CN103593361B - Movement space-time trajectory analysis method in sense network environment - Google Patents
Movement space-time trajectory analysis method in sense network environment Download PDFInfo
- Publication number
- CN103593361B CN103593361B CN201210290571.4A CN201210290571A CN103593361B CN 103593361 B CN103593361 B CN 103593361B CN 201210290571 A CN201210290571 A CN 201210290571A CN 103593361 B CN103593361 B CN 103593361B
- Authority
- CN
- China
- Prior art keywords
- data
- space
- time
- track
- semantic
- 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.)
- Active
Links
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/90—Details of database functions independent of the retrieved data types
- G06F16/95—Retrieval from the web
- G06F16/953—Querying, e.g. by the use of web search engines
- G06F16/9537—Spatial or temporal dependent retrieval, e.g. spatiotemporal queries
Abstract
The invention relates to the technical field of movement behavioral analysis and prediction in a sense network environment, and specifically to a movement space-time trajectory analysis method in the sense network environment. The movement space-time trajectory analysis method in the sense network environment comprises data reception of receiving trajectory movement position data generated by a positioning device and resolving the data format into a data format applicable to data treatment; semantic treatment of performing clustering operation on the semantic trajectory data; space-time correlation of performing characteristic analysis and statistics on clustered semantic trajectory data in a time domain and a space domain, and performing time-space correlation analysis in combination with the time domain and the space domain; correlation similarity analysis of calculating space-time correlation similarity of the semantic trajectory and performing analysis and calculation on the correlation among different space domains and different movement objects; outputting a result. The movement space-time trajectory analysis method in the sense network environment solves the problem of continuous treatment and mutual correlation of time and space dimensions in a traditional transactional database, and meets the need from a sense network application service to real-time analysis of trajectory movement data.
Description
Technical field
The present invention relates to the mobile behavior analysis under sensing network environment and electric powder prediction, specifically a kind of sense
Answer Mobile Space-time trajectory analysis method under network environment.
Background technology
At present, the popularization with the shift position such as GPS harvester and be wirelessly transferred, the development of ubiquitous computation technology,
The space-time trajectory analysis necks such as the behavior patterns mining based on moving object position information, real time position service, shift position prediction
The research in domain increasingly causes the concern of academia and industrial circle, and the application of its correlation is also increasingly extensive.At present in intelligent transportation
Management and the aspect such as scheduling, the monitoring process of rapid onset flood, the change perception of ecological environment, mobile network's value-added service
Existing related base application.Because space-time trajectory data is respectively provided with continuation property on time dimension and Spatial Dimension, with
When space time correlation universally present in trajectory analysis during, therefore carry out trajectory analysis ten with reference to Spatial dimensionality distribution character
Divide necessity.But, the mobile analysis method in existing track or the distribution characteristicss only considering Spatial Dimension at present, or only consider
Shift position, according to the spatial distribution characteristic of time order and function order, there is no the analysis side of maturation for space time correlation track aspect
Method.It is simultaneously based on background knowledge（As geo-demographics' distribution, shift position point semantic expressiveness etc.）, time and space mutually closes
Connection similarity cluster, the mobility model of semantic space represents etc. that aspect lacks the analysis and research method of correlation, and this moves for track
Dynamic analysis brings a huge difficult problem with the application of Information Mobile Service.Therefore, in the urgent need to one kind trajectory analysis method pair effectively
Carry out feature analysiss and the pattern extraction of profound level in mobile location information.
Content of the invention
For the above-mentioned problems in the prior art, the invention provides a kind of based on shift position trajectory analysis it is
System property method, carries out the analysis of track and the discovery of pattern by space time correlation analysis with locus semantic background, effectively solves
The deficiency that the association analysiss aspect of the moving object position trace information determined under LBS exists, meets Information Mobile Service application right
Needs in aspects such as real-time, complexity, integration, actualities.
The present invention be employed technical scheme comprise that for achieving the above object：Mobile Space-time trajectory analysis under sensing network environment
Method, comprises the following steps：
Data receiver and parsing：Track mobile position data produced by receiving positioner, including shift position points
According to corresponding time data；Noise data therein, redundant data, wrong data and deficiency of data are filtered
Cleaning；Linear interpolation operation is carried out to the data after cleaning, adjacent position data time spacing value is exceeded with the data of threshold value,
Linearisation point of addition point data between adjacent position, this threshold value is combined with specific application background and is given by user；
Semantic processes：Track mobile position data after parsing is converted into the semantic track data on abstract sense, that is,
The mobile position data that space-time three-dimensional coordinate represents is carried out with the semantic conversion under two-dimensional coordinate, specially will be by GPS longitude, dimension
The space two-dimensional element that degree represents is converted to the region semantic one-dimensional element under geography information, and corresponding time dimension element is not
Become；Proximate region position data in semantic track data is sorted out on basis by here；
Space time correlation：In time domain and spatial domain, distribution characteristicss and density feature are pressed to the data after semantic processes respectively
Carry out similarity analysis statistics, binding time domain and spatial domain carry out space time correlation degree analysis；Described association similarity analysis be：
Calculate the space time correlation similarity of semantic track, for the degree of association between different spaces domain, between different mobile object respectively
Calculated；
Output：Probabilistic model is set up according to above-mentioned association similarity analysis result, the trajectory model being found is entered
Row semantic intergrationization is processed, and produces readable output result；Calculate the individual space-time track probability with colony of mobile object, prediction
Its following space-time track position.
The object of described parsing includes various criterion acquired in the collecting device of different shift positions, the rail of different-format
Mark mobile position data.
Described locus semantic knowledge information represents social satellite information, including demographics distributed intelligence, economic society
Can information and mechanism's setting, region division.
Described semantic track data after semantic processes is stored in semantic knowledge-base.
Track mobile position data produced by described positioner is sent to corresponding movement in the way of prompting message and sets
Standby upper.
Described prompting message includes data is activation, transmission message and abnormal conditions prompting.
Described space time correlation is specially：
Position between produce similarity measure matrix：1）The trajectory range that motion track is covered is with network interconnection
Mode carries out location network calculating, trajectory range is divided into n mutually disjunct regional ensemble, to any two in this set
Individual region is based on its track of topological relationship calculation and connects number；
2）Calculate its region interest measure corresponding to above-mentioned divided region：
Value=f (Nin,Nout,ΔT)
Wherein NinIndicate entry into the track number in this region, NoutRepresent the track number leaving this region, Δ T represents that track is stopped
The accumulated time staying, Value represents the interest measure of the area of space being drawn based on above three parameter；
3）Carry out cluster between analogous location with interregional track on the basis of region interestingness measure is connected, thus setting up
Region and association in time quantitative relationship, and draw that there is the region that same trajectories access feature；
0≤lI, j≤1
Wherein, lI, jRepresent the similarity value between ith zone and j-th region, and matrix diagonals line element is identical
In 1；
4）Position under utilization space semanteme clusters to locus to similar matrix, makes the sky with similar semantic
Between position be classified as a class；
Similarity measure matrix is set up between mobile object：Based on mobile object trajectory range network topology, to not
Set up metric matrix with the mobile object similarity relation on region, this metric matrix is in order to represent n mobile object in a certain area
The similar incidence relation of movement on domain, the such as time of staying, travel frequency, initial and final position,
0≤mI, j≤1
Wherein, mI, jRepresent the similarity value between i-th mobile object and j-th mobile object, matrix diagonals line element
Plain mI, iIt is constantly equal to 1.
Described data receiver, semantic processes, space time correlation, association similarity analysis and result output are all in monitor state
Under carry out, alarm is carried out for exception and error situation.
Track data after described parsing carries out semantic conversion processing, the semantic flow data one side after conversion and history rail
Mark data compares, and carries out individual Track association analysis and colony's Track association analysis respectively；On the other hand using presetting
Known event condition carry out condition coupling, if meeting certain event structure condition set in advance, that is, be considered some
Determine the generation of event, thus producing the operation such as abnormal alarm.
The anomalous event that described monitoring obtains is saved in historical data base to carry out historical events renewal.
The present invention has advantages below：
By shift position perceive the mancarried device or equipment acquisition and recording to mobile object itself mobile message, can between
The relevant information of the relevant information of external environment condition and mobile colony residing for ground connection reflection mobile object.Track mobile conduct sensing
Directly perceived under network environment, dynamic message form not only can provide location Based service, mobile message to hand over mobile object
Mutually wait application service, and the inherent law of mobile colony can be perceived with variation tendency and predict, simultaneously can be right
Environmental information is reflected construction and maintenance in order to managing, optimizing public infrastructure in real time.
The analysis method of track mobile location information weakening with disappearance to the phase under sensing network in space time correlation dimension
Close application and create larger inhibition, become the bottleneck that sensing network related application is widely popularized to a certain extent,
Apply the quick inspection in real time service offer, abnormal conditions especially for complicated integrated service on real-time position information basis
Survey and define obvious restriction with the aspect such as tracking, comprehensive extraction of mobile behavior pattern.
Provided by the present invention it is mutually related trajectory analysis method based on time, Spatial Dimension, in conjunction with trajectory location points
Semantic expressiveness and relevant position demographics distributed intelligence, in track historical time record, real-time time record and future
The different aspects such as finite time interval between single individual, same community, be analyzed between different groups comparing, solve
Between position semantic background knowledge, demographics distributed intelligence and locus point combine defective tightness, time dimension information with
Spatial positional information cannot cannot interact etc. related between efficient association, space-time track mobile behavior pattern and real knowledge excavation
Problem.
Brief description
Fig. 1 is method of the present invention flow chart；
Fig. 2 is that space time correlation of the present invention processes schematic diagram；
Fig. 3 is track of the present invention flow data real-time processing engine principles structure chart；
Fig. 4 is the integrated system structure chart of present invention application.
Specific embodiment
Below in conjunction with the accompanying drawings and embodiment the present invention is described in further detail.
As shown in figure 1, being method of the present invention flow chart.Space time correlation is analyzed（Spatial-Temporal
Correlation Analysis, STCA）Based on semantic knowledge-base track data is carried out semantic conversion on Spatial dimensionality and
Represent, compared by the association analyzer of time domain, spatial domain calculate diverse location between, the pass between different mobile object
Connection similarity, using the track data in historical data base as comparison other, ultimately generates semantic track behavioral pattern.Space-time closes
Connection analysis is mainly made up of following assembly：
1. track data receives：For track mobile position data produced by receiving positioner.
2. parse：Track for various criterion acquired in the collecting device of different shift positions for the parsing, different-format
Position data.
3. semantic knowledge-base：The locus semantic knowledge information of storage track mobile institute overlay area, including population system
Meter distributed intelligence, economic society information and the society such as mechanism's setting, region division satellite information, and the shifting on time dimension
Dynamic statistical distribution knowledge etc., semantic knowledge-base provides for the operation such as the pretreatment of space-time track, division, cluster as background knowledge and props up
Hold.
4. semantic processes：Interact with semantic knowledge-base, for parsing produced by track data carry out semantic expressiveness,
Semantic coordinate transformation, Semantic Clustering etc. operate；Semantic expressiveness is the semantic rail being converted into initial trace data on abstract sense
Mark data, semantic coordinate transformation is the two-dimensional coordinate table being converted into the space-time three-dimensional coordinate of initial trace data under semantic coordinate
Show, Semantic Clustering is the cluster operation on here basis, semantic track being carried out.On the one hand reject redundancy track data, another
Aspect notes abnormalities track.
5. message produces：Produce and be sent to data is activation on associated mobile device and transmission message and abnormal conditions
Prompting message.
6. space time correlation analysis：In time domain and spatial domain, feature analysiss and statistics are carried out to semantic track data respectively,
Carry out space time correlation degree analysis in combination with time domain and spatial domain.
7. similarity analysis are associated：For calculating the space time correlation similarity of semantic track, for different spaces region it
Between, the degree of association between different mobile object is analyzed calculating.
8. flow data processes engine：The real time knowledge providing oriented locus flow data finds to support work(with application service
Can, and carry out data renewal, transmission with portable running fix equipment, interact.
9. monitoring management：It is responsible for specially to track data reception, parsing, semanteme converts and process, space time correlation are analyzed, phase
It is monitored like operations such as degree calculating.
10. export：It is responsible for setting up probabilistic model according to Similarity Measure statistical law, the trajectory model being found is entered
Row semantic intergrationization is processed to produce more succinct readability, more abstract complicated semantic intergration output result, base simultaneously
In probabilistic model, for mobile object, the individual Future Trajectory movement with colony and behavior are analyzed and predict.
Space-time trajectory data flow chart of data processing is as shown in Figure 2：After being sent to trajectory analysis system receiving terminal, analysis
System is by the identification operation that by historical data base, it is carried out with space-time mobile behavior and track data, semantic knowledge-base afterwards
Track data will be carried out with the association identification process of semantic knowledge information, thereafter will respectively position between and mobile object it
Between produce similarity measure matrix.For position between similarity measure matrix, space time correlation analysis first by track move institute
The trajectory range covering carries out location network calculating in the way of network interconnection, and utilization space semantic information is to locus afterwards
Carry out Semantic Clustering.In cluster process, the locus with similar semantic will be classified as a class, the semantic locations point of exception
Semantic association analysis part will be sent to and detect abnormal track behavior.By semantic coordinate transformation process, by semantic locations rail
Mark extracts as semantic space probabilistic model, the region in built vertical statistical significance and association in time quantitative relationship.Mobile object it
Between similar matrix calculate first calculate mobile object network topology, and then take mobile object semanteme conversion process draw
The Semantic Clustering relation of mobile object.By position between similarity measure can be found that having same trajectories accesses feature
Region, and then combine semantic knowledge, track data can be analyzed, explain and predict.By the phase between mobile object
Likelihood metric can carry out cluster analyses to the individuality with similar mobile behavior and colony, sets up the mobile power in colony's meaning
Pattern knowledge, provides more targeted, more selectively service support for Mobile solution service.
Space time correlation analysis in the present invention（STAC）Affiliated track flow data processes the principle assumption diagram of engine modules such as
Shown in Fig. 3：Individual flow data is activation collected by running fix station acquisition device to while trajectory analysis system preliminary
Pass to flow data after pretreatment and process engine, flow data processes engine and utilizes its internal semantic knowledge management plug-in unit convection current
Data carries out semantic conversion processing.Semantic flow data one side after conversion, compared with historical trajectory data, carries out individual respectively
The analysis of body Track association and colony's Track association analysis；On the other hand semantic flow data passes through event monitor, using setting before
Fixed known event condition carries out condition coupling, once meeting certain set event structure condition, that is, is considered some
Determine the generation of event, thus producing the operation such as abnormal alarm, to realize the purpose of real-time monitoring mobile object behavior.Institute simultaneously
Monitor the anomalous event obtaining will be saved in historical data base to carry out historical events renewal.
The mobile flow data space time correlation analysis of track designed by the present invention is as shown in Figure 4 with integrated morphology：Mobile portable
Formula terminal and various application platform are connected with track BMAT server by cloud network, are on the one hand gathered itself
Track mobile data pass through wireless network transmissions to cloud network platform, another aspect background server is that it provides real-time
Related Mobile solution calculates service support.Space-time track flow data passes to space-time trajectory analysis system in real time by transmission platform
System, system it is carried out preliminary pretreatment and backup preserve operation after, by the space language of space-time Track association analyzer
Behavioral pattern data storehouse carries out space time correlation analysis to real-time streaming data, by comparing language for adopted data base, location database
After the feature clustering relation on time dimension and Spatial Dimension, comprehensive spatial and temporal association enters every trade to it to adopted track data
For analyzing and researching, integrating engine and space time correlation engine carry out higher level semantic collection to the mobile semanteme behavior being drawn into
Become and operation associated, final track knowledge is saved in be updated to rule base in knowledge base, export available simultaneously
Integrated serve the representation of knowledge.
Claims (8)
1. under a kind of sensing network environment Mobile Space-time trajectory analysis method it is characterised in that comprising the following steps：
Data receiver and parsing：Track mobile position data produced by receiving positioner, including shift position point data and
Corresponding time data；Noise data therein, redundant data, wrong data and deficiency of data are carried out filter clearly
Wash；Linear interpolation operation is carried out to the data after cleaning, adjacent position data time spacing value is exceeded with the data of threshold value,
Linearisation point of addition point data between adjacent position, this threshold value is combined with specific application background and is given by user；
Semantic processes：That is, pair track mobile position data after parsing is converted into semantic track data on abstract sense, when
The mobile position data that empty three-dimensional coordinate represents carries out the semantic conversion under two-dimensional coordinate, specially will be by GPS longitude, dimension table
The space two-dimensional element showing is converted to the region semantic one-dimensional element under geography information, and corresponding time dimension element is constant；?
On this basis, the proximate region position data in semantic track data is sorted out；
Space time correlation：In time domain and spatial domain, the data after semantic processes is carried out with density feature by distribution characteristicss respectively
Similarity analysis count, and binding time domain and spatial domain carry out space time correlation degree analysis；Described association similarity analysis be：Calculate
The space time correlation similarity of semantic track, is carried out respectively for the degree of association between different spaces domain, between different mobile object
Calculate；
Described space time correlation is specially：
Position between produce similarity measure matrix：1) trajectory range that motion track is covered is in the way of network interconnection
Carry out location network calculating, trajectory range is divided into n mutually disjunct regional ensemble, to any two area in this set
Domain is based on its track of topological relationship calculation and connects number；
2) calculate its region interest measure corresponding to above-mentioned divided region：
Value=f (Nin,Nout,ΔT)
Wherein NinIndicate entry into the track number in this region, NoutRepresent the track number leaving this region, Δ T represents what track stopped
Accumulated time, Value represents the interest measure of the area of space being drawn based on above three parameter；
3) carry out cluster between analogous location with interregional track on the basis of region interestingness measure is connected, thus setting up region
With association in time quantitative relationship, and draw have same trajectories access feature region；
Wherein, li,jRepresent the similarity value between ith zone and j-th region, and matrix diagonals line element is constantly equal to 1；
4) position under utilization space semanteme clusters to locus to similar matrix, makes the space bit with similar semantic
Put and be classified as a class；
Similarity measure matrix is set up between mobile object：Based on mobile object trajectory range network topology, to not same district
Mobile object similarity relation on domain sets up metric matrix, and this metric matrix is in order to represent n mobile object on a certain area
The similar incidence relation of movement,
Wherein, mi,jRepresent the similarity value between i-th mobile object and j-th mobile object, matrix diagonals line element
mi,iIt is constantly equal to 1；
Output：Probabilistic model is set up according to above-mentioned association similarity analysis result, language is carried out for the trajectory model being found
Adopted integrated approach, produces readable output result；Calculate the individual space-time track probability with colony of mobile object, predict it not
The space-time track position come；
Described data storage after semantic processes is in semantic knowledge-base.
2. under sensing network environment according to claim 1 Mobile Space-time trajectory analysis method it is characterised in that described solution
The object of analysis includes various criterion acquired in the collecting device of different shift positions, the track shift position number of different-format
According to.
3. under sensing network environment according to claim 1 Mobile Space-time trajectory analysis method it is characterised in that institute's predicate
Memory space position semantic knowledge information in adopted knowledge base, represents social satellite information, including demographics distributed intelligence, economy
Social information and mechanism's setting, region division.
4. under sensing network environment according to claim 1 Mobile Space-time trajectory analysis method it is characterised in that described fixed
Track mobile position data produced by the device of position is sent on corresponding mobile device in the way of prompting message.
5. according to claim 4 sensing network environment under Mobile Space-time trajectory analysis method it is characterised in that described carry
Show that message includes data is activation, transmission message and abnormal conditions prompting.
6. under sensing network environment according to claim 1 Mobile Space-time trajectory analysis method it is characterised in that described number
It is all to carry out under monitor state according to reception, semantic processes, space time correlation, association similarity analysis and result output, for different
Normal and error situation carries out alarm.
7. under sensing network environment according to claim 1 Mobile Space-time trajectory analysis method it is characterised in that described solution
On the one hand and historical trajectory data track mobile position data after analysis carries out semantic conversion processing, and the semantic flow data after conversion
Compare, carry out individual Track association analysis and colony's Track association analysis respectively；On the other hand utilize set in advance known
Event condition carries out condition coupling, if meeting certain event structure condition set in advance, that is, is considered that some determines thing
The generation of part, thus produce abnormal alarm operation.
8. under sensing network environment according to claim 7 Mobile Space-time trajectory analysis method it is characterised in that described product
The event of raw abnormal alarm is saved in historical data base to carry out historical events renewal.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201210290571.4A CN103593361B (en) | 2012-08-14 | 2012-08-14 | Movement space-time trajectory analysis method in sense network environment |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201210290571.4A CN103593361B (en) | 2012-08-14 | 2012-08-14 | Movement space-time trajectory analysis method in sense network environment |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN103593361A CN103593361A (en) | 2014-02-19 |
| CN103593361B true CN103593361B (en) | 2017-02-22 |
Family
ID=50083510
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201210290571.4A Active CN103593361B (en) | 2012-08-14 | 2012-08-14 | Movement space-time trajectory analysis method in sense network environment |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN103593361B (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN108710637A (en) * | 2018-04-11 | 2018-10-26 | 上海交通大学 | Taxi exception track real-time detection method based on time-space relationship |
Families Citing this family (40)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103914563A (en) * | 2014-04-18 | 2014-07-09 | 中国科学院上海微系统与信息技术研究所 | Pattern mining method for spatio-temporal track |
| CN104036139B (en) * | 2014-06-12 | 2017-07-07 | 中国科学院软件研究所 | A kind of mobile object track monitoring method |
| CN104252527B (en) * | 2014-09-02 | 2018-04-20 | 百度在线网络技术（北京）有限公司 | A kind of method and apparatus of the resident information of definite mobile subscriber |
| CN104679911B (en) * | 2015-03-25 | 2018-03-27 | 武汉理工大学 | It is a kind of based on discrete weak related cloud platform decision forest sorting technique |
| CN104765873B (en) * | 2015-04-24 | 2019-03-26 | 百度在线网络技术（北京）有限公司 | User's similarity determines method and apparatus |
| US10073908B2 (en) | 2015-06-15 | 2018-09-11 | International Business Machines Corporation | Functional space-time trajectory clustering |
| CN105652304B (en) * | 2016-01-06 | 2017-10-20 | 成都小步创想畅联科技有限公司 | Merge the place recognition methods of multisensor |
| CN105426553B (en) * | 2016-01-15 | 2018-09-11 | 四川农业大学 | A kind of object real-time tracking method for early warning and system based on smart machine |
| CN105719191B (en) * | 2016-01-20 | 2019-10-11 | 东北大学 | The social groups that behavior semanteme is not known under multiscale space find method |
| CN107229940A (en) * | 2016-03-25 | 2017-10-03 | 阿里巴巴集团控股有限公司 | Data adjoint analysis method and device |
| CN105893537B (en) * | 2016-03-31 | 2019-06-07 | 百度在线网络技术（北京）有限公司 | The determination method and apparatus of geography information point |
| CN106570062B (en) * | 2016-10-08 | 2021-01-05 | 中国人民解放军理工大学 | Road network track uncertain moving object range query system and method |
| CN106649656B (en) * | 2016-12-13 | 2020-03-17 | 中国科学院软件研究所 | Database-oriented space-time trajectory big data storage method |
| CN106844585A (en) * | 2017-01-10 | 2017-06-13 | 广东精规划信息科技股份有限公司 | A kind of time-space relationship analysis system based on multi-source Internet of Things location aware |
| CN106951455A (en) * | 2017-02-24 | 2017-07-14 | 河海大学 | A kind of similar track analysis system and its analysis method |
| CN108537241A (en) * | 2017-03-02 | 2018-09-14 | 镇江雅迅软件有限责任公司 | A kind of building moving object track method for measuring similarity |
| CN107133646B (en) * | 2017-05-03 | 2019-09-17 | 山东合天智汇信息技术有限公司 | A kind of method and system by human behavior track identification emphasis personnel |
| CN107180378A (en) * | 2017-05-11 | 2017-09-19 | 北京旷视科技有限公司 | Commodity attention rate preparation method and device |
| CN108268597B (en) * | 2017-12-18 | 2020-10-09 | 中国电子科技集团公司第二十八研究所 | Moving target activity probability map construction and behavior intention identification method |
| CN108170793B (en) * | 2017-12-27 | 2020-10-09 | 厦门市美亚柏科信息股份有限公司 | Vehicle semantic track data-based dwell point analysis method and system |
| CN108052924B (en) * | 2017-12-28 | 2020-10-27 | 武汉大学深圳研究院 | Identification method of spatial motion behavior semantic mode |
| CN108629000A (en) * | 2018-05-02 | 2018-10-09 | 深圳市数字城市工程研究中心 | A kind of the group behavior feature extracting method and system of mobile phone track data cluster |
| CN108898614B (en) * | 2018-06-05 | 2022-06-21 | 南京大学 | Object trajectory proposing method based on hierarchical spatio-temporal region combination |
| CN108920555A (en) * | 2018-06-20 | 2018-11-30 | 上海百林通信网络科技服务股份有限公司 | A kind of auxiliary information based on the associated similar personnel's population analysis method of LTE mobile network's big data |
| CN109726737B (en) * | 2018-11-27 | 2020-11-10 | 武汉极意网络科技有限公司 | Track-based abnormal behavior detection method and device |
| CN109656973B (en) * | 2018-11-30 | 2022-07-08 | 武汉烽火众智数字技术有限责任公司 | Target object association analysis method and device |
| CN109783515B (en) * | 2019-01-25 | 2021-04-23 | 上海创景信息科技有限公司 | Multi-relation data track tracing method and system based on database |
| CN110162586B (en) * | 2019-05-24 | 2021-10-19 | 中国科学院地理科学与资源研究所 | Similarity query system and method suitable for branch track of moving target |
| CN110519324B (en) * | 2019-06-06 | 2020-08-25 | 特斯联（北京）科技有限公司 | Person tracking method and system based on network track big data |
| CN110134097B (en) * | 2019-07-10 | 2019-09-20 | 江苏金恒信息科技股份有限公司 | A kind of control method and device acquiring equipment |
| WO2021029822A1 (en) * | 2019-08-13 | 2021-02-18 | Hitachi, Ltd. | System and method for dispatching vehicles technical field |
| CN110991539B (en) * | 2019-09-05 | 2023-10-31 | 北京无线电测量研究所 | Space target high-frequency repetitive behavior recognition method |
| CN110888912A (en) * | 2019-10-15 | 2020-03-17 | 中国人民解放军国防科技大学 | Target behavior semantic track prediction method based on space-time big data |
| CN110837529B (en) * | 2019-11-27 | 2022-04-29 | 广东大秦纪元信息科技有限公司 | Big data analysis monitoring method and device, server and readable storage medium |
| CN111739056B (en) * | 2020-06-23 | 2024-02-13 | 杭州海康威视数字技术股份有限公司 | Track tracking system |
| CN112383875B (en) * | 2020-06-28 | 2021-07-30 | 中国信息通信研究院 | Data processing method and electronic equipment |
| CN112199609B (en) * | 2020-11-17 | 2021-09-21 | 东北大学 | POI recommendation system and method for sensing space-time semantic interval under self-attention |
| CN112732929A (en) * | 2021-01-06 | 2021-04-30 | 东莞理工学院 | Ontology-based movement track modeling and semantic query system and construction method |
| CN114530018B (en) * | 2022-04-24 | 2022-08-16 | 浙江华眼视觉科技有限公司 | Voice prompt method and device based on pickup trajectory analysis |
| CN115542308B (en) * | 2022-12-05 | 2023-03-31 | 德心智能科技(常州)有限公司 | Indoor personnel detection method, device, equipment and medium based on millimeter wave radar |
Family Cites Families (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101231642A (en) * | 2007-08-27 | 2008-07-30 | 中国测绘科学研究院 | Space-time database administration method and system |
| US8224766B2 (en) * | 2008-09-30 | 2012-07-17 | Sense Networks, Inc. | Comparing spatial-temporal trails in location analytics |
-
2012
- 2012-08-14 CN CN201210290571.4A patent/CN103593361B/en active Active
Non-Patent Citations (3)
| Title |
|---|
| Finding Similar Users Using Category-Based Location History;Xiangye Xiao 等;《international conference on advances in geographic information systems》;20101231;442-445 * |
| 基于时空约束的轨迹聚类方法研究与应用;张旭;《中国优秀硕士学位论文全文数据库 信息科技辑》;20101115(第11期);I140-34 * |
| 用于交通出行调查的GPS时空轨迹数据简化与语义增强研究;张波;《中国优秀硕士学位论文全文数据库 工程科技Ⅱ辑》;20110915(第09期);C034-14 * |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN108710637A (en) * | 2018-04-11 | 2018-10-26 | 上海交通大学 | Taxi exception track real-time detection method based on time-space relationship |
Also Published As
| Publication number | Publication date |
|---|---|
| CN103593361A (en) | 2014-02-19 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN103593361B (en) | Movement space-time trajectory analysis method in sense network environment | |
| Qin et al. | When things matter: A survey on data-centric internet of things | |
| Sundhari et al. | IoT assisted Hierarchical Computation Strategic Making (HCSM) and Dynamic Stochastic Optimization Technique (DSOT) for energy optimization in wireless sensor networks for smart city monitoring | |
| CN103152823B (en) | A kind of wireless indoor location method | |
| Bin et al. | Research on data mining models for the internet of things | |
| Sacharidis et al. | On-line discovery of hot motion paths | |
| CN111209261B (en) | User travel track extraction method and system based on signaling big data | |
| CN108398934B (en) | equipment fault monitoring system for rail transit | |
| Peng et al. | Hierarchical edge computing: A novel multi-source multi-dimensional data anomaly detection scheme for industrial Internet of Things | |
| CN102929903A (en) | Rapid video retrieval method based on layered structuralized description of video information | |
| CN105375995A (en) | Intelligent wireless frequency spectrum online monitoring system and realization method thereof | |
| CN106649801A (en) | Time-space relationship analysis system based on multi-source internet-of-things position awareness | |
| Moreno-Cano et al. | Big data for IoT services in smart cities | |
| CN104202719B (en) | Number measure and crowd situation monitoring method and system based on position credibility | |
| CN106649809A (en) | Internet of Things analysis method | |
| CN106646110A (en) | Low-voltage distribution network fault positioning system based on GIS and Petri technologies | |
| CN109672986A (en) | A kind of space-time big data analysis system | |
| CN115600513A (en) | Karst collapse monitoring early warning and prevention and control integrated informatization simulation studying and judging system | |
| Du et al. | Transit pattern detection using tensor factorization | |
| Qian et al. | Detecting taxi trajectory anomaly based on spatio-temporal relations | |
| Li et al. | Estimating crowd flow and crowd density from cellular data for mass rapid transit | |
| Zhang et al. | Empirical study on taxi gps traces for vehicular ad hoc networks | |
| Yang et al. | Power inspection design by Internet of Things and RFID technology in smart city | |
| Ding et al. | Anomaly detection in large-scale trajectories using hybrid grid-based hierarchical clustering | |
| Chen et al. | Periodic pattern mining based on GPS trajectories |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| C06 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| C14 | Grant of patent or utility model | ||
| GR01 | Patent grant |