Weak evidence aggregation-based common sense causal reasoning method and system

Abstract

The invention provides a common sense causal reasoning method and system based on weak evidence aggregation. The causal reasoning problem of a user is deduced by using the weak causal evidence and the common sense causal knowledge so as to obtain a causal sentence pair. The method is characterized in that the method comprises the following steps: acquiring a causal reasoning problem, determining a corresponding problem type, a problem premise and a candidate item according to the causal reasoning problem; identifying the type of the problem to obtain an identification result, and preprocessing the premise of the problem and the candidate item according to the identification result to obtain preprocessed data; inputting the preprocessed data into a pre-trained common sense causal reasoning model, and obtaining a causal sentence pair, so that a user makes judgment according to the causal sentence, wherein the common sense causal reasoning model not only considers the coverage rate and the accuracy rate of causal evidence, but also fuses various sparse weak evidence aggregation models containing common sense causal knowledge, so the method has a good causal reasoning effect.

Description

technical field [0001] The invention belongs to the field of data identification, and in particular relates to a common sense causal reasoning method and system based on weak evidence aggregation. Background technique [0002] Since the dawn of artificial intelligence, commonsense reasoning has been recognized as one of the major challenges in this field. Common sense is a basic and important concept in human thinking and knowledge. It is born naturally from human daily behavior, established by convention, and shared by most people. Common sense knowledge is the most basic knowledge in the world. Common sense reasoning is an application of common sense knowledge. For example, it is known that cold and cold are synonyms, and cold and frozen are synonyms, and then it can be inferred that cold and freezing are synonyms; it is known that it has rained for a week, and it can be deduced that the air is very humid. The causal relationship is the basic law summed up by human being...

AI Technical Summary

Problems solved by technology

However, common-sense causal knowledge is difficult to obtain, and common-sense causal knowledge is usually widely known and sparsely present in the corpus

Images