Hash feature compression method and related device

Abstract

The embodiment of the invention discloses a Hash feature compression method and a related device in the field of artificial intelligence, and the method comprises the steps: obtaining a to-be-compressed Hash code corresponding to a target object belonging to a target data type, and the to-be-compressed Hash code is obtained through the coding processing of a target feature of the target object through a target Hash model; determining a low-efficiency hash bit in the to-be-compressed hash code based on the low-efficiency hash bit index, and removing the low-efficiency hash bit to obtain a compressed hash code corresponding to the target object; the low-efficiency hash bit index is an index value of a hash bit of which the importance degree meets a preset non-important condition in the target hash code; the low-efficiency hash bit index is determined according to target features of the training object belonging to the target data type and a training hash code obtained by encoding the target features of the training object through a target hash model. According to the method, the information with low reference value in the hash code can be effectively reduced, and the application of multimedia retrieval, advertisement retrieval and the like in an Internet of Vehicles scene or an intelligent traffic scene can be realized.

Description

Technical field [0001] This application relates to the field of computer technology, and more particularly to a hash special compression method and related device. Background technique [0002] With the rapid development of Internet technology and computer technology, multimedia data such as images, text, and video has grown sharply, and large-scale data retrieval has become the current research hotspot. In the face of massive multimedia data, the nearest neighboring search (Approximate Neighbor, ANN) shows a significant application advantage, making a key technique in the field of data search. [0003] Hash technology under ANN technology has received more and more attention from relevant technicians due to low storage costs and efficient query efficiency. Hash technology is used to encode high dimension data into a low-dimensional compact binary hash code; specific, given a Dimensional sample feature vector x i ∈R 1×d Hash technology aims to pass a map (ie hash function) Code ...

AI Technical Summary

Problems solved by technology

[0004] In some cases, the hash code calculated by hash technology may include information with low reference value (such as redundant information, etc.), that is, not all hash bits in the hash code are meaningful and can be Playing a positive role, storing this hash code will cause a waste of storage resources and increase unnecessary storage costs

Images