Looking for breakthrough ideas for innovation challenges? Try Patsnap Eureka!

A kind of object recognition method and related device based on artificial intelligence

An object and a technology to be identified, applied in the field of data processing, can solve problems such as large fluctuations in identification accuracy, achieve the effects of eliminating human influence, stabilizing identification accuracy, and improving computing performance and computing efficiency

Active Publication Date: 2021-08-06
TENCENT TECH (SHENZHEN) CO LTD
View PDF6 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0004] However, the accuracy of identifying abnormal users through simple rules is directly related to the personal experience of rule setters, resulting in large fluctuations in identification accuracy.

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 kind of object recognition method and related device based on artificial intelligence
  • A kind of object recognition method and related device based on artificial intelligence
  • A kind of object recognition method and related device based on artificial intelligence

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0034] Embodiments of the present application are described below in conjunction with the accompanying drawings.

[0035] In the related art, the objects in the network, such as users or devices, are mostly identified by manually setting rules to determine whether they are abnormal. However, the way of artificial rule setting is greatly affected by human experience, and the recognition accuracy is unstable.

[0036] To this end, the embodiment of the present application provides an object recognition method, which determines the association relationship between multiple objects involved in the implementation of network behavior through network behavior data, and when identifying an object as an object to be recognized, according to the to-be-recognized object Identify the temporal behavior characteristics of the associated objects of the object, and determine a set of neighbor features with a specified number through a unified construction method. This construction method can...

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 embodiment of the present application discloses an artificial intelligence-based object recognition method and related devices. By acquiring network behavior data, multiple objects that implement network behaviors and the implemented network behaviors can be determined. For the types of objects to be identified, The associated object can be determined based on the association established between the network behavior and the object to be identified, and the time series behavior characteristics of the associated object carry a large amount of effective content related to the type of the object to be identified, which can provide a basis for identifying the object to be identified. Moreover, for any object to be identified, the constructed neighbor feature set includes a specified number of time-series behavior features. Through this unified construction method, a neighbor feature set with high feature consistency is determined. This unified construction method can provide It has good generalizability, can be effectively applied to different network behavior data, has stable recognition accuracy, improves computing performance and computing efficiency, and excludes human influence in object recognition.

Description

technical field [0001] The present application relates to the field of data processing, in particular to an artificial intelligence-based object recognition method and related devices. Background technique [0002] With the popularization of the Internet, users can realize normal daily and work needs through network behavior. For example, you can log in to a game through a mobile phone to play against other users, log in to a shopping software through a computer to shop online, and log in to a social software through a laptop to chat with friends. [0003] However, some users will realize improper needs through online behaviors, such as cheating in games through mobile devices, swiping orders in shopping, buying and selling virtual currency, etc. In order to identify such abnormal users who carry out improper network behaviors, related technologies mainly use preset rules to screen network behavior data to identify abnormal users. [0004] However, the accuracy of identify...

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): H04L29/08G06N3/08
CPCG06N3/08H04L67/535
Inventor 温蕊
Owner TENCENT TECH (SHENZHEN) CO LTD
Who we serve
  • R&D Engineer
  • R&D Manager
  • IP Professional
Why Patsnap Eureka
  • Industry Leading Data Capabilities
  • Powerful AI technology
  • Patent DNA Extraction
Social media
Patsnap Eureka Blog
Learn More
PatSnap group products

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