CN110473085B - Vehicle risk discrimination method and device - Google Patents

Vehicle risk discrimination method and device Download PDF

Info

Publication number
CN110473085B
CN110473085B CN201910744263.6A CN201910744263A CN110473085B CN 110473085 B CN110473085 B CN 110473085B CN 201910744263 A CN201910744263 A CN 201910744263A CN 110473085 B CN110473085 B CN 110473085B
Authority
CN
China
Prior art keywords
vehicle
sample
gps data
position information
information
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.)
Active
Application number
CN201910744263.6A
Other languages
Chinese (zh)
Other versions
CN110473085A (en
Inventor
王志刚
朱瑞
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
Ubiai Information Technology Beijing Co ltd
Original Assignee
Ubiai Information Technology Beijing Co ltd
Priority date (The priority date 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 date listed.)
Filing date
Publication date
Application filed by Ubiai Information Technology Beijing Co ltd filed Critical Ubiai Information Technology Beijing Co ltd
Priority to CN201910744263.6A priority Critical patent/CN110473085B/en
Publication of CN110473085A publication Critical patent/CN110473085A/en
Application granted granted Critical
Publication of CN110473085B publication Critical patent/CN110473085B/en
Active legal-status Critical Current
Anticipated expiration legal-status Critical

Links

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
    • G06F16/29—Geographical information databases
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F18/00—Pattern recognition
    • G06F18/20—Analysing
    • G06F18/23—Clustering techniques
    • G06F18/232—Non-hierarchical techniques
    • G06F18/2321—Non-hierarchical techniques using statistics or function optimisation, e.g. modelling of probability density functions
    • G06F18/23213—Non-hierarchical techniques using statistics or function optimisation, e.g. modelling of probability density functions with fixed number of clusters, e.g. K-means clustering
    • 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
    • G06Q40/00—Finance; Insurance; Tax strategies; Processing of corporate or income taxes
    • G06Q40/03—Credit; Loans; Processing thereof

Landscapes

  • Engineering & Computer Science (AREA)
  • Theoretical Computer Science (AREA)
  • Data Mining & Analysis (AREA)
  • Physics & Mathematics (AREA)
  • General Physics & Mathematics (AREA)
  • Business, Economics & Management (AREA)
  • Finance (AREA)
  • General Engineering & Computer Science (AREA)
  • Databases & Information Systems (AREA)
  • Accounting & Taxation (AREA)
  • Evolutionary Computation (AREA)
  • Life Sciences & Earth Sciences (AREA)
  • Bioinformatics & Computational Biology (AREA)
  • Computer Vision & Pattern Recognition (AREA)
  • Evolutionary Biology (AREA)
  • Artificial Intelligence (AREA)
  • Remote Sensing (AREA)
  • Bioinformatics & Cheminformatics (AREA)
  • Probability & Statistics with Applications (AREA)
  • Development Economics (AREA)
  • Economics (AREA)
  • Marketing (AREA)
  • Strategic Management (AREA)
  • Technology Law (AREA)
  • General Business, Economics & Management (AREA)
  • Traffic Control Systems (AREA)

Abstract

The application relates to a vehicle risk discrimination method and a vehicle risk discrimination device, wherein the method comprises the following steps: collecting vehicle running information and preprocessing the vehicle running information; and carrying out risk judgment on the vehicle according to the preprocessed vehicle running information. According to the technical scheme, the position information of the vehicle is monitored in real time, pre-loan risk examination and loan risk early warning are effectively achieved, the property quality of automobile loan is improved, and a new risk control means is provided for modern automobile finance.

Description

Vehicle risk judgment method and device
Technical Field
The application relates to the technical field of automobile financial risk assessment, in particular to a vehicle risk judgment method and device.
Background
The rapid growth of automobile consumption, the youth of consumption subjects and the transformation of consumption concepts lead the automobile financial market in China to continuously grow, the huge market means that the risk control and the post-loan management of automobile finance are more critical, and the traditional automobile financial pneumatic control mode of judging the repayment capability by the central credit investigation of customers cannot meet the requirements of the new era. The development of the intelligent vehicle networking technology provides a technical basis for collecting vehicle state and driving behavior data.
In the related technology, the automobile normal stop points are obtained by utilizing K-means clustering, the start points and the stop points take the city level as a standard but have overlarge ranges, and different clustering results and different accuracy rates can be generated by different clustering centers in consideration of the sensitive factors of a clustering model to vehicle driving information data, so that the inaccuracy of the clustering results is caused, and the judgment of automobile risks is influenced.
Disclosure of Invention
In order to overcome the problem that the clustering result of the automobile constant stopping point does not accurately influence the automobile risk judgment in the related technology at least to a certain extent, the application provides a method and a device for judging the automobile risk.
According to a first aspect of embodiments of the present application, there is provided a vehicle risk discrimination method, including:
collecting vehicle running information and preprocessing the vehicle running information;
and carrying out risk judgment on the vehicle according to the preprocessed vehicle running information.
Preferably, the vehicle travel information includes: ID information of a vehicle owner, GPS data of the vehicle and parking time length data of the vehicle;
the GPS data of the vehicle comprises position information of a plurality of vehicles, and the position information of the vehicle consists of a GPS longitude coordinate of the vehicle and a GPS latitude coordinate of the vehicle;
the parking duration data of the vehicle includes a parking start time of the vehicle, a parking end time of the vehicle, and a parking duration of the vehicle.
Further, the preprocessing the vehicle driving information includes:
a. converting GPS data of the vehicle in the vehicle running information into a terrestrial coordinate system;
b. deleting abnormal values and interpolating missing values of the GPS data of the vehicle converted into the terrestrial coordinate system;
c. normalizing the GPS data of the vehicle subjected to abnormal value deletion and missing value interpolation by using a discrete normalization method to acquire the GPS data of the vehicle to be used;
d. if the parking start time of the vehicle corresponding to the position information of the vehicle in the GPS data of the vehicle to be used is greater than or equal to the parking end time of the vehicle, deleting the position information of the vehicle until the parking start time of the vehicle corresponding to the position information of the vehicle in the GPS data of the vehicle is not greater than or equal to the parking end time of the vehicle, and outputting the GPS data of the vehicle to be used;
and if the parking start time of the vehicle corresponding to the position information of the vehicle does not exist in the GPS data of the standby vehicle is greater than or equal to the parking end time of the vehicle, outputting the GPS data of the standby vehicle.
Specifically, the step c includes:
if the position information of the vehicle does not belong to the threshold value range of the GPS data of the vehicle converted into the terrestrial coordinate system in the GPS data of the vehicle converted into the terrestrial coordinate system, the position information of the vehicle is abnormal, and the position information of the vehicle is deleted;
if the GPS data of the vehicles converted into the terrestrial coordinate system has the position information of the vehicles missing, the mean value of the position information of the front 5 vehicles and the position information of the rear 5 vehicles of the position information of the vehicles is utilized for interpolation.
Further, the risk judgment of the vehicle according to the preprocessed vehicle running information includes:
s1, initializing a clustering radius Eps and a density threshold MinPts, taking the position information of a vehicle in the GPS data of the vehicle to be used as a sample, and dividing the GPS data of the vehicle to be used into K clustering clusters by using a DBSCAN density clustering algorithm;
s2, randomly selecting a sample i from K clustering clusters, and calculating the average distance a from the sample i to other samples except the sample i in the clustering cluster corresponding to the sample ii；
S3, calculating the average distance b from the sample i to all samples in the jth clusteri,jLet the intra-cluster dissimilarity b of the sample ii＝min[bi,1,…,bi,j,…,bi,K]；
S4, utilizing the average distance a from the sample i to other samples except the sample i in the cluster corresponding to the sample iiAnd intra-cluster dissimilarity b of said sample iiAcquiring a contour coefficient s (i) of the sample i;
s5, if the outline coefficient s (i) of the sample i is larger than or equal to 0.6, judging whether the ID information of the vehicle owner is true or not by using the K clustering clusters;
if the profile coefficients s (i) of the i samples are less than 0.6, adjusting the clustering radius Eps and the density threshold value MinPts until the profile coefficients s (i) of the samples i in the K clustering clusters are greater than or equal to 0.6;
wherein i belongs to [1, A ], A is the total number of samples in the kth clustering cluster, j belongs to [1, K ] and j is not equal to K.
Specifically, the step S2 includes:
determining the average distance a from the sample i to other samples except the sample i in the cluster corresponding to the sample i according to the following formulai：
Figure BDA0002165032940000031
In the above formula, l is E [1, A ]]And l is not equal to i, A is the total number of samples in the cluster corresponding to the sample i; di,lAnd the distance from the sample i to the ith sample in the clustering cluster corresponding to the sample i.
Specifically, the step S3 includes:
determining the average distance b from the sample i to all samples in the jth cluster according to the following formulai,j：
Figure BDA0002165032940000041
In the above formula, m is E [1, B ∈]B is the total number of samples in the jth clustering cluster; di,mThe distance from the sample i to the mth sample in the jth cluster is obtained.
Specifically, the step S4 includes:
determining the profile coefficients s (i) of the sample i as follows:
Figure BDA0002165032940000042
specifically, the determining whether the ID information of the vehicle owner is substantial by using the K cluster clusters includes:
if the distances between all samples in the cluster and the driver's residence and working places in the ID information of the vehicle owner are less than or equal to 5 kilometers in the K clusters, the driver's residence and working places in the ID information of the vehicle owner are real;
and if the distance between all the samples in the K clustering clusters and the driver's residence or working place in the ID information of the vehicle owner is not more than 5 kilometers, triggering an abnormal alarm.
According to a second aspect of embodiments of the present application, there is provided a vehicle risk discrimination device including:
the processing unit is used for acquiring vehicle running information and preprocessing the vehicle running information;
and the judging unit is used for judging the risk of the vehicle according to the preprocessed vehicle running information.
The technical scheme provided by the embodiment of the application can have the following beneficial effects: by preprocessing the vehicle driving information and carrying out risk judgment on the vehicle according to the preprocessed vehicle driving information, the real-time monitoring of the position information of the vehicle is realized, the pre-loan risk examination and the loan risk early warning are effectively realized, the business innovation on the automobile finance is realized, the property quality of the automobile loan is improved, and a new risk control means is provided for the modern automobile finance;
according to the method and the device, the GPS data of the vehicle to be used is divided into K cluster clusters by using the DBSCAN density clustering algorithm, so that the dense GPS data in any shape is clustered, sensitive factors of the GPS data of the vehicle are reduced, the accuracy of a clustering result is improved, and the accuracy of automobile risk judgment is also improved.
It is to be understood that both the foregoing general description and the following detailed description are exemplary and explanatory only and are not restrictive of the application.
Drawings
The accompanying drawings, which are incorporated in and constitute a part of this specification, illustrate embodiments consistent with the present application and together with the description, serve to explain the principles of the application.
FIG. 1 is a flow chart illustrating a method of vehicle risk discrimination according to an exemplary embodiment;
FIG. 2 is a visual distribution diagram of a car parking spot shown in accordance with an exemplary embodiment;
fig. 3 is a block diagram showing a vehicle risk discriminating device according to two exemplary embodiments.
Detailed Description
Reference will now be made in detail to the exemplary embodiments, examples of which are illustrated in the accompanying drawings. When the following description refers to the accompanying drawings, like numbers in different drawings represent the same or similar elements unless otherwise indicated. The embodiments described in the following exemplary embodiments do not represent all embodiments consistent with the present application. Rather, they are merely examples of apparatus and methods consistent with certain aspects of the present application, as detailed in the appended claims.
Fig. 1 is a flow chart illustrating a vehicle risk discrimination method according to an exemplary embodiment, and referring to fig. 1, the method includes:
101. collecting vehicle running information and preprocessing the vehicle running information;
102. and carrying out risk judgment on the vehicle according to the preprocessed vehicle running information.
Further, the vehicle travel information includes: ID information of a vehicle owner, GPS data of the vehicle and parking time length data of the vehicle;
the GPS data of the vehicle comprises position information of a plurality of vehicles, and the position information of the vehicle consists of a GPS longitude coordinate of the vehicle and a GPS latitude coordinate of the vehicle;
the parking duration data of the vehicle includes a parking start time of the vehicle, a parking end time of the vehicle, and a parking duration of the vehicle.
Wherein the parking time period t of the vehicle is determined according to the following formula:
t＝t2-t1
in the above formula, t1Is the parking start time, t, of the vehicle2Is the parking end time of the vehicle.
Further, the preprocessing the vehicle driving information in the step 101 includes:
a. converting GPS data of the vehicle in the vehicle running information into a terrestrial coordinate system;
b. deleting abnormal values and interpolating missing values of the GPS data of the vehicle converted into the terrestrial coordinate system;
c. normalizing the GPS data of the vehicle subjected to abnormal value deletion and missing value interpolation by using a discrete normalization method to acquire the GPS data of the vehicle to be used;
d. if the parking start time of the vehicle corresponding to the position information of the vehicle in the GPS data of the vehicle to be used is greater than or equal to the parking end time of the vehicle, deleting the position information of the vehicle until the parking start time of the vehicle corresponding to the position information of the vehicle in the GPS data of the vehicle is not greater than or equal to the parking end time of the vehicle, and outputting the GPS data of the vehicle to be used;
and if the parking start time of the vehicle corresponding to the position information of the vehicle does not exist in the GPS data of the standby vehicle is greater than or equal to the parking end time of the vehicle, outputting the GPS data of the standby vehicle.
Specifically, the step c includes:
if the position information of the vehicle does not belong to the threshold value range of the GPS data of the vehicle converted into the terrestrial coordinate system in the GPS data of the vehicle converted into the terrestrial coordinate system, the position information of the vehicle is abnormal, and the position information of the vehicle is deleted;
if the GPS data of the vehicles converted into the terrestrial coordinate system has the position information of the vehicles missing, the mean value of the position information of the front 5 vehicles and the position information of the rear 5 vehicles of the position information of the vehicles is utilized for interpolation.
Wherein, the mean value E of the position information of the front 5 vehicles and the position information of the rear 5 vehicles of the position information of the vehicle is determined according to the following formula:
Figure BDA0002165032940000071
in the above formula, g is E [1,5 ]]，h∈[1,5]，beforegPosition information of the preceding g vehicles, after, for the position information of the vehiclehPosition information of the next h vehicles which is the position information of the one vehicle.
Specifically, before the step d, the method further includes converting the parking duration data of the vehicle into a time stamp type.
Specifically, after the vehicle driving information is preprocessed, the step 102 includes:
s1, initializing a clustering radius Eps and a density threshold MinPts, taking the position information of a vehicle in the GPS data of the vehicle to be used as a sample, and dividing the GPS data of the vehicle to be used into K clustering clusters by using a DBSCAN density clustering algorithm;
s2, randomly selecting a sample i from K clustering clusters, and calculating the average distance a from the sample i to other samples except the sample i in the clustering cluster corresponding to the sample ii；
S3, calculating the average distance b from the sample i to all samples in the jth clusteri,jLet the intra-cluster dissimilarity b of the sample ii＝min[bi,1,…,bi,j,…,bi,K]；
S4, utilizing the average distance a from the sample i to other samples except the sample i in the cluster corresponding to the sample iiAnd intra-cluster dissimilarity b of said sample iiAcquiring a contour coefficient s (i) of the sample i;
s5, if the outline coefficient s (i) of the sample i is larger than or equal to 0.6, judging whether the ID information of the vehicle owner is true or not by using the K clustering clusters;
if the profile coefficients s (i) of the i samples are less than 0.6, adjusting the clustering radius Eps and the density threshold value MinPts until the profile coefficient of the sample i in the K clustering clusters is greater than or equal to 0.6;
wherein i belongs to [1, A ], A is the total number of samples in the kth clustering cluster, j belongs to [1, K ] and j is not equal to K;
specifically, the adjusting the clustering radius Eps and the density threshold MinPts includes:
reducing the clustering radius Eps and/or increasing the density threshold Minpts according to the actual situation;
wherein, reducing the clustering radius Eps increases the density of each cluster; increasing the density threshold Minpts can deepen the clustering effect of the parking points of each clustering cluster; decreasing the clustering radius Eps and/or increasing the density threshold Minpts will cause aiBecome smaller, biBecomes large so that the contour coefficient s (i) gradually increases.
For example, the position information of the vehicle in the GPS data of the vehicle of the first vehicle owner is clustered, and the visual distribution map of the vehicle parking spot shown in fig. 2 is obtained, where the clustering result is: the longitude and latitude ranges of the automobile stop points of the automobile owner A are 39.00-41.00 and 116.00-116.50 respectively in 4 clustering centers; by passing
The clustering is carried out by adopting the DBSCAN density clustering algorithm, sensitive factors to the data sets can be reduced, any dense data set can be clustered, the map visualization is carried out on the clustering result, the clustering process is refined, the clustering effect of the concentration ratio is optimized, the centralized characteristic of the automobile stop points is effectively described, and the method is an important reference basis for user information auditing.
Specifically, the step S2 includes:
determining the average distance a from the sample i to other samples except the sample i in the cluster corresponding to the sample i according to the following formulai：
Figure BDA0002165032940000081
In the above formula, l is E [1, A ∈]And l is not equal to i, A is the total number of samples in the cluster corresponding to the sample i; di,lAnd the distance from the sample i to the ith sample in the clustering cluster corresponding to the sample i.
Specifically, the step S3 includes:
determining the average distance b from the sample i to all samples in the jth cluster according to the following formulai,j：
Figure BDA0002165032940000082
In the above formula, m is E [1, B ∈]B is the total number of samples in the jth clustering cluster; di,mThe distance from the sample i to the mth sample in the jth cluster is obtained.
Specifically, the step S4 includes:
determining the contour coefficients s (i) of the sample i as follows:
Figure BDA0002165032940000091
specifically, the determining whether the ID information of the vehicle owner is substantial by using the K cluster clusters includes:
if the distances between all samples in the cluster and the driver's residence and working places in the ID information of the vehicle owner are less than or equal to 5 kilometers in the K clusters, the driver's residence and working places in the ID information of the vehicle owner are real;
and if the distance between all the samples in the K clustering clusters and the driver's residence or working place in the ID information of the vehicle owner is not more than 5 kilometers, triggering an abnormal alarm.
If the distance between all samples in the K clustering clusters and the residence or working place of the driver in the ID information of the vehicle owner is not more than 5 kilometers, the residence or working place declared by the vehicle owner is not real, the vehicle owner is classified as a blacklist user of the vehicle loan, and risk warning is carried out, so that pre-loan risk review and in-loan risk early warning are effectively achieved.
According to the vehicle risk judging method, the position information of the vehicle in the GPS data of the vehicle is accurate to the longitude and latitude, and the stopping ending time of the vehicle and the stopping starting time of the vehicle corresponding to the position information of the vehicle in the GPS data of the vehicle to be used are judged, so that the accuracy of a clustering result is improved, and the accuracy of vehicle risk judgment is further improved; the position information of the vehicle in the GPS data of the vehicle to be used is clustered by utilizing a DBSCAN density clustering algorithm, the constant stop point range of the vehicle owner is obtained, the GPS stop point data of the vehicle is periodically replaced in real time, the position information of the vehicle owner can be monitored in real time, pre-loan risk examination and loan risk early warning are effectively achieved, business innovation on vehicle finance is realized, the property quality of vehicle loan is improved, and a new risk control means is provided for modern vehicle finance.
Fig. 3 is a block diagram of a vehicle risk determination device according to two exemplary embodiments. Referring to fig. 3, the apparatus includes:
the processing unit is used for acquiring vehicle running information and preprocessing the vehicle running information;
and the judging unit is used for judging the risk of the vehicle according to the preprocessed vehicle running information.
Further, the vehicle travel information includes: ID information of a vehicle owner, GPS data of the vehicle and parking time length data of the vehicle;
the GPS data of the vehicle comprises position information of a plurality of vehicles, and the position information of the vehicle consists of a GPS longitude coordinate of the vehicle and a GPS latitude coordinate of the vehicle;
the parking duration data of the vehicle includes a parking start time of the vehicle, a parking end time of the vehicle, and a parking duration of the vehicle.
Further, a processing unit comprising:
the conversion module is used for converting GPS data of the vehicle in the vehicle running information into a terrestrial coordinate system;
the optimization module is used for deleting abnormal values and interpolating missing values of the GPS data of the vehicle converted into the terrestrial coordinate system;
the normalization module is used for normalizing the GPS data of the vehicle subjected to abnormal value deletion and missing value interpolation by using a discrete normalization method to acquire the GPS data of the vehicle for standby;
the first judgment module is used for deleting the position information of the vehicle until the starting ending time of the vehicle corresponding to the position information of the vehicle does not exist in the GPS data of the vehicle is greater than or equal to the stopping ending time of the vehicle and outputting the GPS data of the vehicle to be used if the stopping starting time of the vehicle corresponding to the position information of the vehicle in the GPS data of the vehicle to be used is greater than or equal to the stopping ending time of the vehicle; and if the parking start time of the vehicle corresponding to the position information of the vehicle does not exist in the GPS data of the standby vehicle is greater than or equal to the parking end time of the vehicle, outputting the GPS data of the standby vehicle.
Specifically, the normalization module is specifically configured to:
if the position information of the vehicle does not belong to the threshold value range of the GPS data of the vehicle converted into the terrestrial coordinate system in the GPS data of the vehicle converted into the terrestrial coordinate system, the position information of the vehicle is abnormal, and the position information of the vehicle is deleted;
if the GPS data of the vehicles converted into the terrestrial coordinate system has the position information of the vehicles missing, the mean value of the position information of the front 5 vehicles and the position information of the rear 5 vehicles of the position information of the vehicles is utilized for interpolation.
Further, the determination unit includes:
the device comprises an initialization module, a clustering module and a density threshold MinPts module, wherein the initialization module is used for initializing a clustering radius Eps and a density threshold MinPts, taking the position information of a vehicle in the GPS data of the vehicle to be used as a sample, and dividing the GPS data of the vehicle to be used into K clustering clusters by using a DBSCAN density clustering algorithm;
a first calculating module, configured to randomly select a sample i from the K clustering clusters, and calculate an average distance a from the sample i to another sample except the sample i in the clustering cluster corresponding to the sample ii；
A second calculating module for calculating the average distance b from the sample i to all samples in the jth clusteri,jLet the intra-cluster dissimilarity b of the sample ii＝min[bi,1,…,bi,j,…,bi,K]；
An obtaining module, configured to use an average distance a from the sample i to another sample except the sample i in a cluster corresponding to the sample iiAnd intra-cluster dissimilarity b of said sample iiAcquiring a contour coefficient s (i) of the sample i;
a second judging module, configured to judge whether the ID information of the vehicle owner is true by using the K cluster clusters if the contour coefficient s (i) of the sample i is greater than or equal to 0.6; if the profile coefficients s (i) of the i samples are less than 0.6, adjusting the clustering radius Eps and the density threshold value MinPts until the profile coefficients s (i) of the samples i in the K clustering clusters are greater than or equal to 0.6;
wherein i belongs to [1, A ], A is the total number of samples in the kth clustering cluster, j belongs to [1, K ] and j is not equal to K.
Specifically, the first calculating module is specifically configured to determine an average distance a from the sample i to another sample except the sample i in the cluster corresponding to the sample i according to the following formulai：
Figure BDA0002165032940000111
In the above formula, l is E [1, A ∈]And l ≠ i, A is that the sample i corresponds toThe total number of samples in the cluster; di,lAnd the distance from the sample i to the ith sample in the clustering cluster corresponding to the sample i.
Specifically, the second calculating module is specifically configured to determine an average distance b from the sample i to all samples in the jth cluster according to the following formulai,j：
Figure BDA0002165032940000121
In the above formula, m is E [1, B ]]B is the total number of samples in the jth clustering cluster; di,mThe distance from the sample i to the mth sample in the jth cluster is obtained.
Specifically, the obtaining module is specifically configured to determine a contour coefficient s (i) of the sample i according to the following formula:
Figure BDA0002165032940000122
specifically, the second determining module is further configured to:
if the distances between all samples in the cluster and the driver's residence and working places in the ID information of the vehicle owner are less than or equal to 5 kilometers in the K clusters, the driver's residence and working places in the ID information of the vehicle owner are real;
and if the distance between all samples in the K clustering clusters and the residence or working place of the driver in the ID information of the vehicle owner is not more than 5 kilometers, triggering an abnormal alarm.
It is understood that the same or similar parts in the above embodiments may be mutually referred to, and the same or similar parts in other embodiments may be referred to for the content which is not described in detail in some embodiments.
It should be noted that, in the description of the present application, the terms "first", "second", etc. are used for descriptive purposes only and are not to be construed as indicating or implying relative importance. Further, in the description of the present application, the meaning of "a plurality" means at least two unless otherwise specified.
Any process or method descriptions in flow charts or otherwise described herein may be understood as representing modules, segments, or portions of code which include one or more executable instructions for implementing specific logical functions or steps of the process, and the scope of the preferred embodiments of the present application includes other implementations in which functions may be executed out of order from that shown or discussed, including substantially concurrently or in reverse order, depending on the functionality involved, as would be understood by those reasonably skilled in the art of the present application.
It should be understood that portions of the present application may be implemented in hardware, software, firmware, or a combination thereof. In the above embodiments, the various steps or methods may be implemented in software or firmware stored in memory and executed by a suitable instruction execution system. For example, if implemented in hardware, as in another embodiment, any one or combination of the following techniques, which are known in the art, may be used: a discrete logic circuit having a logic gate circuit for implementing a logic function on a data signal, an application specific integrated circuit having an appropriate combinational logic gate circuit, a Programmable Gate Array (PGA), a Field Programmable Gate Array (FPGA), or the like.
It will be understood by those skilled in the art that all or part of the steps carried by the method for implementing the above embodiments may be implemented by hardware related to instructions of a program, which may be stored in a computer readable storage medium, and when the program is executed, the program includes one or a combination of the steps of the method embodiments.
In addition, functional units in the embodiments of the present application may be integrated into one processing module, or each unit may exist alone physically, or two or more units are integrated into one module. The integrated module can be realized in a hardware mode, and can also be realized in a software functional module mode. The integrated module, if implemented in the form of a software functional module and sold or used as a stand-alone product, may also be stored in a computer readable storage medium.
The storage medium mentioned above may be a read-only memory, a magnetic or optical disk, etc.
In the description herein, reference to the description of the term "one embodiment," "some embodiments," "an example," "a specific example," or "some examples," etc., means that a particular feature, structure, material, or characteristic described in connection with the embodiment or example is included in at least one embodiment or example of the application. In this specification, the schematic representations of the terms used above do not necessarily refer to the same embodiment or example. Furthermore, the particular features, structures, materials, or characteristics described may be combined in any suitable manner in any one or more embodiments or examples.
Although embodiments of the present application have been shown and described above, it is understood that the above embodiments are exemplary and should not be construed as limiting the present application, and that variations, modifications, substitutions and alterations may be made to the above embodiments by those of ordinary skill in the art within the scope of the present application.

Claims (7)

1. A vehicle risk discrimination method, characterized by comprising:
collecting vehicle running information and preprocessing the vehicle running information;
carrying out risk judgment on the vehicle according to the preprocessed vehicle running information;
the vehicle travel information includes: ID information of a vehicle owner, GPS data of the vehicle and parking time length data of the vehicle;
the GPS data of the vehicle comprises position information of a plurality of vehicles, and the position information of the vehicle consists of a GPS longitude coordinate of the vehicle and a GPS latitude coordinate of the vehicle;
the parking duration data of the vehicle comprises the parking starting time of the vehicle, the parking ending time of the vehicle and the parking duration of the vehicle;
the preprocessing of the vehicle driving information comprises:
a. converting GPS data of the vehicle in the vehicle running information into a terrestrial coordinate system;
b. deleting abnormal values and interpolating missing values of the GPS data of the vehicle converted into the terrestrial coordinate system;
c. normalizing the GPS data of the vehicle subjected to abnormal value deletion and missing value interpolation by using a discrete normalization method to acquire the GPS data of the vehicle to be used;
d. if the parking start time of the vehicle corresponding to the position information of the vehicle in the GPS data of the vehicle to be used is greater than or equal to the parking end time of the vehicle, deleting the position information of the vehicle until the parking start time of the vehicle corresponding to the position information of the vehicle in the GPS data of the vehicle is not greater than or equal to the parking end time of the vehicle, and outputting the GPS data of the vehicle to be used;
if the parking start time of the vehicle corresponding to the position information of the vehicle does not exist in the GPS data of the vehicle to be used is more than or equal to the parking end time of the vehicle, outputting the GPS data of the vehicle to be used;
the risk judgment of the vehicle according to the preprocessed vehicle running information comprises the following steps:
s1, initializing a clustering radius Eps and a density threshold MinPts, taking the position information of a vehicle in the GPS data of the vehicle to be used as a sample, and dividing the GPS data of the vehicle to be used into K clustering clusters by using a DBSCAN density clustering algorithm;
s2, randomly selecting a sample i from K clustering clusters, and calculating the average distance a from the sample i to other samples except the sample i in the clustering cluster corresponding to the sample ii；
S3, calculating the average distance b from the sample i to all samples in the jth clusteri,jLet the intra-cluster dissimilarity b of the sample ii＝min[bi,1,…,bi,j,…,bi,K]；
S4, utilizing the average distance a from the sample i to other samples except the sample i in the cluster corresponding to the sample iiAnd intra-cluster dissimilarity b of said sample iiAcquiring a contour coefficient s (i) of the sample i;
s5, if the outline coefficient s (i) of the sample i is larger than or equal to 0.6, judging whether the ID information of the vehicle owner is true or not by using the K clustering clusters;
if the profile coefficients s (i) of the i samples are less than 0.6, adjusting the clustering radius Eps and the density threshold value MinPts until the profile coefficients s (i) of the samples i in the K clustering clusters are greater than or equal to 0.6;
wherein i belongs to [1, A ], A is the total number of samples in the kth clustering cluster, j belongs to [1, K ] and j is not equal to K.
2. The method of claim 1, wherein step c comprises:
if the position information of the vehicle does not belong to the threshold value range of the GPS data of the vehicle converted into the terrestrial coordinate system in the GPS data of the vehicle converted into the terrestrial coordinate system, the position information of the vehicle is abnormal, and the position information of the vehicle is deleted;
if the GPS data of the vehicles converted into the terrestrial coordinate system has the position information of the vehicles missing, the mean value of the position information of the front 5 vehicles and the position information of the rear 5 vehicles of the position information of the vehicles is utilized for interpolation.
3. The method according to claim 1, wherein step S2 includes:
determining the average distance a from the sample i to other samples except the sample i in the cluster corresponding to the sample i according to the following formulai：
Figure FDA0003555722460000021
In the above formula, l is E [1, A ∈]And l is not equal to i, A is the total number of samples in the cluster corresponding to the sample i; di,lAnd the distance from the sample i to the ith sample in the clustering cluster corresponding to the sample i.
4. The method according to claim 1, wherein step S3 includes:
determining the samples i toAverage distance b of all samples in jth clusteri,j：
Figure FDA0003555722460000031
In the above formula, m is E [1, B ∈]B is the total number of samples in the jth clustering cluster; di,mThe distance from the sample i to the mth sample in the jth cluster is obtained.
5. The method according to claim 1, wherein step S4 includes:
determining the contour coefficients s (i) of the sample i as follows:
Figure FDA0003555722460000032
6. the method according to claim 1, wherein the determining whether the ID information of the vehicle owner is true by using the K clusters includes:
if the distances between all samples in the cluster and the driver's residence and working places in the ID information of the vehicle owner are less than or equal to 5 kilometers in the K clusters, the driver's residence and working places in the ID information of the vehicle owner are real;
and if the distance between all the samples in the K clustering clusters and the driver's residence or working place in the ID information of the vehicle owner is not more than 5 kilometers, triggering an abnormal alarm.
7. A vehicle risk discrimination device, characterized by comprising:
the processing unit is used for acquiring vehicle running information and preprocessing the vehicle running information;
the judging unit is used for judging the risk of the vehicle according to the preprocessed vehicle running information;
the vehicle travel information includes: ID information of a vehicle owner, GPS data of the vehicle and parking time length data of the vehicle;
the GPS data of the vehicle comprises position information of a plurality of vehicles, and the position information of the vehicle consists of a GPS longitude coordinate of the vehicle and a GPS latitude coordinate of the vehicle;
the parking duration data of the vehicle comprises the parking starting time of the vehicle, the parking ending time of the vehicle and the parking duration of the vehicle;
the processing unit comprises:
the conversion module is used for converting GPS data of the vehicle in the vehicle running information into a terrestrial coordinate system;
the optimization module is used for deleting abnormal values and interpolating missing values of the GPS data of the vehicle converted into the terrestrial coordinate system;
the normalization module is used for normalizing the GPS data of the vehicle subjected to abnormal value deletion and missing value interpolation by using a discrete normalization method to acquire the GPS data of the vehicle for standby;
the first judgment module is used for deleting the position information of the vehicle until the starting ending time of the vehicle corresponding to the position information of the vehicle does not exist in the GPS data of the vehicle is greater than or equal to the stopping ending time of the vehicle and outputting the GPS data of the vehicle to be used if the stopping starting time of the vehicle corresponding to the position information of the vehicle in the GPS data of the vehicle to be used is greater than or equal to the stopping ending time of the vehicle; if the parking start time of the vehicle corresponding to the position information of the vehicle does not exist in the GPS data of the vehicle to be used is more than or equal to the parking end time of the vehicle, outputting the GPS data of the vehicle to be used;
the discrimination unit includes:
the device comprises an initialization module, a clustering module and a density threshold MinPts module, wherein the initialization module is used for initializing a clustering radius Eps and a density threshold MinPts, taking the position information of a vehicle in the GPS data of the vehicle to be used as a sample, and dividing the GPS data of the vehicle to be used into K clustering clusters by using a DBSCAN density clustering algorithm;
a first calculating module, configured to randomly select a sample i from K cluster clusters, and calculate the sample i to a cluster corresponding to the sample iAverage distance a of other samples than sample ii；
A second calculating module for calculating the average distance b from the sample i to all samples in the jth clusteri,jLet the intra-cluster dissimilarity b of the sample ii＝min[bi,1,…,bi,j,…,bi,K]；
An obtaining module, configured to use an average distance a from the sample i to another sample except the sample i in a cluster corresponding to the sample iiAnd the intra-cluster dissimilarity b of the sample iiAcquiring a contour coefficient s (i) of the sample i;
a second judging module, configured to judge whether the ID information of the vehicle owner is true by using the K cluster clusters if the contour coefficient s (i) of the sample i is greater than or equal to 0.6; if the profile coefficients s (i) of the i samples are less than 0.6, adjusting the clustering radius Eps and the density threshold value MinPts until the profile coefficients s (i) of the samples i in the K clustering clusters are greater than or equal to 0.6;
wherein i belongs to [1, A ], A is the total number of samples in the kth clustering cluster, j belongs to [1, K ] and j is not equal to K.
CN201910744263.6A 2019-08-13 2019-08-13 Vehicle risk discrimination method and device Active CN110473085B (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN201910744263.6A CN110473085B (en) 2019-08-13 2019-08-13 Vehicle risk discrimination method and device

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN201910744263.6A CN110473085B (en) 2019-08-13 2019-08-13 Vehicle risk discrimination method and device

Publications (2)

Publication Number Publication Date
CN110473085A CN110473085A (en) 2019-11-19
CN110473085B true CN110473085B (en) 2022-05-10

Family

ID=68511779

Family Applications (1)

Application Number Title Priority Date Filing Date
CN201910744263.6A Active CN110473085B (en) 2019-08-13 2019-08-13 Vehicle risk discrimination method and device

Country Status (1)

Country Link
CN (1) CN110473085B (en)

Families Citing this family (4)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN108492023A (en) * 2018-03-19 2018-09-04 浙江工业大学 A kind of vehicle loan air control method based on trajectory analysis
CN112785055B (en) * 2021-01-18 2024-02-06 优必爱信息技术（北京）有限公司 Method and equipment for predicting vehicle refueling date
CN113423063B (en) * 2021-06-11 2022-10-18 芜湖雄狮汽车科技有限公司 Vehicle monitoring method and device based on vehicle-mounted T-BOX, vehicle and medium
CN113888302A (en) * 2021-08-09 2022-01-04 深圳市麦谷科技有限公司 Risk early warning method and system for automobile financial vehicle loan

Family Cites Families (3)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US10621214B2 (en) * 2015-10-15 2020-04-14 Verizon Patent And Licensing Inc. Systems and methods for database geocoding
CN107301433A (en) * 2017-07-14 2017-10-27 南京华苏科技有限公司 Net based on clustering and discriminant model about car discrimination method and system
CN108492023A (en) * 2018-03-19 2018-09-04 浙江工业大学 A kind of vehicle loan air control method based on trajectory analysis

Also Published As

Publication number Publication date
CN110473085A (en) 2019-11-19

Similar Documents

Publication Publication Date Title
CN110473085B (en) Vehicle risk discrimination method and device
US7283056B2 (en) Method and computer program for identification of inattentiveness by the driver of a vehicle
WO2020107894A1 (en) Driving behavior scoring method and device and computer-readable storage medium
CN110588658A (en) Method for detecting risk level of driver based on comprehensive model
CN112463898B (en) Noise map updating method combining speed and noise monitoring data
CN109635852B (en) User portrait construction and clustering method based on multi-dimensional attributes
CN110562261B (en) Method for detecting risk level of driver based on Markov model
CN111724505A (en) Method and device for constructing driving condition
CN109344903B (en) Urban road pavement fault real-time detection method based on vehicle-mounted sensing data
CN110705628A (en) Method for detecting risk level of driver based on hidden Markov model
CN114419894B (en) Method and system for setting and monitoring parking positions in road
CN113192340B (en) Method, device, equipment and storage medium for identifying highway construction vehicles
CN111775948B (en) Driving behavior analysis method and device
CN114169247A (en) Method, device and equipment for generating simulated traffic flow and computer readable storage medium
CN113221843A (en) Driving style classification method based on empirical mode decomposition characteristics
CN118070154B (en) Driving fatigue judging method and device based on LSTM neural network
CN110827570A (en) Parking space state monitoring method, equipment and system and computer storage medium
CN116499772B (en) Vehicle braking performance evaluation method and device, electronic equipment and storage medium
CN117719524B (en) Driving safety risk identification early warning method, device, terminal and storage medium
CN115273456B (en) Method, system and storage medium for judging illegal running of two-wheeled electric vehicle
US20230048139A1 (en) System and method facilitating determination of automotive signal quality marker
CN118470954A (en) Traffic event detection method for road side millimeter wave radar
CN116702606A (en) Driving behavior risk assessment method, system, equipment and storage medium
CN117669730A (en) Automatic driving evaluation method, device, equipment and medium based on causal inference
CN118439034A (en) Driving style recognition method, driving style recognition device, computer equipment and storage medium

Legal Events

Date Code Title Description
PB01 Publication
PB01 Publication
SE01 Entry into force of request for substantive examination
SE01 Entry into force of request for substantive examination
GR01 Patent grant
GR01 Patent grant