Searching method and device, computer equipment and storage medium

Abstract

The invention relates to a search method and device, computer equipment, a storage medium and a computer program product. The method comprises the following steps: in response to a query request for a target object, determining a to-be-queried feature vector corresponding to the target object; according to a preset vector segment division rule, dividing the to-be-queried feature vector to obtain multiple segments of to-be-queried sub-vectors, and based on a pre-stored codebook database, performing clustering calculation on the to-be-queried sub-vectors to obtain sub-distances between the to-be-queried sub-vectors and multiple clustering centers corresponding to each segment; determining a target index distance according to the sub-distances corresponding to the multiple segments of to-be-queried sub-vectors, and determining a target feature vector corresponding to the target index distance according to the target index distance and the index sub-vectors corresponding to the clustering centers; and searching according to the identification information of the target feature vector to obtain media data corresponding to the target object. By the adoption of the method, rapid retrieval and real-time processing of the newly-added objects can be carried out in mass data.

Description

technical field [0001] The present application relates to the technical field of artificial intelligence, and in particular, to a search method, apparatus, computer equipment, storage medium and computer program product. Background technique [0002] With the rapid development of Internet technology and the rapid development of 5th Generation Mobile Communication Technology (5G), mainstream applications represented by Weibo, WeChat, Douyin, and Kuaishou will generate massive amounts of media data. It may include various types of data, such as picture data, voice data, and video data, etc. The above-mentioned massive media data has become the main carrier of information dissemination. With the generation of massive media data, the types of data are becoming more and more diverse, and the confrontation of multimedia technology is rapidly increasing. There are more and more demands for business scenario analysis of media data, and the requirements for media retrieval dimensions...

AI Technical Summary

Problems solved by technology

[0003] The method of media analysis and retrieval in related technologies is to perform customized scenario training on a media engine in advance, such as specific person detection, specific environment detection, and specific object detection, and analyze, process and score real-time data for these customized scenarios. Determine whether one of the scenarios is satisfied, mark the data that meets the scenario, and the upper-level business application system searches for data according to the mark, and cannot retrieve new objects

Images