Index construction method and device, vector search method and retrieval system

Abstract

The invention relates to the technical field of data retrieval, and discloses an index construction method and device, a vector search method and a retrieval system. The index construction method comprises the steps that a target vector and a first clustering set where the target vector is located are determined, and the first clustering set has a corresponding first representative point; determining at least one second representative point meeting a preset condition for the first clustering set; index association between the target vector and the first representative point and the index association between the target vector and the second representative point are established respectively. Based on the above scheme, in the subsequent vector retrieval process, the distances between the first representative point and the query vector and between the second representative point and the query vector can be calculated respectively to query the corresponding target cluster set, so that the target vector corresponding to the query vector is obtained more accurately, and the query efficiency is improved. The problem that the search precision is low due to the fact that the center point of the clustering set cannot completely represent all the feature vectors in the clustering set can be effectively avoided, and the search precision is effectively improved.

Description

technical field [0001] The present application relates to the technical field of data retrieval, and in particular, to an index construction method, device, vector search method and retrieval system. Background technique [0002] With the rapid growth of data, data retrieval is widely used in image, video, speech, protein molecular structure retrieval and other fields. Since all kinds of data, such as picture data, can be abstracted into high-dimensional feature vectors, the difference between data The similarity can be quantified as the distance between feature vectors in the vector space. For example, the closer the distance between two feature vectors, the higher the similarity of the original data corresponding to the two feature vectors. Therefore, data retrieval can be transformed into vector search in the vector space, that is, the process of searching the database for several data similar to the data to be queried is transformed into the process of searching the dat...

AI Technical Summary

Problems solved by technology

[0005] In order to solve the problem of low accuracy of the retrieval results of the vector retrieval method, the embodiment of the present application provides an index construction method, device, vector retrieval method and retrieval system

Images