Semantic matching method and device based on multi-task twin network, equipment and medium

Abstract

The invention relates to the field of artificial intelligence, in particular to a semantic matching method and device based on a multi-task twin network, equipment and a medium. The method comprises the steps of obtaining a to-be-processed text and a standard text; inputting the to-be-processed text into a first feature extractor to obtain a word quantity, a word vector and a word combination vector corresponding to the to-be-processed text, and inputting the standard text into a second feature extractor to obtain a word vector, a word vector and a word combination vector corresponding to thestandard text, wherein the first feature extractor and the second feature extractor are twin networks; inputting the obtained character vector, word vector and word combination vector into a pre-trained target semantic matching model to obtain target similarity between the to-be-processed text and the standard text; and outputting a standard text corresponding to the to-be-processed text accordingto the target similarity. In addition, the invention also relates to the blockchain technology, and the standard text and the target semantic matching model can be stored in the blockchain. The method can improve the accuracy.

Description

technical field [0001] The present application relates to the technical field of artificial intelligence, in particular to a semantic matching method, device, device and medium based on a multi-task twin network. Background technique [0002] With the development of artificial intelligence technology, natural language processing technology has emerged, which involves semantic matching, that is, judging whether two sentences have the same meaning, and completing the semantic matching task through semantic matching, that is, performing data processing on the natural language expressed by users. Analysis and processing can identify the deep meaning that users actually want to express, so that they can accurately identify what customers want to ask and understand customer needs, so as to help enterprises respond quickly and solve customer problems in a timely manner, thereby improving customer satisfaction. [0003] Traditional semantic matching uses one-hot encoding or pre-trai...

AI Technical Summary

Problems solved by technology

However, one-hot encoding only has a few dimensions of 1 in the word bag-sized space, and it is difficult to represent the semantic information of a sentence in a high-dimensional sparse space.

The way of pre-training word vectors is to map words into a low-dimensional dense space, and the semantic representation of words is more mature, but the semantic representation trained in the language model task is difficult to meet the needs of semantic matching tasks, resulting in the semantic matching tasks. inaccurate result

Images