Mobile phone signaling data pedestrian traffic track prediction method based on deep learning

A mobile phone signaling and deep learning technology, which is applied in neural learning methods, prediction, data processing applications, etc., can solve the problems of using the time-space correlation logic relationship without signaling data, it is difficult to find the regularity of pedestrians, etc., and achieve a reasonable design Effect

Inactive Publication Date: 2017-12-15
QINGDAO UNIV OF SCI & TECH
View PDF3 Cites 17 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

These algorithms obviously do not take advantage of the logical relationship behind the temporal-spatial correlation of signaling data, so it is difficult to find the regularity in traffic that travelers really have

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
  • Mobile phone signaling data pedestrian traffic track prediction method based on deep learning

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0022] Below in conjunction with accompanying drawing and specific embodiment the present invention is described in further detail:

[0023] Introduce deep learning technology to carry out semantic processing on signaling data. The accumulation of vocabulary is not language. The development of language will inevitably bring about the context, usage and timing of words. This is semantics, so our language is logical. It is organized to express our behavior or to describe something, and has a natural internal connection and a logically reasonable structure; because we know that the temporal and spatial correlation of signaling data is an objective rule of pedestrian travel. Reflect, or say that the signaling data of pedestrians has a certain logical connection inside. Treat signaling data as a language, in which a single data of signaling data is used as a word or word, several sets of connected signaling data are used as phrases, and one day's signaling data is used as sentences...

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 mobile phone signaling data pedestrian traffic track prediction method based on deep learning, and belongs to the mobile phone signaling data pedestrian traffic track prediction field; the method comprises the following steps: combining adjacent cells surrounding a traveler spot into a cell group, converting geological position adjacency into natural language similarity, wherein the geological position adjacent cells are highly likely selected by pedestrians as destinations like logical similar vocabularies; the cell group selection can greatly improve the travel mode excavation reliability and authenticity; the method can use the excellent performances obtained by a RNN network on natural language prediction, thus excavating traveler traveling habits mapped as language modes with high performance; according to the travel rule theoretical basis, the method can summarize the traveling modes, thus exceeding existing pedestrian behavior mode excavation method based on signaling data, and improving the performance by 42-49%.

Description

technical field [0001] The invention belongs to the field of pedestrian traffic trajectory prediction based on mobile phone signaling data, and in particular relates to a method for predicting pedestrian traffic trajectory based on mobile phone signaling data. Background technique [0002] Cell phone signaling data are signals dedicated to control circuits, which allow program-controlled switching, network databases, and other "smart" nodes in the network to exchange information about: call setup, monitoring, teardown, information required for distributed application processes (between processes query / response or user-to-user data), network management information. Therefore, the signaling includes the communication location, time, communication duration, and communication mode, etc.; the determination principle of the communication location is as follows: the user communication must pass through the base station of the cell where the mobile phone is located, and then communi...

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): G06N3/08G06Q10/04
CPCG06N3/08G06Q10/04
Inventor 徐文进
Owner QINGDAO UNIV OF SCI & TECH
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
Try Eureka
PatSnap group products

Browse by: Latest US Patents, China's latest patents, Technical Efficacy Thesaurus, Application Domain, Technology Topic.

© 2024 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap