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

User track prediction method and system based on multi-relation fusion analysis

A user trajectory and trajectory prediction technology, applied in prediction, data processing applications, character and pattern recognition, etc., can solve problems such as insufficient utilization of user influence information and inaccurate prediction, and achieve enhanced robustness, improved accuracy, and improved prediction. The effect of improved accuracy

Pending Publication Date: 2022-05-10
NAT COMP NETWORK & INFORMATION SECURITY MANAGEMENT CENT +1
View PDF0 Cites 2 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0006] In order to solve the problems of inaccurate prediction caused by the division of granularity required by existing user trajectory prediction algorithms, insufficient utilization of user influence information, and relatively simple methods of measuring influence, the present invention provides a user trajectory prediction method based on multi-relationship fusion analysis and system

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
  • User track prediction method and system based on multi-relation fusion analysis
  • User track prediction method and system based on multi-relation fusion analysis
  • User track prediction method and system based on multi-relation fusion analysis

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0036] The present invention will be described in further detail below through specific embodiments and accompanying drawings.

[0037] The invention provides a user trajectory prediction technology based on multi-relationship fusion analysis. This method proposes a new hypothesis, which not only utilizes the trajectory behavior information of adjacent pedestrians, but also considers the trajectory of users with similar historical trajectories, and combines the two influence groups to construct a trajectory relationship graph. Then, based on the relationship between users in the trajectory relationship graph, an improved LSTM model is used, and an attention mechanism is added to synchronize the trajectories of group users, and predict the future trajectories of target users, taking into account the differences in the influence of different users on trajectories. figure 1 is the model graph based on multi-feature depth coding of the present invention, user u 2 with user u 1 ,...

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 relates to a user track prediction method and system based on multi-relation fusion analysis. According to the method, a trajectory relation graph is constructed according to a historical trajectory similarity relation and a position proximity relation of users, and then a future trajectory of a target user is predicted by using a trajectory prediction model integrated with an attention mechanism based on a relation between the users in the trajectory relation graph. According to the method, the time regularity characteristic of user travel is fully considered, the social behavior information in the crowd is fully mined, and the prediction precision is obviously improved; according to the method, the influence is calculated by using the trajectory relation graph integrated with the attention mechanism, and the difference of the influence of different users on the trajectory is integrated, so that the method is more in line with the actual situation; according to the method, the trajectory behavior information of pedestrians adjacent in position is utilized, the trajectory conditions of users with similar historical trajectories are also considered, two influencing crowds are combined together to construct the trajectory relation graph, and the problem of how to model various types of information is solved.

Description

technical field [0001] The present invention relates to the technical field of computer data mining and analysis, in particular to the technical field of stream data mining, and specifically refers to a trajectory prediction method and system based on multi-relationship fusion analysis. Background technique [0002] Due to its complexity, the subject of human motion trajectory prediction has been a hot topic of research by scholars at home and abroad in recent years. With the rise and popularization of artificial intelligence technology, intelligent applications such as intelligent security systems, self-driving cars, and robot navigation systems have gradually entered the public eye. If it is possible to understand and predict the trajectories of people in complex real-world scenes, and dynamically predict the future location of each individual in real time, smart applications can improve the service accuracy and availability of the above-mentioned smart applications based ...

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 Applications(China)
IPC IPC(8): G06F16/9537G06K9/62G06N3/04G06Q10/04
CPCG06F16/9537G06Q10/04G06N3/044G06F18/23G06F18/22
Inventor 井雅琪佟玲玲方芳段东圣任博雅段运强时磊曹亚男尚燕敏
Owner NAT COMP NETWORK & INFORMATION SECURITY MANAGEMENT CENT
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