Commodity search query strategy generation method and device

Abstract

The invention discloses a commodity search query strategy generation method and device, and the method comprises the steps: selecting a matching range limiting strategy when the length of a search statement meets a first threshold value, or else, selecting a field weighting strategy; when a matching range limiting strategy is selected, if segmented words in a word segmentation result of the searchstatement are successfully matched with phrase windows in pre-acquired offline data, limiting the matching range of the search statement according to the phrase windows which are successfully matched, and generating a query strategy; and when a field weighting strategy is selected, if the segmented words in the word segmentation result of the search statement contain the feature words of the query intention in the offline data, weighting the query intention fields corresponding to the segmented words in the word segmentation result to generate a query strategy. According to the method, the query strategy is generated according to the matching range limiting strategy or the field weighting strategy, so that the sorting effect of different types of searches is improved, and the sorting correlation of candidate commodities is improved under the condition of considering the recall rate.

Description

technical field [0001] The invention relates to the technical field of Internet e-commerce commodity search, in particular to a method and device for generating a query strategy for commodity search. Background technique [0002] In the existing technology, the search is usually matched against the literal text symbols of words, that is, word segmentation is performed on the search terms, and then all field information of the product is traversed. If a product contains all or most of the terms of the search term (referring to the word segmentation results in ), the product will be matched, but due to other factors, the product may not meet the search expectations, and the following phenomena will exist: [0003] 1. The search effect of long-tail words with weak regularity between terms is not good; [0004] 2. The ordering of accessories will appear in disorder in front of the main parts; [0005] 3. The ability to distinguish intent search is weak, mainly involving "trial...

AI Technical Summary

Problems solved by technology

[0007] In order to solve the problems of the prior art, an embodiment of the present invention provides a method and device for generating a query strategy for product search, so as to overcome the problems in the prior art that the products in the search results are not strongly correlated with the search sentences.

Images