Semantic matching method and device and storage medium

Abstract

The embodiment of the invention discloses a semantic matching method and device and a storage medium, and is applied to the technical field of information processing. The method includes: enabling Thesemantic matching device to determine word pair characteristics of the to-be-matched text and the target text according to the first word characteristic of the to-be-matched text and the second wordcharacteristic of the target text; And converting the word pair characteristics, the first word characteristics and the second word characteristics into semantic matching vectors, enabling the formatsof the semantic matching vectors to be the same as the format of input data in a preset semantic classification model, and determining the similarity between the to-be-matched text and the target text according to the semantic matching vectors and the semantic classification model. In this process, when a semantic matching vector is determined, the text to be matched and the target text are directly obtained, the time of multiplication calculation between vectors is saved, the matching process of the text to be matched and the target text is simplified, then the structure for achieving semantic matching is simplified, and the training process of the structure for achieving semantic matching is correspondingly simplified.

Description

technical field [0001] The invention relates to the technical field of information processing, in particular to a semantic matching method, device and storage medium. Background technique [0002] Semantic matching technology can be applied to user interaction systems such as search engines and question answering systems. Specifically, users can input text or voice through the user interaction system, so that the user interaction system will perform semantic matching on the text or voice input by the user to determine the user's The intention of the input text or voice, so as to give feedback to the user according to the result of semantic matching. [0003] An existing semantic matching method is mainly based on keywords for matching, and in addition uses word-level information such as word weights to assist in judgment, which is fast and interpretable. However, this method does not deal with unknown words, resulting in computational complexity. The accuracy rate is lower....

AI Technical Summary

Problems solved by technology

[0003] An existing semantic matching method is mainly based on keywords for matching, and in addition uses word-level information such as word weights to assist in judgment, which is fast and interpretable. However, this method does not deal with unknown words, resulting in computational complexity. low accuracy

[0004] Another semantic matching method is mainly based on the semantic matching model of learning, which can better calculate the semantic similarity of non-keyword hits. In this process, the semantic matching model needs to analyze the word feature vectors of each text Multiplication and other calculations make the structure of the semantic matching model more complicated, so it needs to rely on a large amount of training data and more training time to train the semantic matching model, and the training prediction speed is slow

Images