Similarity search method and device
A similarity search and similarity technology, applied in the computer field, can solve problems such as low query rate per second, slow index creation, QPS, memory occupation, etc., so as to reduce the search range, improve the similarity search efficiency, and improve the calculation efficiency. Effect
Pending Publication Date: 2021-12-07
BEIJING WODONG TIANJUN INFORMATION TECH CO LTD +1
View PDF0 Cites 0 Cited by
- Summary
- Abstract
- Description
- Claims
- Application Information
AI Technical Summary
Problems solved by technology
In the current field of similarity search, due to technical reasons such as slow index creation and low query QPS (Queries PerSecond, query rate per second), it is impossible to support targets to be matched on the order of billions and millions of orders Search for query targets. At the same time, the existing similarity search system will occupy a large amount of memory for a long time, making it impossible to apply to offline query business or scenarios with limited memory.
Method used
the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
View moreImage
Smart Image Click on the blue labels to locate them in the text.
Smart ImageViewing Examples
Examples
Experimental program
Comparison scheme
Effect test
Embodiment Construction
[0027] Exemplary embodiments of the present invention are described below in conjunction with the accompanying drawings, which include various details of the embodiments of the present invention to facilitate understanding, and they should be regarded as exemplary only. Accordingly, those of ordinary skill in the art will recognize that various changes and modifications of the embodiments described herein can be made without departing from the scope and spirit of the invention. Also, descriptions of well-known functions and constructions are omitted in the following description for clarity and conciseness.
[0028] It should be noted that, in the case of no conflict, the embodiments of the present invention and the technical features in the embodiments can be combined with each other.
[0029] figure 1 is a schematic diagram of the main steps of the similarity search method according to the embodiment of the present invention.
[0030] Such as figure 1 As shown, the similar...
the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to View More PUM
Login to View More Abstract
The invention discloses a similarity search method and device, and relates to the technical field of computers. A specific embodiment of the method comprises the following steps: acquiring feature vectors of a plurality of to-be-matched targets, and distributing the feature vectors to a plurality of computing nodes in a computer cluster according to categories to which the to-be-matched targets belong; creating an index for the feature vectors of the to-be-matched targets of each category at each computing node, wherein the feature vectors with the same index are located in the same index partition corresponding to the index; establishing a mapping relationship between the category and the index partition; obtaining a feature vector of the query target, determining an index partition corresponding to the query target according to the category to which the query target belongs and the mapping relationship; and searching in the determined index partition by using the feature vector of the query target to obtain a preset first number of to-be-matched targets similar to the query target. According to the embodiment, similarity search for billions of to-be-matched targets and millions of query targets can be supported.
Description
technical field [0001] The invention relates to the field of computer technology, in particular to a similarity search method and device. Background technique [0002] Similarity search refers to obtaining one or more targets most similar to the input query target among a large number of targets to be matched. In the current field of similarity search, due to technical reasons such as slow index creation and low query QPS (Queries PerSecond, query rate per second), it is impossible to support targets to be matched on the order of billions and millions of orders At the same time, the existing similarity search system will occupy a large amount of memory for a long time, making it impossible to apply to offline query business or scenarios with limited memory. Contents of the invention [0003] In view of this, the embodiments of the present invention provide a similarity search method and device, which can improve search efficiency and support similarity search for billions...
Claims
the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to View More Application Information
Patent Timeline
Login to View More Patent Type & Authority Applications(China)
IPC IPC(8): G06F16/2458G06F16/2453G06K9/62G06F16/951
CPCG06F16/2462G06F16/24539G06F16/951G06F18/22
Inventor 范聪
Owner BEIJING WODONG TIANJUN INFORMATION TECH CO LTD