Recommendation method and apparatus, and computer device
A recommendation method and technology of preset time, applied in the field of live broadcast, can solve problems such as failure to bring surprises to users, small changes in the recommendation list, live broadcast types, and visual fatigue of users
- Summary
- Abstract
- Description
- Claims
- Application Information
AI Technical Summary
Problems solved by technology
Method used
Image
Examples
Embodiment 1
[0052] This embodiment provides a recommendation method, which is applied to a live broadcast platform, such as figure 1 As shown, the method includes:
[0053] S101. Obtain the first total number of times the user watches the live broadcast room i and the second total number of times the user enters the live broadcast partition s to which the live broadcast room i belongs within the time period before the preset time t;
[0054] Since this embodiment needs to count the user's viewing behavior, such as viewing frequency, viewing time interval, etc., in this step, it is necessary to obtain the first total number of times the user watched the live broadcast room i within the time period before the preset time t , and the second total number of times of entering the live broadcast partition s to which the live broadcast room i belongs. Wherein, the time period before the preset time t is also preset, which may be 1 day, 1 week, or 1 month. In order to improve the recommendation...
Embodiment 2
[0084] Corresponding to Embodiment 1, this embodiment also provides a recommendation device, such as figure 2 shown, said figure 2Including: a first acquisition unit 21, a second acquisition unit 22, a third acquisition unit 23 and a determination unit 24; wherein,
[0085] Since in this embodiment, the user's viewing behavior needs to be counted, such as viewing frequency, viewing time interval, etc., the first obtaining unit 21 is used to obtain the user's first viewing of the live broadcast room i in the time period before the preset time t. A total number of times, and a second total number of times of entering the live broadcast zone s to which the live broadcast room i belongs.
[0086] Wherein, the time period before the preset time t is also preset, which may be 1 day, 1 week, or 1 month. In order to improve the recommendation accuracy, the time period in this embodiment is 1 day.
[0087] Here, when the first total number of times and the second total number of t...
Embodiment 3
[0112] In practical applications, when using the method provided in Embodiment 1 and the device provided in Embodiment 2 to calculate the surprise value of live room i, the specific implementation is as follows:
[0113] Obtain the first total number of times the user watches the live broadcast room i and the second total number of times the user enters the live broadcast zone s to which the live broadcast room i belongs within the time period before the preset time t. Wherein, the time period before the preset time t is also preset, and the time period in this embodiment is 1 month. The first total number of times is 10, and the second total number of times is 30; the ρ i is 0.1, ρ s is 0.1.
[0114] Then the value of the first impact factor can be calculated:
[0115]
[0116] Then obtain the first time when the user watched the live room i for the last time before the time t, and the second time when the user watched any live room in the live partition s for the last ...
PUM
Abstract
Description
Claims
Application Information
- R&D Engineer
- R&D Manager
- IP Professional
- Industry Leading Data Capabilities
- Powerful AI technology
- Patent DNA Extraction
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