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

Frequent Trajectory Extraction Method and Its Mining System Based on Massive Spatiotemporal Data

A technology of spatiotemporal data and trajectory extraction, which is applied in electrical digital data processing, structured data retrieval, geographic information database, etc., to achieve the effect of overcoming limitations

Active Publication Date: 2020-08-25
南京柏跃软件有限公司
View PDF10 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0004] The present invention mainly solves the problem of extracting frequent paths from complex target trajectory data in the case of massive spatiotemporal data

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
  • Frequent Trajectory Extraction Method and Its Mining System Based on Massive Spatiotemporal Data
  • Frequent Trajectory Extraction Method and Its Mining System Based on Massive Spatiotemporal Data

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0048] figure 1 Shows the method for mining frequent trajectories based on massive spatio-temporal data according to the present invention, including the following steps:

[0049] S1: Segmentation of spatio-temporal data. The original collected data is divided into multiple tracks according to the date to form a sequence data set D. The original collection time is pushed forward by N hours (for example, 4 hours), and the collected data is divided according to the attribution date that was pushed back. When N=4, that is, every day starts from 4:00 a.m. of the current day to 4:00 a.m. of the next day. The trajectories of each day are independent of each other, and the trajectories of each day are called a transaction.

[0050] S2: Obtain the sequence data set D, the support threshold α, the deduplication time interval threshold ΔT, and the same trajectory point time interval threshold Δt.

[0051] S3: Each sub-track in the sequence data set D is deduplicated. If two or more...

Embodiment 2

[0078] figure 2 It shows a frequent trajectory mining system for massive spatio-temporal data according to the method described in Embodiment 1, including a data preprocessing module, a first-order frequent trajectory mining module, and a k-order frequent trajectory mining module.

[0079] The data preprocessing module is used to divide the data into multiple independent transactions, and deduplicate the traces within the transactions with a time difference threshold of Δt.

[0080] The first-order frequent trajectory mining module is used to mine frequent trajectories with a length of 1, and includes a trajectory merging module within the same site and a support threshold α filtering module.

[0081] The k-order frequent trajectory mining module is used to mine frequent trajectories with a length of k, and only takes effect when the return value of the k-order frequent trajectory mining module is not empty, and also includes a trajectory merging module and a support threshol...

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 provides a method for extracting frequent tracks with time constraints from historical spatio-temporal data, and belongs to the field of big data mining. The method comprises the steps of continuously performing track segmentation; performing data cleaning, such as duplicate removal of continuous track sites; generating 1- frequent track sets; filtering a support degree threshold alpha; generating a k + 1 sequence; and filtering the support degree threshold alpha of the k + 1 sequence; repeatedly executing the steps of generating the high-order candidate tracks by the low-order frequent tracks and screening to obtain the frequent tracks to complete mining of all the frequent tracks of the spatio-temporal data. According to the invention, time interval constraints are added inthe frequent track mining process, so that the method has higher practical reference value and applicability. Massive historical trajectory data are mined, frequent tracks of a target are finally output through track division and sub-track induction, and the method has important significance for users to effectively process trajectory data, filter redundant information, research front-back association between trajectories and the like.

Description

technical field [0001] The invention relates to the field of big data mining, and is a trajectory feature extraction method and system based on massive spatio-temporal data. Background technique [0002] The original trajectory formed by the order of position and time stamp is meaningless to people, and effective information cannot be obtained intuitively. It is necessary to deeply mine massive spatio-temporal data to find out the activity rules of the target. In order to solve this problem, frequent trajectories that meet the support threshold can be displayed to users through trajectory division and trajectory induction. Considering the trajectory of each day as an independent transaction, this problem can be transformed into a frequent sequence mining problem, that is, each path formed by a combination of sites is regarded as a frequent sequence, and we find the sequence with the most occurrences. At present, such algorithm models already include the classic PrefixSpan a...

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 Patents(China)
IPC IPC(8): G06F16/2458G06F16/29
CPCG06F16/2465G06F16/29
Inventor 吴善新
Owner 南京柏跃软件有限公司