CN114817273A - Data identification method and system for high-frequency man-vehicle association abnormity - Google Patents
Data identification method and system for high-frequency man-vehicle association abnormity Download PDFInfo
- Publication number
- CN114817273A CN114817273A CN202210762813.9A CN202210762813A CN114817273A CN 114817273 A CN114817273 A CN 114817273A CN 202210762813 A CN202210762813 A CN 202210762813A CN 114817273 A CN114817273 A CN 114817273A
- Authority
- CN
- China
- Prior art keywords
- data
- denr
- human
- vehicle related
- dmat
- 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 55
- 238000012545 processing Methods 0.000 claims abstract description 29
- 230000008859 change Effects 0.000 claims abstract description 25
- 101150088702 Denr gene Proteins 0.000 claims description 108
- 230000002159 abnormal effect Effects 0.000 claims description 57
- 239000011159 matrix material Substances 0.000 claims description 47
- 238000004364 calculation method Methods 0.000 claims description 15
- 230000006870 function Effects 0.000 claims description 12
- 238000004590 computer program Methods 0.000 claims description 9
- 101100129590 Schizosaccharomyces pombe (strain 972 / ATCC 24843) mcp5 gene Proteins 0.000 claims description 6
- 238000004422 calculation algorithm Methods 0.000 claims description 4
- 230000008569 process Effects 0.000 claims description 4
- 101100311460 Schizosaccharomyces pombe (strain 972 / ATCC 24843) sum2 gene Proteins 0.000 claims description 3
- 230000009286 beneficial effect Effects 0.000 abstract description 6
- 238000006073 displacement reaction Methods 0.000 abstract description 3
- 238000003860 storage Methods 0.000 description 4
- 230000005856 abnormality Effects 0.000 description 3
- 230000000694 effects Effects 0.000 description 2
- 238000005516 engineering process Methods 0.000 description 2
- 238000012986 modification Methods 0.000 description 2
- 230000004048 modification Effects 0.000 description 2
- 238000004080 punching Methods 0.000 description 2
- 238000013473 artificial intelligence Methods 0.000 description 1
- 230000001413 cellular effect Effects 0.000 description 1
- 238000006243 chemical reaction Methods 0.000 description 1
- 238000012790 confirmation Methods 0.000 description 1
- 238000007418 data mining Methods 0.000 description 1
- 238000001514 detection method Methods 0.000 description 1
- 238000010586 diagram Methods 0.000 description 1
- 238000009826 distribution Methods 0.000 description 1
- 238000000605 extraction Methods 0.000 description 1
- 238000002955 isolation Methods 0.000 description 1
- 238000004519 manufacturing process Methods 0.000 description 1
- 238000010295 mobile communication Methods 0.000 description 1
- 238000011160 research Methods 0.000 description 1
- 239000007787 solid Substances 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/20—Information retrieval; Database structures therefor; File system structures therefor of structured data, e.g. relational data
- G06F16/22—Indexing; Data structures therefor; Storage structures
- G06F16/2291—User-Defined Types; Storage management thereof
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/20—Information retrieval; Database structures therefor; File system structures therefor of structured data, e.g. relational data
- G06F16/24—Querying
- G06F16/245—Query processing
- G06F16/2457—Query processing with adaptation to user needs
- G06F16/24575—Query processing with adaptation to user needs using context
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/20—Information retrieval; Database structures therefor; File system structures therefor of structured data, e.g. relational data
- G06F16/24—Querying
- G06F16/245—Query processing
- G06F16/2458—Special types of queries, e.g. statistical queries, fuzzy queries or distributed queries
- G06F16/2465—Query processing support for facilitating data mining operations in structured databases
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/20—Information retrieval; Database structures therefor; File system structures therefor of structured data, e.g. relational data
- G06F16/29—Geographical information databases
-
- 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
- G06Q50/40—Business processes related to the transportation industry
-
- Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
- Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
- Y02D—CLIMATE CHANGE MITIGATION TECHNOLOGIES IN INFORMATION AND COMMUNICATION TECHNOLOGIES [ICT], I.E. INFORMATION AND COMMUNICATION TECHNOLOGIES AIMING AT THE REDUCTION OF THEIR OWN ENERGY USE
- Y02D10/00—Energy efficient computing, e.g. low power processors, power management or thermal management
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Databases & Information Systems (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Data Mining & Analysis (AREA)
- General Engineering & Computer Science (AREA)
- Software Systems (AREA)
- Business, Economics & Management (AREA)
- Computational Linguistics (AREA)
- General Health & Medical Sciences (AREA)
- Human Resources & Organizations (AREA)
- Remote Sensing (AREA)
- Mathematical Physics (AREA)
- Health & Medical Sciences (AREA)
- Economics (AREA)
- Fuzzy Systems (AREA)
- Probability & Statistics with Applications (AREA)
- Marketing (AREA)
- Primary Health Care (AREA)
- Strategic Management (AREA)
- Tourism & Hospitality (AREA)
- General Business, Economics & Management (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
The invention provides a data identification method and a data identification system for high-frequency man-vehicle association anomaly, which are characterized in that a sequence formed by positioning data and time data of each passenger on various public transport means is collected at a plurality of different moments as man-vehicle association data, a set formed by the man-vehicle association data of each passenger is used as a man-vehicle association data set, the man-vehicle association data set is subjected to space-time change processing to obtain man-vehicle association quantity, the man-vehicle association quantity is subjected to anomaly search to obtain an anomaly point set, an anomaly track is obtained through the anomaly point set, and the beneficial effect of rapidly searching the time-space displacement data of a plurality of complex passengers to obtain the anomaly track is realized.
Description
Technical Field
The invention belongs to the field of big data processing, and particularly relates to a data identification method and system for high-frequency man-vehicle association abnormity.
Background
The difference is that in various artificial intelligence floor application technologies, time and space data are used for feature extraction and dimension conversion, and then abnormal data distribution features in the data are detected. In large and medium-sized cities with dense population, public transport networks are large in scale and high in transportation efficiency, and when passengers board various public transport means, the passengers need to record data based on traffic cards, travel cards, punching cards and the like, so that the travel time and the positioning coordinates of the passengers can be obtained, and the data of high-frequency people and vehicles correlation abnormity can be identified. Patent document CN201910526181.4 discloses a biometric and vehicle identification joint detection method, which can perform biometric identification and vehicle identification simultaneously on a person and a vehicle, perform data association between two identification results, and perform single identity confirmation by using any identification means, but cannot effectively track an abnormal motion trajectory.
Disclosure of Invention
The invention aims to provide a data identification method and a data identification system for high-frequency man-vehicle association abnormity, which are used for solving one or more technical problems in the prior art and at least providing a beneficial selection or creation condition.
The invention provides a data identification method and a data identification system for high-frequency man-vehicle association anomaly, which are characterized in that a sequence formed by positioning data and time data of each passenger on various public transport means is collected at different moments as man-vehicle association data, a set formed by the man-vehicle association data of each passenger is used as a man-vehicle association data set, the man-vehicle association data set is subjected to space-time change processing to obtain man-vehicle association quantity, the man-vehicle association quantity is subjected to anomaly search to obtain an anomaly point set, and an anomaly track is obtained through the anomaly point set.
In order to achieve the above object, according to an aspect of the present invention, there is provided a data identification method for high-frequency human-vehicle related abnormality, the method including the steps of:
s100, collecting a sequence formed by positioning data and time data of each passenger on various public transport means at a plurality of different moments as human-vehicle related data;
s200, taking a set formed by the person-vehicle related data of each passenger as a person-vehicle related data set;
s300, performing space-time change processing on the human-vehicle related data set to obtain human-vehicle related quantity;
s400, carrying out abnormal search on the human-vehicle correlation quantity to obtain an abnormal point set;
and S500, obtaining an abnormal track through the abnormal point set.
Further, in S100, the method for collecting the sequence of the positioning data and the time data of each passenger on various public transportation vehicles at different time points as the human-vehicle related data is as follows:
the method comprises the steps of obtaining positioning coordinates of passengers on a public transport means and corresponding moments at a plurality of different moments as positioning data and time data respectively, taking a sequence formed by the time data of the passengers at each moment and the positioning data according to the time sequence as people and vehicle related data corresponding to the passengers, recording the time data as time, and collecting the people and vehicle related data of each passenger by using the positioning data as longitude and latitude values of the positioning coordinates.
Further, in S200, a method of using a set of the person-vehicle related data of each passenger as a person-vehicle related data set includes: taking a set formed by human-vehicle related data corresponding to a plurality of different passengers as a human-vehicle related data set, recording the human-vehicle related data set into a set Dset, setting the number of elements in the human-vehicle related data set as n, setting the serial number of the elements in the human-vehicle related data set as i, setting i as [1, n ], keeping the corresponding relation between the serial number i and the passenger in the human-vehicle related data set, and setting the human-vehicle related data with the serial number i in the human-vehicle related data set as D (i);
recording the number of the moments in the different moments as k, the sequence numbers of the moments in the different moments as d, and the d belongs to [1, k ];
the human-vehicle related data D (i) is a sequence consisting of k elements, where each element in D (i) corresponds to time data and positioning data at a time, an element with a sequence number D in D (i) is D (i, D), D (i, D) consists of corresponding time data t (i, D) and positioning data p (i, D), a longitude value in the positioning data p (i, D) is long (i, D), and a latitude value in the positioning data p (i, D) is lat (i, D).
Further, in S300, the human-vehicle related data set is subjected to spatiotemporal change processing, and the method for obtaining the human-vehicle related quantity includes:
using the human-vehicle related data set as a matrix Dmat, wherein the matrix Dmat is a matrix of k rows and n columns, the serial numbers of the rows in the matrix Dmat are consistent with the serial numbers of all the different moments, the serial numbers of the columns in the matrix Dmat are consistent with the serial numbers of the elements in the Dset, the column with the serial number i in the matrix Dmat is D (i), the column with the serial number i in the Dmat and the element with the row serial number D in the Dmat are D (i, D);
according to the matrix Dmat, performing space-time change processing on the human-vehicle related data set, wherein the result obtained by the space-time change processing is that a matrix with k rows and n columns is recorded as Denr, and the specific process of performing the space-time change processing is as follows:
let the row number in the matrix Denr and the row number in the Dmat be consistent, the column number in Denr and the column number in Dmat be consistent, the element with the column number i and the row number D in the matrix Denr is Denr (i, D), the element Denr (i, D) in Denr and the element D (i, D) with the same row number and column number in Dmat are in correspondence, the numerical calculation formula of Denr (i, D) is:
wherein Temp (i, d) represents a time variation value of time data t (i, d) of an element with a column number i and a row number d in the matrix Dmat for time data of each element in a column with a matrix Dmat number i, Pos (i, d) represents a space variation value of positioning data p (i, d) of an element with a column number i and a row number d in the matrix Dmat for positioning data of each element in a row with a matrix Dmat number d;
the formula for Temp (i, d) is:
the function G () represents the time difference between two time data, and the time difference is calculated in seconds, and then subjected to dimensionless processing and taken as an absolute value; d-1 is used to represent the previous sequence number of the sequence number D, the time data corresponding to the element D (i, D-1) with the row sequence number D-1 in the sequence number i in the matrix Dmat, which is the element D (i, D-1) corresponding to the D (i, D) corresponding to t (i, D) is t (i, D-1),
the calculation formula for Pos (i, d) is:
the function E () represents the Euclidean distance for calculating the longitude and latitude value between two positioning data, the result of the Euclidean distance is calculated in meters, and then the result is subjected to dimensionless processing and the absolute value is taken;
i-1 represents the previous sequence number of the sequence number i, and the positioning data corresponding to the element D (i-1, D) with the column sequence number of i-1 in the row with the sequence number of D in the matrix Dmat is p (i-1, D);
the method for obtaining the people-vehicle association quantity has the advantages that the linear relation between the movement trends of different passengers in the time dimension is ignored in the existing people-vehicle movement association method, so that potential anomalies among the passengers cannot be mined by data, and in the process of calculating the people-vehicle association quantity, the linear relation among the time-space data of the passengers is displayed on a matrix by calculating the linear product between the time change numerical value of the time data of each element and the space change numerical value of the positioning data of each element, so that the calculation cost of data mining for the potential anomalies among the passengers is reduced.
Further, in S400, the method of performing an abnormal search on the human-vehicle related quantity to obtain an abnormal point set includes:
setting a set Tset as a set for collecting abnormal positioning data, and enabling an initial value of the set Tset to be an empty set;
setting a pointer as pivot (i, d), wherein variables i and d in the pivot (i, d) are consistent with the meanings indicated by variables i and d in Denr (i, d), and the pivot (i, d) is a pointer pointing to Denr (i, d);
acquiring the arithmetic mean value of each element value in Denr as davg;
the specific steps of carrying out abnormal search on the human-vehicle correlation quantity are as follows:
s401, obtaining an element with the largest numerical value in Denr as an initial value of Denr (i, d), and enabling pivot (i, d) to point to the Denr (i, d) which is currently used as the initial value in Denr;
s402, obtaining a current Denr (i, d) pointed by the pivot (i, d), obtaining elements adjacent to the current Denr (i, d) in the Denr (i, d) (i.e., upper, lower, left, and right), recording the number of the adjacent elements as sum1, recording the number of the adjacent elements not smaller than davg in the adjacent elements as num1, recording the ratio of the number of the adjacent elements not smaller than davg to the number of the adjacent elements as r1, and calculating r1 as r1= exp (num1)/exp (sum 1);
exp () is an exponential function with a natural number e as the base;
s403, selecting one element with the largest value in the adjacent elements as Denr (i1, d1), namely, the column number of the element Denr (i1, d1) is i1, and the row number is d 1;
s404, acquiring an element adjacent to Denr (i1, d1) in Denr, and noting that the number of elements adjacent to Denr (i1, d1) is sum2, noting that the number of elements adjacent to Denr (i1, d1) having a value not less than davg is num2, noting that the ratio of the number of elements adjacent to Denr (i1, d1) having a value not less than davg to the number of elements adjacent to Denr (i1, d1) is r2, and the calculation formula of r2 is r2= exp (num2)/exp (sum 2);
s405, calculating and judging whether r2> r1 is met, if yes, turning to S406, and if not, turning to S407;
s406, acquiring an element with the largest value in the elements adjacent to the Denr (i1, d1) as the Denr (i2, d 2);
according to the corresponding relation between Denr (i2, D2) and the elements with the same row number and column number in Dmat, acquiring the elements corresponding to Denr (i2, D2) in Dmat as D (i2, D2), further acquiring the positioning data corresponding to D (i2, D2) as p (i2, D2), and adding p (i2, D2) as an element into the set Tset;
to point pivot (i, d) to Denr (i2, d2), to update Denr (i2, d2) to the current Denr (i, d) pointed to by pivot (i, d); go to S408;
s407, point the pivot (i, d) to Denr (i1, d1), update the value of Denr (i1, d1) to the current Denr (i, d) pointed to by pivot (i, d); go to S408;
s408, judging whether the number of elements in the set Tset is more than or equal to k, if so, turning to S409, otherwise, turning to S402;
s409, removing repeated elements in the set Tset, and outputting the Tset;
each element in the output Tset is each positioning data, each positioning data is each abnormal point, and the output Tset is an abnormal point set;
(wherein, the calculation of the abnormal point set has the beneficial effect that, unlike the existing abnormal recognition method in which the abnormal recognition is performed by a plurality of positioning coordinates acquired at specific time, so that the limitation that the data calculation is performed in isolation in time and space is provided, the method provided by the scheme searches for the abnormal point in the adjacent elements of the time space quickly and efficiently by performing calculation comparison on the adjacent elements of the human-vehicle correlation quantity, thereby breaking the limitation in time and space).
Further, in S500, the method for obtaining the abnormal trajectory through the abnormal point set includes:
when the number of elements in the abnormal point set is larger than 1, fitting each positioning data in the abnormal point set into a curve by using a curve fitting algorithm including a method for approximating discrete data by an analytical expression, a least square method and the like, wherein the curve obtained by fitting is the abnormal track.
The invention also provides a data identification system for the high-frequency man-vehicle association abnormity, which comprises the following steps: the processor executes the computer program to realize the steps in the data identification method of the high-frequency human-vehicle related abnormity, the data identification system of the high-frequency human-vehicle related abnormity can be operated in computing equipment such as desktop computers, notebook computers, palm computers and cloud data centers, and the operable system can include, but is not limited to, the processor, the memory and the server cluster, and the processor executes the computer program to operate in the units of the following systems:
the system comprises a human-vehicle related data acquisition unit, a human-vehicle related data acquisition unit and a passenger identification unit, wherein the human-vehicle related data acquisition unit is used for collecting a sequence formed by positioning data and time data of each passenger on various public transport means at a plurality of different moments as human-vehicle related data;
the system comprises a human-vehicle related data set acquisition unit, a human-vehicle related data set acquisition unit and a human-vehicle related data set acquisition unit, wherein the human-vehicle related data set acquisition unit is used for taking a set formed by human-vehicle related data of each passenger as a human-vehicle related data set;
the time-space change processing unit is used for performing time-space change processing on the human-vehicle related data set to obtain human-vehicle related quantity;
the abnormal searching unit is used for performing abnormal searching on the human-vehicle correlation quantity to obtain an abnormal point set;
and the abnormal track acquisition unit is used for acquiring an abnormal track through the abnormal point set.
The beneficial effects of the invention are as follows: the invention provides a data identification method and a data identification system for high-frequency man-vehicle association anomaly, which are characterized in that a sequence formed by positioning data and time data of each passenger on various public transport means is collected at a plurality of different moments as man-vehicle association data, a set formed by the man-vehicle association data of each passenger is used as a man-vehicle association data set, the man-vehicle association data set is subjected to space-time change processing to obtain man-vehicle association quantity, the man-vehicle association quantity is subjected to anomaly search to obtain an anomaly point set, an anomaly track is obtained through the anomaly point set, and the beneficial effect of rapidly searching the time-space displacement data of a plurality of complex passengers to obtain the anomaly track is realized.
Drawings
The above and other features of the present invention will become more apparent by describing in detail embodiments thereof with reference to the attached drawings in which like reference numerals designate the same or similar elements, it being apparent that the drawings in the following description are merely exemplary of the present invention and other drawings can be obtained by those skilled in the art without inventive effort, wherein:
FIG. 1 is a flow chart of a data identification method for high-frequency man-vehicle association anomaly;
fig. 2 is a system configuration diagram of a data identification system for high-frequency man-vehicle related abnormality.
Detailed Description
The conception, the specific structure and the technical effects of the present invention will be clearly and completely described in conjunction with the embodiments and the accompanying drawings to fully understand the objects, the schemes and the effects of the present invention. It should be noted that the embodiments and features of the embodiments in the present application may be combined with each other without conflict.
In the description of the present invention, the meaning of a plurality of means is one or more, the meaning of a plurality of means is two or more, and larger, smaller, larger, etc. are understood as excluding the number, and larger, smaller, inner, etc. are understood as including the number. If the first and second are described for the purpose of distinguishing technical features, they are not to be understood as indicating or implying relative importance or implicitly indicating the number of technical features indicated or implicitly indicating the precedence of the technical features indicated.
Fig. 1 is a flowchart illustrating a data identification method for high-frequency human-vehicle related anomalies according to the present invention, and a description is given below with reference to fig. 1 to describe a data identification method and system for high-frequency human-vehicle related anomalies according to an embodiment of the present invention.
The invention provides a data identification method for high-frequency man-vehicle association abnormity, which specifically comprises the following steps:
s100, collecting a sequence formed by positioning data and time data of each passenger on various public transport means at a plurality of different moments as human-vehicle related data;
s200, taking a set formed by the person-vehicle related data of each passenger as a person-vehicle related data set;
s300, performing space-time change processing on the human-vehicle related data set to obtain human-vehicle related quantity;
s400, carrying out abnormal search on the human-vehicle correlation quantity to obtain an abnormal point set;
and S500, obtaining an abnormal track through the abnormal point set.
Further, in S100, the method for collecting the sequence of the positioning data and the time data of each passenger on various public transportation vehicles at different time points as the human-vehicle related data is as follows:
acquiring positioning coordinates of passengers on a public transport means and corresponding moments at a plurality of different moments as positioning data and time data respectively, and taking a sequence formed by the time data of the passengers at each moment and the positioning data according to the time sequence as people-vehicle related data corresponding to the passengers, wherein the time data is a record of time, the positioning data is a longitude and latitude value of the positioning coordinates, and the people-vehicle related data is collected for each passenger;
the plurality of public transportation vehicles may include: subways, buses, trams, trains, high-speed rails, planes, shared cars, ships;
the specific operation of recording the time as time data and the positioning coordinate as positioning data at the moment by the mobile communication equipment can be realized by a traffic card, a trip card punching card, a GPS, a mobile phone positioning and tracking and the like.
Further, in S200, a method of using a set of the person-vehicle related data of each passenger as a person-vehicle related data set includes: taking a set formed by human-vehicle related data corresponding to a plurality of different passengers as a human-vehicle related data set, recording the human-vehicle related data set into a set Dset, setting the number of elements in the human-vehicle related data set as n, setting the serial number of the elements in the human-vehicle related data set as i, setting i as [1, n ], keeping the corresponding relation between the serial number i and the passenger in the human-vehicle related data set, and setting the human-vehicle related data with the serial number i in the human-vehicle related data set as D (i);
recording the number of the moments in the different moments as k, the sequence numbers of the moments in the different moments as d, and the d belongs to [1, k ];
the human-vehicle related data D (i) is a sequence composed of k elements, where D (i) each element corresponds to time data and positioning data at a time, D (i, D) is an element with a sequence number D, D (i, D) is composed of time data t (i, D) corresponding to D and positioning data p (i, D), a longitude value in the positioning data p (i, D) is long (i, D), and a latitude value in the positioning data p (i, D) is lat (i, D).
Further, in S300, the human-vehicle related data set is subjected to spatiotemporal change processing, and the method for obtaining the human-vehicle related quantity includes:
using the human-vehicle related data set as a matrix Dmat, wherein the matrix Dmat is a matrix of k rows and n columns, the serial numbers of the rows in the matrix Dmat are consistent with the serial numbers of all the different moments, the serial numbers of the columns in the matrix Dmat are consistent with the serial numbers of the elements in the Dset, the column with the serial number i in the matrix Dmat is D (i), the column with the serial number i in the Dmat and the element with the row serial number D in the Dmat are D (i, D);
according to the matrix Dmat, performing space-time change processing on the human-vehicle related data set, wherein the result obtained by the space-time change processing is that a matrix with k rows and n columns is recorded as Denr, and the specific process of performing the space-time change processing is as follows:
let the row number in the matrix Denr and the row number in the Dmat be consistent, the column number in Denr and the column number in Dmat be consistent, the element with the column number i and the row number D in the matrix Denr is Denr (i, D), the element Denr (i, D) in Denr and the element D (i, D) with the same row number and column number in Dmat are in correspondence, the numerical calculation formula of Denr (i, D) is:
wherein Temp (i, d) represents a time variation value of time data t (i, d) of an element with a column number i and a row number d in the matrix Dmat for time data of each element in a column with a matrix Dmat number i, Pos (i, d) represents a space variation value of positioning data p (i, d) of an element with a column number i and a row number d in the matrix Dmat for positioning data of each element in a row with a matrix Dmat number d;
the formula for Temp (i, d) is:
the function G () represents the time difference between two time data, and the time difference is calculated in seconds, and then subjected to dimensionless processing and taken as an absolute value; d-1 is used to represent the previous sequence number of the sequence number D, the time data corresponding to the element D (i, D-1) with the row sequence number D-1 in the sequence number i in the matrix Dmat, which is the element D (i, D-1) corresponding to the D (i, D) corresponding to t (i, D) is t (i, D-1),
the calculation formula for Pos (i, d) is:
the function E () represents the Euclidean distance for calculating the longitude and latitude value between two positioning data, the result of the Euclidean distance is calculated in meters, and then the result is subjected to dimensionless processing and the absolute value is taken;
i-1 represents the previous sequence number of the sequence number i, and the positioning data corresponding to the element D (i-1, D) with the column sequence number of i-1 in the row with the sequence number of D in the matrix Dmat is p (i-1, D).
Further, in S400, the method of performing an abnormal search on the human-vehicle related quantity to obtain an abnormal point set includes:
setting a set Tset as a set for collecting abnormal positioning data, and enabling an initial value of the set Tset to be an empty set;
setting a pointer to be denoted as pivot (i, d), wherein variables i and d in the pivot (i, d) are consistent with meanings indicated by variables i and d in Denr (i, d), and the pivot (i, d) is a pointer pointing to Denr (i, d);
acquiring the arithmetic mean value of each element value in Denr as davg;
the specific steps of carrying out abnormal search on the human-vehicle correlation quantity are as follows:
s401, obtaining an element with the largest numerical value in Denr as an initial value of Denr (i, d), and enabling pivot (i, d) to point to the Denr (i, d) which is currently used as the initial value in Denr;
s402, obtaining a current Denr (i, d) pointed by the pivot (i, d), obtaining an element adjacent to the current Denr (i, d) in the Denr, and noting that the number of the adjacent element is sum1, noting that the number of the adjacent element having a value not less than davg is num1, noting that the ratio of the number of the adjacent element having a value not less than davg to the number of the adjacent element is r1, and the calculation formula of r1 is r1= exp (num1)/exp (sum 1); exp is an exponential function with a natural number e as the base;
s403, selecting one element with the largest value in the adjacent elements as Denr (i1, d1), namely, the column number of the element Denr (i1, d1) is i1, and the row number is d 1;
s404, acquiring an element adjacent to Denr (i1, d1) in Denr, and noting that the number of elements adjacent to Denr (i1, d1) is sum2, noting that the number of elements adjacent to Denr (i1, d1) having a value not less than davg is num2, noting that the ratio of the number of elements adjacent to Denr (i1, d1) having a value not less than davg to the number of elements adjacent to Denr (i1, d1) is r2, and the calculation formula of r2 is r2= exp (num2)/exp (sum 2);
s405, calculating and judging whether r2> r1 is met, if yes, turning to S406, and if not, turning to S407;
s406, acquiring an element with the largest value in the elements adjacent to the Denr (i1, d1) as the Denr (i2, d 2);
according to the corresponding relation between Denr (i2, D2) and the elements with the same row number and column number in Dmat, acquiring the elements corresponding to Denr (i2, D2) in Dmat as D (i2, D2), further acquiring the positioning data corresponding to D (i2, D2) as p (i2, D2), and adding p (i2, D2) as an element into the set Tset;
to point pivot (i, d) to Denr (i2, d2), to update Denr (i2, d2) to the current Denr (i, d) pointed to by pivot (i, d); go to S408;
s407, point pivot (i, d) to Denr (i1, d1), update Denr (i1, d1) to the current Denr (i, d) pointed to by pivot (i, d); go to S408;
s408, judging whether the number of elements in the set Tset is more than or equal to k, if so, turning to S409, otherwise, turning to S402;
s409, removing repeated elements in the set Tset, and outputting the Tset;
each element in the output Tset is each positioning data, each positioning data is each anomaly point, and the output Tset is an anomaly point set.
Further, in S500, the method for obtaining the abnormal trajectory through the abnormal point set includes:
when the number of elements in the abnormal point set is more than 1, a curve fitting algorithm (refer to a paper [1] Zhao Yugang, Yuwei, Zhao Jian, etc.. curve and other error straight line fitting algorithm research and application [ J ] manufacturing technology and machine tool, 2010(6): 5.) are used for fitting each positioning data in the abnormal point set into a curve, and the curve obtained by fitting is an abnormal track.
The data identification system for the high-frequency man-vehicle association abnormity comprises the following components: the processor executes the computer program to implement the steps in the above-mentioned data identification method embodiment of the high-frequency human-vehicle related anomaly, the data identification system of the high-frequency human-vehicle related anomaly may be run in a desktop computer, a notebook computer, a palm computer, a cloud data center and other computing devices, and the executable systems may include, but are not limited to, a processor, a memory, and a server cluster.
As shown in fig. 2, the data identification system for high-frequency human-vehicle related abnormality according to the embodiment of the present invention includes: the processor executes the computer program to realize the steps in the data identification method embodiment of the high-frequency man-vehicle related abnormity, and executes the computer program to run in the following units of the system:
the system comprises a human-vehicle related data acquisition unit, a human-vehicle related data acquisition unit and a passenger identification unit, wherein the human-vehicle related data acquisition unit is used for collecting a sequence formed by positioning data and time data of each passenger on various public transport means at a plurality of different moments as human-vehicle related data;
the system comprises a human-vehicle related data set acquisition unit, a human-vehicle related data set acquisition unit and a human-vehicle related data set acquisition unit, wherein the human-vehicle related data set acquisition unit is used for taking a set formed by human-vehicle related data of each passenger as a human-vehicle related data set;
the time-space change processing unit is used for performing time-space change processing on the human-vehicle related data set to obtain human-vehicle related quantity;
the abnormal searching unit is used for performing abnormal searching on the human-vehicle correlation quantity to obtain an abnormal point set;
and the abnormal track acquisition unit is used for acquiring an abnormal track through the abnormal point set.
The data identification system for the high-frequency people and vehicle association abnormity can be operated in computing equipment such as a desktop computer, a notebook computer, a palm computer and a cloud data center. The data identification system for the high-frequency man-vehicle related abnormity comprises a processor and a memory. It can be understood by those skilled in the art that the example is only an example of the data identification method and system for the high-frequency human-vehicle related abnormity, and does not constitute a limitation to the data identification method and system for the high-frequency human-vehicle related abnormity, and the data identification method and system for the high-frequency human-vehicle related abnormity may include more or less components than the above ratio, or combine some components, or different components, for example, the data identification system for the high-frequency human-vehicle related abnormity may further include an input-output device, a network access device, a bus, and the like.
The Processor may be a Central Processing Unit (CPU), other general purpose Processor, a Digital Signal Processor (DSP), an Application Specific Integrated Circuit (ASIC), a Field Programmable Gate Array (FPGA) or other Programmable logic device, discrete component Gate or transistor logic, discrete hardware components, etc. The general processor can be a microprocessor or the processor can also be any conventional processor and the like, the processor is a control center of the data identification system for the high-frequency human-vehicle related abnormity, and various interfaces and lines are utilized to connect all subareas of the data identification system for the high-frequency human-vehicle related abnormity.
The memory can be used for storing the computer programs and/or the modules, and the processor realizes various functions of the data identification method and the data identification system for the high-frequency man-vehicle related abnormity by running or executing the computer programs and/or the modules stored in the memory and calling the data stored in the memory. The memory may mainly include a storage program area and a storage data area, wherein the storage program area may store an operating system, an application program required by at least one function (such as a sound playing function, an image playing function, etc.), and the like; the storage data area may store data (such as audio data, a phonebook, etc.) created according to the use of the cellular phone, and the like. In addition, the memory may include high speed random access memory, and may also include non-volatile memory, such as a hard disk, a memory, a plug-in hard disk, a Smart Media Card (SMC), a Secure Digital (SD) Card, a Flash memory Card (Flash Card), at least one magnetic disk storage device, a Flash memory device, or other volatile solid state storage device.
The invention provides a data identification method and a data identification system for high-frequency man-vehicle association anomaly, which are characterized in that a sequence formed by positioning data and time data of each passenger on various public transport means is collected at a plurality of different moments as man-vehicle association data, a set formed by the man-vehicle association data of each passenger is used as a man-vehicle association data set, the man-vehicle association data set is subjected to space-time change processing to obtain man-vehicle association quantity, the man-vehicle association quantity is subjected to anomaly search to obtain an anomaly point set, an anomaly track is obtained through the anomaly point set, and the beneficial effect of rapidly searching the time-space displacement data of a plurality of complex passengers to obtain the anomaly track is realized.
Preferably, all undefined variables in the present invention may be threshold values set manually if they are not defined explicitly.
Although the present invention has been described in considerable detail and with reference to certain illustrated embodiments, it is not intended to be limited to any such details or embodiments or any particular embodiment, so as to effectively encompass the intended scope of the invention. Furthermore, the foregoing describes the invention in terms of embodiments foreseen by the inventor for which an enabling description was available, notwithstanding that insubstantial modifications of the invention, not presently foreseen, may nonetheless represent equivalent modifications thereto.
Claims (7)
1. A data identification method for high-frequency man-vehicle association abnormity is characterized by comprising the following steps:
s100, collecting a sequence formed by positioning data and time data of each passenger on various public transport means at a plurality of different moments as human-vehicle related data;
s200, taking a set formed by the person-vehicle related data of each passenger as a person-vehicle related data set;
s300, performing space-time change processing on the human-vehicle related data set to obtain human-vehicle related quantity;
s400, carrying out abnormal search on the human-vehicle correlation quantity to obtain an abnormal point set;
and S500, obtaining an abnormal track through the abnormal point set.
2. The method for identifying high-frequency people-vehicle related anomalies according to claim 1, characterized in that in S100, the method for collecting the sequence of the positioning data and the time data of each passenger on various public transportation means at a plurality of different moments as the people-vehicle related data is as follows:
the method comprises the steps of obtaining positioning coordinates of passengers on a public transport means and corresponding moments at a plurality of different moments as positioning data and time data respectively, taking a sequence formed by the time data of the passengers at each moment and the positioning data according to the time sequence as people and vehicle related data corresponding to the passengers, recording the time data as time, and collecting the people and vehicle related data of each passenger by using the positioning data as longitude and latitude values of the positioning coordinates.
3. The method for identifying the data of the high-frequency human-vehicle related anomaly according to the claim 1, wherein in S200, the method for taking the set formed by the human-vehicle related data of each passenger as the human-vehicle related data set comprises the following steps: taking a set formed by human-vehicle related data corresponding to a plurality of different passengers as a human-vehicle related data set, recording the human-vehicle related data set into a set Dset, setting the number of elements in the human-vehicle related data set as n, setting the serial number of the elements in the human-vehicle related data set as i, setting i as [1, n ], keeping the corresponding relation between the serial number i and the passenger in the human-vehicle related data set, and setting the human-vehicle related data with the serial number i in the human-vehicle related data set as D (i);
recording the number of the moments in the different moments as k, the sequence numbers of the moments in the different moments as d, and the d belongs to [1, k ];
the human-vehicle related data D (i) is a sequence composed of k elements, where each element of D (i) corresponds to time data and positioning data at a time, an element with a sequence number D in D (i) is D (i, D), D (i, D) is composed of corresponding time data t (i, D) and positioning data p (i, D), a longitude value in the positioning data p (i, D) is long (i, D), and a latitude value in the positioning data p (i, D) is lat (i, D).
4. The method for identifying the data of the high-frequency human-vehicle related anomaly according to the claim 3, wherein in S300, the human-vehicle related data set is subjected to space-time change processing, and the method for obtaining the human-vehicle related quantity comprises the following steps:
using the human-vehicle related data set as a matrix Dmat, wherein the matrix Dmat is a matrix of k rows and n columns, the serial numbers of the rows in the matrix Dmat are consistent with the serial numbers of all the different moments, the serial numbers of the columns in the matrix Dmat are consistent with the serial numbers of the elements in the Dset, the column with the serial number i in the matrix Dmat is D (i), the column with the serial number i in the Dmat and the element with the row serial number D in the Dmat are D (i, D);
according to the matrix Dmat, performing space-time change processing on the human-vehicle related data set, wherein the result obtained by the space-time change processing is that a matrix with k rows and n columns is recorded as Denr, and the specific process of performing the space-time change processing is as follows:
let the row number in the matrix Denr and the row number in the Dmat be consistent, the column number in Denr and the column number in Dmat be consistent, the element with the column number i and the row number D in the matrix Denr is Denr (i, D), the element Denr (i, D) in Denr and the element D (i, D) with the same row number and column number in Dmat are in correspondence, the numerical calculation formula of Denr (i, D) is:
wherein Temp (i, d) represents a time variation value of time data t (i, d) of an element with a column number i and a row number d in the matrix Dmat for time data of each element in a column with a matrix Dmat number i, Pos (i, d) represents a space variation value of positioning data p (i, d) of an element with a column number i and a row number d in the matrix Dmat for positioning data of each element in a row with a matrix Dmat number d;
the formula for Temp (i, d) is:
the function G () represents calculating the difference in time between two time data;
the calculation formula for Pos (i, d) is:
the function E () represents the euclidean distance for calculating the latitude and longitude values between two positioning data.
5. The method for identifying the data of the high-frequency human-vehicle related anomaly according to the claim 4, wherein in S400, the method for searching the human-vehicle related quantity for the anomaly to obtain the anomaly point set comprises the following steps:
setting a set Tset as a set for collecting abnormal positioning data, and enabling an initial value of the set Tset to be an empty set;
setting a pointer to be denoted as pivot (i, d), wherein variables i and d in the pivot (i, d) are consistent with meanings indicated by variables i and d in Denr (i, d), and the pivot (i, d) is a pointer pointing to Denr (i, d);
acquiring the arithmetic mean value of each element value in Denr as davg;
the specific steps of carrying out abnormal search on the human-vehicle correlation quantity are as follows:
s401, obtaining an element with the largest numerical value in Denr as an initial value of Denr (i, d), and enabling pivot (i, d) to point to the Denr (i, d) which is currently used as the initial value in Denr;
s402, obtaining a current Denr (i, d) pointed by the pivot (i, d), obtaining an element adjacent to the current Denr (i, d) in the Denr, and noting that the number of the adjacent element is sum1, noting that the number of the adjacent element having a value not less than davg is num1, noting that the ratio of the number of the adjacent element having a value not less than davg to the number of the adjacent element is r1, and the calculation formula of r1 is r1= exp (num1)/exp (sum 1);
s403, selecting one element with the largest value in the adjacent elements as Denr (i1, d1), namely, the column number of the element Denr (i1, d1) is i1, and the row number is d 1;
s404, acquiring an element adjacent to Denr (i1, d1) in Denr, and noting that the number of elements adjacent to Denr (i1, d1) is sum2, noting that the number of elements adjacent to Denr (i1, d1) having a value not less than davg is num2, noting that the ratio of the number of elements adjacent to Denr (i1, d1) having a value not less than davg to the number of elements adjacent to Denr (i1, d1) is r2, and the calculation formula of r2 is r2= exp (num2)/exp (sum 2);
s405, calculating and judging whether r2> r1 is met, if yes, turning to S406, and if not, turning to S407;
s406, acquiring an element with the largest value in the elements adjacent to the Denr (i1, d1) as the Denr (i2, d 2);
according to the corresponding relation between Denr (i2, D2) and the elements with the same row number and column number in Dmat, acquiring the elements corresponding to Denr (i2, D2) in Dmat as D (i2, D2), further acquiring the positioning data corresponding to D (i2, D2) as p (i2, D2), and adding p (i2, D2) as an element into the set Tset;
to point pivot (i, d) to Denr (i2, d2), to update Denr (i2, d2) to the current Denr (i, d) pointed to by pivot (i, d); go to S408;
s407, the pint (i, d) points to Denr (i1, d1), and the value of Denr (i1, d1) is updated to the current Denr (i, d) pointed to by the pint (i, d); go to S408;
s408, judging whether the number of elements in the set Tset is more than or equal to k, if so, turning to S409, otherwise, turning to S402;
s409, removing repeated elements in the set Tset, and outputting the Tset;
each element in the output Tset is each positioning data, each positioning data is each anomaly point, and the output Tset is an anomaly point set.
6. The method for identifying the data of the high-frequency man-vehicle related abnormity according to claim 5, wherein in S500, the method for obtaining the abnormal track through the abnormal point set comprises the following steps:
and when the number of elements in the abnormal point set is more than 1, fitting each positioning data in the abnormal point set into a curve by using a curve fitting algorithm, wherein the curve obtained by fitting is the abnormal track.
7. A data identification system for high-frequency human-vehicle related abnormity is characterized by comprising the following steps: the processor, the memory and the computer program stored in the memory and running on the processor, when the processor executes the computer program, the steps of the data identification method for the high-frequency human-vehicle related abnormity of any one of claims 1 to 6 are realized, and the data identification system for the high-frequency human-vehicle related abnormity runs in the computing equipment of a desktop computer, a notebook computer, a palm computer or a cloud data center.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202210762813.9A CN114817273B (en) | 2022-07-01 | 2022-07-01 | Data identification method and system for high-frequency man-vehicle association abnormity |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202210762813.9A CN114817273B (en) | 2022-07-01 | 2022-07-01 | Data identification method and system for high-frequency man-vehicle association abnormity |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN114817273A true CN114817273A (en) | 2022-07-29 |
| CN114817273B CN114817273B (en) | 2022-09-27 |
Family
ID=82522785
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202210762813.9A Active CN114817273B (en) | 2022-07-01 | 2022-07-01 | Data identification method and system for high-frequency man-vehicle association abnormity |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN114817273B (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN115439938A (en) * | 2022-09-09 | 2022-12-06 | 湖南智警公共安全技术研究院有限公司 | Anti-splitting face archive data merging processing method and system |
Citations (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN105701123A (en) * | 2014-11-27 | 2016-06-22 | 阿里巴巴集团控股有限公司 | Passenger-vehicle relationship identification method and apparatus |
| CN106205143A (en) * | 2016-08-29 | 2016-12-07 | 苏州金螳螂怡和科技有限公司 | Intelligent bayonet networked system |
| CN106803933A (en) * | 2017-02-22 | 2017-06-06 | 成都华安视讯科技有限公司 | Can be used for the camera system and image capture method of the unification monitoring of people's car |
| CN111144727A (en) * | 2019-12-18 | 2020-05-12 | 东南大学 | Urban rail transit arrival passenger flow toughness evaluation system and method |
| EP3660716A1 (en) * | 2018-11-30 | 2020-06-03 | Ovh | Service infrastructure and methods of predicting and detecting potential anomalies at the service infrastructure |
| CN112992298A (en) * | 2021-02-10 | 2021-06-18 | 北京声智科技有限公司 | Abnormity identification method, test tube associated personnel determination method and related equipment |
| CN113506065A (en) * | 2021-07-23 | 2021-10-15 | 拉扎斯网络科技（上海）有限公司 | Distribution track correction method and device |
| AU2021202723A1 (en) * | 2020-05-06 | 2021-11-25 | Ncs Pte. Ltd. | System and method for identifying persons-of-interest |
-
2022
- 2022-07-01 CN CN202210762813.9A patent/CN114817273B/en active Active
Patent Citations (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN105701123A (en) * | 2014-11-27 | 2016-06-22 | 阿里巴巴集团控股有限公司 | Passenger-vehicle relationship identification method and apparatus |
| CN106205143A (en) * | 2016-08-29 | 2016-12-07 | 苏州金螳螂怡和科技有限公司 | Intelligent bayonet networked system |
| CN106803933A (en) * | 2017-02-22 | 2017-06-06 | 成都华安视讯科技有限公司 | Can be used for the camera system and image capture method of the unification monitoring of people's car |
| EP3660716A1 (en) * | 2018-11-30 | 2020-06-03 | Ovh | Service infrastructure and methods of predicting and detecting potential anomalies at the service infrastructure |
| CN111144727A (en) * | 2019-12-18 | 2020-05-12 | 东南大学 | Urban rail transit arrival passenger flow toughness evaluation system and method |
| AU2021202723A1 (en) * | 2020-05-06 | 2021-11-25 | Ncs Pte. Ltd. | System and method for identifying persons-of-interest |
| CN112992298A (en) * | 2021-02-10 | 2021-06-18 | 北京声智科技有限公司 | Abnormity identification method, test tube associated personnel determination method and related equipment |
| CN113506065A (en) * | 2021-07-23 | 2021-10-15 | 拉扎斯网络科技（上海）有限公司 | Distribution track correction method and device |
Non-Patent Citations (1)
| Title |
|---|
| 吴华意等: "出租车轨迹数据挖掘进展", 《测绘学报》 * |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN115439938A (en) * | 2022-09-09 | 2022-12-06 | 湖南智警公共安全技术研究院有限公司 | Anti-splitting face archive data merging processing method and system |
| CN115439938B (en) * | 2022-09-09 | 2023-09-19 | 湖南智警公共安全技术研究院有限公司 | Anti-splitting face archive data merging processing method and system |
Also Published As
| Publication number | Publication date |
|---|---|
| CN114817273B (en) | 2022-09-27 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN107784597B (en) | Travel mode identification method and device, terminal equipment and storage medium | |
| CN110991311B (en) | Target detection method based on dense connection deep network | |
| US8798357B2 (en) | Image-based localization | |
| CN111476826A (en) | Multi-target vehicle tracking method based on SSD target detection | |
| Yan et al. | SeTraStream: semantic-aware trajectory construction over streaming movement data | |
| CN114817273B (en) | Data identification method and system for high-frequency man-vehicle association abnormity | |
| CN110490507B (en) | Method, device and equipment for detecting newly added line of logistics network | |
| CN111289998A (en) | Obstacle detection method, obstacle detection device, storage medium, and vehicle | |
| CN112782743B (en) | Vehicle positioning method and device, computer equipment and storage medium | |
| Belhadi et al. | Hybrid group anomaly detection for sequence data: Application to trajectory data analytics | |
| Li et al. | Robust inferences of travel paths from GPS trajectories | |
| CN112434566A (en) | Passenger flow statistical method and device, electronic equipment and storage medium | |
| Sharma et al. | Vehicle detection in 1‐m resolution satellite and airborne imagery | |
| CN111414933A (en) | Electric vehicle stolen area analysis method and system based on RFID and clustering algorithm | |
| CN110852261B (en) | Target detection method and device, electronic equipment and readable storage medium | |
| CN110502601B (en) | Method and device for searching warehouse | |
| CN116244356A (en) | Abnormal track detection method and device, electronic equipment and storage medium | |
| CN115713769A (en) | Training method and device of text detection model, computer equipment and storage medium | |
| CN112241736A (en) | Text detection method and device | |
| CN116244391A (en) | Method for extracting typical array position of massive track targets | |
| CN114216467A (en) | Road positioning method, device, computer equipment and storage medium | |
| CN114548284A (en) | Freight vehicle accident judgment system, method, equipment and medium | |
| CN114169247A (en) | Method, device and equipment for generating simulated traffic flow and computer readable storage medium | |
| CN113743359A (en) | Vehicle weight recognition method, model training method and related device | |
| CN109612467B (en) | Track simplifying method and system and track visualization system |
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 |