CN109634946A - A kind of track intelligent Matching association analysis algorithm model excavated based on big data - Google Patents
A kind of track intelligent Matching association analysis algorithm model excavated based on big data Download PDFInfo
- Publication number
- CN109634946A CN109634946A CN201811488911.8A CN201811488911A CN109634946A CN 109634946 A CN109634946 A CN 109634946A CN 201811488911 A CN201811488911 A CN 201811488911A CN 109634946 A CN109634946 A CN 109634946A
- Authority
- CN
- China
- Prior art keywords
- vehicle
- string number
- data
- electronics string
- electronics
- 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
Landscapes
- Information Retrieval, Db Structures And Fs Structures Therefor (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
The present invention provides a kind of track intelligent Matching association analysis algorithm model excavated based on big data, belongs to big data digging technology field.This method includes carrying out duplicate removal to vehicle and electronics string source data, deleting the cleaning treatments such as missing values record;Equipment and the progress co-sited matching of vehicle snapshot bayonet are acquired to code is detectd using equipment longitude and latitude, and judge whether vehicle and electronics string course bearing are consistent;Various dimensions feature is extracted as sample to data, and outlier and abnormal point in Rejection of samples;Treated vehicle and electronics string number with Logistic Regression algorithm are finally established into model, and model is optimized.The present invention detects code to vehicle and electronics string number and has carried out association analysis, it can comprehensive grasp vehicle crew and vehicle characteristics, improve the associated accuracy of people's vehicle, good supporting role is played to the analysis of traffic big data, personnel are provided for the investigation of certain department's traffic case and seek look into Deng important technologies, to fight crime.
Description
Technical field
The present invention relates to big data excavation applications, are a kind of intelligent of tracks excavated based on big data more specifically
With association analysis algorithm model.
Background technique
With the improvement of people's living standards, the owning amount of vehicle constantly rises, the scope of activities of people also gradually expands,
It is simultaneously to encroach on the crime case of target also increasing by main means of transport of motor vehicle or with motor vehicle.Due to motor-driven
The features such as that there are users is more for vehicle, and scope of activities is big, and speed is fast, therefore increase the difficulty of certain organ's case investigation.In recent years, exist
What the motor vehicle promoted the use of in nationwide raided the system of deploying to ensure effective monitoring and control of illegal activities (abbreviation bayonet system) and electronics string electronic equipment detects code
System realizes the data of vehicle data and electronics string number on road and acquires, and for certain organ, cracking of cases provides line abundant
Rope.But since data collection capacity is excessively huge and adheres to not homologous ray separately, need further to be excavated and analyzed, it establishes not
With the incidence relation of resource data, by the application of data mining technology can by these potential rules be associated with domination, look for
The incidence relation of people's vehicle out.However it is currently relatively fewer for the associated research of people's vehicle, and majority uses traditional association algorithm,
The problems such as there is the time and spatially process performance is low needs preferably to excavate for the data of people, the such magnanimity of vehicle
The value and related information of image watermarking.
The present invention detects a yard data according to what license plate candid photograph data and equipment acquired, is based on big data algorithm, constructs license plate
With the association mode of electronics string number, the relationship match of people's vehicle is realized, be the case investigation of certain department's traffic administration and traffic accident
Important technology is provided to support.
Summary of the invention
The embodiment of the present invention is designed to provide a kind of track intelligent Matching association analysis calculation excavated based on big data
Method model, it is intended to by carrying out analytical calculation to big data, provide the accurate associated information of people's vehicle.
To achieve the goals above, technical scheme is as follows:
S1: the source data of vehicle and electronics string number processing;Respectively by the number for detecing decoding apparatus acquisition of vehicle and electronics string number
According to progress duplicate removal, delete the cleaning treatments such as missing values record;
S2: site match;Determined by equipment longitude and latitude detect code acquire equipment and vehicle snapshot equipment whether be in it is same
Place;
S3: judge whether course bearing is consistent;By taking any one vehicle in data record as an example, according to the traveling rail of vehicle
Mark, when vehicle is in T1Time passes through P1Website, then time T1The corresponding electronics string number collection of ± Δ T is combined into A, vehicle T2Time passes through P2
Website, then time T2The corresponding electronics string number of ± Δ T, which integrates, to be combined into B (Δ T is time threshold), while T2± Δ T corresponds to P3Website
Electronics string number collection is combined into C, P3Website and P2Website distance N works as N >=Lmax(LmaxFor the threshold value of distance), and then vehicle exists C ∈ A
Time [T1,T2] in the efficient set of electronics string number be A-C+B, successively recurrence, calculates and the associated electronics string number of vehicle collects
It closes;
S4: various dimensions feature is extracted as initial sample to data;And storing data;
S5: the outlier and abnormal point in Fisher diagnostic method Rejection of samples are utilized;
S6: people's vehicle correlation model is established and optimization;To treated, sample establishes model, calculates vehicle and electronics string number
The degree of association.
Preferably, in the step S5, for the statistical data that Macro or mass analysis obtains, sample is collected, sample includes electronics
Characteristic (label classification is 1), electronics string number and the vehicle that string number clearly has one-to-one relationship with vehicle are clear not
There are the characteristic of one-to-one relationship (label classification are 0), by Fisher diagnostic method by classification in 0 data
Outlier is filtered, and reduces the point that larger negative effect may be generated to result, improves data set for the quasi- of model hypothesis
It is right.
Preferably, the step S6 is specifically included:
S601, will treated sample set, obtain estimates of parameters with Logistic Regression algorithm model
The estimates of parameters that S602, basis obtainThe Logit (p) of each group of vehicle and electronics string number is calculated, and will
Logit (p) mapping converges to section [0,1], obtains the degree of association of final vehicle and electronics string number.
A kind of application method of the track intelligent Matching association analysis algorithm model excavated based on big data, including following step
It is rapid:
Client inputs some electronics string number or license board information in systems, system, that is, exportable corresponding license plate or
The degree of association of electronics string number.
Compared with prior art, the beneficial effects of the present invention are: the present invention is directed to all vehicles and all electronics strings
Number, by co-sited association analysis, people, car data are constantly analyzed, excavated, calculates the associated matching degree of people's vehicle, herein
On the basis of improve many and diverse of traditional association algorithm, improve the associated accuracy of people's vehicle.
Detailed description of the invention
Fig. 1 is the flow diagram of method in the embodiment of the present invention 1;
Fig. 2 is the idiographic flow schematic diagram of method in the embodiment of the present invention 1;
Fig. 3 is the structural block diagram of system in the embodiment of the present invention 2.
Specific embodiment
Below with reference to example to a kind of track intelligent Matching association analysis calculation excavated based on big data of the present invention
Method model is described further.
It is preferred example of the present invention below, does not therefore limit the scope of protection of the present invention.
Embodiment 1
Fig. 1 shows a kind of track intelligent Matching association analysis algorithm mould excavated based on big data of the present invention
Type, comprising the following steps:
S1: the source data of vehicle and electronics string number processing;Respectively by the number for detecing decoding apparatus acquisition of vehicle and electronics string number
According to progress duplicate removal, delete the cleaning treatments such as missing values record;
S2: site match;Determined by equipment longitude and latitude detect code acquire equipment and vehicle snapshot equipment whether be in it is same
Place;
S3: judge whether course bearing is consistent;By taking any one vehicle in data record as an example, according to the traveling rail of vehicle
Mark, when vehicle is in T1Time passes through P1Website, then time T1The corresponding electronics string number collection of ± Δ T is combined into A, vehicle T2Time passes through P2
Website, then time T2The corresponding electronics string number of ± Δ T, which integrates, to be combined into B (Δ T is time threshold), while T2± Δ T corresponds to P3Website
Electronics string number collection is combined into C, P3Website and P2Website distance N works as N >=Lmax(LmaxFor the threshold value of distance), and then vehicle exists C ∈ A
Time [T1,T2] in the efficient set of electronics string number be A-C+B, successively recurrence, calculates and the associated electronics string number of vehicle collects
It closes;
S4: various dimensions feature is extracted as initial sample to data, and storing data;
S5: the outlier and abnormal point in Fisher diagnostic method Rejection of samples are utilized;
S6: people's vehicle correlation model is established and optimization;To treated, sample establishes model, calculates vehicle and electronics string number
The degree of association.
In the present embodiment, Fig. 2 shows the detailed process steps of method of the present invention, wherein more specifically:
(1) source data of vehicle and electronics string number is handled;
When vehicle data is that vehicle passes through bayonet monitoring device, the vehicle traveling information of equipment acquisition.Electronics string number
It is the information such as a certain range of mobile phone IMSI, the IMEI for detecing code acquisition equipment acquisition.The step is mainly original to collecting
Data carry out duplicate removal, delete the cleaning treatments such as missing values record.
(2) bayonet monitoring device is matched with code acquisition equipment co-sited is detectd;
Since vehicle and electronics string number are acquired by two different equipment, therefore it must judge whether two equipment are in same position
It sets.According to the longitude and latitude of equipment present position, by the bayonet monitoring device in same geographical location and detect code acquire equipment into
Row matching.
(3) judge whether license plate and electronics string course bearing are consistent
According to (2) matched bayonet monitoring device and detect code acquisition equipment sentenced on the basis of one day wheelpath of vehicle
Whether the course bearing for powering off substring number is consistent with the course bearing of the license plate, if unanimously, the license plate and the conduct of electronics string
One group of associated group.By taking any one vehicle in data record as an example, according to the driving trace of vehicle, sometime T1 if it exists, when
Vehicle passes through P1Website, then time T1The corresponding electronics string number collection of ± Δ T is combined into A, as vehicle T2Time passes through P2Website, then when
Between T2The corresponding electronics string number of ± Δ T, which integrates, to be combined into B (Δ T is time threshold), while T2± Δ T corresponds to P3The electronics string number of website
Collection is combined into C, P3Website and P2Website distance N works as N >=Lmax(LmaxFor the threshold value of distance), and C ∈ A then vehicle in time [T1,
T2] in the efficient set of electronics string number be A-C+B, successively recurrence, calculates and the associated electronics string number of vehicle is gathered.
(4) various dimensions feature samples arrange storage
The associated group of the license plate and electronics string number that are obtained according to (3) probes into its potential form and data structure, then by vehicle
Board data and the segmentation of electronics string number attribute and combination carry out feature construction, with vehicle, electronics string number, license plate and electronics string number
For three big dimensions, the feature with physical significance found out using other such as match number of days, matching times be sub- dimension as
Initial sample and storing data.
(5) sample process rejects outlier and abnormal point
In the sample be calculated by (4), clearly there is the sample of one-to-one relationship to vehicle and electronics string number, marks
Classification is 1, vehicle and electronics string number is clearly not present the sample of one-to-one relationship, and label classification is 0.It is 0 to classification
Sample (data volume is far longer than the sample that classification is 1), is filtered, deletion may generate result with Fisher diagnostic method
The point of larger negative effect, to improve sample for the degree of fitting of model hypothesis.
(6) model is established, people's vehicle degree of association is calculated
By (5) treated data, as the sample for establishing model, with Logistic Regression algorithm mould
Type obtains estimates of parametersAccording to obtained estimates of parametersThe Logit of each group of vehicle and electronics string number can be calculated
(p), Logit (p) mapping is converged into section [0,1], obtains the degree of association of final vehicle and electronics string number.
Embodiment 2
Fig. 3 shows the system that the method according to embodiment 1 carries out people's vehicle calculation of relationship degree, including crosses car data and deposit
Storage module detects a yard data memory module, people's wheel paths matching primitives module, statistical data memory module, people's vehicle association analysis mould
Block, people's vehicle association results parsing module;
The car data memory module excessively detects yard data memory module for managing original car data and the electronics excessively of acquisition
String number;
People's wheel paths matching primitives module is used to calculate the various dimensions feature samples of vehicle Yu electronics string number, and rejects
Outlier and abnormal point;
The statistical data memory module is used to store the various dimensions feature samples of vehicle and electronics string number;
People's vehicle association analysis module is used to calculate vehicle and electronics string number based on Logistic Regression algorithm
The degree of association;
People's vehicle association results parsing module, the degree of association result for will be calculated are parsed and are stored.
Preferably, described cross car data memory module, detect yard data memory module and statistical data memory module is adopted
It is stored with database distributed completion.
Preferably, people's wheel paths matching primitives module and people's vehicle association analysis module are that big data calculates, divides
Analysis center completes to calculate by Logistic Regression algorithm model.
In conclusion the present invention provides a kind of track intelligent Matching association analysis algorithm model excavated based on big data,
Belong to big data digging technology field.This method includes carrying out duplicate removal to vehicle and electronics string source data, deleting missing values note
The cleaning treatments such as record;Equipment and the progress co-sited matching of vehicle snapshot bayonet are acquired to code is detectd using equipment longitude and latitude, and judge vehicle
It is whether consistent with electronics string course bearing;Various dimensions feature is extracted as sample to data, and peeling off in Rejection of samples
Point and abnormal point;Treated vehicle and electronics string number with Logistic Regression algorithm are finally established into mould
Type, and model is optimized.The present invention detects code to vehicle and electronics string number and has carried out association analysis, can comprehensive grasp vehicle
Personnel and vehicle characteristics, improve the associated accuracy of people's vehicle, play good supporting role to the analysis of traffic big data, are
Certain department's traffic case investigation offer personnel seek look into Deng important technologies, to fight crime.
The foregoing is merely illustrative of the preferred embodiments of the present invention, is not intended to limit the invention, all in essence of the invention
Made any modifications, equivalent replacements, and improvements etc., should all be included in the protection scope of the present invention within mind and principle.
Claims (7)
1. a kind of track intelligent Matching association analysis algorithm model excavated based on big data, which is characterized in that including following step
It is rapid:
S1: the source data of vehicle and electronics string number processing;Respectively by the data for detecing decoding apparatus acquisition of vehicle and electronics string number into
Row duplicate removal deletes the cleaning treatments such as missing values record;
S2: site match;Determine whether detect code acquisition equipment and vehicle snapshot equipment is in same place by equipment longitude and latitude;
S3: judge whether course bearing is consistent;By taking any one vehicle in data record as an example, according to the driving trace of vehicle, when
Vehicle is in T1Time passes through P1Website, then time T1The corresponding electronics string number collection of ± Δ T is combined into A, vehicle T2Time passes through P2Website,
Then time T2The corresponding electronics string number of ± Δ T, which integrates, to be combined into B (Δ T is time threshold), while T2± Δ T corresponds to P3The electronics of website
A string number collection is combined into C, P3Website and P2Website distance N works as N >=Lmax(LmaxFor the threshold value of distance), and C ∈ A then vehicle in the time
[T1,T2] in the efficient set of electronics string number be A-C+B, successively recurrence, calculates and the associated electronics string number of vehicle is gathered;
S4: various dimensions feature is extracted as initial sample to data;And storing data;
S5: the outlier and abnormal point in Fisher diagnostic method Rejection of samples are utilized;
S6: people's vehicle correlation model is established and optimization;To treated, sample establishes model, and calculating vehicle is associated with electronics string number
Degree.
2. the track intelligent Matching association analysis algorithm model according to claim 1 excavated based on big data, feature
It is, in the step S5, for the statistical data that Macro or mass analysis obtains, collects sample, sample includes electronics string number and vehicle
An a pair is clearly not present in characteristic (label classification is 1), electronics string number and the vehicle that clearly there is one-to-one relationship
The characteristic (label classification is 0) for the relationship answered, the outlier in data for being 0 by classification by Fisher diagnostic method carry out
Filtering reduces the point that larger negative effect may be generated to result, improves data set for the degree of fitting of model hypothesis.
3. the track intelligent Matching association analysis algorithm model according to claim 1 excavated based on big data, feature
It is, the step S6 is specifically included:
S601, will treated sample set, obtain estimates of parameters with Logistic Regression algorithm model
The estimates of parameters that S602, basis obtainCalculate the Logit (p) of each group of vehicle and electronics string number, and by Logit
(p) mapping converges to section [0,1], obtains the degree of association of final vehicle and electronics string number.
4. a kind of track intelligent Matching association analysis according to any one of claims 1 to 3 excavated based on big data is calculated
Method model system, which is characterized in that including crossing car data memory module, detecing a yard data memory module, people's wheel paths matching primitives
Module, statistical data memory module, people's vehicle association analysis module, people's vehicle association results parsing module;
The car data memory module excessively detects yard data memory module for managing original car data and the electronics string number excessively of acquisition
Data;
People's wheel paths matching primitives module is used to calculate the various dimensions feature samples of vehicle Yu electronics string number, and rejects and peel off
Point and abnormal point;
The statistical data memory module is used to store the various dimensions feature samples of vehicle and electronics string number;
People's vehicle association analysis module is used to calculate the pass of vehicle and electronics string number based on Logistic Regression algorithm
Connection degree;
People's vehicle association results parsing module, the degree of association result for will be calculated are parsed and are stored.
5. the track intelligent Matching association analysis algorithm model system according to claim 4 excavated based on big data,
It is characterized in that, it is described to cross car data memory module, detect yard data memory module and statistical data memory module using database point
Cloth completes storage.
6. the track intelligent Matching association analysis algorithm model system according to claim 4 excavated based on big data,
It is characterized in that, people's wheel paths matching primitives module and people's vehicle association analysis module are big data calculating, analysis center, are passed through
Logistic Regression algorithm model is completed to calculate.
7. a kind of track intelligent Matching association analysis algorithm model system according to claim 4 excavated based on big data
Application method, which comprises the following steps:
Client inputs some electronics string number or license board information, system, that is, exportable corresponding license plate or electronics in systems
The degree of association of string number.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201811488911.8A CN109634946B (en) | 2018-12-06 | 2018-12-06 | Intelligent track matching correlation analysis method based on big data mining |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201811488911.8A CN109634946B (en) | 2018-12-06 | 2018-12-06 | Intelligent track matching correlation analysis method based on big data mining |
Publications (2)
Publication Number | Publication Date |
---|---|
CN109634946A true CN109634946A (en) | 2019-04-16 |
CN109634946B CN109634946B (en) | 2020-08-18 |
Family
ID=66071574
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201811488911.8A Active CN109634946B (en) | 2018-12-06 | 2018-12-06 | Intelligent track matching correlation analysis method based on big data mining |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN109634946B (en) |
Cited By (7)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN110191429A (en) * | 2019-05-29 | 2019-08-30 | 福建威盾科技集团有限公司 | A method of it is crashed based on the vehicle of swarm intelligence algorithm with wifi |
CN111222587A (en) * | 2020-04-22 | 2020-06-02 | 南京森根安全技术有限公司 | Method and system for predicting dangerous driving behavior of people with loss of evidence based on feature fusion |
CN111246375A (en) * | 2020-03-26 | 2020-06-05 | 广州金越软件技术有限公司 | Man-car accompanying technology based on electronic fence and bayonet information |
CN112101234A (en) * | 2020-09-16 | 2020-12-18 | 上海寰创通信科技股份有限公司 | Detection code matching processing method and image code joint detection system |
CN113160551A (en) * | 2021-01-12 | 2021-07-23 | 北京品恩科技股份有限公司 | Traffic big data based accompanying model application method |
CN113255723A (en) * | 2021-04-14 | 2021-08-13 | 南京森根安全技术有限公司 | Black car identification method based on track characteristics and pedestrian and vehicle association |
CN116595325A (en) * | 2023-04-18 | 2023-08-15 | 南京小唐安朴科技有限公司 | Method for calculating virtual coupling of vehicle portrait and detection code equipment |
Citations (7)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
WO2008156925A2 (en) * | 2007-06-12 | 2008-12-24 | Insightexpress, Llc | Online survey spawning, administration and management |
CN104468787A (en) * | 2014-12-09 | 2015-03-25 | 浪潮电子信息产业股份有限公司 | Big-data-based driver-vehicle associate recognition method |
CN104658248A (en) * | 2013-11-22 | 2015-05-27 | 上海宝康电子控制工程有限公司 | System and method for automatically associating, processing and controlling portrait of vehicle running red light |
CN106611167A (en) * | 2016-12-28 | 2017-05-03 | 山东合天智汇信息技术有限公司 | Tracking method and system |
CN106940794A (en) * | 2017-03-23 | 2017-07-11 | 中国电子科技集团公司第三十八研究所 | A yard adjoint system is detectd in a kind of target collection |
CN108346289A (en) * | 2018-02-13 | 2018-07-31 | 重庆交通大学 | A kind of highway people vehicle interconnected system and method |
CN108848460A (en) * | 2018-05-31 | 2018-11-20 | 重庆市城投金卡信息产业股份有限公司 | People's vehicle correlating method based on RFID and GPS data |
-
2018
- 2018-12-06 CN CN201811488911.8A patent/CN109634946B/en active Active
Patent Citations (7)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
WO2008156925A2 (en) * | 2007-06-12 | 2008-12-24 | Insightexpress, Llc | Online survey spawning, administration and management |
CN104658248A (en) * | 2013-11-22 | 2015-05-27 | 上海宝康电子控制工程有限公司 | System and method for automatically associating, processing and controlling portrait of vehicle running red light |
CN104468787A (en) * | 2014-12-09 | 2015-03-25 | 浪潮电子信息产业股份有限公司 | Big-data-based driver-vehicle associate recognition method |
CN106611167A (en) * | 2016-12-28 | 2017-05-03 | 山东合天智汇信息技术有限公司 | Tracking method and system |
CN106940794A (en) * | 2017-03-23 | 2017-07-11 | 中国电子科技集团公司第三十八研究所 | A yard adjoint system is detectd in a kind of target collection |
CN108346289A (en) * | 2018-02-13 | 2018-07-31 | 重庆交通大学 | A kind of highway people vehicle interconnected system and method |
CN108848460A (en) * | 2018-05-31 | 2018-11-20 | 重庆市城投金卡信息产业股份有限公司 | People's vehicle correlating method based on RFID and GPS data |
Cited By (11)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN110191429A (en) * | 2019-05-29 | 2019-08-30 | 福建威盾科技集团有限公司 | A method of it is crashed based on the vehicle of swarm intelligence algorithm with wifi |
CN110191429B (en) * | 2019-05-29 | 2022-09-27 | 福建威盾科技集团有限公司 | Vehicle and wifi collision method based on group intelligent algorithm |
CN111246375A (en) * | 2020-03-26 | 2020-06-05 | 广州金越软件技术有限公司 | Man-car accompanying technology based on electronic fence and bayonet information |
CN111222587A (en) * | 2020-04-22 | 2020-06-02 | 南京森根安全技术有限公司 | Method and system for predicting dangerous driving behavior of people with loss of evidence based on feature fusion |
CN112101234A (en) * | 2020-09-16 | 2020-12-18 | 上海寰创通信科技股份有限公司 | Detection code matching processing method and image code joint detection system |
CN112101234B (en) * | 2020-09-16 | 2022-11-22 | 上海寰创通信科技股份有限公司 | Detection code matching processing method and graph code joint detection system |
CN113160551A (en) * | 2021-01-12 | 2021-07-23 | 北京品恩科技股份有限公司 | Traffic big data based accompanying model application method |
CN113255723A (en) * | 2021-04-14 | 2021-08-13 | 南京森根安全技术有限公司 | Black car identification method based on track characteristics and pedestrian and vehicle association |
CN113255723B (en) * | 2021-04-14 | 2021-10-26 | 南京森根安全技术有限公司 | Black car identification method based on track characteristics and pedestrian and vehicle association |
CN116595325A (en) * | 2023-04-18 | 2023-08-15 | 南京小唐安朴科技有限公司 | Method for calculating virtual coupling of vehicle portrait and detection code equipment |
CN116595325B (en) * | 2023-04-18 | 2023-11-21 | 南京小唐安朴科技有限公司 | Method for calculating virtual coupling of vehicle portrait and detection code equipment |
Also Published As
Publication number | Publication date |
---|---|
CN109634946B (en) | 2020-08-18 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN109634946A (en) | A kind of track intelligent Matching association analysis algorithm model excavated based on big data | |
CN106998444B (en) | Big data face monitoring system | |
CN104809180B (en) | Illegal vehicle in use recognition methods based on unsupervised intelligence learning algorithm | |
CN108734129A (en) | mobile phone and vehicle location analysis method and system | |
CN109241349A (en) | A kind of monitor video multiple target classification retrieving method and system based on deep learning | |
CN104778245A (en) | Similar trajectory mining method and device on basis of massive license plate identification data | |
CN111090681B (en) | Method, device, equipment and storage medium for group excavation | |
CN106710208A (en) | Traffic state acquisition method and device | |
CN103294775A (en) | Police service cloud image recognition vehicle management and control system based on geographic space-time constraint | |
CN107993444B (en) | Suspected vehicle identification method based on bayonet vehicle-passing big data analysis | |
CN105427586A (en) | Vehicle foothold analysis method based on multi-loci collision | |
CN108595606A (en) | Public security case space-time analysis method and device based on carrier data | |
CN105046959B (en) | Urban Travel Time extracting method based on Dual-window shiding matching mechanism | |
CN111008574A (en) | Key person track analysis method based on body shape recognition technology | |
CN116778292B (en) | Method, device, equipment and storage medium for fusing space-time trajectories of multi-mode vehicles | |
CN105760548A (en) | Vehicle first appearance analysis method and system based on big data cross-domain comparison | |
CN106530331A (en) | Video monitoring system and method | |
CN104778355B (en) | The abnormal track-detecting method of traffic system is distributed based on wide area | |
CN110097074B (en) | Vehicle track compression method based on sequence similarity | |
CN115203354B (en) | Vehicle code track pre-association method and device, computer equipment and storage medium | |
CN115982658A (en) | Hydrological data anomaly identification and repair method based on federated learning framework | |
CN115563652A (en) | Track embedding leakage prevention method and system | |
CN115439412A (en) | Bridge surface crack detection method and device of lightweight convolutional network | |
CN111651484B (en) | Method and device for analyzing accompanying relation of moving object based on semantic track similarity | |
Li et al. | A GPS Trajectory Segmentation Method for Transportation Mode Inference |
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 | ||
CB02 | Change of applicant information | ||
CB02 | Change of applicant information |
Address after: 210000 building De, yunshangcheng, ningshuang Road, Yuhuatai District, Nanjing City, Jiangsu Province Applicant after: Nanjing sengen Technology Co., Ltd Address before: Room 303-9, Building 30, Fengzhan Road, Yuhuatai District, Nanjing City, Jiangsu Province Applicant before: NANJING SENGEN TECHNOLOGY DEVELOPMENT Co.,Ltd. |
|
GR01 | Patent grant | ||
GR01 | Patent grant |