Looking for breakthrough ideas for innovation challenges? Try Patsnap Eureka!

User preference-based user similarity calculation method and device, equipment and medium

A technology of user similarity and calculation method, applied in the field of Internet live broadcast, can solve problems such as no consideration, similarity difference, etc.

Active Publication Date: 2019-04-09
武汉斗鱼鱼乐网络科技有限公司
View PDF4 Cites 1 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

It can be seen that the disadvantage of this algorithm is that it only measures the similarity between two users from the number of views, and does not consider that even if two users watch the same live broadcast room, the difference in similarity may be caused by the difference in viewing time.

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
  • User preference-based user similarity calculation method and device, equipment and medium
  • User preference-based user similarity calculation method and device, equipment and medium
  • User preference-based user similarity calculation method and device, equipment and medium

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0049] figure 1It is a schematic flowchart of a method for calculating user similarity based on user preference provided by Embodiment 1 of the present invention. The method for calculating user similarity based on user preferences disclosed in this embodiment is applicable to the situation of identifying viewing preferences of a large number of users in a live broadcast room, so as to push appropriate live programs to users based on viewing preferences of users. The method can be executed by a device for calculating user similarity based on user preferences, wherein the device can be implemented by software and / or hardware, and is generally integrated in a terminal, such as a server. For details, see figure 1 As shown, the method may include the following steps:

[0050] Step 110, determine the set of common live broadcast rooms watched by the two users within the set time period.

[0051] Wherein, the set time period usually takes 30 days or 60 days closest to the current...

Embodiment 2

[0068] figure 2 It is a schematic flowchart of a method for calculating user similarity based on user preference provided by Embodiment 2 of the present invention. On the basis of the above-mentioned embodiment, this embodiment performs the above-mentioned step 130 "calculating the degree of preference difference between the two users based on each user's preference for each live room in the common live room set" For further optimization, the relative preference difference factor between two users for the same live broadcast room is added, and the calculation accuracy of the similarity between two users is further improved. For details, see figure 2 As shown, the method includes the following steps:

[0069] Step 210, determine the set of common live broadcast rooms watched by the two users within the set time period.

[0070] Step 220, respectively calculating the likeness of each of the two users for each live room in the common live room set.

[0071] Step 230, respec...

Embodiment 3

[0093] image 3 It is a schematic structural diagram of an apparatus for calculating user similarity based on user preference provided by Embodiment 3 of the present invention. see image 3 As shown, the device includes: a determination module 310, a preference calculation module 320, a preference difference calculation module 330 and a similarity calculation module 340;

[0094] Among them, the determination module 310 is used to determine the set of common live broadcast rooms watched by two users within a set time period; the preference calculation module 320 is used to calculate the common live broadcast room set of each user in the two users respectively. The preference degree of each live room in the set of live rooms; the preference difference calculation module 330, which is used to calculate the preference difference between the two users based on each user's preference for each live room in the common set of live room degree; the similarity calculation module 340 i...

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 embodiment of the invention discloses a user preference-based user similarity calculation method and device, equipment and a medium. The method comprises the following steps of determining a common live broadcast room set watched by two users within a set time period; respectively calculating the preference degree of each user of the two users to each live broadcast room in the common live broadcast room set; calculating a preference difference degree between the two users based on the preference degree of each user for each live broadcast room in the common live broadcast room set; and calculating the similarity between the two users according to the preference difference between the two users in combination with the common live broadcast room set and the live broadcast room union setwatched by the two users in a set time period. By adopting the technical scheme, the calculation accuracy of the user similarity can be improved, so that personalized recommendation is realized.

Description

technical field [0001] The embodiments of the present invention relate to the technical field of Internet live broadcasting, and in particular to a method, device, device and medium for calculating user similarity based on user preferences. Background technique [0002] In the application field of big data, an important direction is to make personalized recommendations to users based on massive data. [0003] In the live broadcast platform, the common recommendation strategy is to recommend rooms similar to the rooms the user has watched, so it is necessary to measure the similarity between the rooms in the live broadcast room. In addition, in some user-based collaborative filtering recommendation algorithms, it is also necessary to calculate the similarity between two users, so as to recommend a room that one user likes to watch to a user with a higher similarity with the user. [0004] The commonly used algorithm for calculating the similarity between two users is the Jac...

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
IPC IPC(8): H04N21/25H04N21/258H04N21/466H04N21/442G06F16/9535G06K9/62
CPCH04N21/252H04N21/25891H04N21/44222H04N21/4667H04N21/4668G06F18/22
Inventor 王璐
Owner 武汉斗鱼鱼乐网络科技有限公司
Who we serve
  • R&D Engineer
  • R&D Manager
  • IP Professional
Why Patsnap Eureka
  • Industry Leading Data Capabilities
  • Powerful AI technology
  • Patent DNA Extraction
Social media
Patsnap Eureka Blog
Learn More
PatSnap group products

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

© 2024 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap|About US| Contact US: help@patsnap.com