CN108536851A - A kind of method for identifying ID based on motion track similarity-rough set - Google Patents
A kind of method for identifying ID based on motion track similarity-rough set Download PDFInfo
- Publication number
- CN108536851A CN108536851A CN201810339338.8A CN201810339338A CN108536851A CN 108536851 A CN108536851 A CN 108536851A CN 201810339338 A CN201810339338 A CN 201810339338A CN 108536851 A CN108536851 A CN 108536851A
- Authority
- CN
- China
- Prior art keywords
- region
- similarity
- track
- tracks
- probability
- 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
- 238000000034 method Methods 0.000 title claims abstract description 29
- 239000000203 mixture Substances 0.000 claims description 4
- 239000013598 vector Substances 0.000 abstract description 9
- 238000004364 calculation method Methods 0.000 abstract description 3
- 238000013507 mapping Methods 0.000 abstract 1
- 239000011159 matrix material Substances 0.000 description 3
- 238000013461 design Methods 0.000 description 2
- 235000013399 edible fruits Nutrition 0.000 description 2
- 230000010267 cellular communication Effects 0.000 description 1
- 230000001413 cellular effect Effects 0.000 description 1
- 238000004891 communication Methods 0.000 description 1
- 238000007405 data analysis Methods 0.000 description 1
- 238000013480 data collection Methods 0.000 description 1
- 230000000694 effects Effects 0.000 description 1
- 238000005516 engineering process Methods 0.000 description 1
- 238000002474 experimental method Methods 0.000 description 1
- 238000005259 measurement Methods 0.000 description 1
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/22—Matching criteria, e.g. proximity measures
-
- 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
- G06Q50/00—Information and communication technology [ICT] specially adapted for implementation of business processes of specific business sectors, e.g. utilities or tourism
- G06Q50/10—Services
- G06Q50/26—Government or public services
-
- 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)
- Business, Economics & Management (AREA)
- Theoretical Computer Science (AREA)
- Physics & Mathematics (AREA)
- Data Mining & Analysis (AREA)
- Tourism & Hospitality (AREA)
- General Physics & Mathematics (AREA)
- Signal Processing (AREA)
- Life Sciences & Earth Sciences (AREA)
- Evolutionary Biology (AREA)
- General Engineering & Computer Science (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Bioinformatics & Computational Biology (AREA)
- Computer Networks & Wireless Communication (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Artificial Intelligence (AREA)
- Development Economics (AREA)
- Educational Administration (AREA)
- Evolutionary Computation (AREA)
- Health & Medical Sciences (AREA)
- Economics (AREA)
- General Health & Medical Sciences (AREA)
- Human Resources & Organizations (AREA)
- Marketing (AREA)
- Primary Health Care (AREA)
- Strategic Management (AREA)
- General Business, Economics & Management (AREA)
- Navigation (AREA)
- Information Retrieval, Db Structures And Fs Structures Therefor (AREA)
Abstract
The invention discloses a kind of method for identifying ID based on motion track similarity-rough set, and city is divided into the frequency occurred in each grid through, latitude network, statistics track first, by count out be more than threshold value Vp mesh mapping to a set；Then the similarity for two tracks matched is calculated；One candidate thresholds Vr is finally set, i.e., forms a Candidate Set with the Top N sequences that region quantity is more than Vr, matching and the most like track Top N sequences in object to be identified track in the track Top N sequence sets pre-saved.Compared with traditional method for directly calculating frequency distribution vector, due to more frequently occurring the regular stronger of region, calculation amount is significantly reduced not sacrificing the while of identifying accurate.
Description
Technical field
The invention belongs to data analysis technique fields, are related to a kind of method of user identity identification, and in particular to Yi Zhongji
In the personal identification method of motion track measuring similarity.
Technical background
Location-based service including GPS, cellular communications networks base station location has become one of people's daily life
Point.Based on the multi-sources mobile trajectory data collection such as mobile phone, network, vehicle mounted guidance, using track similarity to a variety of of suspicion object
Trace information carries out identities match, and whereabouts and mechanics, the understanding of a bad actor are grasped using personal multi-source trace information
Identity is to contain that criminal offence is the new opportunities of social safety Control Technology system.
China mobile number of users reaches hundred meter levels close to 1,300,000,000 people, the cellular base station positioning accuracy of urban area, and GPS is fixed
Position precision is even more to reach meter level, and China has begun to carry out mobile phone identification policy for 2015.Theoretically, fixed by operator base station
Position, almost everyone space operation can be grasped.Corresponding to the same physical identity in multiple virtual identities, (such as one right
Situation as using multiple phone numbers) this kind of identity identification task in, since true physical object is unique, although
Used different meanss of communication and be judged to multiple virtual identities, but rotation use mobile phone when physical object activity occasion
Big variation will not generally occur.At this point, can differentiate multiple mobile phones (or hand by spatial movement action trail similarity measurement
Machine number) it is the same holder.Therefore, the spatial behavior mechanics of object is a kind of important identity identification information.
The method directed quantity model and Hash model for calculating track similitude, it is similar that there are commonly cosine in vector model
Degree, the similarity based on trajectory distance；There are MinHash and SimHash based on Jaccard coefficients in Hash model.It grinds part
The person of studying carefully proposes some identification algorithms based on motion track based on both models, is known in early days with Bayes' theorem
Not, many experiments show that this method is not suitable for asynchronous information scene.Zhang Hongji et al. proposes the hot spot for asynchronous information
Matrix algorithm, this method directly use cosine similarity, i.e., sparse hot spot matrix are directly changed into one-dimensional vector, different
70% identification accuracy can be reached in step scene, but due to the extreme sparsity of hot spot matrix, the meter for causing this method to identify
Calculation amount is quite big.Wei Cao et al. propose the personal identification method of one kind of multiple data sources, similar using two kinds of SIG and WJS
Property method collaboration identification, SIG not only considers observation signal, it is also contemplated that the relevance between position occurs in stimulus signal, such as public
It takes charge of and closes on subway station there are a relationship, WJS is similar to Jaccard coefficients.The method identification accuracy is very high, but calculation amount
It is huge.
Invention content
In order to solve the above technical problem, the present invention provides a kind of method for identifying ID based on motion track,
This method uses the distributed areas Top-N cosine similarity and the distributed areas Top-N probability of occurrence mean square deviation similarity.Knowing simultaneously
When other, minimum threshold Vr is set, i.e., the quantity in the region that database track occurred jointly with target trajectory to be identified filters out
Candidate tracks collection ensures its identification accuracy while reducing calculating consumption.
The technical solution adopted in the present invention is：A kind of user identity identification side based on motion track similarity-rough set
Method, which is characterized in that include the following steps：
Step 1：By the rectangular area that city is considered as a highest warp, latitude is surrounded with minimum warp, latitude, and with scheduled
Urban area is divided through, latitude step-length, obtains M × K longitude and latitude networks；
Step 2：Counting user tracing point is denoted as a frequency in the frequency of each small grid area distribution；
Step 3：It is more than the small grid area maps of threshold value Vp to a grid set by frequency；
Step 4：The net region for finding out N before the frequency of grid set midpoint, obtains track and is frequently distributed the regions Top-N collection
It closes, set element form is a tuple (coordinate puts frequency)；
Step 5：It is frequently distributed Top-N regional ensemble A, B by two of two tracks, is matched two-by-two by minimum distance
It is right；
Step 6：Calculate the similarity for two tracks matched；
Step 7：It seeks the frequent distribution Top-N regional ensembles of all user trajectories in advance by step 1- steps 4, stores
To database；
Step 8：When target to be identified occurs, ergodic data library solves similarity, and most like matching track is tied as identification
Fruit.
The present invention has the advantages that：
1) present invention can not only be based on motion track and carry out identification to user, moreover it is possible to by comparing track similarity reality
The lookup of existing similar users；
2) present invention can ensure its identification accuracy while reducing calculating consumption.
Description of the drawings
The flow chart of Fig. 1 embodiment of the present invention.
Specific implementation mode
Understand for the ease of those of ordinary skill in the art and implement the present invention, with reference to the accompanying drawings and embodiments to this hair
It is bright to be described in further detail, it should be understood that implementation example described herein is merely to illustrate and explain the present invention, not
For limiting the present invention.
See Fig. 1, a kind of personal identification method based on motion track similarity system design provided by the invention, including following step
Suddenly：
Step 1：By the rectangular area that city is considered as a highest warp, latitude is surrounded with minimum warp, latitude, and with scheduled
Urban area is divided through, latitude step-length, obtains M × K longitude and latitude networks；
Step 2：Counting user tracing point is denoted as a frequency in the frequency of each small grid area distribution；
Step 3：It is more than the small grid area maps of threshold value Vp to a grid set by frequency；
Step 4：The net region for finding out N before the frequency of grid set midpoint, obtains track and is frequently distributed the regions Top-N collection
It closes, set element form is a tuple (coordinate puts frequency)；
It sorts from big to small by frequency to the element in grid set, chooses top n element, composition track is frequently distributed
Top-N regional ensembles.
Step 5：It is frequently distributed Top-N regional ensemble A, B by two of two tracks, is matched two-by-two by minimum distance
It is right；
For the either element in set A, the element with its Euclidean distance minimum is searched from set B, constitutes an area
Domain pair is formed until N number of element all in A all matches<A,B>Region is to set；Similarly, for any member in set B
Element, searched from set A with the element of its Euclidean distance minimum, one region pair of composition, until N number of element all in B all
Pairing is formed<B,A>Region is to set.
Step 6：Calculate the similarity for two tracks matched；
The present embodiment calculates the similarity for two tracks matched using following two methods；
Method 1：The similarity of two tracks is calculated using weighted cosine value；
Here the cosine value of cosine value and two one-dimensional vectors difference.When seeking the dot-product of two vectors, consider
The distance in non-same region, if distance is not zero, the weights for non-same region, this element vector should be small, and distance is fallen here
Number regards the weights of element vector as；When seeking vectorial mould, pairing vector field homoemorphism is not sought, but gathers vector field homoemorphism before asking pairing.
Furthermore define rule by two collection and pairing in step 5 looks for A to match there may be difference it is found that A looks for B to match with B,
Therefore consider here<A,B>With<B,A>Cosine value is matched, its mean value is taken to indicate its similarity.Specific calculate is given by following formula
Go out：
Wherein, N is the quantity in the track regions distribution Top-N,I-th of pairing region is indicated to the region element in A,Point frequency for track A in the region,Indicate the vectorial modular multiplication before the pairing of set A, B
Product.
Method 2：The similarity for two tracks matched is calculated, specific implementation includes following sub-step：
Step 6.1：Ask in step 5 in two Top-N regional ensembles A, B matched each region element in respective track
In probability of occurrence；
The probability for asking track to occur in each elemental areas respectively indicates it with the ratio of frequency and tracing point total number
Probability；
Step 6.2：Ask two tracks having matched in the probability variance of the respective probability of occurrence in same region；
The calculating of probability variance consider pairing region to the distance between, pairing region is adjusted the distance bigger, probability difference
Weights are also with big, here with weights that the natural logrithm of square distance is the pairing region pair.In addition, when distance is quite big
When, indicate that probability difference, i.e. two regions are completely uncorrelated with the mathematical expectation of probability of pairing region pair.Also due to<A,B>With<B,A>Match
To difference, take here<A,B>With<B,A>Probability mean variance is as A, B probability variance.Specific calculate is given by：
Wherein, N is the quantity in the track regions distribution Top-N,It is kth pairing region to region in set A, in track A
The probability of middle appearance；It is kth pairing region to the region in set A, VPA,BIndicate that region element finds pairing in B in A
It is required with region presence probability variance result afterwards.
Step 6.3：Seek the similarity of two tracks；
The similarity of two tracks is：
Wherein, H is the pairing quantity that distance is zero, and N is the quantity in the track regions distribution Top-N, VPABIndicate two tracks
The probability variance of respective probability of occurrence in same region.
Step 7：It seeks the frequent distribution Top-N regional ensembles of all user trajectories in advance by step 1- steps 4, stores
To database；
Step 8：When target to be identified occurs, ergodic data library solves similarity, and most like matching track is tied as identification
Fruit.
The present invention can be identified and similar use user identity by two kinds of simple track similarity system design methods
It searches at family.The present invention only examines rate track and is frequently distributed the regions Top-N, can ensure its identification while reducing calculating consumption
Accuracy.
It should be understood that the part that this specification does not elaborate belongs to the prior art.
It should be understood that the above-mentioned description for preferred embodiment is more detailed, can not therefore be considered to this
The limitation of invention patent protection range, those skilled in the art under the inspiration of the present invention, are not departing from power of the present invention
Profit requires under protected ambit, can also make replacement or deformation, each fall within protection scope of the present invention, this hair
It is bright range is claimed to be determined by the appended claims.
Claims (7)
1. a kind of method for identifying ID based on motion track similarity-rough set, which is characterized in that include the following steps：
Step 1：By the rectangular area that city is considered as highest warp, latitude is surrounded with minimum warp, latitude, and with scheduled warp,
Latitude step-length divides urban area, obtains M × K longitude and latitude networks；
Step 2：Counting user tracing point is denoted as a frequency in the frequency of each small grid area distribution；
Step 3：It is more than the small grid area maps of threshold value Vp to a grid set by frequency；
Step 4：The net region for finding out N before the frequency of grid set midpoint, obtains track and is frequently distributed Top-N regional ensembles, collects
It is a tuple to close element form (coordinate puts frequency)；
Step 5：It is frequently distributed Top-N regional ensemble A, B by two of two tracks, is matched two-by-two by minimum distance；
Step 6：Calculate the similarity for two tracks matched；
Step 7：Seek the frequent distribution Top-N regional ensembles of all user trajectories, storage to number in advance by step 1- steps 4
According to library；
Step 8：When target to be identified occurs, ergodic data library solves similarity, and most like matching track is as recognition result.
2. the method for identifying ID according to claim 1 based on motion track similarity-rough set, it is characterised in that：
Step 4, it sorts from big to small by frequency to the element in grid set, chooses top n element, composition track is frequently distributed
Top-N regional ensembles.
3. the method for identifying ID according to claim 1 based on motion track similarity-rough set, it is characterised in that：
In step 5, for the either element in set A, the element with its Euclidean distance minimum is searched from set B, constitutes an area
Domain pair is formed until N number of element all in A all matches<A,B>Region is to set；Similarly, for any member in set B
Element, searched from set A with the element of its Euclidean distance minimum, one region pair of composition, until N number of element all in B all
Pairing is formed<B,A>Region is to set.
4. the method for identifying ID according to claim 1 based on motion track similarity-rough set, which is characterized in that
The similarity of two tracks is calculated in step 6 using weighted cosine value：
Wherein, N is the quantity in the track regions distribution Top-N,I-th of pairing region is indicated to the region element in A,For
Track A the region point frequency,Indicate the vectorial modular multiplication product before the pairing of set A, B.
5. the method for identifying ID according to claim 1 based on motion track similarity-rough set, which is characterized in that
The similarity for two tracks matched is calculated described in step 6, specific implementation includes following sub-step：
Step 6.1：Ask in step 5 in two Top-N regional ensembles A, B matched each region element in respective track
Probability of occurrence；
Step 6.2：Ask two tracks having matched in the probability variance of the respective probability of occurrence in same region；
Step 6.3：Seek the similarity of two tracks.
6. the method for identifying ID according to claim 5 based on motion track similarity-rough set, which is characterized in that
In step 6.2 using pairing region to cum rights probability difference approach calculate two tracks the respective probability of occurrence in same region probability
Variance：
Wherein, N is the quantity in the track regions distribution Top-N,It is kth pairing region to region in set A, goes out in the A of track
Existing probability；It is kth pairing region to the region in set A, VPA,BIndicate that region element finds institute after pairing in B in A
It seeks common ground region presence probability variance result.
7. the method for identifying ID according to claim 5 based on motion track similarity-rough set, which is characterized in that
The similarity of two tracks is in step 6.3：
Wherein, H is the pairing quantity that distance is zero, and N is the quantity in the track regions distribution Top-N, VPABIndicate two tracks same
The probability variance of the respective probability of occurrence in region.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201810339338.8A CN108536851B (en) | 2018-04-16 | 2018-04-16 | User identity recognition method based on moving track similarity comparison |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201810339338.8A CN108536851B (en) | 2018-04-16 | 2018-04-16 | User identity recognition method based on moving track similarity comparison |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN108536851A true CN108536851A (en) | 2018-09-14 |
| CN108536851B CN108536851B (en) | 2021-04-16 |
Family
ID=63481270
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201810339338.8A Active CN108536851B (en) | 2018-04-16 | 2018-04-16 | User identity recognition method based on moving track similarity comparison |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN108536851B (en) |
Cited By (16)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN109947758A (en) * | 2019-04-03 | 2019-06-28 | 深圳市甲易科技有限公司 | A kind of route crash analysis method in Behavior-based control track library |
| CN109977109A (en) * | 2019-04-03 | 2019-07-05 | 深圳市甲易科技有限公司 | A kind of track data cleaning method and adjoint analysis method |
| CN110795705A (en) * | 2019-10-22 | 2020-02-14 | 武汉极意网络科技有限公司 | Track data processing method, device, equipment and storage medium |
| CN110958599A (en) * | 2018-09-26 | 2020-04-03 | 北京融信数联科技有限公司 | One-machine multi-card user distinguishing method based on track similarity |
| CN111125189A (en) * | 2019-12-12 | 2020-05-08 | 四川大学 | Track similarity measurement method based on weighted real number cost edit distance |
| CN111507732A (en) * | 2019-01-30 | 2020-08-07 | 北京嘀嘀无限科技发展有限公司 | System and method for identifying similar trajectories |
| CN111814914A (en) * | 2020-08-26 | 2020-10-23 | 珠海大横琴科技发展有限公司 | Target object identification method and device |
| CN111897910A (en) * | 2019-05-05 | 2020-11-06 | 北京京东尚科信息技术有限公司 | Information pushing method and device |
| CN112653995A (en) * | 2019-10-12 | 2021-04-13 | 中国移动通信有限公司研究院 | User identity recognition method and device and computer readable storage medium |
| CN112738724A (en) * | 2020-12-17 | 2021-04-30 | 福建新大陆软件工程有限公司 | Method, device, equipment and medium for accurately identifying regional target crowd |
| CN112738725A (en) * | 2020-12-18 | 2021-04-30 | 福建新大陆软件工程有限公司 | Real-time identification method, device, equipment and medium for target crowd in semi-closed area |
| CN113095448A (en) * | 2021-06-10 | 2021-07-09 | 南京森根安全技术有限公司 | Method for realizing heterogeneous multi-scale track link |
| CN113312596A (en) * | 2021-06-10 | 2021-08-27 | 重庆市勘测院 | User identity recognition method based on deep learning and asynchronous track data |
| CN113469220A (en) * | 2021-06-09 | 2021-10-01 | 广州虎牙科技有限公司 | Track identification method and related device and equipment |
| CN113704373A (en) * | 2021-08-19 | 2021-11-26 | 国家计算机网络与信息安全管理中心 | User identification method and device based on movement track data and storage medium |
| CN117150319A (en) * | 2023-10-30 | 2023-12-01 | 北京艾瑞数智科技有限公司 | Method and device for identifying multiple numbers of one person |
Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20110208425A1 (en) * | 2010-02-23 | 2011-08-25 | Microsoft Corporation | Mining Correlation Between Locations Using Location History |
| US20160154643A1 (en) * | 2014-11-28 | 2016-06-02 | Baidu Online Network Technology (Beijing) Co., Ltd . | Method and system for updating in-vehicle navigation map, in-vehicle navigation device and mobile terminal |
| CN106506705A (en) * | 2016-12-29 | 2017-03-15 | 平安科技（深圳）有限公司 | Listener clustering method and device based on location-based service |
| US20170242879A1 (en) * | 2007-07-26 | 2017-08-24 | Hamid Hatami-Hanza | Ontological Subjects Of A Universe And Knowledge Representations Thereof |
| CN107644204A (en) * | 2017-09-12 | 2018-01-30 | 南京凌深信息科技有限公司 | A kind of human bioequivalence and tracking for safety-protection system |
-
2018
- 2018-04-16 CN CN201810339338.8A patent/CN108536851B/en active Active
Patent Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20170242879A1 (en) * | 2007-07-26 | 2017-08-24 | Hamid Hatami-Hanza | Ontological Subjects Of A Universe And Knowledge Representations Thereof |
| US20110208425A1 (en) * | 2010-02-23 | 2011-08-25 | Microsoft Corporation | Mining Correlation Between Locations Using Location History |
| US20160154643A1 (en) * | 2014-11-28 | 2016-06-02 | Baidu Online Network Technology (Beijing) Co., Ltd . | Method and system for updating in-vehicle navigation map, in-vehicle navigation device and mobile terminal |
| CN106506705A (en) * | 2016-12-29 | 2017-03-15 | 平安科技（深圳）有限公司 | Listener clustering method and device based on location-based service |
| CN107644204A (en) * | 2017-09-12 | 2018-01-30 | 南京凌深信息科技有限公司 | A kind of human bioequivalence and tracking for safety-protection system |
Cited By (23)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110958599A (en) * | 2018-09-26 | 2020-04-03 | 北京融信数联科技有限公司 | One-machine multi-card user distinguishing method based on track similarity |
| CN110958599B (en) * | 2018-09-26 | 2022-05-24 | 北京融信数联科技有限公司 | One-machine multi-card user distinguishing method based on track similarity |
| CN111507732B (en) * | 2019-01-30 | 2023-07-07 | 北京嘀嘀无限科技发展有限公司 | System and method for identifying similar trajectories |
| CN111507732A (en) * | 2019-01-30 | 2020-08-07 | 北京嘀嘀无限科技发展有限公司 | System and method for identifying similar trajectories |
| CN109977109A (en) * | 2019-04-03 | 2019-07-05 | 深圳市甲易科技有限公司 | A kind of track data cleaning method and adjoint analysis method |
| CN109947758A (en) * | 2019-04-03 | 2019-06-28 | 深圳市甲易科技有限公司 | A kind of route crash analysis method in Behavior-based control track library |
| CN111897910A (en) * | 2019-05-05 | 2020-11-06 | 北京京东尚科信息技术有限公司 | Information pushing method and device |
| CN112653995A (en) * | 2019-10-12 | 2021-04-13 | 中国移动通信有限公司研究院 | User identity recognition method and device and computer readable storage medium |
| CN112653995B (en) * | 2019-10-12 | 2023-03-28 | 中国移动通信有限公司研究院 | User identity recognition method and device and computer readable storage medium |
| CN110795705A (en) * | 2019-10-22 | 2020-02-14 | 武汉极意网络科技有限公司 | Track data processing method, device, equipment and storage medium |
| CN111125189A (en) * | 2019-12-12 | 2020-05-08 | 四川大学 | Track similarity measurement method based on weighted real number cost edit distance |
| CN111814914A (en) * | 2020-08-26 | 2020-10-23 | 珠海大横琴科技发展有限公司 | Target object identification method and device |
| CN112738724A (en) * | 2020-12-17 | 2021-04-30 | 福建新大陆软件工程有限公司 | Method, device, equipment and medium for accurately identifying regional target crowd |
| CN112738724B (en) * | 2020-12-17 | 2022-09-23 | 福建新大陆软件工程有限公司 | Method, device, equipment and medium for accurately identifying regional target crowd |
| CN112738725A (en) * | 2020-12-18 | 2021-04-30 | 福建新大陆软件工程有限公司 | Real-time identification method, device, equipment and medium for target crowd in semi-closed area |
| CN112738725B (en) * | 2020-12-18 | 2022-09-23 | 福建新大陆软件工程有限公司 | Real-time identification method, device, equipment and medium for target crowd in semi-closed area |
| CN113469220A (en) * | 2021-06-09 | 2021-10-01 | 广州虎牙科技有限公司 | Track identification method and related device and equipment |
| CN113095448B (en) * | 2021-06-10 | 2021-08-31 | 南京森根安全技术有限公司 | Method for realizing heterogeneous multi-scale track link |
| CN113312596A (en) * | 2021-06-10 | 2021-08-27 | 重庆市勘测院 | User identity recognition method based on deep learning and asynchronous track data |
| CN113095448A (en) * | 2021-06-10 | 2021-07-09 | 南京森根安全技术有限公司 | Method for realizing heterogeneous multi-scale track link |
| CN113704373A (en) * | 2021-08-19 | 2021-11-26 | 国家计算机网络与信息安全管理中心 | User identification method and device based on movement track data and storage medium |
| CN113704373B (en) * | 2021-08-19 | 2023-12-05 | 国家计算机网络与信息安全管理中心 | User identification method, device and storage medium based on movement track data |
| CN117150319A (en) * | 2023-10-30 | 2023-12-01 | 北京艾瑞数智科技有限公司 | Method and device for identifying multiple numbers of one person |
Also Published As
| Publication number | Publication date |
|---|---|
| CN108536851B (en) | 2021-04-16 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN108536851A (en) | A kind of method for identifying ID based on motion track similarity-rough set | |
| Wu et al. | Location estimation via support vector regression | |
| Hwang et al. | Mining mobile group patterns: A trajectory-based approach | |
| CN104635203B (en) | Radio interference source direction-finding and positioning method based on particle filter algorithm | |
| Poulose et al. | Performance analysis of fingerprint matching algorithms for indoor localization | |
| CN104394588B (en) | Indoor orientation method based on Wi Fi fingerprints and Multidimensional Scaling | |
| CN109726594A (en) | A kind of novel track data dissemination method based on difference privacy | |
| CN106658704A (en) | Positioning method and system of starting point of indoor positioning | |
| CN104661306B (en) | Mobile terminal Passive Location and system | |
| Zhou et al. | FreeTrack: Device-free human tracking with deep neural networks and particle filtering | |
| Jiang et al. | Predicting human mobility based on location data modeled by Markov chains | |
| CN110445772B (en) | Internet host scanning method and system based on host relationship | |
| Qian et al. | Time and location aware points of interest recommendation in location-based social networks | |
| Li et al. | Outdoor location estimation using received signal strength feedback | |
| Zheng et al. | RSS-based indoor passive localization using clustering and filtering in a LTE network | |
| Wu et al. | Practical privacy protection scheme in WiFi fingerprint-based localization | |
| Dyrmishi et al. | Mobile positioning and trajectory reconstruction based on mobile phone network data: A tentative using particle filter | |
| Frias-Martinez et al. | Sensing urban land use with twitter activity | |
| CN111970685B (en) | One-person multi-card identification method in big data environment | |
| IL258250A (en) | System and method for identifying associated subjects from location histories | |
| Zhang et al. | Context-aware telco outdoor localization | |
| Mantoro et al. | Mobile user location determination using extreme learning machine | |
| Zhong et al. | A wifi positioning algorithm based on deep learning | |
| Zhang et al. | Confidence model-based data repair for telco localization | |
| Yu et al. | Discovery of Travelling Companions from Trajectories with Different Sampling Rates |
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 |