Multivariate evidence correlation analysis method in judicial field

By constructing a multi-faceted evidence information network using Bayesian networks and stochastic policy reinforcement learning algorithms, the problem of complex correlations among multiple pieces of evidence in the judicial field is solved, enabling efficient acquisition and analysis of evidence information and supporting intelligent judicial decision-making.

CN121328694APending Publication Date: 2026-01-13BEIJING INST OF COMP TECH & APPL
4 Cites 0 Cited by

Patent Information

Application Number
CN202511483070.1
Authority / Receiving Office
CN · China
Patent Type
Applications(China)
Current Assignee / Owner
Filing Date
2025-10-16
Publication Date
2026-01-13

AI Technical Summary

Technical Problem

In the judicial field, the complex relationships between diverse evidence make it difficult to quickly and effectively obtain key information. Existing technologies are inefficient in cases with multiple types of evidence and cannot meet the needs of smart justice.

Method used

A multivariate evidence information network is constructed using a Bayesian network model and a stochastic policy reinforcement learning algorithm. The conditional probability of the correlation information between evidence is calculated through evidence trigger words and element tables. The evidence network is optimized using the Monte Carlo policy gradient algorithm, which automatically searches for key evidence points and selects the most valuable evidence subnet.

Benefits of technology

It simplifies the issue of relevance between multiple pieces of evidence, improves the efficiency of evidence analysis, provides generalization ability and flexibility, and assists in judicial decision support systems.

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

Abstract

The invention relates to a multivariate evidence correlation analysis method in the judicial field, and belongs to the technical field of intelligent processing of documents. The method comprises the following steps: loading judicial case file data and extracting an evidence content text; constructing an evidence rule template according to judicial domain knowledge and expert opinions; extracting evidence elements based on the rule template and constructing an evidence library; building a multivariate evidence information network, calculating the condition probability of association information among evidence elements based on a Bayesian network, and forming a multivariate evidence association analysis model; optimizing the multivariate evidence information network through a random strategy reinforcement learning algorithm; and calculating an information probability value of the multivariate evidence subnet, and selecting the most valuable multivariate evidence information network. According to the method, a multivariate evidence correlation analysis event of a judicial case is converted into an updating and optimizing task of a multivariate evidence information network, the complex correlation problem among multivariate evidences is simplified, a correlation model among the multivariate evidences is given, and certain auxiliary support is provided in a judicial decision support system.
Need to check novelty before this filing date? Find Prior Art