Fault diagnosis knowledge graph updating method and device

Abstract

The invention relates to a fault diagnosis knowledge graph updating method and device, computer equipment, a storage medium and a computer program product. The method comprises the following steps: acquiring a fault diagnosis knowledge graph, wherein the edge weight of the fault diagnosis knowledge graph comprises a subjective weight and an objective weight; performing fault diagnosis according to the edge weight of the fault diagnosis knowledge graph to obtain a fault diagnosis result recommendation list; pushing the fault diagnosis result recommendation list to the user, and collecting a feedback result of the user; and according to a feedback result, updating the subjective weight and the objective weight in the edge weights of the fault diagnosis knowledge graph to obtain an updated fault diagnosis knowledge graph. By adopting the method, high-precision fault diagnosis can be supported.

Description

technical field [0001] The present application relates to the technical field of fault diagnosis, and in particular to a method, device, computer equipment, storage medium and computer program product for updating a knowledge map of fault diagnosis. Background technique [0002] With the advancement of science and technology, the functions of various equipment or systems are becoming more and more powerful, the structures are becoming more and more complex, and the corresponding failure rate is also increasing. In order to ensure the normal operation of equipment or systems and ensure safety and reliability , to improve operating efficiency and reduce the failure loss rate, it is very necessary to perform fault diagnosis. Among them, fault diagnosis based on knowledge graph is a widely used method. Accurate fault diagnosis results can avoid equipment or system failure during operation. It can help the staff to obtain the real cause of the failure, and perform technical repai...

AI Technical Summary

Problems solved by technology

[0003] In the prior art, when diagnosing faults by constructing knowledge graphs and Bayesian networks, only the impact of big data on the accuracy of knowledge graphs is considered, which is limited by the amount of data, that is, when the amount of current data is small, its faults The accuracy of the diagnosis results is low; and the method of sorting out the fault list is manual, which is highly subjective and relatively large in error, which affects the accuracy of the fault diagnosis results

The above method has the problem that the fault diagnosis result is not accurate enough

Images