Commodity search method and device, server and storage medium

Abstract

The invention discloses a commodity search method and device, a server and a storage medium, and belongs to the technical field of the Internet. The commodity search method comprises the steps: obtaining target semantic information in response to a target search request of a terminal; according to the target semantic information, determining at least one target commodity category corresponding tothe target semantic information and a position weight of the target commodity category; determining position information of a target commodity corresponding to the target commodity category in the commodity interface according to the position weight of the target commodity category; and returning the commodity information and the position information of the target commodity to the terminal. According to the method, the target commodity category can be directly judged according to the target semantic information of the target search request, manual configuration is not needed, and the generalization ability is high. Moreover, the position information of the target commodity corresponding to the target commodity category in the commodity interface is determined according to the position weight of the target commodity category, so the commodity required by the user can be preferentially displayed in the commodity interface.

Description

technical field [0001] The present application relates to the technical field of the Internet, in particular to a commodity search method, device, server and storage medium. Background technique [0002] With the development of Internet technology, more and more e-commerce companies have emerged, including fresh food e-commerce companies. Fresh food e-commerce refers to the use of e-commerce to sell fresh products, such as fruits, vegetables or meat, on the Internet. Users can search for the desired fresh products through the client installed on the terminal. However, Chinese expressions generally have multiple meanings. The same word expression often corresponds to multiple types of products. For example, when a user searches for "apple", it may be the fruit they want to eat, or it may be apple-flavored yogurt. At this time, it is necessary to distinguish the commodity category that the user intends to search, so as to help the user find the desired commodity faster and b...

AI Technical Summary

Problems solved by technology

[0004] However, the cost and maintenance cost of manual configuration of commodity categories is high and difficult, and the randomness of user search request expression leads to low coverage of manual configuration and poor generalization ability, which makes it difficult to meet the massive demand for online services of fresh food search engines. Search requests for commodity category intent judgment requirements

Images