Intelligence relation extraction method based on neural network and attention mechanism

Abstract

The invention discloses an intelligence relation extraction method based on neural network and attention mechanism, and relates to the field of recurrent neural network, natural language processing and intelligence analysis combined with attention mechanism. The method is used for solving the problem of large workload and low generalization ability in the existing intelligence analysis system based on artificial constructed knowledge base. The implementation of the method includes a training phase and an application phase. In the training phase, firstly a user dictionary and training word vectors are constructed, then a training set is constructed from a historical information database, then corpus is pre-processed, and then neural network model training is conducted; in the application phase, information is obtained, information pre-processing is conducted, intelligence relation extraction task can be automatically completed, at the same time expanding user dictionary and correction judgment are supported, training neural network model with training set is incremented. The intelligence relation extraction method can find the relationship between intelligence, and provide the basis for integrating event context and decision making, and has a wide range of practical value.

Description

technical field [0001] The invention relates to the fields of cyclic neural network combined with attention mechanism, natural language processing, and information analysis, in particular to a method for extracting information relationship using a bidirectional cyclic neural network combined with attention mechanism. Background technique [0002] With the development of various technologies in the information age, the amount of information data is growing explosively. Today, intelligence information acquisition and storage technologies are relatively mature, but in the fields of intelligence analysis and key information extraction of massive intelligence data, many technical improvements are still needed. Intelligence data has the characteristics of strong theme, high timeliness, and rich implicit information. Carrying out relationship analysis on intelligence under the same theme, and integrating intelligence according to time-space, causality, etc., can complete the descr...

AI Technical Summary

Problems solved by technology

[0005] Based on the above research status, there are mainly the following problems in the relationship extraction method for intelligence: First, intelligence analysis based on knowledge framework or model requires a large number of historical cases with a wide coverage, and requires domain experts with rich professional knowledge to construct the knowledge base , that is, the workload is heavy and the completed framework may have weak generalization ability; second, the methods based on neural networks mostly stay in the research of theoretical methods, and need certain adjustments in practical applications, and now use more convolutional neural networks. Network, the effect of grasping the context of the whole sentence is not good, and the accuracy rate is not as good as Bi-directional RNN without special processing

Images