Supercharge Your Innovation With Domain-Expert AI Agents!

Method and system for predicting single-point payment purchase video of intelligent television platform user

A smart TV and prediction method technology, which is applied in video data retrieval, metadata video data retrieval, biological neural network model, etc., can solve the problems of few pay-per-view video records, insufficient expression of embedded vectors, etc., and achieve accurate prediction results Effect

Pending Publication Date: 2022-07-05
SHANDONG UNIV
View PDF0 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0008] In order to solve the above problems, the present invention proposes a method and system for predicting a pay-per-view video purchased by users on a smart TV platform, constructing a graph for all user video viewing records, and solving the embedded vector expression caused by fewer pay-per-view video records insufficient problem

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
  • Method and system for predicting single-point payment purchase video of intelligent television platform user
  • Method and system for predicting single-point payment purchase video of intelligent television platform user
  • Method and system for predicting single-point payment purchase video of intelligent television platform user

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0046] like figure 1 As shown, this embodiment provides a method for predicting the purchase of a pay-per-view video by a smart TV platform user, including:

[0047] Obtain users' video viewing records and video purchase records;

[0048] Construct an adjacency graph based on the chronological order of videos viewed by users in the video viewing records;

[0049] For each video node in the adjacency graph, construct a video embedding vector according to its own feature splicing vector and the feature splicing vector of its neighbor nodes; the feature splicing vector includes the time embedding vector at the viewing moment and the edge with the adjacent node;

[0050] For the video viewing record of the target user, the viewing sequence is obtained according to the time embedding vector and the video embedding vector of the viewing moment, and attention weighting is performed on each video in the viewing sequence to obtain the viewing interest feature;

[0051] For the video pu...

Embodiment 2

[0137] The present embodiment provides a video prediction system for a smart TV platform user to purchase a pay-per-view video, including:

[0138] The graph building module is configured to build an adjacency graph based on the chronological order of the videos viewed by the user in the video viewing records;

[0139] The video embedding vector building module is configured to construct a video embedding vector for each video node in the adjacency graph according to its own feature splicing vector and the feature splicing vector of its neighbor nodes; the feature splicing vector includes the time embedding vector of the viewing moment and edges with adjacent nodes;

[0140] The viewing interest feature extraction module is configured to obtain the viewing sequence according to the time embedding vector and the video embedding vector of the video viewing record of the target user, and perform attention weighting on each video in the viewing sequence to obtain the viewing inter...

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 method and a system for predicting a single-point payment video purchased by a smart television platform user. The method comprises the following steps: constructing an adjacent graph for a video watching record; constructing a video embedding vector for each video node in the adjacent graph; for a video watching record of a target user, obtaining a watching sequence according to the time embedding vector and the video embedding vector of the watching moment, and performing attention weighting on each video in the watching sequence to obtain watching interest features; for the video purchase record of the target user, obtaining purchase preference characteristics according to the video embedding vector of the purchased video and the purchase amount thereof; and predicting and recommending the to-be-recommended video according to the watching interest features and the purchase preference features. And graph construction is carried out on video watching records of all users, so that the problem of insufficient embedded vector expression caused by less single-point payment video records is solved. Time factors are considered in modeling of video embedding vectors, watching interest features and purchase preference features, so that prediction results are more accurate.

Description

technical field [0001] The invention relates to the technical field of video recommendation, in particular to a method and a system for predicting a single-point payment video purchased by a user of a smart TV platform. Background technique [0002] The statements in this section merely provide background information related to the present invention and do not necessarily constitute prior art. [0003] Single-point video is a paid video that users need to purchase separately and watch within a specified time range, and need to purchase again if it expires. It is very important for both the service provider and the user to understand the purchase intention of the user. From the perspective of service providers, understanding users’ current purchasing interests can increase the platform’s revenue. According to users’ purchasing intentions, various preferential activities, such as issuing time-limited coupons, can be used to promote user consumption and increase revenue. At t...

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): G06F16/78G06F16/901G06N3/04
CPCG06F16/7867G06F16/9024G06N3/047G06N3/048G06N3/044
Inventor 彭朝晖王健郝佳凝郝振云王雪崔明宇
Owner SHANDONG UNIV
Features
  • R&D
  • Intellectual Property
  • Life Sciences
  • Materials
  • Tech Scout
Why Patsnap Eureka
  • Unparalleled Data Quality
  • Higher Quality Content
  • 60% Fewer Hallucinations
Social media
Patsnap Eureka Blog
Learn More

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

© 2025 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap|About US| Contact US: help@patsnap.com