Accident causal reasoning method and device, electronic equipment and readable storage medium

Abstract

The invention provides an accident causal reasoning method and device, electronic equipment and a readable storage medium. The accident causal reasoning method comprises the following steps: acquiring a plurality of accident related factors; according to the plurality of accident related factors, constructing an uncertain information Bayesian network topological structure used for reflecting the mutual influence relationship among the plurality of accident related factors; performing calculation according to the accident investigation reports and the uncertain information Bayesian network topology structure to obtain first parameter information and second parameter information; calculating a comparison result and an uncertain information Bayesian network topological structure according to the posterior probability of the first parameter information and the second parameter information, and determining an accident causal reasoning model; and inputting the received accident evidence into the accident causal reasoning model, so that the accident causal reasoning model outputs an accident causal reasoning result. Therefore, by implementing the implementation mode, the potential relationship between accident factors during small sample data can be reflected, so that the accuracy of a causal reasoning result is improved.

Description

Technical field [0001] The present application relates to the field of artificial intelligence, in particular, to a method and apparatus causal inference accident. Background technique [0002] With the rapid development of industrial economy, transportation and storage and other needs became more and more, along with its growth, as well as the occurrence of accidents. Since the accident can not be completely avoided, so how the accident causal reasoning, and one of the most important current issues in accordance with its risk control has become a causal inference result. However, causal reasoning Fault Tree Analysis (FTA) commonly used and event tree analysis (ET), although this method can study the relationship between the cause of the accident and the results systematically, and to establish the concept of a hierarchical, structured Model. However, when this method is calculated based on Boolean logic, which led to causal inference results do not reflect the potential of the r...

AI Technical Summary

Problems solved by technology

However, this method is based on Boolean logic, which leads to the fact that the obtained causal inference results cannot reflect the potential relationship between accident factors, resulting in poor accuracy of causal inference results.

Although Bayesian network (BN) is a useful tool for describing uncertain information in causal inference models in recent years, the form of point probability of this method requires a large amount of complete data, and the results are less reliable when the data is insufficient.

Images