Text word segmentation method and device, electronic equipment and computer readable medium

Abstract

The embodiment of the invention discloses a text word segmentation method and device, electronic equipment and a computer readable medium. A specific embodiment of the method comprises the following steps: creating a first initial word library instance; for each target text corresponding to the target task information, executing a lexicon instance information replacement step: obtaining a lexicon instance information sequence corresponding to the category information sequence, wherein category information in the category information sequence is category information corresponding to the target text; and sequentially replacing the lexicon instance information of the first initial lexicon instance according to the sequence of the lexicon instance information in the lexicon instance information sequence so as to perform word segmentation on the target text. According to the embodiment, word segmentation can be quickly and efficiently carried out on the text.

Description

Technical field [0001] Embodiments of the present disclosure relate to the field of computer technology, and more particularly to text score methods, devices, electronic devices, and computer readable media. Background technique [0002] In the natural language field, the text word can be split into one word into one sentence or an article. Since there are many industry-specific vocabulary in various industries, it is often necessary to maintain multiple speakers for more preciseness. For a variety of words, the target text is used, the usual use is: During the scan target text, the corresponding rut library is loaded for the corresponding ruts. [0003] However, when the object text is used in the above manner, there is often a technical problem: [0004] First, when using the word library to perform a word, the word library is often required to be loaded into memory. Since the Chinese language is generally relatively large, and the target text is often necessary to load multipl...

AI Technical Summary

Problems solved by technology

Since the Chinese lexicon is generally relatively large, and the target text word segmentation often needs to load multiple lexicons, there is a problem of long loading time, and the efficiency of the target text word segmentation is low

[0005] Second, loading multiple thesaurus also takes up a lot of memory resources

Images