Eureka AIR delivers breakthrough ideas for toughest innovation challenges, trusted by R&D personnel around the world.

Application object recognition method and device, application object recognition model training method and device and medium

A technology for applying objects and identifying models, applied in the Internet field, can solve the problems of lag, frequent update of plug-in features, etc.

Active Publication Date: 2019-06-07
TENCENT TECH (SHENZHEN) CO LTD
View PDF6 Cites 13 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0004] Embodiments of the present application provide a training method, device and storage medium for applying object recognition and logistic regression models, which are used to solve the problem of using cheat features to identify cheats in the prior art, requiring manual frequent update of cheat features and detection based on cheat features Problems with certain hysteresis etc.

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
  • Application object recognition method and device, application object recognition model training method and device and medium
  • Application object recognition method and device, application object recognition model training method and device and medium
  • Application object recognition method and device, application object recognition model training method and device and medium

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0042] In order to improve the utilization efficiency of processing resources, the embodiments of the present application provide a training method, device and storage medium for application object recognition and its recognition model. In order to better understand the technical solutions provided by the embodiments of this application, here is a brief description of the nouns involved in the solutions:

[0043] GameClient: Game client, which refers to the game terminal where game players log in and operate.

[0044] GameServer: Game server; a server that provides game services and is used to interact with game clients to complete game operations of game players.

[0045] LA SERVER: Logic Analysis Server, which receives and processes the PBC protocol data sent from GameClient / GameServer, and the CFR protocol data reported by GameClient, and analyzes and mines the control behavior of game players on game characters from these data.

[0046] PBC: Player Behavior Customized, a ...

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 an application object recognition method and device, an application object recognition model training method and device and a storage medium, and relates to the technical fieldof the Internet. According to the embodiment of the invention, the method comprises the steps: training the application object recognition model by using the behavior characteristics of the game player in the game, specifically, training a model by a labled sample, including behavior characteristic samples when the plug-in is used and behavior characteristic samples when the plug-in is not used.As the game role control behavior of the player is relatively stable, the behavior characteristics are relatively stable, and the detection based on the characteristics cannot be frequently updated and maintained like plug-in characteristics. And the situation that plug-in detection cannot be carried out due to updating and maintenance is further avoided, so that the hysteresis problem of plug-indetection in the prior art is avoided.

Description

technical field [0001] The present application relates to the technical field of the Internet, and in particular to a training method, device and storage medium for applied object recognition and an applied object recognition model. Background technique [0002] Since game cheats can help players pass the level easily, many players like to use cheats when playing games. However, the use of cheats usually makes the game lack of fairness. In related technologies, a method for identifying game cheats has also appeared. [0003] Generally, the method for identifying cheats includes: obtaining cheat samples, then analyzing the characteristics of cheats based on the cheat samples, and monitoring whether players use cheats based on the characteristics of cheats. However, the plug-in will be updated regularly and frequently, which will cause the characteristics of the plug-in to change frequently, and manual maintenance of the plug-in features will be required frequently, which wi...

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): G06K9/62G06N3/04A63F13/75
Inventor 韦宇殷赵辉胡和君应小全潘泓陈翔宇李伟宋润青岑韵弦刘翔
Owner TENCENT TECH (SHENZHEN) CO LTD
Who we serve
  • R&D Engineer
  • R&D Manager
  • IP Professional
Why Eureka
  • Industry Leading Data Capabilities
  • Powerful AI technology
  • Patent DNA Extraction
Social media
Eureka Blog
Learn More
PatSnap group products