CN106408124A - Moving path hybrid forecasting method oriented to data sparse environment - Google Patents
Moving path hybrid forecasting method oriented to data sparse environment Download PDFInfo
- Publication number
- CN106408124A CN106408124A CN201610841545.4A CN201610841545A CN106408124A CN 106408124 A CN106408124 A CN 106408124A CN 201610841545 A CN201610841545 A CN 201610841545A CN 106408124 A CN106408124 A CN 106408124A
- Authority
- CN
- China
- Prior art keywords
- data
- forecasting method
- semantic
- predicted
- path
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Granted
Links
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q10/00—Administration; Management
- G06Q10/04—Forecasting or optimisation specially adapted for administrative or management purposes, e.g. linear programming or "cutting stock problem"
Landscapes
- Engineering & Computer Science (AREA)
- Business, Economics & Management (AREA)
- Human Resources & Organizations (AREA)
- Economics (AREA)
- Strategic Management (AREA)
- Marketing (AREA)
- Game Theory and Decision Science (AREA)
- Entrepreneurship & Innovation (AREA)
- Development Economics (AREA)
- Operations Research (AREA)
- Quality & Reliability (AREA)
- Tourism & Hospitality (AREA)
- Physics & Mathematics (AREA)
- General Business, Economics & Management (AREA)
- General Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
The invention provides a moving path hybrid forecasting method oriented to a data sparse environment. The moving path hybrid forecasting method comprises the steps of: acquiring mobile position data information; processing data , wherein data preprocessing and data semantic analysis are carried out on the data; constructing a semantic knowledge base, wherein original trajectory data is subjected to rich semantic transformation and fusion processing, so as to construct the semantic knowledge base; constructing a hybrid online prediction model which is based on the semantic knowledge base and established on the basis of forward pattern similarity degree matching calculation and a high-order Markov model; and outputting a predicted path, wherein a trajectory fragment to be predicted is input into the hybrid online prediction model for prediction, and the predicted path is output. The moving path hybrid forecasting method effectively overcomes the problem of pattern matching failure caused by data sparse condition, significantly improves the accuracy of path prediction, and satisfies the requirements on real-time performance, high efficiency, predictability and the like of mobile service application.
Description
Technical field
The invention belongs to field of mobile computing, particularly to being a kind of mobile route under data-oriented sparse environment
Hybrid forecasting method.
Background technology
At present, with running fix and tracer technique fast development with widely available so that utilizing location aware devices
It is possibly realized with the historical trajectory data obtaining mobile object.Asked with calculating by historical trajectory data is carried out with semantization modeling
Solution, is extracted and Knowledge Discovery with the value realizing historical track big data, thus supporting related Information Mobile Service application, has become as
The notable trend of of mobile computing field and necessary feature, cause the highest attention of academia and industrial circle simultaneously.
Perceive historical trajectory data based on large-scale groups, efficiently excavate and extract wherein have universality, regular
Moving characteristic and behavioral pattern, build mobile behavior knowledge base；By the mathematical modeling to motion track, using maximum of probability
Derivation method, can achieve and mobile subscriber is precisely predicted in thread path.This technology can be widely applied to urban transportation intelligence
Change the numerous areas such as scheduling is marketed, tourism route is recommended with management, location-based business accurate advertisement.However, answering actual
With in, there are two aspects in said method, be embodied in：1) acquisition that is difficult of context and background knowledge data makes
Must be in conjunction with map match (Map Matching Technique) or traffic flow (Traffic Flow) statistical method is to change
Kind path prediction precision is difficult to prove effective；2) Sparse that perception data value density this substitutive characteristics low are brought is asked
Topic (Data Sparsity Problem) makes traditional calculate or the method for pattern match is difficult to prove effective based on the degree of approximation.
The presence of the problems referred to above brings huge challenge for the application service of path prediction aspect.Therefore, for magnanimity sense
Know the openness distribution characteristicss of track data, how to build application under conditions of context and background knowledge shortage of data
By force, the accurate forecast model of the high mobile route of reliability and method are of great practical significance and using value.
Content of the invention
Invention provides a kind of path Forecasting Methodology towards the openness distribution of magnanimity mobile trajectory data, the technology being adopted
Scheme is：
A kind of mobile route hybrid forecasting method under data-oriented sparse environment, comprises the following steps：
S1：Obtain mobile position data information；
S2：Data processing：The semantic parsing of data prediction data is carried out for data；
S3：Build semantic knowledge-base：Initial trace data is carried out with rich semantic conversion and fusion treatment, builds semantic knowledge-base；
S4：Build mixed on-line estimating model：Based on semantic knowledge-base, set up and calculated and height based on forward mode similarity mode
The mixed on-line estimating model of rank Markov model；
S5：Predicted path exports：Input path segment to be predicted to be predicted, output prediction road in mixed on-line estimating model
Footpath.
Further, the mobile route hybrid forecasting method under a kind of data-oriented sparse environment, mobile position in described S1
Put data message and include path segment to be predicted.
Further, the mobile route hybrid forecasting method under a kind of data-oriented sparse environment, data in described S2
Semantic parsing includes data is carried out with unitized semantic Coordinate Conversion operation, is divided into complete motion track section, rower of going forward side by side
Note.
Further, the mobile route hybrid forecasting method under a kind of data-oriented sparse environment, to former in described S3
Beginning track data carries out rich semantization conversion and fusion treatment includes：Implicit cartographic semantics segmentation, the brief node of road network skeleton
Extraction, Move Mode Knowledge Discovery.
Further, the mobile route hybrid forecasting method under a kind of data-oriented sparse environment, to former in described S3
Beginning track data carries out the conversion of rich semantization and fusion treatment also includes region class Pair transition matrix, described region class Pair
Transition matrix is to be calculated based on implicit cartographic semantics dividing processing.
Further, the mobile route hybrid forecasting method under a kind of data-oriented sparse environment, to former in described S3
Beginning track data carries out rich semantization conversion and fusion treatment also includes many continuous states transition probability model, described many sequential like
State transition probability model is used for segmentation track Sequence Transformed semantic data.
Further, the mobile route hybrid forecasting method under a kind of data-oriented sparse environment, forward direction in described S4
Pattern match includes Match of elemental composition and distance calculates.
Further, the mobile route hybrid forecasting method under a kind of data-oriented sparse environment, to mould before preferential execution
Formula mates prediction process, exports predicted path when matching process has solution；When matching process no solves, execution Markov probability pushes away
Reason model, on the basis of current moving state, forward recursion corresponding order continuous state transition probability is distributed, with maximum probability value
The predicted path that person is 1 as the step-length being exported, by recursion cycle process, using the destination locations information predicted as
End condition, exports predicted path.
Further, the mobile route hybrid forecasting method under a kind of data-oriented sparse environment, to be predicted in described S5
The data processing in corresponding S2 will be executed before path segment input.
Further, the mobile route hybrid forecasting method under a kind of data-oriented sparse environment, pre- for data in S2
Process and devise corresponding dynamic monitoring management and message generation Row control with semantic analyzing step.
The invention provides a kind of path Forecasting Methodology towards the openness distribution of mobile trajectory data, by historical track
Data builds city map semantic model to realize the rich semantic conversion to initial trace data and fusion, sets up history and moves mould
Formula matching primitives (Pattern Matching Computing) and high-order Markov (Higher Order Markov
Model) hybrid forecasting method, it is exactly substantially to build mixing, interchangeable cooperating type forecast model, before on the one hand making full use of
To advantage in terms of sequential no constrains historical information for the Pattern similarity coupling, to lift path precision of prediction；On the other hand with
Interchangeable high-order Markov model builds the segmentation track mobile status transition probability matrix model under strict sequential order relation,
Effectively to overcome the pattern match that Sparse brought to lose efficacy (No Pattern Matching) problem, simultaneously notable carry
Rise the accuracy of path prediction, meet the demand for aspects such as real-time, high efficiency, predictabilitys for the Information Mobile Service application.
Brief description
Fig. 1 is the mobile route hybrid forecasting method step schematic diagram under a kind of present invention data-oriented sparse environment；
Fig. 2 is the mobile route hybrid forecasting method forward mode similarity mode under a kind of present invention data-oriented sparse environment
Result schematic diagram；
Fig. 3 is for the mobile route hybrid forecasting method on-line prediction track difference under a kind of present invention data-oriented sparse environment
Know that the path under length predicts the outcome；
Fig. 4 is that the mobile route hybrid forecasting method under a kind of present invention data-oriented sparse environment predicts the outcome schematic diagram.
Specific embodiment
A kind of mobile route hybrid forecasting method under data-oriented sparse environment, comprises the following steps：
S1：Obtain mobile position data information；
Described information receives and data storage from multi-source location aware source (vehicle GPS, intelligent movable mobile phone, PDA etc.).This enforcement
In example, mobile position data information includes path segment to be predicted.
S2：Data processing：Data is carried out with the semantic parsing of data prediction data；
As shown in Figure 1：Wherein carrying out pretreatment to data is：Collected historical trajectory data is carried out with pretreatment operation, tool
Body includes：1) due to the introduced noise number of channel variation in the change of positioner signal strength and data transmission procedure
According to this module carries out noise measuring and filtration treatment；2) due to mobile object quick moving process link connect unstable
The shortage of data phenomenon that packet loss phenomenon in property and data transmission procedure is led to, this module carries out the data of constant duration
Interpolation operation；
Wherein data semantic parsing includes data is carried out with unitized semantic Coordinate Conversion operation, is divided into complete motion track
Section, and be labeled：1) due to the automatic flow of motion track gatherer process and the disappearance of mark attribute, this module is to even
The language of the Complete complete trajectory section based on time interval threshold value and space interval distance threshold for the continuous collection motion track execution
Adopted cutting operation；2) diversity reason (the WGS84 coordinate in terms of space coordinatess system selection due to multi-source running fix equipment
System, GGRS87 coordinate system, GSM coordinate system etc.), the unitized semantic Coordinate Conversion operation of this module execution.
In the present embodiment, this step S2 data processing step is devised with dynamic monitoring management and message accordingly and produces stream
Process control, that is, in mobile trajectory data reception and resolving, is received by process controller control data and semantic parsing
The procedure operation of process.
S3：Build semantic knowledge-base：Initial trace data is carried out with rich semantic conversion and fusion treatment, builds semantic knowledge
Storehouse；In described S3, rich semantization conversion is carried out to initial trace data and fusion treatment includes：
As shown in figure 3, implicit cartographic semanticsization segmentation implements process being：Based on the offline trajectory location points of extensive history
Spatial distribution characteristic calculates its two-dimentional density function, approaches value set in conjunction with two-dimentional density function and border, realizes to impliedly
The reconstruct of figure geographical space semanteme topological relation and the secondary partition process of region class spatial area；
The brief node of road network skeleton extracts：Similar with implicit cartographic semanticsization segmentation module, based on Large-scale Mobile track data
Spacial distribution density feature, the implicit location point of the mobile restricted track data under extraction belt road network, formed road network bone
The brief node set of frame.
Road network skeleton brief node extraction process is calculated as with the mobile corner of the adjacent k sequence in historical movement path
Foundation, extracts crucial road-net node by density clustering method.
Move Mode Knowledge Discovery is specially with implicit cartographic semantics segmentation and road network skeleton brief node output set
Based on, rich semantization conversion process is carried out to acquired original mobile trajectory data, so high based on Sequential Pattern Mining Algorithm
Effect extracts potential mobile behavior set of modes, provides knowledge to support for follow-up path prediction.
In described S3, initial trace data is carried out with rich semantization conversion and fusion treatment also includes region class Pair and moves
Move matrix, described region class Pair transition matrix is to be calculated based on implicit cartographic semantics dividing processing, specifically real
It is now that input data is combined into the Complete complete trajectory section collection in mobile trajectory data semantic meaning analysis module, extract therein
Pair point set, and then realize the rich semantic of corresponding Pair point set based on the region class spatial area division of implicit cartographic semantics
Change transformation process, build the corresponding Pair transition probability matrix-block under conditional probability using Bayesian network.Wherein pair is
It is right to another place from one place to refer to, and comprises the beginning and end responding；The pair of region class refers to from a region
Start, terminate to another region.
In described S3, initial trace data is carried out with rich semantization conversion and fusion treatment also includes many continuous states and moves
Move probabilistic model, described many continuous states transition probability model is used for segmentation track Sequence Transformed semantic data.
Wherein semantic knowledge-base refers to store mobile behavior set of modes, the shifting that Move Mode Knowledge Discovery module is excavated
The high state based on Markov probabilistic process that dynamic behavior correlation rule and many continuous states transition probability are exported moves
Transition matrix knowledge.
S4：Build mixed on-line estimating model：Based on semantic knowledge-base, set up and calculated based on forward mode similarity mode
Mixed on-line estimating model with high-order Markov model；
Wherein forward mode coupling includes Match of elemental composition and distance calculates, for realizing in Partial track to be predicted and being sent out
Between the Move Mode of pick, the degree of approximation calculating process based on matching direction and distance, compares output by degree of approximation threshold value simultaneously
Path prediction result.
Wherein Markov Probabilistic Prediction Model：For realizing Partial track to be predicted and the many continuous states being counted
The probability calculation on the basis of current moving state, with high-order Markov exponent number as step-length between transition probability matrix and prediction
Process, output step-length is 1 path prediction result simultaneously.
In the present embodiment, preferential execution forward mode coupling prediction process, the history in maximized utilization Partial is moved
Dynamic information, be effectively improved output predicted path precision, wherein forward mode matching process pass through Partial path segment with
Identity element coupling between the Move Mode excavated, and compare Move Mode one by one to distance calculating before same coupling element
Similarity degree and Partial fragment between, returns corresponding suffix array as output in the case that matching process has solution
Predicted path；In the case of matching process no solution, execute Markov probabilistic reasoning model, on the basis of current moving state,
Forward recursion corresponding order continuous state transition probability is distributed, the prediction being 1 as the step-length being exported using maximum probability value person
Path, by recursion cycle process, using the Partial destination locations information derived as end condition, produces final
Output predicted path.
In hybrid prediction model, forward mode similarity mode computational methods are as follows：
In above formula (1), degree represents the similarity value between historical movement pattern and online fragment motion track, and cov is
The pattern match length of the two, dis represents the compound distance between the current location of online query track and historical pattern, sup
Support for historical pattern.In formula (2), ekFor all elements matching with online query track in historical pattern, eendTable
Show the current location of online query track.
Above-mentioned forward mode similarity mode process is done with brief elaboration, as shown in Fig. 2 circular sequence is moved for online query
Dynamic path segment, be respectively present in historical movement pattern 3 can match pattern, wherein triangular representation coupling element, square
Represent short-term forecast path, the wherein value of candidate pattern 1 is 2, is 1.
In high-order Markov computation model, step-length is that 1 next step potential site Rank computing formula is：
arg Max:score(loc)
Wherein score (loc) represents the Rank value of position candidate loc, dorigRepresent the original position of position loc and fragment track
Distance, ddestFor the distance of position loc and fragment track reasoning destination, pro (loc) is by position loc in the height trained
Transition probability value in rank Markov model.By calculating to the Rank value of m position candidate loc, Rank value the maximum is taken to be
The next step predicted position of online query fragment track.
S5：Predicted path exports：Input path segment to be predicted to be predicted, output is pre- in mixed on-line estimating model
Survey path.
For the openness distribution characteristicss of mobile trajectory data, with above-mentioned mixing, complementary predictive mode realize to
The purpose of the following path prediction of path segment inquired about by line.To 5000 test trails fragments in known length it is respectively
10%th, 20%, 30%, 40% and 50% 5 kind in the case of be predicted route result and compare checking, respectively with 1 rank Markov
Model method is compared with 2 rank Markov model methods, hybrid prediction model (the Hybrid Moving constructed by the present invention
Route Prediction, HMRP) there is significant advantage, see Fig. 3, Fig. 4.
Claims (10)
1. the mobile route hybrid forecasting method under a kind of data-oriented sparse environment it is characterised in that：Described method includes
Following steps：
S1：Obtain mobile position data information；
S2：Data processing：
The semantic parsing of data prediction data is carried out for data；
S3：Build semantic knowledge-base：
Initial trace data is carried out with rich semantic conversion and fusion treatment, builds semantic knowledge-base；
S4：Build mixed on-line estimating model：
Based on semantic knowledge-base, set up online with the mixing of high-order Markov model based on the calculating of forward mode similarity mode
Forecast model；
S5：Predicted path exports：
Input path segment to be predicted to be predicted in mixed on-line estimating model, export predicted path.
2. the mobile route hybrid forecasting method under a kind of data-oriented sparse environment according to claim 1, its feature
It is：In described S1, mobile position data information includes path segment to be predicted.
3. the mobile route hybrid forecasting method under a kind of data-oriented sparse environment according to claim 1, its feature
It is：In described S2, data semantic parsing includes data is carried out with unitized semantic Coordinate Conversion operation, is divided into complete
Motion track section, and be labeled.
4. the mobile route hybrid forecasting method under a kind of data-oriented sparse environment according to claim 1, its feature
It is：In described S3, rich semantization conversion is carried out to initial trace data and fusion treatment includes：Implicit cartographic semantics divides
Cut, the brief node of road network skeleton extracts, Move Mode Knowledge Discovery.
5. the mobile route hybrid forecasting method under a kind of data-oriented sparse environment according to claim 4, its feature
It is：In described S3, initial trace data is carried out with rich semantization conversion and fusion treatment also includes region class Pair transition moment
Battle array, described region class Pair transition matrix is to be calculated based on implicit cartographic semantics dividing processing.
6. the mobile route hybrid forecasting method under a kind of data-oriented sparse environment according to claim 4, its feature
It is：In described S3, initial trace data is carried out with rich semantization conversion and fusion treatment also includes many continuous state migrations generally
Rate model, described many continuous states transition probability model is used for segmentation track Sequence Transformed semantic data.
7. the mobile route hybrid forecasting method under a kind of data-oriented sparse environment according to claim 6, its feature
It is：In described S4, forward mode coupling includes Match of elemental composition and distance calculates.
8. the mobile route hybrid forecasting method under a kind of data-oriented sparse environment according to claim 1, its feature
It is：Preferential execution forward mode coupling prediction process, exports predicted path when matching process has solution；No solve in matching process
When, execute Markov probabilistic reasoning model, on the basis of current moving state, the migration of forward recursion corresponding order continuous state is general
Rate is distributed, and the predicted path being 1 as the step-length being exported using maximum probability value person, by recursion cycle process, to be predicted
Destination locations information as end condition, export predicted path.
9. the mobile route hybrid forecasting method under a kind of data-oriented sparse environment according to claim 1, its feature
It is：The data processing step in corresponding S2 will be executed before path segment input to be predicted in described S5.
10. according to the mobile route hybrid forecasting method under a kind of arbitrary described data-oriented sparse environment of claim 1-9,
It is characterized in that：Devise corresponding dynamic monitoring management for data prediction in S2 and semantic analyzing step to produce with message
Row control.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201610841545.4A CN106408124B (en) | 2016-09-22 | 2016-09-22 | Moving path hybrid prediction method oriented to data sparse environment |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201610841545.4A CN106408124B (en) | 2016-09-22 | 2016-09-22 | Moving path hybrid prediction method oriented to data sparse environment |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN106408124A true CN106408124A (en) | 2017-02-15 |
| CN106408124B CN106408124B (en) | 2020-01-10 |
Family
ID=57996884
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201610841545.4A Expired - Fee Related CN106408124B (en) | 2016-09-22 | 2016-09-22 | Moving path hybrid prediction method oriented to data sparse environment |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN106408124B (en) |
Cited By (11)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN108981739A (en) * | 2018-06-08 | 2018-12-11 | 南方科技大学 | A kind of paths planning method, device, server and storage medium |
| CN109034448A (en) * | 2018-06-14 | 2018-12-18 | 重庆邮电大学 | Trajectory predictions method based on track of vehicle semantic analysis and deepness belief network |
| CN109190656A (en) * | 2018-07-16 | 2019-01-11 | 浙江大学 | A kind of low semantic track mark in interior and complementing method sampled under localizing environment |
| CN109697221A (en) * | 2018-11-22 | 2019-04-30 | 东软集团股份有限公司 | Method for digging, device, storage medium and the electronic equipment of track rule |
| CN109714263A (en) * | 2019-01-18 | 2019-05-03 | 北京邮电大学 | A kind of routing resource and device in satellite communication network |
| CN109997014A (en) * | 2017-11-03 | 2019-07-09 | 北京嘀嘀无限科技发展有限公司 | System and method for determining track |
| CN110321343A (en) * | 2019-07-11 | 2019-10-11 | 广东工业大学 | A kind of wearable device trajectory predictions methods, devices and systems |
| CN110475208A (en) * | 2019-08-06 | 2019-11-19 | 上海连尚网络科技有限公司 | For determining the method and apparatus of user equipment travel path |
| CN110795519A (en) * | 2019-10-28 | 2020-02-14 | 天聚地合(苏州)数据股份有限公司 | Markov model and probability statistics-based position prediction method and readable storage medium |
| CN110909592A (en) * | 2019-10-11 | 2020-03-24 | 重庆特斯联智慧科技股份有限公司 | Target tracking method and system based on multi-scale characteristic quantity |
| CN110909913A (en) * | 2019-10-11 | 2020-03-24 | 重庆特斯联智慧科技股份有限公司 | Scenic spot tour guide service pre-estimation system and method based on intelligent tracking |
Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102713520A (en) * | 2009-10-12 | 2012-10-03 | 通腾科技股份有限公司 | Navigation device & method |
| CN103177562A (en) * | 2011-12-26 | 2013-06-26 | 中国移动通信集团公司 | Method and device for obtaining information of traffic condition prediction |
| CN103415070A (en) * | 2013-07-04 | 2013-11-27 | 百度在线网络技术（北京）有限公司 | Positioning method and device based on mobile path |
| US20140258505A1 (en) * | 2013-03-08 | 2014-09-11 | Disney Enterprises, Inc. | Network condition predictions for multimedia streaming |
-
2016
- 2016-09-22 CN CN201610841545.4A patent/CN106408124B/en not_active Expired - Fee Related
Patent Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102713520A (en) * | 2009-10-12 | 2012-10-03 | 通腾科技股份有限公司 | Navigation device & method |
| CN103177562A (en) * | 2011-12-26 | 2013-06-26 | 中国移动通信集团公司 | Method and device for obtaining information of traffic condition prediction |
| US20140258505A1 (en) * | 2013-03-08 | 2014-09-11 | Disney Enterprises, Inc. | Network condition predictions for multimedia streaming |
| CN103415070A (en) * | 2013-07-04 | 2013-11-27 | 百度在线网络技术（北京）有限公司 | Positioning method and device based on mobile path |
Non-Patent Citations (2)
| Title |
|---|
| 余雪岗等: "用于移动路径预测的混合Markov模型", 《通信学报》 * |
| 张盼盼: "融合复合特征的移动轨迹预测方法的研究与实现", 《万方数据》 * |
Cited By (21)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN109997014B (en) * | 2017-11-03 | 2023-08-18 | 北京嘀嘀无限科技发展有限公司 | System and method for determining trajectory |
| US11692829B2 (en) | 2017-11-03 | 2023-07-04 | Beijing Didi Infinity Technology And Development Co., Ltd. | System and method for determining a trajectory of a subject using motion data |
| CN109997014A (en) * | 2017-11-03 | 2019-07-09 | 北京嘀嘀无限科技发展有限公司 | System and method for determining track |
| CN108981739B (en) * | 2018-06-08 | 2022-02-22 | 南方科技大学 | Path planning method, device, server and storage medium |
| CN108981739A (en) * | 2018-06-08 | 2018-12-11 | 南方科技大学 | A kind of paths planning method, device, server and storage medium |
| CN109034448A (en) * | 2018-06-14 | 2018-12-18 | 重庆邮电大学 | Trajectory predictions method based on track of vehicle semantic analysis and deepness belief network |
| CN109034448B (en) * | 2018-06-14 | 2022-02-11 | 重庆邮电大学 | Trajectory prediction method based on vehicle trajectory semantic analysis and deep belief network |
| CN109190656B (en) * | 2018-07-16 | 2020-07-21 | 浙江大学 | Indoor semantic track marking and complementing method under low-sampling positioning environment |
| CN109190656A (en) * | 2018-07-16 | 2019-01-11 | 浙江大学 | A kind of low semantic track mark in interior and complementing method sampled under localizing environment |
| CN109697221B (en) * | 2018-11-22 | 2021-07-09 | 东软集团股份有限公司 | Track law mining method and device, storage medium and electronic equipment |
| CN109697221A (en) * | 2018-11-22 | 2019-04-30 | 东软集团股份有限公司 | Method for digging, device, storage medium and the electronic equipment of track rule |
| CN109714263B (en) * | 2019-01-18 | 2021-01-29 | 北京邮电大学 | Path selection method and device in satellite communication network |
| CN109714263A (en) * | 2019-01-18 | 2019-05-03 | 北京邮电大学 | A kind of routing resource and device in satellite communication network |
| CN110321343A (en) * | 2019-07-11 | 2019-10-11 | 广东工业大学 | A kind of wearable device trajectory predictions methods, devices and systems |
| CN110321343B (en) * | 2019-07-11 | 2023-11-14 | 广东工业大学 | Wearable device track prediction method, device and system |
| CN110475208A (en) * | 2019-08-06 | 2019-11-19 | 上海连尚网络科技有限公司 | For determining the method and apparatus of user equipment travel path |
| CN110909913A (en) * | 2019-10-11 | 2020-03-24 | 重庆特斯联智慧科技股份有限公司 | Scenic spot tour guide service pre-estimation system and method based on intelligent tracking |
| CN110909592A (en) * | 2019-10-11 | 2020-03-24 | 重庆特斯联智慧科技股份有限公司 | Target tracking method and system based on multi-scale characteristic quantity |
| CN110909592B (en) * | 2019-10-11 | 2020-12-18 | 重庆特斯联智慧科技股份有限公司 | Target tracking method and system based on multi-scale characteristic quantity |
| CN110909913B (en) * | 2019-10-11 | 2021-06-04 | 重庆特斯联智慧科技股份有限公司 | Scenic spot tour guide service pre-estimation system and method based on intelligent tracking |
| CN110795519A (en) * | 2019-10-28 | 2020-02-14 | 天聚地合(苏州)数据股份有限公司 | Markov model and probability statistics-based position prediction method and readable storage medium |
Also Published As
| Publication number | Publication date |
|---|---|
| CN106408124B (en) | 2020-01-10 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN106408124A (en) | Moving path hybrid forecasting method oriented to data sparse environment | |
| CN104462190B (en) | A kind of online position predicting method excavated based on magnanimity space tracking | |
| CN108955693B (en) | Road network matching method and system | |
| Ye et al. | Vehicle trajectory prediction based on Hidden Markov Model | |
| Zhao et al. | Predictive task assignment in spatial crowdsourcing: a data-driven approach | |
| Qiao et al. | A self-adaptive parameter selection trajectory prediction approach via hidden Markov models | |
| Ding et al. | Network-matched trajectory-based moving-object database: Models and applications | |
| CN102708698B (en) | Vehicle optimal-path navigation method based on vehicle internet | |
| CN106202335B (en) | A kind of traffic big data cleaning method based on cloud computing framework | |
| CN109167805A (en) | Analysis and processing method based on car networking space-time data in City scenarios | |
| CN108133611A (en) | Vehicle driving trace monitoring method and system | |
| CN102799897A (en) | Computer recognition method of GPS (Global Positioning System) positioning-based transportation mode combined travelling | |
| CN105976048A (en) | Power transmission network extension planning method based on improved artificial bee colony algorithm | |
| CN104598621A (en) | Track compression method based on sliding window | |
| CN110598917B (en) | Destination prediction method, system and storage medium based on path track | |
| CN111144281B (en) | Urban rail transit OD passenger flow estimation method based on machine learning | |
| CN104135750A (en) | Multiple mobile beacon set moving path planning method based on network density clustering of wireless sensor network | |
| Gu et al. | An improved RRT algorithm based on prior AIS information and DP compression for ship path planning | |
| Li et al. | Bus arrival time prediction based on mixed model | |
| CN115560771A (en) | Sampling-based path planning method and device and automatic driving equipment | |
| CN103593435A (en) | Approximate treatment system and method for uncertain data PT-TopK query | |
| Ji et al. | Clockwise compression for trajectory data under road network constraints | |
| Hu et al. | A comprehensive survey of recommendation system based on taxi GPS trajectory | |
| Jabeen et al. | Autonomous Vehicle Health Monitoring Based on Cloud-Fog Computing | |
| CN113903171B (en) | Vehicle crowd sensing node optimization method based on spatial-temporal characteristics of highway network |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| C06 | Publication | ||
| PB01 | Publication | ||
| C10 | Entry into substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant | ||
| CF01 | Termination of patent right due to non-payment of annual fee |
Granted publication date: 20200110 Termination date: 20210922 |
|
| CF01 | Termination of patent right due to non-payment of annual fee |