Method and system for recommending search terms

Abstract

The invention provides a method and system for recommending search terms. The method for recommending the search terms comprises the steps that header information of information issued by an issuer is extracted to obtain one or more subject terms and one or more descriptors used for limiting the subject terms; the combinations of the subject terms and one or more descriptors are used as the search terms; first evaluation values of the search terms are respectively obtained by multiplying the term frequency of the search terms by the inverse document frequency of the search terms; the inverse category frequency of the search terms in specific categories is respectively calculated and used as second evaluation values of the search terms; the evaluation values of the search terms are respectively added in a weighing mode to obtain issuer recommendation degree evaluation values of the search terms; recommendation terms are selected from the search terms according to the issuer recommendation degree evaluation values. The method and system can improve the information matching degree of the issuer and a finder.

Description

technical field [0001] The invention relates to the network field, in particular to a method and system for recommending search words. Background technique [0002] With the development of e-commerce websites, more and more commodity transactions and transactions have moved from offline to online. There are three main roles here, buyers, buyers and platforms; platforms provide sellers with information release and display, and buyers Provide information query to obtain the products you need. Common e-commerce platforms generally provide buyers with search services to find the products they need. Generally, they provide a search engine as a tool for obtaining buyer information. Which products and which merchants are listed on it, find the products that meet your needs and complete the transaction, so the platform can establish a bridge for information communication between buyers and sellers, or information publishers and searchers with similar relationships. [0003] Howeve...

AI Technical Summary

Problems solved by technology

[0005] The problem with such a solution is that although a certain scale of buyer behavior can be considered, it can partially solve the one-sided search method of a certain part of users, but the biggest problem with this solution is one-sidedness, and the richness and satisfaction of information expansion are not enough. , only using buyer information, that is, the search habits of specific customer groups on this website, it is difficult to detect the emergence of new search words, and cannot solve the problem of information mismatch to the greatest extent; because the website generally uses user search words Statistics, and then form an extended word recommendation list by means of clustering and association, but it is difficult to give good recommendation results for new products or suddenly popular products; and it is impossible to really solve the problem of information mismatch between buyers and sellers. In the case of asymmetric professional knowledge, the seller's description method sometimes does not match the buyer's, which leads to the failure of some sellers' information and products to be well displayed in the search, which affects the user experience and revenue of website buyers and sellers

Images