Historical data-based missing path recovery method

A path recovery and historical data technology, applied in the field of trajectory calculation, can solve the problems of increased path diversity, low specificity of popular paths, unsatisfactory recovery results, etc., and achieve the effect of maintaining reliability and accuracy

Active Publication Date: 2016-12-21
FUDAN UNIV
View PDF4 Cites 13 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

When the missing distance of the path becomes longer, the number of trajectories between the beginning and the end of the missing path in the historical data will also decrease, and the diversity of paths will also increase, resulting in less specificity of popular paths, and eventually leading to Recovery results are not ideal

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
  • Historical data-based missing path recovery method
  • Historical data-based missing path recovery method
  • Historical data-based missing path recovery method

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0038] The specific implementation process of the present invention will be described below in conjunction with specific examples:

[0039] 1. Train model parameters based on historical data

[0040] (1) Define MDP model, state set S={s 1 ,s 2 ,...,s 17}, an action is defined as a transition between two adjacent states, such as s 1 →s 2 ,s13 →s 17 , define the attenuation coefficient γ, such as γ=0.95.

[0041] (2) The initial reward function of each state is defined as its road length,

[0042] That is, R(s 1 )=s 1 .len, R(s 2 )=s 2 .len,...,R(s 17 )=s 17 .len,

[0043] Among them, s.len represents the length of road segment s. Total return function set R={R(s 1 ), R(s 2 ),...,R(s 17 )}.

[0044] (3) For the dotted historical track tr 1 Do Posterior Probability Calculations

[0045] (a) will terminate state s 17 The return function of is set to 0;

[0046] (b) Use the value iteration method for the current MDP to obtain the optimal value function V for e...

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 belongs to the technical field of trajectory calculation and particularly relates to a historical data-based missing path recovery method. The method comprises the steps of in a training stage, performing modeling on a trajectory by utilizing a Markov decision process model, and training model parameters according to historical trajectory data; and in an online query stage, calculating a transfer probability between roads according to a trained model, constructing a graph, assigning a weight of the edge by using a negative logarithm of the transfer probability, obtaining a path with a highest probability by using shortest path search in the graph, and recovering a missing part by using the path. According to the method, the reliability and accuracy of an algorithm also can be kept under a long-distance missing condition.

Description

technical field [0001] The invention belongs to the technical field of trajectory calculation, and in particular relates to a method for recovering missing paths based on historical data. Background technique [0002] The popularity of mobile GPS devices has promoted the development of location-based services, and trajectory calculation has also emerged as the times require. The accuracy of trajectory data directly affects the quality of service. However, due to various factors in real life, such as equipment power, storage space, and online transmission costs, the sampling frequency of GPS data is not high, that is, there are a large number of trajectory data samples. The interval is more than 1 minute. The low sampling rate of GPS trajectory data directly leads to the lack of user driving paths, which will greatly affect the quality of location-based services, such as route recommendation, road condition prediction, trajectory prediction, frequent pattern mining, etc. Ap...

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): G06F17/30
CPCG06F16/29
Inventor 孙未未吴昊
Owner FUDAN UNIV
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