Calculation method, device, equipment and storage medium for anchor similarity

A calculation method and similarity technology, which are applied in the field of neural networks to achieve the effect of increasing exposure and increasing viewing time.

Active Publication Date: 2021-08-13
GUANGZHOU HUYA TECH CO LTD
View PDF5 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0005] The present invention provides a method, device, device and storage medium for calculating anchor similarity, which solves the problem of how to accurately recommend anchors with high user similarity when user data is sparse

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 more

Image

Smart Image Click on the blue labels to locate them in the text.
Viewing Examples
Smart Image
  • Calculation method, device, equipment and storage medium for anchor similarity
  • Calculation method, device, equipment and storage medium for anchor similarity
  • Calculation method, device, equipment and storage medium for anchor similarity

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0026] figure 1 It is a flow chart of a calculation method for anchor similarity provided by Embodiment 1 of the present invention. The technical solution in this embodiment is optionally applicable to a scenario where the anchor similarity is calculated through the list of anchors followed by the user. However, it can be understood that this technical solution can also be applied to other application scenarios, as long as there is a problem that the similarity between words needs to be calculated through word vectors. The method is executed by a device for calculating the similarity of anchors. The device can be implemented by software and / or software, and is usually configured in electronic equipment, typically in a processor. It can be set on the client side or on the server side. refer to figure 1 , the method includes:

[0027] S101. Obtain multiple anchor subscription lists.

[0028] Wherein, the host subscription list refers to a list formed by audience users subsc...

Embodiment 2

[0038] figure 2 It is a flow chart of a calculation method for anchor similarity provided by Embodiment 2 of the present invention. This embodiment is refined on the basis of Embodiment 1, and mainly describes the specific method of converting anchor information into anchor vectors and subsequent behaviors after obtaining the similarity between anchor information.

[0039] refer to figure 2 , this embodiment specifically includes the following steps:

[0040] S201. Obtain anchor information subscribed by a user.

[0041] Specifically, the means for calculating the anchor similarity acquires the anchor information of the anchors subscribed (followed) by the audience users during the live broadcast process.

[0042] S202. Generate the anchor subscription list based on the anchor information in order of subscription time.

[0043] Specifically, the means for calculating the anchor similarity sorts the anchor information according to the chronological order in which viewers ...

Embodiment 3

[0063] image 3 It is a structural diagram of an anchor similarity computing device provided in Embodiment 3 of the present invention. The device includes: a subscription list acquisition module 31 , an anchor vector conversion module 32 and a similarity calculation module 33 . in:

[0064] Subscription list acquisition module 31, configured to acquire a plurality of anchor subscription lists, each anchor subscription list has anchor information subscribed by the user;

[0065] An anchor vector conversion module 32, configured to convert the anchor information into an anchor vector according to the anchor subscription list;

[0066] A similarity calculation module 33, configured to calculate the similarity between the anchor information according to the anchor vectors.

[0067] In the embodiment of the present invention, multiple anchor subscription lists are obtained, and the anchor information contained in the anchor list is converted into anchor vectors, and the similari...

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

No PUM Login to view more

Abstract

The invention discloses a calculation method, device, equipment and storage medium for anchor similarity. The method includes: acquiring a plurality of anchor subscription lists, each anchor subscription list having anchor information subscribed by a user; converting the anchor information into an anchor vector according to the anchor subscription list; and calculating the anchor information according to the anchor vector similarity between. This method solves the problem of how to accurately recommend anchors with high user similarity when user data is sparse. It has achieved the beneficial effect of reducing the time for users to find their favorite anchors, increasing the user's viewing time and retention on the platform.

Description

technical field [0001] The embodiments of the present invention relate to neural network technology, and in particular to a calculation method, device, device and storage medium for anchor similarity. Background technique [0002] With the development of Internet technology and smart mobile terminal equipment, various Internet products have brought a lot of convenience and entertainment to people's work and life. A more real-time social experience. The live broadcast platform maintains a competitive advantage by relying on a large number of excellent anchor users and audience users. [0003] On the live broadcast platform, a large number of anchors start broadcasting every day. For audience users, it often takes a lot of time to find their favorite anchor, and audience users need to try to watch and accumulate knowledge of the anchor. Usually, users will subscribe or view their favorite anchors, and then the anchors will receive corresponding notifications when they start...

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
no application Login to view more
Patent Type & Authority Patents(China)
IPC IPC(8): H04N21/258H04N21/25H04N21/262G06F16/735G06K9/46G06K9/62
CPCH04N21/252H04N21/25866H04N21/25891H04N21/26258G06V10/464G06F18/22
Inventor 郭酉晨仇贲
Owner GUANGZHOU HUYA TECH CO LTD
Who we serve
  • R&D Engineer
  • R&D Manager
  • IP Professional
Why Eureka
  • Industry Leading Data Capabilities
  • Powerful AI technology
  • Patent DNA Extraction
Social media
Try Eureka
PatSnap group products

Browse by: Latest US Patents, China's latest patents, Technical Efficacy Thesaurus, Application Domain, Technology Topic.

© 2024 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap