Law three-level theory automatic reasoning method and device, and electronic equipment

Abstract

The invention provides a legal three-level theory automatic reasoning method and device, and electronic equipment. The method comprises steps of constructing a legal event evolution interaction map based on the multi-round interaction information; inputting the legal event evolution interaction map into a pre-training reasoning model to obtain a reasoning result of the legal event; wherein the pre-training reasoning model is obtained by constructing proposition probabilistic representations generated by combining proposition representations of different knowledge types in the legal event evolution interaction graph by utilizing a three-level theory. As a predicted path is generated based on legal three-level theory reasoning, prediction can have sufficient interpretability, for example, the condition that a legal proposition is established and the probability of supporting the legal proposition can be explained clearly, and then prediction and evidence support are provided for legal decisions.

Description

technical field [0001] The invention relates to the field of artificial intelligence, in particular to an automatic reasoning method, device and electronic equipment of the three-level theory of law. Background technique [0002] Reasoning is a very important and challenging task in the field of natural language processing. Its purpose is to use existing knowledge and inference techniques to make judgments on unseen input information. Machine reasoning requires heuristics and strategies, which are usually done by knowledgeable domain experts. This process is where machine reasoning becomes difficult for businesses to scale, as it requires a lot of expert human labor to accomplish the strategy. [0003] Machine reasoning works best in deterministic scenarios. That is, to determine if something is true, or if it will happen. Machine Reasoning has good applications in tasks such as common sense question answering, fact detection, natural language reasoning, visual common sen...

AI Technical Summary

Problems solved by technology

For example, for legal events, there is no complete knowledge base, and any expert's cognition may be biased, and legal knowledge is updated dynamically, so it is difficult to obtain complete information

In addition, in legal events, in addition to data such as support rate, winning and losing rate, etc., there is also logic between events. Therefore, it is difficult to achieve perfect reasoning results simply by using data and using machine reasoning to reason legal events.

Images