Basic human error probability evaluation method and apparatus, device, medium and product

By combining a multi-agent analysis framework and a knowledge graph database, the problem of long time consumption and low efficiency in assessing the probability of human error in existing technologies is solved, achieving efficient and accurate assessment of the probability of human error and improving the efficiency of safety risk assessment.

WO2026138586A1 Publication Date: 2026-07-02TSINGHUA UNIVERSITY
5 Cites 1 Cited by

Patent Information

Application Number
PCT/CN2025/142912
Authority / Receiving Office
WO · WO
Patent Type
Applications
Current Assignee / Owner
Priority Date
2024-12-24
Filing Date
2025-12-16
Publication Date
2026-07-02

AI Technical Summary

Technical Problem

Existing technologies rely heavily on expert knowledge when assessing the probability of human error, resulting in a cumbersome and time-consuming assessment process, which is particularly difficult to perform efficiently in complex systems and multi-factor situations.

Method used

By employing a multi-agent analysis framework combined with a knowledge graph database, and through task analysis, context analysis, cognitive activity analysis, and time constraint analysis of target case information, multiple indicator parameters of basic human error probability are generated, thereby assessing the probability of human error.

Benefits of technology

It enables efficient quantification and assessment of the probability of human error, improves the efficiency of safety risk assessment, reduces assessment time, provides strong decision support, and reduces reliance on expert knowledge.

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

Abstract

The present application relates to the technical field of data analysis, in particular to a basic human error probability evaluation method and apparatus, a device, a medium and a product. The method comprises: acquiring target case information that needs to be analyzed; inputting the target case information into a pre-constructed multi-agent analysis framework, the multi-agent analysis framework outputting a multi-agent analysis result of the target case information; and, on the basis of a pre-constructed knowledge graph database and the multi-agent analysis result, generating values of a plurality of indicator parameters of a basic human error probability, and, on the basis of the knowledge graph database and the values of the plurality of indicator parameters, evaluating the basic human error probability for the target case information. Thus, the present application solves the problems of high dependence on expert knowledge, long evaluation time, low evaluation efficiency, etc. in the prior art.
Need to check novelty before this filing date? Find Prior Art