Commodity search method and device, computer equipment and storage medium

Abstract

The invention discloses a commodity search method and device, computer equipment and a storage medium, and the method comprises the steps of receiving a query request of an e-commerce user, and extracting a search keyword in the request; performing data preprocessing on the searched keywords, and constructing a corresponding word vector matrix; inputting the word vector matrix into a category prediction model trained to a convergence state, enabling the category prediction model to execute category prediction operation to determine evaluation scores of different categories in a category structure hit by the word vector matrix, wherein the category structure organizes different categories in at least two levels; and constructing a search result list, and pushing the search result list to the e-commerce user, the search result list comprising a plurality of categories of commodity objects with relatively high evaluation scores. According to the invention, the category structure and the category prediction model are combined, the matched commodities are accurately and efficiently queried for the keywords from the dimension of the category, the commodities are systematically and orderly displayed according to the hierarchy of the category, and the relevance of retrieval is effectively improved.

Description

technical field [0001] Embodiments of the present invention relate to the technical field of e-commerce, in particular, a commodity search method, device, computer equipment, and storage medium. Background technique [0002] At present, users of the e-commerce service platform can search for the goods they need to display by entering search keywords. However, when users enter search keywords, they may not know what keywords to use to express their needs. Therefore, the search results returned according to the search keywords entered by the user may not meet the actual needs of the user, and the number of products displayed in the product display list may be relatively large. On the user's terminal device, due to the limited display area of ​​the device , the number of products displayed in the current display area is also very limited. Therefore, if the platform is inaccurate for the product the user is looking for, the user may need to swipe the screen to browse the product...

AI Technical Summary

Problems solved by technology

[0002] At present, users of the e-commerce service platform can search for the goods they need to display by entering search keywords. However, when users enter search keywords, they may not know what keywords to use to express their needs. Therefore, the search results returned according to the search keywords entered by the user may not meet the actual needs of the user, and the number of products displayed in the product display list may be relatively large. On the user's terminal device, due to the limited display area of ​​the device , the number of products displayed in the current display area is also very limited. Therefore, if the platform is inaccurate for the product the user is looking for, the user may need to swipe the screen to browse the product he is searching for, and correspondingly, Products displayed later may be ignored by users due to the need for a long user operation path, so that these products cannot get effective exposure opportunities

It can be seen that in the process of providing query results, the accuracy of product query results directly affects the sorting of products, and will directly affect the actual transaction results of products

Images