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

Method, device and equipment for predicting moving mode and track of user and storage medium

A technology of user movement and prediction method, applied in equipment and storage media, user movement mode and trajectory prediction method, and device field, to prevent gradient disappearance, reduce human error rate, and improve prediction accuracy.

Active Publication Date: 2021-07-02
浙江非线数联科技股份有限公司
View PDF5 Cites 5 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0005] The present invention provides a method for predicting user movement patterns and trajectories, aiming to solve the problem that in the prior art, multiple methods cannot be used to obtain multi-dimensional data information to achieve accurate prediction of short-term movement trajectories and other information such as stay time and traffic modes. The 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, device and equipment for predicting moving mode and track of user and storage medium
  • Method, device and equipment for predicting moving mode and track of user and storage medium
  • Method, device and equipment for predicting moving mode and track of user and storage medium

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0056] Such as figure 1 As shown, a prediction method of a user movement and trajectory, comprising the following steps:

[0057] S110, acquire multi-source mobile data set, and perform association data fill the mobile data set according to the time order, and extract the mapping relationship between the time node and the corresponding association data from the filling mobile data set;

[0058] S120, based on the mapping relationship, a neural network model is constructed, and the neural network model is used to complete the incomplete field of information after the filling of the filling;

[0059] S130, the completion of the completed mobile data set for feature extraction, and uses a pre-training predictive model to perform a limited secondary training to predict the movement and trajectory.

[0060] According to Embodiment 1, the program acquires the user history of different sources, which includes latitude and time longitudinal node information, and arrange this information i...

Embodiment 2

[0062] Such as figure 2 As shown, a prediction method of user movement and trajectory, including:

[0063] S210, obtains the mobile data set of different sources, the mobile data set to represent the user's historical mobile trajectory;

[0064] S220, arrange the full field in the mobile data set in time order, to obtain a unified data structure, and add corresponding correlation data to the corresponding time node, while the data sets the threshold in the mobile data set after the data is added Clean;

[0065] S230, extract the first field from the cleaning mobile data set, and acquire a mapping relationship between the time node in the first field and the corresponding association data, the first field is used to indicate the transfer data set after the cleaning. A field containing associated information;

[0066] S240, based on the mapping relationship to construct a neural network model, and use the neural network model to complete the incomplete information of the incompatibl...

Embodiment 3

[0070] Such as image 3 As shown, a prediction method of user movement and trajectory, including:

[0071] S310, acquire multi-source mobile data set, perform associated data fills on the mobile data set according to the time order, and extract the mapping relationship between the time node and the corresponding associated data from the filling mobile data set;

[0072] S320, according to the mapping relationship training neural network model, the neural network model is used for data completion;

[0073] S330, enters the second field in the cleaning mobile data set into the neural network model, and uses the related information that has been missing in the second field, the second field is used to indicate the cleaning. The mobile data set is associated with an empty field;

[0074] S340, the completion of the completed mobile data set, and utilizes a pre-training predictive model to provide a limited secondary training to predict the movement and trajectory.

[0075] According to...

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 for predicting moving mode and track of user, which comprises the steps of acquiring a multi-source moving data set, and performing cleaning fusion processing on the moving data set; constructing different neural network models according to the data size of the mobile data set, and inputting the incomplete fields into the corresponding neural network models for data completion; and sliding the frame to take the complete data set for feature extraction, and inputting the extracted features into a pre-trained prediction model according to a preset rule for training. According to the method, obtained multi-dimensional features can be effectively utilized through data completion, the reasonability of a prediction result is higher, meanwhile, a corresponding neural network model is trained from the two aspects of multi-field and single-field needing to be completed, the accuracy rate of a test set is as high as 90%, training test data used for final prediction is extracted based on time sequence sliding, and the data utilization rate is effectively improved.

Description

Technical field [0001] The present invention relates to the field of data mining processing, and more particularly to a prediction method, apparatus, apparatus, and storage medium for user movement and trajectory. Background technique [0002] In recent years, under the rapid development of information and communication technology, mobile data in human daily lives has exploded, passively generated data, such as GPS data and cellular data, bring huge opportunities for human mobility analysis and transportation applications. Since their main purposes are usually unrelated to transport, they need to process passive data to extract strokes. Most of the travel extraction methods are now dependent on single-bit technologies such as GPS, such as GPS, or three-pointed data through the cellular tower. The so-called single source data, the lack of data generated from a variety of positioning techniques is also a method of extracting stroke information in multi-source data. [0003] In the ...

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): H04W4/029G06N3/04G06N3/08
CPCH04W4/029G06N3/08G06N3/044G06N3/045
Inventor 潘澳涔张聪贾立峰
Owner 浙江非线数联科技股份有限公司
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