User legal provision prediction method based on a filtering door mechanism

Abstract

The invention discloses a user legal provision prediction method based on a filtering door mechanism. The user legal provision prediction method based on the filter door mechanism comprises the stepsthat a bidirectional LSTM network is adopted to encode case description, and a coded vector passes through a filter door structure to obtain high-level representation of the case description; Selecting an appropriate text feature for each criminal name by utilizing an attention mechanism, and splicing the vector passing through the maximum pooling layer and the attention representation of each criminal name to obtain a final vector for prediction; And judging whether each criminal name starts from the case description or not by utilizing a binary classification model. The method has the advantages that in a traditional method in a user legal provision prediction system, manual features are usually matched with classic text classifiers, so that the accuracy of final legal provision prediction highly depends on the quality of the manual features, the universality of cross-business prediction is not achieved, and meanwhile the law of similar cases cannot be well predicted through the traditional method.

Description

technical field [0001] The invention relates to the field of computers, in particular to a method for predicting user laws based on a filter gate mechanism. Background technique [0002] Artificial intelligence AI technology is of great significance to the construction of service-oriented justice and modern justice, and it is also an important means to meet the legal needs of the people. AI technology has already carried out many practical applications in many fields, such as autonomous driving technology, artificial intelligence finance, AI online translation, etc. Although law belongs to the category of social science rather than natural science, it is different from philosophy, sociology and other disciplines. It has strong formal characteristics, the logic of legal reasoning is relatively clear, and the legal information is also vast and updated very quickly. AI His ability to quickly process massive amounts of data has allowed him to excel in the judicial industry. Pe...

AI Technical Summary

Problems solved by technology

There are two main problems in this way: First, manual feature extraction requires a lot of manpower, and it is not universal, and the method of extracting features or the effect of features may become invalid in another business scenario; second, the current mainstream method used in legal forecasting The model cannot handle the situation where two similar cases correspond to different legal provisions. During the modeling process, the key contextual information hidden in the data will be lost, and the contextual information can often distinguish the differences and connections between cases very well.

Therefore, the existing law prediction methods rely too much on feature engineering and cannot fully mine and understand text context information.

Images