Method for identifying sensitive information in judgment document

Abstract

The embodiment of the invention provides a method for identifying sensitive information in a judgment document, which comprises the following steps of: 1, obtaining the judgment document from a Chinese judgment document network, and performing sentence segmentation and word segmentation processing on the judgment document; 2, carrying out named entity recognition on the processed judgment document, and extracting entities and attribute values; 3, carrying out semantic role labeling on the processed judgment document, and constructing a triple about the event occurrence situation; 4, carrying out relation extraction on the extracted entities and the attribute values, and constructing a relation triple; 5, constructing a structural data network through entity alignment according to the triples and the relational triples of the event occurrence conditions; and step 6, defining sensitive information according to the information content which is not suitable for being disclosed, and markingthe corresponding sensitive information in the judgment document by utilizing the structure data network. The embodiment of the invention provides the method for identifying the sensitive informationin the judgment document, the sensitive information in the judgment document is identified by utilizing semantic understanding of machine learning on legal concepts and natural languages, and the identification method has good practical significance for judicial disclosure and guarantee of public right of informed and supervision.

Description

technical field [0001] The present invention relates to the technical field of data mining, in particular to a method for identifying sensitive information in referee documents. Background technique [0002] In order for the people's courts to implement the principle of trial openness and protect the public's right to know and supervision, judicial openness is the only way for the development of a society ruled by law. Judicial openness requires that the judicial process and results be disclosed to the parties and the society, so as to realize the openness and transparency of judicial procedures. However, for some sensitive cases or sensitive words in the cases that the public is concerned about, it will have a certain impact on the social emotions and behaviors of the public, and at the same time, public opinion will also have an impact on the trial of the case. Therefore, the filtering of sensitive information and the risk assessment of the release of trial documents have...

AI Technical Summary

Problems solved by technology

[0003] At present, the automated analysis of information in the judicial field cannot meet the actual needs. The fundamental reason is that the analysis mechanism needs to be based on the semantic understanding of legal concepts and natural language by machine learning. Due to the complexity of judicial business processes and related data Incomplete and incomplete semantic understanding and NLP theory cannot achieve application effects in other fields

Images