Unlock instant, AI-driven research and patent intelligence for your innovation.

A cheating video identification method and device

A technology of video recognition and target video, applied in the field of data processing, can solve problems such as reducing the efficiency of users' search for effective data and wasting data traffic.

Active Publication Date: 2021-03-26
BEIJING QIYI CENTURY SCI & TECH CO LTD
View PDF7 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

However, driven by profit, some users may intentionally edit cheating keywords in the video title, thereby attracting other users to click to watch, and cheating videos whose video titles are seriously inconsistent with the video content will greatly reduce the user’s search efficiency for valid data , wasting data traffic, therefore, there is an urgent need for a method that can identify cheating videos

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
  • A cheating video identification method and device
  • A cheating video identification method and device
  • A cheating video identification method and device

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0063] refer to figure 1 , shows a flow chart of a cheating video identification method, which may specifically include the following steps:

[0064] Step 101: Determine the median viewing duration ratio of the target video according to the median viewing duration of each object watching the target video within a preset time period and the total duration of the target video.

[0065] In the video website managed by the data processing device, there are usually a large number of registered user objects and a large number of videos. After each object watches a video, the video terminal can determine the viewing time of the object watching the video, and then can use the viewing time data Feedback to the data processing device, so that the data processing device can obtain the viewing time data of each object watching each video in real time.

[0066] Wherein, the preset time period is a time period before the current time that satisfies the preset duration, for example, within ...

Embodiment 2

[0084] refer to figure 2 , showing a flow chart of another cheating video identification method, the method may specifically include the following steps:

[0085] Step 201: Determine the median viewing duration ratio of the target video according to the median viewing duration of each object watching the target video within a preset time period and the total duration of the target video.

[0086] When it is necessary to determine whether the target video in the video website is a cheating video, the data processing device can select each object to watch the respective viewing duration data of the target video from the viewing duration data within a preset time period, and then determine each viewing duration The median value of the data, that is, the median value of the viewing duration of each object watching the target video within the preset time period, and then the data processing device can compare the median viewing duration of each object watching the target video wit...

Embodiment 3

[0128] refer to image 3 , shows a block diagram of a cheating video identification device 300, which may specifically include:

[0129] The first determining module 301 is used to determine the median viewing duration ratio of the target video according to the median viewing duration of each object watching the target video within the preset time period and the total duration of the target video;

[0130] The second determination module 302 is used to determine the completion degree parameters of each object watching the target video within the preset time period;

[0131] The third determination module 303 is used to determine the cheating parameters of the target video according to the median viewing time ratio and completion parameters of the target video;

[0132] The fourth determining module 304 is configured to determine that the target video is a cheating video when the cheating parameters of the target video meet preset cheating conditions.

[0133] Embodiments of ...

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

Embodiments of the present invention provide a cheating video identification method and device, which relate to the technical field of data processing. Wherein, the method includes: determining the median viewing duration ratio of the target video according to the median viewing duration of each object watching the target video within a preset time period and the total duration of the target video; determining the preset time Each object in the section watches the completion parameter of the target video; according to the median viewing time ratio and the completion parameter of the target video, determine the cheating parameter of the target video; when the cheating parameter of the target video satisfies When preset cheating conditions, it is determined that the target video is a cheating video. In the embodiment of the present invention, the cheating parameters of the video can be characterized by user behavior parameters, and then when the cheating parameters of the video meet the preset cheating conditions, it can be determined that the video is a cheating video, so that the title and the content of the video can be identified through the viewing behavior of the user. Cheating videos with grossly inaccurate content.

Description

technical field [0001] The invention relates to the technical field of data processing, in particular to a cheating video recognition method and device. Background technique [0002] With the continuous improvement of search engine performance and data volume, people use search engines to obtain the required data more and more frequently. Among them, video, as an important data bearing form, has a considerable amount of indexing. [0003] In today's Internet, a large number of users upload a large number of original videos all the time. For such original videos, users can edit video titles independently, so as to facilitate content introduction and search by other users. However, driven by profit, some users may intentionally edit cheating keywords in the video title, thereby attracting other users to click to watch, and cheating videos whose video titles are seriously inconsistent with the video content will greatly reduce the user’s search efficiency for valid data , wast...

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): G06K9/00G06F16/951G06F16/953G06F16/9532G06F16/732
CPCG06V20/47
Inventor 梁召陈英傑胡军
Owner BEIJING QIYI CENTURY SCI & TECH CO LTD