CN114394099A

CN114394099A - Vehicle driving abnormity identification method and device, computer equipment and storage medium

Info

Publication number: CN114394099A
Application number: CN202210059155.7A
Authority: CN
Inventors: 孙振; 司健伟
Original assignee: Ping An International Financial Leasing Co Ltd
Current assignee: Ping An International Financial Leasing Co Ltd
Priority date: 2022-01-19
Filing date: 2022-01-19
Publication date: 2022-04-26
Anticipated expiration: 2042-01-19
Also published as: CN114394099B

Abstract

The invention relates to the technical field of artificial intelligence, and discloses a method and a device for identifying vehicle driving abnormity, computer equipment and a storage medium, wherein the method comprises the following steps: acquiring GPS data of a target vehicle and setting the GPS data as target data; acquiring GPS data of at least one comparison vehicle, setting the GPS data of the comparison vehicle with content similar to the target data as similar data, constructing a mileage travel curve according to the target data and the similar data, identifying the position relationship between the target travel mileage of the target data and the mileage travel curve, and judging whether the position relationship accords with a preset abnormal judgment rule or not; if so, judging that the target vehicle is in a mileage normal driving state; if not, the target vehicle is judged to be in the abnormal mileage running state. The invention realizes the purpose of identifying whether the target vehicle has the abnormal driving condition that the mileage is too short due to poor operation or the vehicle runs for a long distance continuously due to the shortage of the motorcade vehicles in time.

Description

Vehicle driving abnormity identification method and device, computer equipment and storage medium

Technical Field

The invention relates to the technical field of artificial intelligence, in particular to a vehicle driving abnormity identification method and device, computer equipment and a storage medium.

Background

The current vehicle is very complicated in the real driving process, different routes are usually required to be driven due to the current vehicle, or goods are loaded and unloaded at some addresses, and the driving route and the driving time of the vehicle are usually managed and controlled by a mode of acquiring GPS data.

However, the inventors found that if the GPS data of the vehicle is directly analyzed, only the travel route and the travel time period of the vehicle are obtained, but it is not known whether the vehicle appears such as: the abnormal conditions of the vehicle such as too short mileage due to poor operation in the month or long-distance continuous running of the vehicle due to shortage of the vehicle in the fleet are caused, so that the running abnormality of the vehicle cannot be identified in time.

Disclosure of Invention

The invention aims to provide a vehicle driving abnormity identification method, a vehicle driving abnormity identification device, a computer device and a storage medium, which are used for solving the problem that in the prior art, only a driving route and driving time of a vehicle are obtained, but the driving abnormity of the vehicle cannot be obtained.

In order to achieve the above object, the present invention provides a vehicle driving abnormality recognition method including:

acquiring GPS data of a target vehicle and setting the GPS data as target data; wherein, the GPS data is recorded with the position coordinates of the vehicle at each time point in the driving path;

acquiring GPS data of at least one comparison vehicle, and setting the GPS data of the comparison vehicle with similar content to the target data as similar data;

constructing a mileage travel curve according to the target data and the similar data, wherein the mileage travel curve represents the target mileage of the target vehicle and the distribution rule of the similar mileage of the comparison vehicle corresponding to the similar data;

identifying the position relation between the target driving mileage of the target data and the mileage driving curve, and judging whether the position relation accords with a preset abnormal judgment rule; if so, judging that the target vehicle is in a mileage normal driving state; if not, the target vehicle is judged to be in the abnormal mileage running state.

In the foregoing solution, before the acquiring the GPS data of at least one comparison vehicle, the method further includes:

and acquiring GPS data of at least one other vehicle, setting the GPS data of the other vehicle with a start point coordinate and an end point coordinate consistent with the target data as comparison data, and setting the other vehicle corresponding to the comparison data as a comparison vehicle, wherein the start point coordinate is a position coordinate representing a start point of a driving path in the GPS data, and the end point coordinate is a position coordinate representing an end point of the driving path in the GPS data.

In the foregoing aspect, the setting the GPS data of the comparison vehicle having the content similar to the target data as similar data includes:

extracting a time point in the target data and a position coordinate corresponding to the time point to obtain a target driving feature;

identifying target starting time in the target data, and setting position coordinates corresponding to the target starting time in the target data as target starting characteristics; identifying target termination time in the target data, and setting position coordinates corresponding to the target termination time in the target data as target termination characteristics;

extracting a plurality of target driving features from target data, and performing clustering operation on the plurality of target driving features, the target starting feature and the target ending feature to obtain at least one target clustering point;

extracting a time point in the GPS data of the comparison vehicle and a position coordinate corresponding to the time point to obtain a comparison driving characteristic;

identifying a comparison starting time in the GPS data of the comparison vehicle, and setting a position coordinate corresponding to the comparison starting time in the GPS data of the comparison vehicle as a comparison starting feature; identifying comparison ending time in the GPS data of the comparison vehicle, and setting position coordinates corresponding to the comparison ending time in the GPS data of the comparison vehicle as comparison ending characteristics;

extracting a plurality of comparison driving features from the GPS data of the comparison vehicle, and carrying out clustering operation on the plurality of comparison driving features, the comparison starting feature and the comparison ending feature to obtain at least one comparison clustering point;

calculating a comparison variance value between the target clustering point and the comparison clustering point; and if the comparison variance value is smaller than a preset similarity threshold value, judging that the comparison vehicle is similar to the target vehicle, and setting the GPS data of the comparison vehicle as similar data.

In the foregoing aspect, after setting the GPS data of the comparison vehicle having the content similar to the target data as similar data, the method further includes:

summarizing the comparison vehicles corresponding to the similar data and the target vehicle to obtain a similar train set, and storing the similar train set in a preset similar database;

uploading the similar train sets in the similar database to a block chain.

In the foregoing solution, the constructing a mileage travel curve according to the target data and the similar data includes:

calculating the target mileage of the target data according to the target starting characteristic and the target ending characteristic of the target data, and calculating the target unit mileage of the target mileage according to the preset partition granularity;

calculating similar driving mileage of the similar data according to similar starting features and similar ending features of the similar data, and calculating similar unit mileage of the similar driving mileage according to preset partition granularity;

and constructing a normal distribution curve according to the target unit mileage and the similar unit mileage to serve as the mileage travel curve.

constructing a duration driving curve according to the target data and the similar data, wherein the duration driving curve represents the target driving duration of the target vehicle and the distribution rule of the similar driving durations of the comparison vehicles corresponding to the similar data;

identifying the position relation between the target driving duration of the target data and the duration driving curve, and judging whether the position relation accords with a preset abnormity judgment rule or not; if so, judging that the target vehicle is in a time length normal driving state; if not, determining that the target vehicle is in a time length abnormal driving state.

In the foregoing solution, the constructing a long-term driving curve according to the target data and the similar data includes:

identifying the time length of the position coordinates in the target data in a continuous moving state, setting the time length as a target running time length, calculating the target running time length of the target data, and calculating the target unit time length of the target running time length according to preset partition granularity;

identifying the time length of the position coordinates in the similar data in a continuous moving state, setting the time length as the similar running time length, calculating the similar running time length of the similar data, and calculating the similar unit time length of the similar running time length according to the preset division granularity;

and constructing a normal distribution curve according to the target unit time length and the similar unit time length to serve as the time length driving curve.

In order to achieve the above object, the present invention also provides a vehicle driving abnormality recognition device including:

the target input module is used for acquiring GPS data of a target vehicle and setting the GPS data as target data; wherein, the GPS data is recorded with the position coordinates of the vehicle at each time point in the driving path;

the similar identification module is used for acquiring GPS data of at least one comparison vehicle and setting the GPS data of the comparison vehicle with similar content to the target data as similar data;

the mileage curve construction module is used for constructing a mileage driving curve according to the target data and the similar data, wherein the mileage driving curve represents the target mileage of the target vehicle and the distribution rule of the similar mileage of the comparison vehicle corresponding to the similar data;

the mileage abnormity identification module is used for identifying the position relation between the target driving mileage of the target data and the mileage driving curve and judging whether the position relation accords with a preset abnormity judgment rule or not; if so, judging that the target vehicle is in a mileage normal driving state; if not, the target vehicle is judged to be in the abnormal mileage running state.

In order to achieve the above object, the present invention further provides a computer device, which includes a memory, a processor, and a computer program stored on the memory and executable on the processor, wherein the processor of the computer device implements the steps of the above vehicle driving abnormality identification method when executing the computer program.

In order to achieve the above object, the present invention further provides a computer-readable storage medium having a computer program stored thereon, wherein the computer program stored in the computer-readable storage medium realizes the steps of the above vehicle driving abnormality identification method when being executed by a processor.

According to the vehicle driving abnormity identification method, the vehicle driving abnormity identification device, the computer equipment and the storage medium, the similar vehicle similar to the target vehicle is obtained, and the GPS data of the target vehicle is compared with the GPS data of the similar vehicle, so that whether the abnormal driving condition that the target vehicle has too short mileage due to poor operation or the vehicle runs continuously in a long distance due to vehicle shortage of a fleet is identified in time, and the problem that the abnormal condition of the target vehicle cannot be identified due to the fact that the GPS data of the target vehicle is directly analyzed at present is avoided.

Drawings

FIG. 1 is a flowchart illustrating a first embodiment of a method for identifying abnormal driving conditions of a vehicle according to the present invention;

FIG. 2 is a schematic diagram of an environmental application of a vehicle driving abnormality recognition method according to a second embodiment of the vehicle driving abnormality recognition method of the present invention;

FIG. 3 is a flowchart of a method for identifying vehicle driving abnormality according to a second embodiment of the method for identifying vehicle driving abnormality of the present invention;

FIG. 4 is a schematic diagram showing program modules of a third embodiment of the vehicle driving abnormality recognition apparatus according to the present invention;

fig. 5 is a schematic diagram of a hardware structure of a computer device according to a fourth embodiment of the present invention.

Detailed Description

In order to make the objects, technical solutions and advantages of the present invention more apparent, the present invention is described in further detail below with reference to the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are merely illustrative of the invention and are not intended to limit the invention. All other embodiments, which can be derived by a person skilled in the art from the embodiments given herein without making any creative effort, shall fall within the protection scope of the present invention.

The invention provides a vehicle driving abnormity identification method, a vehicle driving abnormity identification device, computer equipment and a storage medium, which are suitable for the technical field of artificial intelligence and are used for providing a vehicle driving abnormity identification method based on a target input module, a similar identification module, a mileage curve construction module and a mileage abnormity identification module. The method comprises the steps of acquiring GPS data of at least one comparison vehicle by acquiring the GPS data of a target vehicle and setting the GPS data as target data, and setting the GPS data of the comparison vehicle with similar content to the target data as similar data; constructing a mileage driving curve according to the target data and the similar data; identifying the position relation between the target driving mileage of the target data and the mileage driving curve, and judging whether the position relation accords with a preset abnormal judgment rule; if so, judging that the target vehicle is in a mileage normal driving state; if not, the target vehicle is judged to be in the abnormal mileage running state.

The first embodiment is as follows:

referring to fig. 1, a method for identifying a vehicle driving abnormality in the present embodiment includes:

s101: acquiring GPS data of a target vehicle and setting the GPS data as target data; wherein, the GPS data is recorded with the position coordinates of the vehicle at each time point in the driving path;

s103: acquiring GPS data of at least one comparison vehicle, and setting the GPS data of the comparison vehicle with similar content to the target data as similar data;

s105: constructing a mileage travel curve according to the target data and the similar data, wherein the mileage travel curve represents the target mileage of the target vehicle and the distribution rule of the similar mileage of the comparison vehicle corresponding to the similar data;

s107: identifying the position relation between the target driving mileage of the target data and the mileage driving curve, and judging whether the position relation accords with a preset abnormal judgment rule; if so, judging that the target vehicle is in a mileage normal driving state; if not, the target vehicle is judged to be in the abnormal mileage running state.

In an exemplary embodiment, the GPS data of the target vehicle within one month may be extracted to track the travel route of the target vehicle within one month. The GPS data refers to a Global Positioning System (GPS), which is a Positioning System for high-precision radio navigation based on artificial earth satellites, and can provide accurate geographic position, vehicle speed, and time information anywhere in the world and in the near-earth space.

Since even if the driving routes of other vehicles with the same start coordinates and end coordinates are different from the driving route of the target vehicle, the driving routes of other vehicles may not have similar comparison values, so that the step ensures that the driving routes of the target vehicle and the comparison vehicle for performing similarity comparison with the target vehicle are similar by acquiring the GPS data of at least one comparison vehicle and setting the GPS data of the comparison vehicle with the content similar to the target data as similar data, thereby ensuring the accuracy of subsequent target vehicle abnormality identification.

And representing the driving mileage of the target vehicle and the purpose of comparing the distribution rule of the driving mileage of the vehicle corresponding to the similar data by constructing a mileage driving curve reflecting the mathematical relationship between the target data and the similar data.

In order to identify the similarity degree between the target mileage of the target vehicle and similar mileage of other similar vehicles and further deduce the technical effect of whether the target vehicle is abnormal or not, the step identifies the target mileage of the target data and the position of the target mileage on a normal distribution curve corresponding to the mileage travel curve; if the position of the target driving mileage on the normal distribution curve is within the probability threshold range in the abnormal judgment rule, judging that the target vehicle is in a mileage normal driving state; if the position of the target driving mileage on the normal distribution curve is out of the probability threshold range in the abnormality determination rule, determining that the target vehicle has an abnormal mileage state, for example: according to the mathematical expectation of normal distribution, the probability that the vehicle operation mileage is [ mu-2 sigma, mu +2 sigma ] is 95.44%, 95.44% is set as the probability threshold range, and when the vehicle daily average mileage exceeds the range, the vehicle abnormal risk is warned.

In conclusion, the similar vehicles similar to the target vehicle are obtained, and the GPS data of the target vehicle and the GPS data of the similar vehicles are compared, so that whether the target vehicle has an abnormal driving condition that the mileage is too short due to poor operation or the vehicle continuously drives for a long distance due to shortage of the motorcade vehicles or not is timely identified, and the problem that the abnormal condition of the target vehicle cannot be identified due to the fact that the GPS data of the target vehicle is directly analyzed at present is avoided.

In fig. 1, the S107 is shown with the following labels:

s107-1: identifying a positional relationship between a target driving range of the target data and the range driving curve;

s107-2: judging whether the position relation accords with a preset abnormity judgment rule or not;

s107-3: if so, judging that the target vehicle is in a mileage normal driving state;

s107-4: if not, the target vehicle is judged to be in the abnormal mileage running state.

Example two:

the embodiment is a specific application scenario of the first embodiment, and the method provided by the present invention can be more clearly and specifically explained through the embodiment.

The method provided by the present embodiment will be specifically described below by taking, as an example, a server running a vehicle abnormal-driving recognition method, acquiring a comparison vehicle with GPS data content similar to that of the target vehicle, and constructing a mileage driving curve according to the GPS data of the target vehicle and the similar vehicle to recognize an abnormal driving state of the target vehicle. It should be noted that the present embodiment is only exemplary, and does not limit the protection scope of the embodiments of the present invention.

Fig. 2 schematically shows an environment application diagram of the vehicle driving abnormality identification method according to the second embodiment of the present application.

In the exemplary embodiment, the server 2 in which the vehicle driving abnormality recognition method is located is connected to one target vehicle 3 and at least one other vehicle 4, respectively, through a network; the server 2 may provide services through one or more networks, which may include various network devices, such as routers, switches, multiplexers, hubs, modems, bridges, repeaters, firewalls, proxy devices, and/or the like. The network may include physical links, such as coaxial cable links, twisted pair cable links, fiber optic links, combinations thereof, and/or the like. The network may include wireless links, such as cellular links, satellite links, Wi-Fi links, and/or the like; it should be noted that the GPS device of the target vehicle 3 is connected to the network to acquire the GPS data of the target vehicle 3, and the GPS device of the other vehicle 4 is connected to acquire the GPS data of the other vehicle 4.

Fig. 3 is a flowchart of a specific method of a method for identifying a vehicle driving abnormality according to an embodiment of the present invention, where the method specifically includes steps S201 to S208.

S201: acquiring GPS data of a target vehicle and setting the GPS data as target data; wherein, the GPS data is recorded with the position coordinates of the vehicle at each time point in the driving path;

in this step, the GPS data of the target vehicle within one month may be extracted to track the travel route of the target vehicle within one month. The GPS data refers to a Global Positioning System (GPS), which is a Positioning System for high-precision radio navigation based on artificial earth satellites, and can provide accurate geographic position, vehicle speed, and time information anywhere in the world and in the near-earth space.

S202: and acquiring GPS data of at least one other vehicle, setting the GPS data of the other vehicle with a start point coordinate and an end point coordinate consistent with the target data as comparison data, and setting the other vehicle corresponding to the comparison data as a comparison vehicle, wherein the start point coordinate is a position coordinate representing a start point of a driving path in the GPS data, and the end point coordinate is a position coordinate representing an end point of the driving path in the GPS data.

In this step, the GPS data of other vehicles in the same month corresponding to the target vehicle may be extracted to track the driving route of the target vehicle in the month. The GPS data refers to a Global Positioning System (GPS), which is a Positioning System for high-precision radio navigation based on artificial earth satellites, and can provide accurate geographic position, vehicle speed, and time information anywhere in the world and in the near-earth space.

S203: and acquiring GPS data of at least one comparison vehicle, and setting the GPS data of the comparison vehicle with similar content to the target data as similar data.

In a preferred embodiment, the setting the GPS data of the comparison vehicle having the content similar to the target data as the similar data includes:

s31: extracting a time point in the target data and a position coordinate corresponding to the time point to obtain a target driving feature;

specifically, the extracting a time point in the target data and a position coordinate corresponding to the time point to obtain a target driving feature includes:

s311: and calculating the running time of the target vehicle according to the target starting time and the target ending time in the target data, wherein the target starting time is a time point representing that the target vehicle is at the starting point of a running path in the target data, and the ending time is a time point representing that the target vehicle is at the ending point of the running path in the target data.

S312: segmenting the running time according to a preset segmentation number to obtain a plurality of equidistant running time periods and segmentation points corresponding to the segmentation number, and setting time points corresponding to the segmentation points in the target data as segmentation time points;

s313: and setting a position coordinate corresponding to a segmentation time point in the target data as a driving feature.

S32: identifying target starting time in the target data, and setting position coordinates corresponding to the target starting time in the target data as target starting characteristics; identifying target termination time in the target data, and setting position coordinates corresponding to the target termination time in the target data as target termination characteristics;

s33: extracting a plurality of target driving features from target data, and performing clustering operation on the plurality of target driving features, the target starting feature and the target ending feature to obtain at least one target clustering point.

In this step, a k-means clustering algorithm is driven in the clustering model.

Specifically, the performing a clustering operation on the plurality of target driving features, the target start feature, and the target end feature to obtain at least one target clustering point includes:

s331: setting the target driving features with consistent position coordinates in the plurality of target driving features as pause features, and integrating the pause features with consistent position coordinates to form a pause set;

s332: performing descending arrangement on the pause sets according to the number of pause features to obtain pause sequences;

s333: sequentially extracting pause sets from the head of the pause sequence according to a preset pause number, setting the extracted pause sets as pause sets, and setting position coordinates in the pause sets as pause features;

s334: and recording the plurality of target driving features, the target starting features and the target ending features into the clustering model, and driving the clustering model to obtain at least one target clustering point for the plurality of target driving features, the target starting features and the target ending features by taking the target starting features, the target ending features and the stopping features corresponding to the stopping number as initial central points of the clustering model.

S34: extracting a time point in the GPS data of the comparison vehicle and a position coordinate corresponding to the time point to obtain a comparison driving characteristic;

specifically, the extracting a time point in the GPS data of the comparison vehicle and a position coordinate corresponding to the time point to obtain a comparison driving feature includes:

s341: and calculating the running time of the target vehicle according to the comparison starting time and the comparison ending time in the GPS data of the comparison vehicle, wherein the comparison starting time refers to a time point when the target vehicle is represented at the starting point of the running path in the GPS data of the comparison vehicle, and the end time refers to a time point when the target vehicle is represented at the end point of the running path in the GPS data of the comparison vehicle.

S342: segmenting the running time according to preset segmentation quantity to obtain a plurality of equidistant running time periods and segmentation points corresponding to the segmentation quantity, and setting time points corresponding to the segmentation points in the GPS data of the comparison vehicle as segmentation time points;

s343: and setting a position coordinate corresponding to a segmentation time point in the GPS data of the comparison vehicle as a driving characteristic.

S35: identifying a comparison starting time in the GPS data of the comparison vehicle, and setting a position coordinate corresponding to the comparison starting time in the GPS data of the comparison vehicle as a comparison starting feature; identifying comparison ending time in the GPS data of the comparison vehicle, and setting position coordinates corresponding to the comparison ending time in the GPS data of the comparison vehicle as comparison ending characteristics;

s36: and extracting a plurality of comparison driving characteristics from the GPS data of the comparison vehicle, and carrying out clustering operation on the plurality of comparison driving characteristics, the comparison starting characteristics and the comparison ending characteristics to obtain at least one comparison clustering point.

In this step, a k-means clustering algorithm is driven in the clustering model.

Specifically, the performing a clustering operation on the plurality of comparison driving features, the comparison starting feature, and the comparison ending feature to obtain at least one comparison clustering point includes:

s361: setting the comparison driving features with consistent position coordinates in the plurality of comparison driving features as pause features, and integrating the pause features with consistent position coordinates to form a pause set;

s362: performing descending arrangement on the pause sets according to the number of pause features to obtain pause sequences;

s363: sequentially extracting pause sets from the head of the pause sequence according to a preset pause number, setting the extracted pause sets as pause sets, and setting position coordinates in the pause sets as pause features;

s364: and recording the plurality of comparison driving characteristics, the comparison starting characteristics and the comparison ending characteristics into the clustering model, and driving the clustering model to obtain at least one comparison clustering point for the plurality of comparison driving characteristics, the comparison starting characteristics and the comparison ending characteristics by taking the comparison starting characteristics, the comparison ending characteristics and the stop characteristics corresponding to the stop quantity as initial central points of the clustering model.

S37: calculating a comparison variance value between the target clustering point and the comparison clustering point; and if the comparison variance value is smaller than a preset similarity threshold value, judging that the comparison vehicle is similar to the target vehicle, and setting the GPS data of the comparison vehicle as similar data.

In this step, the target cluster point and the comparison cluster point are subtracted to obtain a difference value, and the square of the difference value is calculated to obtain the comparison variance value.

If the number of the target clustering points and the number of the comparison clustering points are multiple, sequencing according to the sequence of the target clustering points on a driving path in target data to obtain a target sequence, and sequencing according to the sequence of the comparison clustering points on the driving path in GPS data of a comparison vehicle to obtain a comparison sequence; and corresponding the target clustering points in the target sequence to the comparison clustering points in the comparison sequence one by one, subtracting the target clustering points in the comparison sequence in sequence to obtain a plurality of difference values, and summing the plurality of difference values after sequentially squaring to obtain the comparison variance value.

It should be noted that, if the target data and the GPS data of the comparison vehicle are directly compared one by one, not only is the amount of computational effort consumed large, but also it is difficult to find similar data having a similarity with the target data.

Therefore, in the embodiment, the starting point feature, the end point feature and the stopping feature are used as the initial clustering center points, and clustering operation is performed to obtain the target key nodes capable of reflecting the driving route corresponding to the target data and the comparison key nodes capable of reflecting the driving route corresponding to the GPS data of the comparison vehicle; therefore, a route similar to the driving route corresponding to the target data can be obtained by only comparing the target key node with the comparison key node, and the GPS data of the comparison vehicle corresponding to the similar route is set as the similar data.

S204: and summarizing the comparison vehicle corresponding to the similar data and the target vehicle to obtain a similar train set, and storing the similar train set in a preset similar database.

In the step, similar vehicle groups are obtained by summarizing the comparison vehicles corresponding to the similar data and the target vehicle, and the similar vehicle groups are stored in a preset similar database so as to be convenient for subsequent retrieval and used for carrying out abnormal identification on the running state of the target vehicle.

And further uploading the similar train sets in the similar database to a block chain.

It should be noted that the corresponding summary information is obtained based on the similar train groups, and specifically, the summary information is obtained by hashing the similar train groups, for example, by using the sha256s algorithm. Uploading summary information to the blockchain can ensure the safety and the fair transparency of the user. The user device may download the summary information from the blockchain to verify that a similar consist has been tampered with. The blockchain referred to in this example is a novel application mode of computer technologies such as distributed data storage, point-to-point transmission, consensus mechanism, encryption algorithm, and the like. A block chain (Blockchain), which is essentially a decentralized database, is a series of data blocks associated by using a cryptographic method, and each data block contains information of a batch of network transactions, so as to verify the validity (anti-counterfeiting) of the information and generate a next block. The blockchain may include a blockchain underlying platform, a platform product service layer, an application service layer, and the like.

S205: and constructing a mileage travel curve according to the target data and the similar data, wherein the mileage travel curve represents the target mileage of the target vehicle and the distribution rule of the similar mileage of the comparison vehicle corresponding to the similar data.

In the step, the purpose of representing the travel mileage of the target vehicle and the purpose of comparing the distribution rule of the travel mileage of the vehicle corresponding to the similar data is achieved by constructing a mileage travel curve reflecting the mathematical relationship between the target data and the similar data.

In a preferred embodiment, the constructing a mileage travel curve based on the target data and the similar data includes:

s51: calculating the target mileage of the target data according to the target starting characteristic and the target ending characteristic of the target data, and calculating the target unit mileage of the target mileage according to the preset partition granularity;

s52: calculating similar driving mileage of the similar data according to similar starting features and similar ending features of the similar data, and calculating similar unit mileage of the similar driving mileage according to preset partition granularity;

s53: and constructing a normal distribution curve according to the target unit mileage and the similar unit mileage to serve as the mileage travel curve.

Because the vehicle can shift and rest, if the target data and the similar data are directly compared, the shift and rest conditions of the vehicle can be easily identified as abnormal conditions; however, if the time for shift and shift is too long, it is also predicted that the vehicle is abnormal, therefore, the target mileage and the similar mileage are divided into the target mileage unit and the similar mileage unit by the division granularity (e.g. dividing into weeks, days, hours, etc.) to cover the situation that the mileage is not generated during normal shift/shift, and the situation that the vehicle is too long during shift/shift or abnormal driving is shown by the normal distribution curve, for example: the vehicle is in a situation that the mileage is too short due to poor operation in the month or the vehicle runs for a long distance due to shortage of the fleet vehicles.

Exemplarily, assuming that the number of similar vehicles is 9, dividing GPS data of one target vehicle and 9 similar vehicles into one group, i.e. dividing 1 target data and 9 similar data into one group;

calculating a target mileage of the target data, and calculating a target unit mileage of the target mileage, that is: target daily average mileage;

calculating similar driving mileage of the similar data, and calculating similar unit mileage of the similar driving mileage, namely: the similar daily average mileage.

Calculating the sum of a target daily average driving mileage and nine similar daily average driving miles, dividing the sum by 10 to obtain an average driving mileage mu, obtaining a daily mileage variance sigma 2 according to the average driving mileage mu, the target daily average driving mileage and the nine similar daily average driving miles, and constructing a normal distribution curve according to the average driving mileage and the daily mileage variance.

Optionally, the calculating the similar driving range of the similar data according to the similar starting feature and the similar ending feature of the similar data includes:

s54: and calculating the mileage average number of the target unit mileage and the similar unit mileage, and constructing a mileage mean value curve according to the mileage average number.

S206: and constructing a duration driving curve according to the target data and the similar data, wherein the duration driving curve represents the target driving duration of the target vehicle and the distribution rule of the similar driving durations of the comparison vehicles corresponding to the similar data.

In the step, the purpose of representing the running time of the target vehicle and the purpose of comparing the distribution rule of the running time of the vehicle corresponding to the similar data is achieved by constructing a time length running curve reflecting the mathematical relationship between the target data and the similar data.

In a preferred embodiment, said constructing a long travel curve based on said target data and said similar data comprises:

s61: identifying the time length of the position coordinates in the target data in a continuous moving state, setting the time length as a target running time length, calculating the target running time length of the target data, and calculating the target unit time length of the target running time length according to preset partition granularity;

s62: identifying the time length of the position coordinates in the similar data in a continuous moving state, setting the time length as the similar running time length, calculating the similar running time length of the similar data, and calculating the similar unit time length of the similar running time length according to the preset division granularity;

s63: and constructing a normal distribution curve according to the target unit time length and the similar unit time length to serve as the time length driving curve.

Because the vehicle can shift and rest, if the target data and the similar data are directly compared, the shift and rest conditions of the vehicle can be easily identified as abnormal conditions; however, if the time for shift and shift is too long, it is also predicted that the vehicle is abnormal, so the target running time and the similar running time are divided into the target unit time and the similar unit time by the division granularity (e.g. dividing into week, day, hour, etc.) to cover the situation that the running time is not generated when the vehicle is normally shifted/shifted, and the situation that the vehicle is shifted/shifted too long or abnormal running is shown by the normal distribution curve, for example: the vehicle is driven for a long distance in the month because of poor operation or because of a shortage of fleet vehicles.

calculating a target travel time length of the target data, and calculating a target unit time length of the target travel time length, that is: a target average daily driving duration;

calculating the similar driving time length of the similar data, and calculating the similar unit time length of the similar driving time length, namely: similar average daily driving time.

Calculating the sum of a target daily average running time and nine similar daily average running times, dividing the sum by 10 to obtain an average running time mu, obtaining a daily time variance sigma 2 according to the average running time mu, the target daily average running time and the nine similar daily average running times, and constructing a normal distribution curve according to the average running time and the daily time variance.

Optionally, the calculating a similar driving time length of the similar data according to the similar starting feature and the similar ending feature of the similar data includes:

s64: and calculating the average time length of the target unit time length and the similar unit time length, and constructing a time length mean value curve according to the average time length.

S207: identifying the position relation between the target driving mileage of the target data and the mileage driving curve, and judging whether the position relation accords with a preset abnormal judgment rule; if so, judging that the target vehicle is in a mileage normal driving state; if not, the target vehicle is judged to be in the abnormal mileage running state.

Optionally, calculating a variance value between the target unit time length and a mean corresponding to the mileage mean curve, and determining whether the variance value exceeds a preset mean variance threshold; if so, judging that the target vehicle is in a mileage normal driving state; if not, the target vehicle is judged to be in the abnormal mileage running state.

In fig. 3, the S207 is shown by using the following labels:

s207-1: identifying a positional relationship between a target driving range of the target data and the range driving curve;

s207-2: judging whether the position relation accords with a preset abnormity judgment rule or not;

s207-3: if so, judging that the target vehicle is in a mileage normal driving state;

s207-4: if not, the target vehicle is judged to be in the abnormal mileage running state.

S208: identifying the position relation between the target driving duration of the target data and the duration driving curve, and judging whether the position relation accords with a preset abnormity judgment rule or not; if so, judging that the target vehicle is in a time length normal driving state; if not, determining that the target vehicle is in a time length abnormal driving state.

In order to identify the similarity degree between the target running time of the target vehicle and the similar running times of other similar vehicles and further deduce the technical effect of whether the target vehicle is abnormal or not, the step identifies the target running time of the target data and the position of the target running time on a normal distribution curve corresponding to the running curve of the time; if the position of the target running time on the normal distribution curve is within the probability threshold range in the abnormity judgment rule, judging that the target vehicle is in a time length normal running state; if the position of the target running time length on the normal distribution curve is out of the probability threshold range in the abnormity determination rule, determining that the time length of the target vehicle is in an abnormal running state, for example: according to the mathematical expectation of normal distribution, the probability that the vehicle operation time length is [ mu-2 sigma, mu +2 sigma ] is 95.44%, 95.44% is set as the probability threshold range, and when the vehicle daily average time length exceeds the range, the vehicle abnormal risk is warned.

Optionally, calculating a variance value of the target unit time length and a mean corresponding to the time length mean curve, and judging whether the variance value exceeds a preset mean variance threshold; if so, judging that the target vehicle is in a time length normal driving state; if not, determining that the target vehicle is in a time length abnormal driving state.

In fig. 3, the step S208 is shown as follows:

s208-1: identifying a positional relationship between a target travel duration of the target data and the duration travel curve;

s208-2: judging whether the position relation accords with a preset abnormity judgment rule or not;

s208-3: if so, judging that the target vehicle is in a time length normal driving state;

s208-4: if not, determining that the target vehicle is in a time length abnormal driving state.

Example three:

referring to fig. 4, a vehicle driving abnormality recognition apparatus 1 of the present embodiment includes:

a target input module 11 for acquiring a GPS data of a target vehicle and setting it as target data; wherein, the GPS data is recorded with the position coordinates of the vehicle at each time point in the driving path;

the similarity identification module 13 is configured to acquire GPS data of at least one comparison vehicle, and set the GPS data of the comparison vehicle having content similar to the target data as similar data;

a mileage curve constructing module 15, configured to construct a mileage driving curve according to the target data and the similar data, where the mileage driving curve represents a target mileage of the target vehicle and a distribution rule of similar mileage of the comparison vehicle corresponding to the similar data;

the mileage abnormity identification module 17 is used for identifying the position relationship between the target driving mileage of the target data and the mileage driving curve and judging whether the position relationship accords with a preset abnormity judgment rule; if so, judging that the target vehicle is in a mileage normal driving state; if not, the target vehicle is judged to be in the abnormal mileage running state.

Optionally, the vehicle driving abnormality recognition device 1 further includes:

the comparison and identification module 12 is configured to acquire GPS data of at least one other vehicle, set GPS data of the other vehicle having a start point coordinate and an end point coordinate that are consistent with the target data as comparison data, and set the other vehicle corresponding to the comparison data as a comparison vehicle, where the start point coordinate is a position coordinate representing a start point of a travel route in the GPS data, and the end point coordinate is a position coordinate representing an end point of the travel route in the GPS data.

Optionally, the similar identification module 13 further includes:

a target driving feature unit 131, configured to extract a time point in the target data and a position coordinate corresponding to the time point to obtain a target driving feature;

a target start-stop feature unit 132, configured to identify a target start time in the target data, and set a position coordinate in the target data corresponding to the target start time as a target start feature; identifying target termination time in the target data, and setting position coordinates corresponding to the target termination time in the target data as target termination characteristics;

the target clustering unit 133 is configured to extract a plurality of target driving features from target data, and perform clustering operation on the plurality of target driving features, the target start feature, and the target end feature to obtain at least one target clustering point.

A comparison driving feature unit 134, configured to extract a time point in the GPS data of the comparison vehicle and a position coordinate corresponding to the time point to obtain a comparison driving feature;

a comparison start-stop feature unit 135, configured to identify a comparison start time in the GPS data of the comparison vehicle, and set a position coordinate in the GPS data of the comparison vehicle corresponding to the comparison start time as a comparison start feature; identifying comparison ending time in the GPS data of the comparison vehicle, and setting position coordinates corresponding to the comparison ending time in the GPS data of the comparison vehicle as comparison ending characteristics;

a comparison clustering unit 136, configured to extract a plurality of comparison driving features from the GPS data of the comparison vehicle, and perform clustering operation on the plurality of comparison driving features, the comparison starting feature, and the comparison ending feature to obtain at least one comparison clustering point;

a similarity identification unit 137, configured to calculate a comparison variance value between the target clustering point and the comparison clustering point; and if the comparison variance value is smaller than a preset similarity threshold value, judging that the comparison vehicle is similar to the target vehicle, and setting the GPS data of the comparison vehicle as similar data.

and the similar storage module 14 is used for summarizing the comparison vehicle corresponding to the similar data and the target vehicle to obtain a similar train set, and storing the similar train set in a preset similar database.

Optionally, the mileage curve constructing module 15 further includes:

a target mileage dividing unit 151, configured to calculate a target mileage of the target data according to a target start feature and a target end feature of the target data, and calculate a target unit mileage of the target mileage according to a preset division granularity;

a similar mileage dividing unit 152, configured to calculate similar mileage of the similar data according to a similar starting feature and a similar ending feature of the similar data, and calculate similar unit mileage of the similar mileage according to a preset division granularity;

and a mileage normal curve unit 153 configured to construct a normal distribution curve according to the target unit mileage and the similar unit mileage, so as to serve as the mileage travel curve.

A mileage mean curve unit 154, configured to calculate a mileage average of the target unit mileage and the similar unit mileage, and construct a mileage mean curve according to the mileage average.

and a duration curve construction module 16, configured to construct a duration driving curve according to the target data and the similar data, where the duration driving curve represents a target driving duration of the target vehicle and a distribution rule of similar driving durations of the comparison vehicles corresponding to the similar data.

Optionally, the time duration curve constructing module 16 further includes:

a target duration dividing unit 161, configured to identify a time length of the target data when the position coordinate is in a continuous moving state, set the time length as a target driving duration, calculate a target driving duration of the target data, and calculate a target unit duration of the target driving duration according to a preset division granularity;

the similar duration dividing unit 162 is configured to identify a time length of the similar data in which the position coordinate is in the continuous movement state, set the time length as a similar driving duration, calculate a similar driving duration of the similar data, and calculate a similar unit duration of the similar driving duration according to a preset division granularity;

and a duration normal curve unit 163, configured to construct a normal distribution curve according to the target unit duration and the similar unit duration, so as to serve as the duration driving curve.

A duration mean curve unit 164, configured to calculate a duration mean of the target unit duration and the similar unit duration, and construct a duration mean curve according to the duration mean.

a duration anomaly identification module 18, configured to identify a position relationship between the target driving duration of the target data and the duration driving curve, and determine whether the position relationship meets a preset anomaly determination rule; if so, judging that the target vehicle is in a time length normal driving state; if not, determining that the target vehicle is in a time length abnormal driving state.

The technical scheme is applied to the field of artificial intelligence intelligent decision making, and comprises the steps of obtaining GPS data of a target vehicle and setting the GPS data as target data, obtaining GPS data of at least one comparison vehicle, setting the GPS data of the comparison vehicle with similar content to the target data as similar data through a clustering algorithm, constructing a mileage travel curve according to the target data and the similar data to serve as a classification model, identifying the position relation between the target travel mileage of the target data and the mileage travel curve, and judging whether the position relation accords with a preset abnormal judgment rule or not; if so, judging that the target vehicle is in a mileage normal driving state; if not, the target vehicle is judged to be in the abnormal mileage running state.

Example four:

in order to achieve the above object, the present invention further provides a computer device 5, in which components of the vehicle driving abnormality recognition apparatus according to the third embodiment can be dispersed in different computer devices, and the computer device 5 can be a smart phone, a tablet computer, a notebook computer, a desktop computer, a rack server, a blade server, a tower server, or a rack server (including an independent server or a server cluster formed by a plurality of application servers) for executing programs, and the like. The computer device of the embodiment at least includes but is not limited to: a memory 51, a processor 52, which may be communicatively coupled to each other via a system bus, as shown in FIG. 5. It should be noted that fig. 5 only shows a computer device with components, but it should be understood that not all of the shown components are required to be implemented, and more or fewer components may be implemented instead.

In this embodiment, the memory 51 (i.e., a readable storage medium) includes a flash memory, a hard disk, a multimedia card, a card-type memory (e.g., SD or DX memory, etc.), a Random Access Memory (RAM), a Static Random Access Memory (SRAM), a read-only memory (ROM), an electrically erasable programmable read-only memory (EEPROM), a programmable read-only memory (PROM), a magnetic memory, a magnetic disk, an optical disk, and the like. In some embodiments, the memory 51 may be an internal storage module of the computer device, such as a hard disk or a memory of the computer device. In other embodiments, the memory 51 may be an external storage device of a computer device, such as a plug-in hard disk, a Smart Media Card (SMC), a Secure Digital (SD) Card, a Flash memory Card (Flash Card), or the like, provided on the computer device. Of course, the memory 51 may also include both internal and external memory modules of the computer device. In this embodiment, the memory 51 is generally used for storing an operating system and various types of application software installed in a computer device, for example, a program code of the vehicle driving abnormality recognition apparatus according to the third embodiment. Further, the memory 51 may also be used to temporarily store various types of data that have been output or are to be output.

Processor 52 may be a Central Processing Unit (CPU), controller, microcontroller, microprocessor, or other data Processing chip in some embodiments. The processor 52 is typically used to control the overall operation of the computer device. In this embodiment, the processor 52 is configured to operate the program codes stored in the memory 51 or process data, for example, operate the vehicle driving abnormality recognition device, so as to implement the vehicle driving abnormality recognition methods of the first and second embodiments.

Example five:

to achieve the above objects, the present invention also provides a computer readable storage medium, such as a flash memory, a hard disk, a multimedia card, a card type memory (e.g., SD or DX memory, etc.), a Random Access Memory (RAM), a Static Random Access Memory (SRAM), a Read Only Memory (ROM), an Electrically Erasable Programmable Read Only Memory (EEPROM), a Programmable Read Only Memory (PROM), a magnetic memory, a magnetic disk, an optical disk, a server, an App application store, etc., on which a computer program is stored, which when executed by a processor 52, implements corresponding functions. The computer-readable storage medium of the present embodiment is used to store a computer program that implements the vehicle travel abnormality identification method, and implements the vehicle travel abnormality identification method of the first and second embodiments when executed by the processor 52.

The above-mentioned serial numbers of the embodiments of the present invention are merely for description and do not represent the merits of the embodiments.

Through the above description of the embodiments, those skilled in the art will clearly understand that the method of the above embodiments can be implemented by software plus a necessary general hardware platform, and certainly can also be implemented by hardware, but in many cases, the former is a better implementation manner.

The above description is only a preferred embodiment of the present invention, and not intended to limit the scope of the present invention, and all modifications of equivalent structures and equivalent processes, which are made by using the contents of the present specification and the accompanying drawings, or directly or indirectly applied to other related technical fields, are included in the scope of the present invention.

Claims

1. A vehicle driving abnormality recognition method characterized by comprising:

2. The vehicle driving abnormality identification method according to claim 1, characterized in that, before said acquisition of GPS data of at least one comparison vehicle, the method further comprises:

3. The vehicle driving abnormality recognition method according to claim 1, wherein the setting of the GPS data of the comparison vehicle having a content similar to the target data as similar data includes:

4. The vehicle driving abnormality recognition method according to claim 1, characterized in that after the GPS data of the comparison vehicle whose contents are similar to the target data is set as similar data, the method further comprises:

uploading the similar train sets in the similar database to a block chain.

5. The vehicle driving abnormality identification method according to claim 1, wherein the constructing a mileage driving curve from the target data and the similar data includes:

6. The vehicle driving abnormality recognition method according to claim 1, characterized in that after the GPS data of the comparison vehicle whose contents are similar to the target data is set as similar data, the method further comprises:

7. The vehicle driving abnormality identification method according to claim 6, characterized in that said constructing a long-duration driving curve from said target data and said similar data includes:

8. A vehicle driving abnormality recognition device characterized by comprising:

9. A computer device comprising a memory, a processor and a computer program stored on the memory and executable on the processor, characterized in that the steps of the vehicle driving abnormality identification method according to any one of claims 1 to 7 are implemented by the processor of the computer device when the computer program is executed.

10. A computer-readable storage medium on which a computer program is stored, the computer program stored in the computer-readable storage medium, when being executed by a processor, implementing the steps of the vehicle travel abnormality identification method according to any one of claims 1 to 7.