Broad application requirement retrieval method and system

Abstract

The invention provides a broad application requirement retrieval method and a system. The method comprises the following steps: analyzing a query word of the broad application requirement retrieval so as to obtain a concept label or an attribute label of the query word, wherein the concept label and the attribute label respectively describe the category and attribute of the application; matching in a pre-arranged application label system according to the concept label or the attribute label of the query word, so as to obtain the applications containing the concept label or the attribute label; obtaining relativity marks of the applications according to the concept label or the attribute label of the query word, ordering the applications according to the marks, and offering the ordered applications, as the result of the query word, to the user. The technical scheme adopted by the invention can improve the diversity and relativity of the retrieval result in broad requirement retrieval scenes.

Description

【Technical Field】 [0001] The present invention relates to the field of Internet applications, in particular to an application-wide demand retrieval method and system. 【Background technique】 [0002] At present, application (APP, Application) retrieval mainly includes pan-demand retrieval and precise retrieval. In the pan-demand retrieval, the query entered by the user describes not a specific application, but a type of application; for example, listening Song software, racing games, etc. In the prior art, the method of performing application retrieval based on the query input by the user is as follows: Step 1. The query input by the user is segmented to obtain a corresponding term list. The term list includes more than one word segmentation obtained after word segmentation, for example, query "Which navigation software is better", the corresponding term list is "term1: navigation, term2: software, term3: which, term4: good"; step 2, according to the word segmentation in the term...

AI Technical Summary

Problems solved by technology

[0003] The above method of application retrieval based on user-input query can achieve good retrieval results when applied to precise retrieval scenarios, and the retrieval results can meet user needs, but the retrieval effect is poor when applied to general-demand retrieval scenarios. For example, simple query Segment words, and search based on the name and title of the application, so it is impossible to accurately locate the user's deep-seated needs for a certain type of application based on the query, and it is impossible to obtain accurate search results. Moreover, when searching for the same type of application, each user expresses There are differences in the habits of query, but the purpose of retrieval is the same. If word segmentation and matching are performed only based on query, only a small number of retrieval results can be provided, and the retrieval results are relatively limited, which cannot meet the retrieval needs of users.

For example, taking the query as "which navigation software is better" as an example, using the current method, when there are three applications in the database, Baidu Maps, Gaode Maps, and Kay Rucker Mobile Navigation, use the title for matching retrieval, that is, the name of the application The term in the query must be clearly included, so that only "Kai Rucker Mobile Navigation" can be retrieved; however, for the query "Which is the best navigation software", what the user wants to get is actually a navigation application, not a specific Application software, therefore, the search results obtained in this way have limitations and cannot meet the user's search needs

Images