Event detection method and system, intelligent terminal and computer readable storage medium

Abstract

The invention discloses an event detection method and system, an intelligent terminal and a computer readable storage medium, and the event detection method carries out event detection based on a self-attention model and a multilayer perceptron, and comprises the steps: obtaining a to-be-detected statement and an event category sequence; combining the to-be-detected statement with the event category sequence to generate to-be-detected data; the self-attention model and the multi-layer perceptron are obtained, the event category probability corresponding to the to-be-detected statement is obtained based on the self-attention model and the multi-layer perceptron, the self-attention model is used for detecting the to-be-detected data and outputting semantic vectors of the to-be-detected data, and the semantic vectors of the to-be-detected data are input to the multi-layer perceptron; the multi-layer perceptron is used for acquiring the probability of each event category in the event category sequence corresponding to the to-be-detected statement based on the semantic vector corresponding to the event category sequence. Compared with the prior art, the scheme of the invention does not need to use keywords, and is beneficial to improving the efficiency and accuracy of event detection.

Description

technical field [0001] The present invention relates to the technical field of natural language processing, in particular to an event detection method, system, intelligent terminal and computer-readable storage medium. Background technique [0002] With the development of science and technology, especially the rapid development of artificial intelligence and deep neural network, natural language processing technology has been widely used, and event detection has also received more and more attention. The purpose of event detection is to judge the event category corresponding to the sentence. Specifically, it can be used to classify natural language data and extract useful information. [0003] Event detection in the prior art relies on keyword recognition technology, specifically, when performing event detection (whether it is based on the sentence that needs to be detected when performing event detection, or in the process of training the model that needs to be used in the ...

AI Technical Summary

Problems solved by technology

[0005] The main purpose of the present invention is to provide an event detection method, system, intelligent terminal and computer-readable storage medium, aiming at solving the problem of identifying and extracting keywords when performing event detection based on keywords in the prior art. The extraction process is complicated, the amount of calculation is large, the time is long, and the accuracy is low, which affects the efficiency and accuracy of event detection and is not conducive to the problem of event detection

Images