CN108920555A - A kind of auxiliary information based on the associated similar personnel's population analysis method of LTE mobile network's big data - Google Patents
A kind of auxiliary information based on the associated similar personnel's population analysis method of LTE mobile network's big data Download PDFInfo
- Publication number
- CN108920555A CN108920555A CN201810633384.9A CN201810633384A CN108920555A CN 108920555 A CN108920555 A CN 108920555A CN 201810633384 A CN201810633384 A CN 201810633384A CN 108920555 A CN108920555 A CN 108920555A
- Authority
- CN
- China
- Prior art keywords
- user
- similarity
- big data
- mobile network
- time
- 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.)
- Pending
Links
Classifications
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04W—WIRELESS COMMUNICATION NETWORKS
- H04W4/00—Services specially adapted for wireless communication networks; Facilities therefor
- H04W4/02—Services making use of location information
- H04W4/029—Location-based management or tracking services
Landscapes
- Engineering & Computer Science (AREA)
- Computer Networks & Wireless Communication (AREA)
- Signal Processing (AREA)
- Information Retrieval, Db Structures And Fs Structures Therefor (AREA)
Abstract
The invention belongs to the mobile big data security application fields LTE, more particularly to a kind of auxiliary information based on the associated similar personnel's population analysis method of LTE mobile network's big data, based on user's big data based on operator mobile network, obtain known concern user information, according to concern user and time of other users and geographical similarity, it analyzes and finds the unknown other users for having similar behavior and relationship, the available other staff not being noted and other location informations.The present invention can excavate potential abnormal personal or group in advance, and carry out potential crime to the personal behavior or group behavior and analyze and identify.
Description
Technical field
The invention belongs to the mobile big data security application fields LTE, more particularly to a kind of the mobile based on LTE of auxiliary information
The associated similar personnel's population analysis method of network big data.
Background technique
Public safety technical field is always by the attention of government, big data especially in recent years, artificial intelligence technology
It emerges, provides more choices of technology and successful case, it is increasingly heavier in China, the U.S., the country variants such as Europe and area
Depending on because of its high efficiency, saving cost, data resource multiplicity, the raising of information technology becomes the following public safety technical field
Development trend.Compare typically, the U.S. is with NSA（U.S.National Security Agency）Skynet system passes through shifting as tool is represented
Personal information is collected by dynamic operator, uses multiple with personal related information dimensions, is excavated using random forests algorithm
Potential dangerous person, and put into practice, NSA is protected national security, is mentioned by the personal information of acquisition mobile operator
The public safety in the U.S. Gao Liao, this method become the standard configuration of following public safety, although NSA endures blame even part to the fullest extent
Member of Parliament's is discontented, but with regard to national security itself with from the point of view of public safety technology, their method and thinking, very
It is worthy of our study and uses for reference.
In recent years, Chinese public safety technology was further added by means of big data technology and big data resource
By force, this respect application technology has had many research achievement and application effect, such as police service big data in China, throughout
More than 2,000 ten thousand of street and road can be with the camera etc. of recognition of face, and the public peace of society undoubtedly can be improved in these
Entirely, but technical aspect can not also excavate the similar individual not being absorbed in and group, and believe with their related geography
Breath, from the point of view of data resource and corresponding technical method, all seeming, comparison is passive, belongs to passive analysis and passive aid decision,
I.e. analysis has occurred and that and can not monitor and excavate with already existing part, the part without generation.
Summary of the invention
The purpose of the present invention is to provide a kind of auxiliary informations based on the associated similar personnel of LTE mobile network's big data
Population analysis method, the relationship between user behavior and user and user based on operator's big data are excavated potential personal
Abnormal and associated Anomaly groups are personal behavior and group behavior carries out potential crime analysis and identifies, in advance into
Row safety analysis and prediction.
To achieve the above object, design a kind of auxiliary information based on the associated similar personnel of LTE mobile network's big data
Population analysis method：Based on user's big data based on operator mobile network, known concern user information is obtained, according to
Pay close attention to user with time of other users and geographical similarity, analyze and find its unknown for having similar behavior and relationship
He is user, the available other staff not being noted and other location informations, and concrete analysis algorithm is as follows：
The first step：Input concern information S1；
Second step：Analyze the spatio-temporal experience of S1；
Third step：Analyze the target A1 of the spatio-temporal similarity within the scope of certain of S1；
4th step：If similarity meets certain condition, target A1 becomes perpetual object；
5th step：S1 and A1 is analyzed and searched for using identical technical method, target B1 is obtained；
6th step：Similarity score is carried out with time and location relationship for all concern targets；
7th step：Extract similarity high period and geographic area；
8th step：Count the other users individual amount of the period geographic area；
9th step：If this region records this region there is no the other users of { S1, A1, B1 } individual；
Tenth step：Counting in the region residence time is more than the user C1 of specified time length；
11st step：Time and the geography track for recording C1, calculate and the time of S1 and geographical similarity.
The concrete application of the analysis method is as follows：
The first step：New user S2 is inputted, using the algorithm above, finds C2；
Second step：New user SN is inputted, using the algorithm above, finds CN；
Third step：According to sequencing of similarity, before ranking 10 user is obtained, be added and updates S set；
4th step：Obtain new concern user set.
The spatio-temporal experience of the S1 includes：Time experience is time set { t1, t2, t3, t4 ... ..., tn }, empty
Between experience be location sets { d1, d2, d3, d4 ... ..., dn }, time set and location sets be it is related, when one
User has corresponding temporal information when passing through certain place.
The target A1 of the analysis similarity, similarity is numeric results, between 0%-100%, needs that phase is manually specified
Like degree range, such as 80%；The similarity judges that the sequence i.e. temporal information for being related to two dimensions and location information, use are general
The calculating formula of similarity of logical two-dimensions.
Beneficial effect of the present invention is embodied in：
1. user's MR data of the LTE based on Domestic Carriers；
2. the inventive technique no longer limits to the behavior point of someone by the space time correlation degree between the individual inside analysis group
Analysis, and the spatio-temporal behavior relation being to provide between personal and group is excavated；
3. the inventive technique can carry out space time correlation search and relational extensions in carrier data relationship, to find more
The group not being concerned and potential individual.
Specific embodiment
The present invention will be further explained below with reference to examples, and the principle of this technology is very for the people of this profession
Clearly, it should be understood that described herein specific examples are only used to explain the present invention, is not intended to limit the present invention.
A kind of auxiliary information based on the associated similar personnel's population analysis method of LTE mobile network's big data：Based on fortune
Based on user's big data of battalion quotient mobile network, known concern user information is obtained, according to using with other for concern user
The time at family and geographical similarity, analyze and find the unknown other users for having similar behavior and relationship, available not have
There are the other staff being noted and other location informations, concrete analysis algorithm is as follows：
The first step：Input concern information S1；
Second step：Analyze the spatio-temporal experience of S1；
Third step：Analyze the target A1 of the spatio-temporal similarity within the scope of certain of S1；
4th step：If similarity meets certain condition, target A1 becomes perpetual object；
5th step：S1 and A1 is analyzed and searched for using identical technical method, target B1 is obtained；
6th step：Similarity score is carried out with time and location relationship for all concern targets；
7th step：Extract similarity high period and geographic area；
8th step：Count the other users individual amount of the period geographic area；
9th step：If this region records this region there is no the other users of { S1, A1, B1 } individual；
Tenth step：Counting in the region residence time is more than the user C1 of specified time length；
11st step：Time and the geography track for recording C1, calculate and the time of S1 and geographical similarity.
The concrete application of the analysis method is as follows：
The first step：New user S2 is inputted, using the algorithm above, finds C2；
Second step：New user SN is inputted, using the algorithm above, finds CN；
Third step：According to sequencing of similarity, before ranking 10 user is obtained, be added and updates S set；
4th step：Obtain new concern user set.
Embodiment：
1. the time and space of certain S1 experience is： { 9:00 No. 16 line Long Yanglu subway stations；9:10 No. 2 line Jin Kelu subway stations
； 9:20 Zhangjiang software centre, 14 building 417 }；
2. the time and space of certain A1 target experience is： { 9:00 No. 16 line Long Yanglu subway stations；9:10 No. 2 line Jin Kelu
Iron station； 9:20 Zhangjiang software centre, 14 building 417 }；
3. the time and space of certain A2 target experience is： { 9:00 No. 16 Long Yanglu subway stations；9:10 No. 2 line Jin Kelu subways
It stands； 9:20 Zhangjiang software centre, 22 building 310 }；
Wherein, the similarity that the similarity of A1 and S1 is 100%, A2 and S1 is 66%.
Claims (2)
1. a kind of auxiliary information based on the associated similar personnel's population analysis method of LTE mobile network's big data, feature exists
In：Based on user's big data based on operator mobile network, obtain it is known pay close attention to user information, according to concern user with
Time of other users and geographical similarity, analyze and find the unknown other users for having similar behavior and relationship, can be with
The other staff not being noted and other location informations, concrete analysis algorithm are as follows：
The first step：Input concern information S1；
Second step：Analyze the spatio-temporal experience of S1；
Third step：Analyze the target A1 of the spatio-temporal similarity within the scope of certain of S1；
4th step：If similarity meets certain condition, target A1 becomes perpetual object；
5th step：S1 and A1 is analyzed and searched for using identical technical method, target B1 is obtained；
6th step：Similarity score is carried out with time and location relationship for all concern targets；
7th step：Extract similarity high period and geographic area；
8th step：Count the other users individual amount of the period geographic area；
9th step：If this region records this region there is no the other users of { S1, A1, B1 } individual；
Tenth step：Counting in the region residence time is more than the user C1 of specified time length；
11st step：Time and the geography track for recording C1, calculate and the time of S1 and geographical similarity.
2. a kind of auxiliary information as described in claim 1 based on the associated similar personnel group of LTE mobile network's big data
Analysis method, it is characterised in that the concrete application of the analysis method is as follows：
The first step：New user S2 is inputted, using the algorithm above, finds C2；
Second step：New user SN is inputted, using the algorithm above, finds CN；
Third step：According to sequencing of similarity, before ranking 10 user is obtained, be added and updates S set；
4th step：Obtain new concern user set.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201810633384.9A CN108920555A (en) | 2018-06-20 | 2018-06-20 | A kind of auxiliary information based on the associated similar personnel's population analysis method of LTE mobile network's big data |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201810633384.9A CN108920555A (en) | 2018-06-20 | 2018-06-20 | A kind of auxiliary information based on the associated similar personnel's population analysis method of LTE mobile network's big data |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN108920555A true CN108920555A (en) | 2018-11-30 |
Family
ID=64422024
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201810633384.9A Pending CN108920555A (en) | 2018-06-20 | 2018-06-20 | A kind of auxiliary information based on the associated similar personnel's population analysis method of LTE mobile network's big data |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN108920555A (en) |
Cited By (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN109710712A (en) * | 2018-12-17 | 2019-05-03 | 中国人民公安大学 | A kind of crime hot spot feature method for digging and system based on case factor analysis |
| CN109828967A (en) * | 2018-12-03 | 2019-05-31 | 深圳市北斗智能科技有限公司 | A kind of accompanying relationship acquisition methods, system, equipment, storage medium |
| CN111460246A (en) * | 2019-12-19 | 2020-07-28 | 南京柏跃软件有限公司 | Real-time activity abnormal person discovery method based on data mining and density detection |
Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103593361A (en) * | 2012-08-14 | 2014-02-19 | 中国科学院沈阳自动化研究所 | Movement space-time trajectory analysis method in sense network environment |
| CN104765808A (en) * | 2015-04-02 | 2015-07-08 | 广州杰赛科技股份有限公司 | Method and system for mining group trace |
| CN105205155A (en) * | 2015-09-25 | 2015-12-30 | 珠海世纪鼎利科技股份有限公司 | Big data criminal accomplice screening system and method |
| CN106203458A (en) * | 2015-04-29 | 2016-12-07 | 杭州海康威视数字技术股份有限公司 | Crowd's video analysis method and system |
| CN106951903A (en) * | 2016-10-31 | 2017-07-14 | 浙江大学 | A kind of method for visualizing of crowd's movement law |
-
2018
- 2018-06-20 CN CN201810633384.9A patent/CN108920555A/en active Pending
Patent Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103593361A (en) * | 2012-08-14 | 2014-02-19 | 中国科学院沈阳自动化研究所 | Movement space-time trajectory analysis method in sense network environment |
| CN104765808A (en) * | 2015-04-02 | 2015-07-08 | 广州杰赛科技股份有限公司 | Method and system for mining group trace |
| CN106203458A (en) * | 2015-04-29 | 2016-12-07 | 杭州海康威视数字技术股份有限公司 | Crowd's video analysis method and system |
| CN105205155A (en) * | 2015-09-25 | 2015-12-30 | 珠海世纪鼎利科技股份有限公司 | Big data criminal accomplice screening system and method |
| CN106951903A (en) * | 2016-10-31 | 2017-07-14 | 浙江大学 | A kind of method for visualizing of crowd's movement law |
Cited By (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN109828967A (en) * | 2018-12-03 | 2019-05-31 | 深圳市北斗智能科技有限公司 | A kind of accompanying relationship acquisition methods, system, equipment, storage medium |
| CN109828967B (en) * | 2018-12-03 | 2021-10-19 | 深圳市北斗智能科技有限公司 | Companion relationship acquisition method, system, equipment and storage medium |
| CN109710712A (en) * | 2018-12-17 | 2019-05-03 | 中国人民公安大学 | A kind of crime hot spot feature method for digging and system based on case factor analysis |
| CN111460246A (en) * | 2019-12-19 | 2020-07-28 | 南京柏跃软件有限公司 | Real-time activity abnormal person discovery method based on data mining and density detection |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| Zhang et al. | Do different datasets tell the same story about urban mobility—A comparative study of public transit and taxi usage | |
| CN108920555A (en) | A kind of auxiliary information based on the associated similar personnel's population analysis method of LTE mobile network's big data | |
| Maccari et al. | Do we need a contact tracing app? | |
| Zang et al. | Anonymization of location data does not work: A large-scale measurement study | |
| CN105574506A (en) | Intelligent face tracking system and method based on depth learning and large-scale clustering | |
| CN105760780B (en) | Track data method for secret protection based on road network | |
| WO2016141641A1 (en) | Method and device for recognizing suspicious person | |
| CN107480626A (en) | A kind of method that census using recognition of face monitors | |
| CN108171842A (en) | A kind of personnel management system | |
| Chen | Community and policing strategies: A Chinese approach to crime control | |
| CN103366566A (en) | Running track prediction method aiming at specific vehicle potential group | |
| CN111353173B (en) | Sensitive tag track data publishing method using graph difference privacy model | |
| CN109859426A (en) | A kind of community security protection management system | |
| CN115169814A (en) | Characterization measurement method for urban public service disaster toughness | |
| Xu et al. | The impact of community residents’ occupational structure on the spatial distribution of different types of crimes | |
| Liu et al. | How to prevent and control community risks? Identifying community burglary risk hotspots based on time-space characteristics | |
| Meng et al. | Understanding dockless bike-sharing spatiotemporal travel patterns: Evidence from ten cities in China | |
| CN201765619U (en) | Stranger portrait early warning system based on portrait biometric identification technology | |
| Katranji et al. | Mobility data disaggregation: A transfer learning approach | |
| CN112689130A (en) | Intelligent community security alarm system and method based on big data | |
| Ruihong et al. | Assisting Telecommunication Fraud Prediction: Detect Individuals Carrying Multiple Phones Based on Trajectory Data Mining | |
| Gao et al. | Big Data assisted Strategy for Resuming of Work and Production during COVID-19 | |
| Fang et al. | Identify individuals behaviors based GPS trajectories in the Internet of Things | |
| Yang et al. | User Matching Algorithm Based on Repeated Transfer Behavior | |
| Xie et al. | Pattern mining, semantic label identification and movement prediction using mobile phone data |
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 | ||
| WD01 | Invention patent application deemed withdrawn after publication | ||
| WD01 | Invention patent application deemed withdrawn after publication |
Application publication date: 20181130 |