A Word Segmentation Method Based on Multidimensional Comprehensive Thesaurus

Abstract

The invention discloses an establishing method based on a multi-dimensional comprehensive lexicon. The method includes the steps of selecting data sources, conducting use amount statistics, selecting keywords according to the constraint conditions, setting up a multi-dimensional maintenance word section for the keywords, obtaining synonyms for the original keywords and singular forms of plural English keywords, completing the content of the lexicon, formulating the central keyword recognition rule, and finding out the central keywords contained in the original keywords. The invention meanwhile discloses a search word separation method based on the multi-dimensional comprehensive lexicon and a central keyword recognition method. By setting up the multi-dimensional comprehensive lexicon, applying the semantic recognition technology in the lexicon and recognizing the central keywords of commodities, a good foundation is set up for matching. By comprehensively applying a character string matching word separation method and a word separation method based on statistics and the lexicon, combining the automatic method with the manual method and participating in the maintenance upgrade of the lexicon, the word separation accuracy is improved.

Description

technical field [0001] The invention relates to the word segmentation technology in the search engine technology, in particular to the word segmentation method in the e-commerce search and the technology for understanding commodity information. Background technique [0002] With the rapid development of e-commerce, more and more suppliers provide a large number of commodities for display on the e-commerce platform. Numerous buyers and buyers want to find products that meet their own needs among so many commodities, and they cannot do without the help of e-commerce search engines. Only by searching for commodities through it can it be possible to find and select products. To browse detailed product information. [0003] In this case, buyers search for products through search, and hope that the products in the search results should not only be comprehensive, but also accurate, which puts forward higher requirements for the accuracy and recall of the search. In search technol...

AI Technical Summary

Problems solved by technology

[0012] In addition, ambiguous words, wrong words, and singular and plural numbers in English are inseparable from the understanding of information. Although the current word segmentation method based on language understanding can eliminate ambiguity to a certain extent, the method has high computational complexity. It is also difficult to adjust after a word segmentation error occurs, and it is difficult to meet the real-time requirements of e-commerce search

Images