Event extraction and processing method for case-following electronic files

Abstract

The invention discloses an event extraction and processing method for case-following electronic files. The method comprises the following steps: step 1, acquiring required file data from a case-following electronic file circulation processing platform and storing the required file data into a database; 2, constructing an event trigger word dictionary, matching an electronic file event descriptionparagraph, and performing text preprocessing methods such as sentence segmentation, word segmentation and part-of-speech tagging; 3, event attribute extraction: combining dependency syntax analysis and a semantic role labeling method to obtain six event attributes including an applicant, a susceptor, a behavior, time, a place and a mode of an event; and step 4, event aggregation: aggregating the atomic events into topic events, combining similar topic events, and storing the topic events into an event database. According to the method, the problem that crime fact information is rapidly obtained by the case-following electronic file is solved, event extraction and organization can be more accurately carried out on crime facts, and the method is a basis for efficient and high-quality paper marking.

Description

technical field [0001] The invention belongs to the technical field of natural language processing, and in particular relates to an event extraction and processing method for case electronic files. Background technique [0002] With the continuous development of science and technology, the construction of judicial informatization is also deepening. At present, the number of electronic case files stored by judicial departments at all levels (procuratorates, courts, and the Ministry of Justice) is increasing by tens of millions every year. The document contains the collective wisdom of judicial practitioners in our country for many years, and the data information contained in it is an important data asset that cannot be fully utilized by existing technologies. According to a third-party evaluation report, courts at all levels across the country have digitized case information in 2016. At present, the construction of judicial informatization has initially solved the problem of...

AI Technical Summary

Problems solved by technology

Some methods such as Chinese patent CN106951438 use convolutional neural network models to identify trigger words, and obtain event parameters through graph models, which require large-scale labeling of corpus. Large-scale high-quality data is difficult to achieve; Chinese patent CN10892044 adopts an event parameter extraction method based on syntactic analysis, and Chinese patent CN106951438 adopts a rule-based event attribute extraction method. high

Images