Deep learning and pattern matching-based person, case and object association relation extraction method

Abstract

The invention relates to a person, case and object association relation extraction method based on deep learning and pattern matching. The method comprises the steps: analyzing a legal instrument, and dividing the legal instrument into five parts: basic information of the instrument, command and control content, dialectical opinions, evidence correlation and judgment content; the method comprises the following steps: performing relation definition and entity definition, summarizing all relation sets and entity sets which need to be extracted, performing relation labeling and entity labeling on legal documents according to the defined relation sets and entity sets, performing entity recognition model training on a training set through a Bert-BiLSTM-CRF model, and performing entity recognition on the entity recognition model through a Bert-BiLSTM-CRF model. Calculating the accuracy rate and the recall rate of the test set through the trained model; performing a dependency syntax analysis task, and performing pattern matching definition on required entities, relationships and entity triple relationships after a relationship set and an entity set are defined; entity position information and sentences are input by taking a corresponding relation as a label and a sentence-based attention mechanism is combined with a CNN network, and a deep learning model is trained.

Description

technical field [0001] The invention relates to a judicial data processing technology, in particular to a method for extracting associations between persons, cases and objects based on deep learning and pattern matching. Background technique [0002] With the continuous growth of data scale, the application of artificial intelligence and big data processing in real life continues to land. People have more urgent needs for the implementation of related applications in the field of smart justice. It is one of them for judges, lawyers and other judicial personnel who are often in contact with the law. In order to obtain the required information, the staff in the judicial field often need to read a large number of legal documents and rely on manpower to extract the required relationship structure information from the legal documents. This process is very inefficient and cumbersome, which seriously affects their work efficiency. Even if the China Judgment Documents Network prov...

AI Technical Summary

Problems solved by technology

Its defects are also very obvious. Due to the data-driven, when the amount of data is insufficient or the data distribution is uneven, the accuracy will be very low

And the data needs a lot of manual labeling, the cost is high, and the interpretability of the results is poor

Images