Unlock instant, AI-driven research and patent intelligence for your innovation.

Traffic prediction method based on time sequence data and functional evolution data

A technology of traffic forecasting and time series data, applied in relational databases, database models, neural learning methods, etc., can solve problems such as ignoring dynamic influences and affecting changes in the number of POIs

Pending Publication Date: 2021-06-01
NANJING UNIV OF AERONAUTICS & ASTRONAUTICS
View PDF0 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0004] Although there are currently many works that combine the distribution data of urban functional areas to assist in flow forecasting, these works only use POI as a static indicator of regional similarity, ignoring the possible dynamic impact of POI changes on flow, and also ignoring Changes in traffic will in turn affect changes in the number of POIs

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
  • Traffic prediction method based on time sequence data and functional evolution data
  • Traffic prediction method based on time sequence data and functional evolution data
  • Traffic prediction method based on time sequence data and functional evolution data

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0077] In order to make the purpose, technical solutions and advantages of the present application more clearly understood, the present application will be described in further detail below with reference to the accompanying drawings and embodiments. It should be understood that the specific implementation cases described here are only used to explain the present application, and are not intended to limit the present application.

[0078] In one embodiment, combined with figure 1 , provides a traffic forecasting method based on time series data and functional evolution data, the method includes the following steps:

[0079] Step 1, preprocessing the collected map query data and POI data to obtain the required data;

[0080] Here, the map query data includes the anonymized user number, the longitude of the query starting point, the latitude of the query starting point, the longitude of the query end point, the latitude of the query end point, and the query time;

[0081] The ...

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 flow prediction method based on time sequence data and functional evolution data, which comprises the following steps: firstly, obtaining a resident travel mode sequence through a clustering method, and then, obtaining a POI (Point of Interest) change mode sequence based on the resident travel mode sequence and the POI change mode sequence; mining the correlation between the distribution of different categories of POIs dynamically changing under different time windows and the resident travel mode, and learning the mutual influence relationship between the two; on the basis of the mutual influence relation matrix, attention operation is carried out in the time dimension and the POI category dimension, and influence information of the POI on the resident travel mode is extracted; and finally, outputting the resident travel mode sequence through an LSTM (Long Short Term Memory) time sequence model, and combining the output with the influence information of the POI on the resident travel mode to predict the travel flow at the next time. According to the method, the implicit rule between the change of the resident travel mode and the regional evolution can be effectively revealed, and important support is provided for predicting the travel flow of resident groups.

Description

technical field [0001] The invention belongs to the field of pattern prediction, and in particular relates to a traffic prediction method based on time series data and function evolution data. Background technique [0002] Mobility plays an important role in the daily life of residents and plays an important role in urban management, land use and public safety. One of the most fundamental issues for future cities is to build efficient transportation systems. To solve this problem, the key is to obtain an accurate prediction model of residents' travel demand. For city managers, by accurately predicting the travel of residents, they can know in advance the time and place where congestion may occur, and even the degree of congestion, so as to take measures in advance to prevent the occurrence of traffic congestion; for investors, It is possible to discover the gathering points that the crowd likes in different situations, so as to carry out targeted advertisement placement, b...

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): G06F16/29G06F16/2458G06F16/28G06N3/04G06N3/08
CPCG06F16/29G06F16/2474G06F16/285G06F16/287G06N3/08G06N3/044G06N3/045
Inventor 顾晶晶闫瑾
Owner NANJING UNIV OF AERONAUTICS & ASTRONAUTICS
Features
  • R&D
  • Intellectual Property
  • Life Sciences
  • Materials
  • Tech Scout
Why Patsnap Eureka
  • Unparalleled Data Quality
  • Higher Quality Content
  • 60% Fewer Hallucinations
Social media
Patsnap Eureka Blog
Learn More

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

© 2025 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap|About US| Contact US: help@patsnap.com