A method and system for recommending video content based on user viewing time
A technology of video content and viewing time, applied in the direction of selective content distribution, image communication, electrical components, etc., can solve the problem of poor judgment results, and achieve the effect of good accuracy and accurate viewing preference evaluation
- Summary
- Abstract
- Description
- Claims
- Application Information
AI Technical Summary
Problems solved by technology
Method used
Image
Examples
Embodiment 1
[0023] A method for recommending video content based on user viewing time, comprising the following steps:
[0024] Step 1: Record the m content P1, P2, P3, P4...Pm recorded by the user in n days and record it as Tn(Pm). Tn(Pm) represents the duration corresponding to the m content watched in the past n days. Let SIM( A)=MAX(Tn(Px)), SIM indicates the length of time for user A to watch the longest content Px in the past n days;
[0025] Step 2: directly divide user groups, obtain Tn (Px) in user group a, if Tn (Px) does not exist, exclude Px, m=m-1, return to step 1;
[0026] Step 3: Obtain user group b whose SIM(A) value is similar to that of user group a;
[0027] Step 4: Find user B in user group b according to the SIM (A) value in step 3, so that Tn (Px) is the longest viewing time of user B to content Px;
[0028] Step 5: If the viewing record contained in user B's history is not in user A's history, recommend user B's history to user A, otherwise exclude user B and ret...
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