CN109784422A - A kind of user trajectory method for detecting abnormality of internet of things oriented mobile terminal device - Google Patents
A kind of user trajectory method for detecting abnormality of internet of things oriented mobile terminal device Download PDFInfo
- Publication number
- CN109784422A CN109784422A CN201910094909.0A CN201910094909A CN109784422A CN 109784422 A CN109784422 A CN 109784422A CN 201910094909 A CN201910094909 A CN 201910094909A CN 109784422 A CN109784422 A CN 109784422A
- Authority
- CN
- China
- Prior art keywords
- sum
- point
- mobile terminal
- terminal device
- internet
- 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
Abstract
The invention proposes a kind of user trajectory method for detecting abnormality of internet of things oriented mobile terminal device, belong to the field of data mining.The method of the present invention solves the problems, such as after being to extract the large-scale geographical location information data in Internet of Things mobile terminal device, and data are cleaned, and generates multiple dwell points, then find discrete point by clustering method, and then find the abnormal track of user.This method complicated and diversified track data suitable for Internet of Things mobile device obtains abnormal point under the premise of guaranteeing calculating speed.
Description
Technical field
The invention belongs to the field of data mining, and in particular to a kind of user trajectory of internet of things oriented mobile terminal device is different
The method often detected.
Background technique
With digitlization and the high speed development of information age, make to mobile terminal device (such as mobile phone) in Internet of Things
With more and more extensive, this makes more and more cases be related to digital information therein, by excavating to these digital informations
The clue of clear up a criminal case can often be searched out.The development of especially various location technologies (such as GPS: global-positioning technology) with it is general
And many mobile terminal devices can obtain the latitude and longitude information of user location in the place with GPS signal, and be retained in and set
In database for itself.It is available to arrive user's daily behavior model by being excavated to these space-time datas, and therefrom
Note abnormalities track.
The object of traditional abnormal track detection algorithm process is all often the object of movement law, such as migratory bird, vehicle rail
Mark etc., and seldom to the abnormality detection research in the action trail of the mankind, it is on the one hand because the abnormal behavior track of the mankind is
It is random, it has no idea to establish suitable locus model, thus the difficulty of detection is increased, while abnormal rail in such circumstances
The concept of mark also becomes more to obscure.Abnormal track is some or all of trace information, in time and space dimension side
The normal trace that face and track data are concentrated has apparent difference.Compared to traditional user can only be obtained from navigation type application
Track compare, at this stage, many applications in smart machine can be transferred through information extraction technology and get with trace information
Data, these data can more comprehensively react the daily behavior of user.But these data often have that complicated, amount is big,
The features such as dimension is high, so that the analysis to these space-time datas becomes a difficult job.
Summary of the invention
The invention proposes a kind of user trajectory Outlier Detection Algorithm, towards be to be mentioned in Internet of Things mobile terminal device
On the one hand the user trajectory information taken solves the problems such as data volume extracted from the device is big and complicated, on the other hand can add
The speed of fast user trajectory outlier detection.
A kind of user trajectory method for detecting abnormality of internet of things oriented mobile terminal device, it is characterised in that: including as follows
Step:
Step 1, the track data sequence G=being sequentially arranged is obtained from each application program of mobile terminal device
(g1,g2,…,gn), wherein tracing point gi=(xi,yi,ti,pi) (0 < i≤n), xiIt is longitude coordinate, yiIt is latitude coordinate, ti
It is timestamp, piIt is the attribute of application program, including social, payment, navigation etc.；
Step 2, the quantity k=0 of track, the sum of longitude coordinate of track Sumx=0, the sum of latitude coordinate Sumy=0, it stays
Stationary point sequence S=(s1, s2..., sm), wherein dwell pointi
With j for identifying tracing point, a is for identifying dwell point, i.e., from first dwell point s1Start,
Step 3, judge whether track point identification i is less than or equal to n, if it is not, step 6 is then jumped to, if so, continuing to hold
Row, if giWith gjMeet condition:
Wherein WtIt is the residence time threshold value and W of settingdIt is the capacity-threshold of setting, then continues to execute, otherwise jump to step
Rapid 5；
Step 4, the data of current tracing point are added, Sumx=Sumx+xi, Sumy=Sumy+yi, k=k+1, i=j,
J=i+1 jumps to step 3；
Step 5, point s is obtaineda:
Wherein, k=0, i=j, j=i+1, Sumx=0, Sumy=0, a=a+1,Jump to step 3；
Step 6, CkIndicate the cluster result after kth time merges, CikIndicate the i-th class partitioned set when kth time merges, then
Cluster result is expressed as Ck={ C1k,C2k,…,Crk, wherein r is cluster numbers, enables k=0, each point constitutes a class by itself, i.e. C0=
{si(i=1,2 ..., m)={ C10,C20,…,Cm0, calculate the average distance d between each partitioned setij, generate distance set
Dk={ dij| 0≤i≤j < k }；
Step 7, in distance set DkIt is middle to find the smallest value dij, i is merged with j two, k=k+l, r=r-1,
Generate new cluster result Ck, the partitioned set after merging is calculated at a distance from other partitioned sets according to the formula in step 6,
Generate new distance set Dk；
Step 8, judge whether r is less than the cluster numbers W of the progress outlier detection of settingN, if so, continue to execute, if
It is not to jump to step 7；
Step 9, cluster result C is takenkIn each partitioned set element number Li=1 set obtains element therein, as
Abnormal point is added in abnormal point set R；
Step 10, judge whether r is equal to 1, if so, end loop, output abnormality point set R, if not then jumping to step
Rapid 7.
Further, in the step 6, the average distance d between each partitioned set is calculatedijFormula it is as follows:
WhereinxpAnd ypIt is partitioned set CikThe latitude and longitude coordinates at midpoint, LiIt is CikIn
The number of element.
One aspect of the present invention solves the problems such as data volume extracted from the device is big and complicated, on the other hand can accelerate to use
The speed of family track outlier detection.
Detailed description of the invention
Fig. 1 is that the process of the user trajectory method for detecting abnormality of internet of things oriented mobile terminal device of the present invention is shown
It is intended to.
Specific embodiment
Technical solution of the present invention is described in further detail with reference to the accompanying drawings of the specification.
A kind of user trajectory method for detecting abnormality of internet of things oriented mobile terminal device, includes the following steps:
Step 1, the track data sequence G=being sequentially arranged is obtained from each application program of mobile terminal device
(g1,g2,…,gn), wherein tracing point gi=(xi,yi,ti,pi) (0 < i≤n), xiIt is longitude coordinate, yiIt is latitude coordinate, ti
It is timestamp, piIt is the attribute of application program, including social, payment, navigation etc..
Step 2, the quantity k=0 of track, the sum of longitude coordinate of track Sumx=0, the sum of latitude coordinate Sumy=0, it stays
Stationary point sequence S=(s1, s2..., sm), wherein dwell pointi
With j for identifying tracing point, a is for identifying dwell point, i.e., from first dwell point s1Start,
Step 3, judge whether track point identification i is less than or equal to n, if it is not, step 6 is then jumped to, if so, continuing to hold
Row, if giWith gjMeet condition:
Wherein WtIt is the residence time threshold value and W of settingdIt is the capacity-threshold of setting, then continues to execute, otherwise jump to step
Rapid 5.
Step 4, the data of current tracing point are added, Sumx=Sumx+xi, Sumy=Sumy+yi, k=k+1, i=j,
J=i+1 jumps to step 3.
Step 5, point s is obtaineda:
Wherein, k=0, i=j, j=i+1, Sumx=0, Sumy=0, a=a+1,Jump to step 3.
Step 6, CkIndicate the cluster result after kth time merges, CikIndicate the i-th class partitioned set when kth time merges, then
Cluster result is expressed as Ck={ C1k,C2k,…,Crk, wherein r is cluster numbers, enables k=0, each point constitutes a class by itself, i.e. C0=
{si(i=1,2 ..., m)={ C10,C20,…,Cm0, calculate the average distance d between each partitioned setij:
WhereinxpAnd ypIt is partitioned set CikThe latitude and longitude coordinates at midpoint, LiIt is CikIn
The number of element generates distance set Dk={ dij| 0≤i≤j < k }.
Step 7, in distance set DkIt is middle to find the smallest value dij, i is merged with j two, k=k+l, r=r-1,
Generate new cluster result Ck, the partitioned set after merging is calculated at a distance from other partitioned sets according to the formula in step 6,
Generate new distance set Dk。
Step 8, judge whether r is less than the cluster numbers W of the progress outlier detection of settingN, if so, continue to execute, if
It is not to jump to step 7.
Step 9, cluster result C is takenkIn each partitioned set element number Li=1 set obtains element therein, as
Abnormal point is added in abnormal point set R.
Step 10, judge whether r is equal to 1, if so, end loop, output abnormality point set R, if not then jumping to step
Rapid 7.
The foregoing is merely better embodiment of the invention, protection scope of the present invention is not with above embodiment
Limit, as long as those of ordinary skill in the art's equivalent modification or variation made by disclosure according to the present invention, should all be included in power
In the protection scope recorded in sharp claim.
Claims (2)
1. a kind of user trajectory method for detecting abnormality of internet of things oriented mobile terminal device, it is characterised in that: including walking as follows
It is rapid:
Step 1, the track data sequence G=(g being sequentially arranged is obtained from each application program of mobile terminal device1,
g2,…,gn), wherein tracing point gi=(xi,yi,ti,pi) (0 < i≤n), xiIt is longitude coordinate, yiIt is latitude coordinate, tiWhen being
Between stab, piIt is the attribute of application program, including social, payment, navigation etc.；
Step 2, the quantity k=0 of track, the sum of longitude coordinate of track Sumx=0, the sum of latitude coordinate Sumy=0, dwell point
Sequence S=(s1, s2..., sm), wherein dwell pointI=1, j=i+1, a
=1, i and j are for identifying tracing point, and a is for identifying dwell point, i.e., from first dwell point s1Start,
Step 3, judge whether track point identification i is less than or equal to n, if it is not, step 6 is then jumped to, if so, continue to execute,
If giWith gjMeet condition:
Wherein WtIt is the residence time threshold value and W of settingdIt is the capacity-threshold of setting, then continues to execute, otherwise jump to step 5；
Step 4, the data of current tracing point are added, Sumx=Sumx+xi, Sumy=Sumy+yi, k=k+1, i=j, j=i
+ 1, jump to step 3；
Step 5, point s is obtaineda:
,
Enable k=0, i=j, j=i+1, Sumx=0, Sumy=0, a=a+1,Jump to step 3；
Step 6, CkIndicate the cluster result after kth time merges, CikIt indicates the i-th class partitioned set when kth time merges, then clusters
As a result it is expressed as Ck={ C1k,C2k,…,Crk, wherein r is cluster numbers, enables k=0, each point constitutes a class by itself, i.e. C0={ si}(i
=1,2 ..., m)={ C10,C20,…,Cm0, calculate the average distance d between each partitioned setij, generate distance set Dk=
{dij| 0≤i≤j < k }；
Step 7, in distance set DkIt is middle to find the smallest value dij, i is merged, k=k+l, r=r-1 with j two, is generated
New cluster result Ck, the partitioned set after merging is calculated at a distance from other partitioned sets according to the formula in step 6, is generated
New distance set Dk；
Step 8, judge whether r is less than the cluster numbers W of the progress outlier detection of settingN, if so, continuing to execute, if not then
Jump to step 7；
Step 9, cluster result C is takenkIn each partitioned set element number Li=1 set obtains element therein, as extremely
Point is added in abnormal point set R；
Step 10, judge whether r is equal to 1, if so, end loop, output abnormality point set R, if not then jumping to step 7.
2. a kind of user trajectory method for detecting abnormality of internet of things oriented mobile terminal device according to claim 1,
It is characterized in that: in the step 6, calculating the average distance d between each partitioned setijFormula it is as follows:
WhereinxpAnd ypIt is partitioned set CikThe latitude and longitude coordinates at midpoint, LiIt is CikMiddle element
Number.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910094909.0A CN109784422B (en) | 2019-01-31 | 2019-01-31 | User track abnormity detection method for mobile terminal equipment of Internet of things |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910094909.0A CN109784422B (en) | 2019-01-31 | 2019-01-31 | User track abnormity detection method for mobile terminal equipment of Internet of things |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN109784422A true CN109784422A (en) | 2019-05-21 |
| CN109784422B CN109784422B (en) | 2022-07-22 |
Family
ID=66503752
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201910094909.0A Active CN109784422B (en) | 2019-01-31 | 2019-01-31 | User track abnormity detection method for mobile terminal equipment of Internet of things |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN109784422B (en) |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110503032A (en) * | 2019-08-21 | 2019-11-26 | 中南大学 | Individual important place detection method based on monitoring camera track data |
| CN116911511A (en) * | 2023-09-14 | 2023-10-20 | 中建三局信息科技有限公司 | Commercial concrete transportation vehicle real-time management method, device, equipment and storage medium |
Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20090143079A1 (en) * | 2007-12-04 | 2009-06-04 | Research In Motion Limited | Mobile tracking |
| CN106878951A (en) * | 2017-02-28 | 2017-06-20 | 上海讯飞瑞元信息技术有限公司 | User trajectory analysis method and system |
| CN108931795A (en) * | 2018-05-21 | 2018-12-04 | 千寻位置网络有限公司 | Positioning equipment track optimization and boundary extraction method and device |
-
2019
- 2019-01-31 CN CN201910094909.0A patent/CN109784422B/en active Active
Patent Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20090143079A1 (en) * | 2007-12-04 | 2009-06-04 | Research In Motion Limited | Mobile tracking |
| CN106878951A (en) * | 2017-02-28 | 2017-06-20 | 上海讯飞瑞元信息技术有限公司 | User trajectory analysis method and system |
| CN108931795A (en) * | 2018-05-21 | 2018-12-04 | 千寻位置网络有限公司 | Positioning equipment track optimization and boundary extraction method and device |
Non-Patent Citations (1)
| Title |
|---|
| 周湛: "概率后缀树在移动用户轨迹异常检测中的应用", 《移动通信》 * |
Cited By (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110503032A (en) * | 2019-08-21 | 2019-11-26 | 中南大学 | Individual important place detection method based on monitoring camera track data |
| CN110503032B (en) * | 2019-08-21 | 2021-08-31 | 中南大学 | Individual important place detection method based on track data of monitoring camera |
| CN116911511A (en) * | 2023-09-14 | 2023-10-20 | 中建三局信息科技有限公司 | Commercial concrete transportation vehicle real-time management method, device, equipment and storage medium |
| CN116911511B (en) * | 2023-09-14 | 2023-12-12 | 中建三局信息科技有限公司 | Commercial concrete transportation vehicle real-time management method, device, equipment and storage medium |
Also Published As
| Publication number | Publication date |
|---|---|
| CN109784422B (en) | 2022-07-22 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN104050196B (en) | A kind of interest point data redundant detecting method and device | |
| Jurgens et al. | Geolocation prediction in twitter using social networks: A critical analysis and review of current practice | |
| US9256689B2 (en) | Mining trajectory for spatial temporal analytics | |
| CN104809377B (en) | Network user identity monitoring method based on webpage input behavior feature | |
| CN107590250A (en) | A kind of space-time orbit generation method and device | |
| CN103399896B (en) | The method and system of incidence relation between identification user | |
| CN104915351A (en) | Picture sorting method and terminal | |
| Yin et al. | Feature-based map matching for low-sampling-rate GPS trajectories | |
| CN110472154A (en) | A kind of resource supplying method, apparatus, electronic equipment and readable storage medium storing program for executing | |
| CN111695019B (en) | Method and device for identifying associated account | |
| Wirz et al. | Towards an online detection of pedestrian flocks in urban canyons by smoothed spatio-temporal clustering of GPS trajectories | |
| CN106649663A (en) | Video copy detection method based on compact video representation | |
| CN103491625B (en) | A kind of localization method and system of mobile radio terminal | |
| Guo et al. | Transportation mode recognition with deep forest based on GPS data | |
| CN109784422A (en) | A kind of user trajectory method for detecting abnormality of internet of things oriented mobile terminal device | |
| Wen et al. | RouteMiner: Mining ship routes from a massive maritime trajectories | |
| JP2012003322A (en) | Group behavior estimation method and program thereof | |
| CN106446102A (en) | Method and device for terminal positioning based on map fences | |
| Wang et al. | Mining personal frequent routes via road corner detection | |
| CN105119743A (en) | Acquisition method of user behavior intention and apparatus | |
| Ding et al. | Anomaly detection in large-scale trajectories using hybrid grid-based hierarchical clustering | |
| Balzano et al. | Setra: A smart framework for gps trajectories' segmentation | |
| CN105488413A (en) | Malicious code detection method and system based on information gain | |
| Meng et al. | Towards the inference of travel purpose with heterogeneous urban data | |
| CN109885475B (en) | Page conversion rate calculation method, device, computer equipment and storage medium |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |