; transformer corpus data and an artificial neural network technology are utilized to train and form an integrated recognition model; and through the integrated identification model, combined identification of user query intentions and slot positions is realized on the basis of corpora, so that user retrieval / question and answer semantics can be accurately identified, and the operation inspection efficiency of the user is effectively improved.

Description

technical field [0001] The invention relates to a semantic matching method and system for power transformer knowledge retrieval and question answering, and belongs to the technical field of power transformer equipment. Background technique [0002] There is a large amount of knowledge in equipment operation and inspection, such as equipment maintenance standards, guidelines, and equipment failure cases. Electric power knowledge is a frequent occurrence and key concern of grassroots inspection personnel in business execution. At present, the application form of these common knowledge is mainly based on keyword retrieval, and the knowledge application such as knowledge-based search and question answering is still in the exploratory stage. [0003] Furthermore, electric power companies have built a vertical knowledge map around transformer equipment. The map contains various knowledge points related to transformers, including transformer ledgers, transformer faults, and testing...

AI Technical Summary

Problems solved by technology

[0007] 2) There are a large number of approximation methods

[0011] Due to the above problems, the existing semantic matching method for power transformer knowledge retrieval and question answering is difficult to accurately identify the retrieval / question semantics of grassroots inspection personnel, which affects the efficiency of inspection personnel at the grassroots level

Images