Method and device for constructing search thesaurus

Abstract

The invention discloses a method and a device for constructing a search lexicon, and relates to the field of computers. A specific implementation of the method includes: determining a plurality of search terms from a data source, and the number of searches corresponding to any of the plurality of search terms; obtaining the initial weight value of any of the search terms, using The initial weight value and the search times corresponding to the search word calculate the actual weight value of the search word; select the search word whose actual weight value meets the preset weight condition, and construct the search word library. This embodiment can quickly build a search vocabulary based on data sources in different language environments, and at the same time can increase the exposure of new items and enhance user experience.

Description

technical field [0001] The invention relates to the field of computers, in particular to a method and device for constructing a search vocabulary. Background technique [0002] The search system is a system that uses specific computer programs to collect information resources according to a certain strategy, and returns the required information to the user according to the user's input. With the rapid development of Internet technology, the search system has become the core system of various Internet application fields. [0003] In the search system, a search word refers to a system preset word that is closely related to the user's search input information and triggered by the search input information for the user to select. For example, if you enter "tea" in the input box of a search system, words such as "tea", "tea set" and "tea table" will appear in the drop-down box, and "black tea" and "jasmine tea" will also appear in the lower part of the input box. etc., the "tea"...

AI Technical Summary

Problems solved by technology

[0005] 1. The construction process of the search thesaurus is relatively complicated; in the case of a shortage of initial data sources, the ability to quickly build the search thesaurus is lacking;

[0006] 2. When determining the search term, the weight of the search term corresponding to the new item is not adjusted, which makes the exposure of the new item lower and affects the user experience;

[0007] 3. The update period of the existing search thesaurus is generally relatively fixed, it is difficult to change reasonably according to the data change, and the system usability is poor;

[0008] 4. Existing construction methods of search thesaurus are mostly built for a specific language, which is highly coupled with this language and has poor applicability to other languages

Images