Railway four-power operation and maintenance knowledge intelligent question answering method and system based on large language model

By introducing syntactic analysis of equipment identification and location data and interlocking relationship graphs into the operation and maintenance of railway electrical systems, and combining the procedural constraints of a large language model, intelligent question-and-answer results that conform to interlocking logic are generated. This solves the problem of mismatch between question-and-answer results and field equipment logic in existing technologies, and improves the accuracy and applicability of operation and maintenance questions and answers.

CN121996769APending Publication Date: 2026-05-08CREC RAILWAY ELECTRIFICATION RAILWAY OPERATIONS MANAGEMENT
4 Cites 3 Cited by

Patent Information

Application Number
CN202610465509.6
Authority / Receiving Office
CN · China
Patent Type
Applications(China)
Current Assignee / Owner
Filing Date
2026-04-10
Publication Date
2026-05-08

AI Technical Summary

Technical Problem

Existing railway electrical, electronic, and electronic control system (Electrical, Electrical, and Electronic) operation and maintenance question-answering methods based on large language models have difficulty effectively capturing the logical constraints between devices when dealing with the status or operational impact of multiple related devices, resulting in deviations between the answers and the actual operation and maintenance procedures.

Method used

By acquiring equipment identification information and spatial location data, performing syntactic analysis using a constraint alignment algorithm, and combining this with a knowledge graph of railway four-electric interlocking relationships for graph traversal, we obtain related equipment entities and interlocking logic information. Then, we apply a set of procedural constraint conditions to a large language model to generate intelligent question-and-answer results that conform to the interlocking logic.

Benefits of technology

Ensuring that the Q&A results are consistent with the logical rules between the equipment on site improves the accuracy and on-site applicability of the operation and maintenance Q&A. Real-time verification and backtracking mechanisms ensure the logical accuracy of the answers.

✦ Generated by Eureka AI based on patent content.
Patent Text Reader

Abstract

The invention relates to the technical field of railway four-power operation and maintenance, provides a railway four-power operation and maintenance knowledge intelligent question-answering method and system based on a large language model, and solves the problems of low logic accuracy and poor field applicability of an operation and maintenance question-answering result. The method comprises the following steps: acquiring a question and answer request containing a device identifier, position data and a question text; performing syntactic analysis on the problem text to obtain a target equipment entity and an operation intention, positioning graph nodes in the railway four-electric interlocking relation knowledge graph according to the equipment identifier, performing graph traversal, obtaining associated equipment entities, an electrical connection relation and interlocking logic information, and combining the associated equipment entities, the electrical connection relation and the interlocking logic information into a regulation constraint condition set; performing vector retrieval based on the equipment identifier and the position data to obtain an operation and maintenance knowledge fragment; and inputting the regulation constraint condition set and the operation and maintenance knowledge fragment into the large language model, and carrying out logic constraint on the generation process according to the regulation constraint condition set to generate an intelligent question and answer result text. The logic accuracy and field applicability of the operation and maintenance question and answer result are improved.
Need to check novelty before this filing date? Find Prior Art