Method and device for determining vehicle abnormal aggregation, electronic equipment and storage medium

Abstract

The application discloses a vehicle abnormal gathering determination method and device, electronic equipment and storage medium, and relates to the technical field of Internet of Vehicles. The method comprises the following steps: acquiring a gathering radius, a first distance threshold, a second distance threshold, a quantity threshold and position data of a plurality of vehicles; determining a plurality of candidate position data from the plurality of position data; determining abnormal position data according to the vector distance between the plurality of candidate position data, wherein the vector distance between the abnormal position data is not less than the second distance threshold; acquiring selected position data in a region corresponding to each abnormal position data; and in response to the number of the selected position data being not less than the quantity threshold, determining vehicle abnormal gathering information, wherein the gathering position in the vehicle abnormal gathering information is the position indicated by the abnormal position data, and the gathering quantity is the total number of the selected position data. The method can obtain the vehicle abnormal gathering condition.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of Internet of Vehicles, and in particular to a method and device for determining vehicle abnormal gathering, an electronic device and a storage medium. BACKGROUND

[0002] With the development of economy and the improvement of people's living standards, the number of vehicles has increased dramatically. Vehicles can provide convenience for people's life, but the problem of vehicle abnormal gathering needs to be solved. Generally, the total number of vehicles parked within a certain range exceeds a certain value, which is considered to be vehicle abnormal gathering, for example, the total number of vehicles parked within 500 meters is greater than 100. Vehicle abnormal gathering may be related to traffic accidents or may be related to collective fights. Therefore, it is particularly important to determine vehicle abnormal gathering.

[0003] In related technologies, image analysis is performed on video data of a monitored scene, and vehicle abnormal gathering is determined by determining the number of vehicles within a certain range.

[0004] However, the vehicle abnormal gathering determination method in related technologies relies on video data, and due to the low transmission efficiency and low image analysis efficiency of video data, the determination efficiency of vehicle abnormal gathering is reduced, which cannot quickly understand the vehicle gathering situation, thereby affecting the supervision of vehicles. SUMMARY

[0005] In view of this, the present application provides a method and device for determining vehicle abnormal gathering, an electronic device and a storage medium, which can obtain the abnormal gathering situation of vehicles, so as to facilitate users to supervise vehicles.

[0006] Specifically, the technical solutions include the following:

[0007] In a first aspect, the present application provides a method for determining vehicle abnormal gathering, the method comprising:

[0008] obtaining a gathering radius, a first distance threshold, a second distance threshold, a quantity threshold, and position data of a plurality of vehicles;

[0009] determining a plurality of candidate position data according to a plurality of position data, each candidate position data satisfying: the average vector distance between other position data in a set region and the candidate position data is less than the first distance threshold, and the set region is a region with the position indicated by the candidate position data as the center and the gathering radius as the radius;

[0010] determining the vector distance between a plurality of candidate position data;

[0011] determine abnormal position data according to vector distances between the plurality of candidate position data, wherein vector distances between the abnormal position data are not less than the second distance threshold;

[0012] obtain selected position data in a region corresponding to each of the abnormal position data, the region corresponding to the abnormal position data being a region with a center at a position indicated by the abnormal position data and a radius of the aggregation radius;

[0013] determine vehicle abnormal aggregation information in response to a number of the selected position data being not less than the number threshold, wherein the vehicle abnormal aggregation information comprises an aggregation position and an aggregation number, the aggregation position being the position indicated by the abnormal position data, and the aggregation number being a total number of the selected position data.

[0014] In some embodiments, the determining a plurality of candidate position data according to the plurality of position data comprises:

[0015] randomly select initial position data from the plurality of position data, and iteratively perform the following steps in response to the initial position data not being the candidate position data until one of the candidate position data is determined:

[0016] determine an i-th set based on i-th position data determined in an i-th iteration in an (i+1)-th iteration in response to the i-th position data not being the candidate position data, wherein the i-th set is a set of position data with positions in a region corresponding to the i-th set and having a center at a position indicated by the i-th position data and a radius of the aggregation radius;

[0017] determine an average vector distance between the i-th position data and other position data in the i-th set;

[0018] determine the offset based on the average vector distance;

[0019] determine (i+1)-th position data in a region corresponding to the i-th set based on the offset,

[0020] wherein i is greater than or equal to 1 and i is a positive integer, and a first position data determined in a first iteration is determined from a region corresponding to the initial position data.

[0021] In some embodiments, after one of the candidate position data is determined, the randomly selecting initial position data from the plurality of position data comprises:

[0022] randomly selecting the initial position data from other position data outside a set corresponding to the determined candidate position data to determine a next candidate position data,

[0023] The set corresponding to the determined candidate position data is a set of position data located in a region with a center at a position indicated by the determined candidate position data and a radius of the aggregation radius.

[0024] In some embodiments, the method further comprises:

[0025] In response to a vector distance between two of the candidate position data being less than the second distance threshold, merging the two candidate position data;

[0026] Determining an updated vector distance between the merged candidate position data and other candidate position data or other merged candidate position data;

[0027] Based on the updated vector distance, determining the abnormal position data.

[0028] In some embodiments, before the determining a plurality of candidate position data according to a plurality of position data, the method further comprises:

[0029] Preprocessing the position data of the plurality of vehicles, the preprocessing comprising at least one of removing data with incomplete fields, removing data with abnormal values, and removing empty rows.

[0030] In some embodiments, after the determining vehicle abnormal aggregation information, the method further comprises:

[0031] Generating a report and a map display interface according to the vehicle abnormal aggregation information.

[0032] In some embodiments, the vehicle abnormal aggregation information further comprises at least one of an offline time, a vehicle model, and a vehicle identification code of a vehicle corresponding to the selected position data.

[0033] In a second aspect, the embodiments of the present application provide a vehicle abnormal aggregation determination device, the device comprising:

[0034] A first obtaining module, configured to obtain an aggregation radius, a first distance threshold, a second distance threshold, a quantity threshold, and position data of a plurality of vehicles;

[0035] A first determining module, configured to determine a plurality of candidate position data according to a plurality of the position data, each of the candidate position data satisfying: an average vector distance between other position data in a set region and the candidate position data being less than the first distance threshold, the set region being a region with a center at a position indicated by the candidate position data and a radius of the aggregation radius;

[0036] A second determining module, configured to determine a vector distance between a plurality of the candidate position data;

[0037] a third determining module, configured to determine abnormal position data according to vector distances between a plurality of the candidate position data, wherein the vector distances between the abnormal position data are not less than the second distance threshold;

[0038] a second obtaining module, configured to obtain selected position data in a region corresponding to each of the abnormal position data, the region corresponding to the abnormal position data being a region with a position indicated by the abnormal position data as a center and with the aggregation radius as a radius;

[0039] a fourth determining module, configured to determine vehicle abnormal aggregation information in response to a number of the selected position data being not less than the number threshold, wherein the vehicle abnormal aggregation information comprises an aggregation position and an aggregation number, the aggregation position being the position indicated by the abnormal position data, and the aggregation number being a total number of the selected position data.

[0040] In a third aspect, an embodiment of the present application provides an electronic device, which comprises:

[0041] a memory;

[0042] a processor, electrically connected with the memory;

[0043] the memory stores a computer program, and the computer program is executed by the processor to implement the method for determining vehicle abnormal aggregation according to the first aspect.

[0044] In a fourth aspect, an embodiment of the present application provides a nonvolatile computer readable storage medium, which stores a computer program, and the computer program is executed by a processor to implement the method for determining vehicle abnormal aggregation according to the first aspect.

[0045] The technical scheme provided by the embodiments of the present application has at least the following beneficial effects:

[0046] The embodiments of the present application provide a method for determining vehicle abnormal aggregation. By using the aggregation radius, the first distance threshold, the second distance threshold and the number threshold input by a user, candidate position data are determined according to position data of a plurality of vehicles, and further, abnormal position data with vector distances not less than the second distance threshold are screened out according to vector distances between a plurality of the candidate position data. When a number of selected position data in a region corresponding to the abnormal position data is not less than the aggregation number, it is considered that there is an abnormal aggregation of vehicles around the position indicated by the abnormal position data, and thus it is considered that there is an abnormal aggregation of vehicles. The aggregation position and the aggregation number and other abnormal aggregation information are determined according to the abnormal position data and the corresponding selected position data, so that the user can intuitively understand the abnormal aggregation of vehicles and supervise the vehicles. BRIEF DESCRIPTION OF DRAWINGS

[0047] In order to more clearly illustrate the technical solutions in the embodiments of the present application, the drawings needed to be used in the embodiment description will be briefly introduced. Obviously, the drawings in the following description are only some embodiments of the present application, and other drawings can be obtained by those skilled in the art without creative labor.

[0048] Figure 1 A method flowchart of a vehicle abnormal aggregation determination method provided by an embodiment of the present application is shown in FIG. 1.

[0049] Figure 2 An implementation environment schematic diagram of a vehicle abnormal aggregation determination method provided by an embodiment of the present application is shown in FIG. 2.

[0050] Figure 3 A method flowchart of another vehicle abnormal aggregation determination method provided by an embodiment of the present application is shown in FIG. 3.

[0051] Figure 4 A structure schematic diagram of a vehicle abnormal aggregation determination device provided by an embodiment of the present application is shown in FIG. 4.

[0052] Figure 5 A structure framework schematic diagram of an electronic device provided by an embodiment of the present application is shown in FIG. 5. DETAILED DESCRIPTION

[0053] The technical solutions in the embodiments of the present application will be described clearly and completely below with reference to the drawings in the embodiments of the present application. Obviously, the described embodiments are only some embodiments of the present application, not all embodiments. Based on the embodiments in the present application, all other embodiments obtained by those skilled in the art without creative labor are within the scope of protection of the present application.

[0054] With the rapid increase of vehicle ownership, the problem of vehicle abnormal aggregation needs to be solved. Generally, the total number of vehicles parked within a certain range is considered to be abnormal aggregation when it exceeds a certain value. For example, the total number of vehicles parked within 500 meters is greater than 100.

[0055] At present, image analysis is performed on video data of a monitoring scene to determine the number of vehicles within a certain range to judge vehicle abnormal aggregation. However, this method is strongly dependent on video data and cannot quickly obtain the vehicle aggregation situation, thereby affecting vehicle supervision.

[0056] In view of this, the present application provides a vehicle abnormal aggregation determination method, which can be executed by a computer and other electronic devices. As shown in FIG. 1, the method comprises: Figure 1

[0057] ​In step 101, the aggregation radius, the first distance threshold, the second distance threshold, the quantity threshold, and the position data of the plurality of vehicles are obtained.

[0058] In step 102, the plurality of candidate position data is determined according to the plurality of position data.

[0059] Each candidate position data satisfies: the average vector distance between other position data in a set region and the candidate position data is less than the first distance threshold, and the set region is a region with the position indicated by the candidate position data as the center and the aggregation radius as the radius.

[0060] In step 103, the vector distance between the plurality of candidate position data is determined.

[0061] In step 104, the abnormal position data is determined according to the vector distance between the plurality of candidate position data.

[0062] The vector distance between the abnormal position data is not less than the second distance threshold.

[0063] In step 105, the selected position data in the region corresponding to each abnormal position data is obtained.

[0064] The region corresponding to the abnormal position data is a region with the position indicated by the abnormal position data as the center and the aggregation radius as the radius.

[0065] In step 106, the vehicle abnormal aggregation information is determined in response to the number of selected position data being not less than the quantity threshold.

[0066] The vehicle abnormal aggregation information includes the aggregation position and the aggregation quantity, the aggregation position is the position indicated by the abnormal position data, and the aggregation quantity is the total number of selected position data.

[0067] The method for determining vehicle abnormal aggregation provided by the embodiments of the present application determines the candidate position data according to the position data of the plurality of vehicles through the parameters such as the aggregation radius, the first distance threshold, the second distance threshold, and the quantity threshold input by the user, and further screens the abnormal position data with the vector distance between each other not less than the second distance threshold according to the vector distance between the plurality of candidate position data. When the number of selected position data in the region corresponding to the abnormal position data is not less than the aggregation quantity, it indicates that too many vehicles are aggregated near the position indicated by the abnormal position data, so it is considered that there is a vehicle abnormal aggregation situation, and the aggregation position and the aggregation quantity and other abnormal aggregation information are determined according to the abnormal position data and the corresponding selected position data, so as to facilitate the user to intuitively understand the vehicle abnormal aggregation situation and facilitate the user to supervise the vehicle.

[0068] In some embodiments, the plurality of candidate position data is determined according to the plurality of position data, including:

[0069] randomly selecting initial position data from the plurality of position data, in response to the initial position data not being the candidate position data, iteratively performing the following steps until a candidate position data is determined:

[0070] in response to the i-th position data determined in the i-th iteration not being the candidate position data, in an (i+1)-th iteration, determining an i-th set based on the i-th position data, wherein the i-th set is a set of position data whose positions are within a region with a center at the position indicated by the i-th position data and a radius of the aggregation radius;

[0071] determining an average vector distance between the i-th position data and other position data within the i-th set;

[0072] determining an offset based on the average vector distance;

[0073] determining the (i+1)-th position data in the region corresponding to the i-th set based on the offset,

[0074] wherein i≥1 and i is a positive integer, and the first position data determined in the first iteration is determined from the region corresponding to the initial position data.

[0075] In some embodiments, after determining a candidate position data, randomly selecting initial position data from the plurality of position data comprises:

[0076] randomly selecting the initial position data from other position data outside the set corresponding to the determined candidate position data to determine a next candidate position data,

[0077] wherein the set corresponding to the determined candidate position data is a set of position data whose positions are within a region with a center at the position indicated by the determined candidate position data and a radius of the aggregation radius.

[0078] In some embodiments, the method further comprises:

[0079] in response to a vector distance between two candidate position data being less than a second distance threshold, merging the two candidate position data;

[0080] determining an updated vector distance between the merged candidate position data and other candidate position data or other merged candidate position data;

[0081] determining an abnormal position data based on the updated vector distance.

[0082] In some embodiments, before determining the plurality of candidate position data from the plurality of position data, the method further comprises:

[0083] The position data of the plurality of vehicles is preprocessed, the preprocessing including at least one of removing incomplete field data, removing abnormal value data, and removing empty row data.

[0084] In some embodiments, after determining the vehicle abnormal aggregation information, the method further includes:

[0085] According to the vehicle abnormal aggregation information, a report and a map display interface are generated.

[0086] In some embodiments, the vehicle abnormal aggregation information further includes at least one of offline time, vehicle type, and vehicle identification code of the vehicle corresponding to the abnormal position data and the selected position data.

[0087] Figure 2 An implementation environment schematic diagram of a vehicle abnormal aggregation determination method provided by the embodiments is provided. Referring to FIG. 1, Figure 2 The implementation environment includes a vehicle terminal 01, a server 02, and a user terminal 03.

[0088] The vehicle terminal 01 is a computer device carried on a vehicle, which can serve as a data source of vehicle position data, offline time, vehicle type, and vehicle identification code of the vehicle, and is in signal connection with the server 02. The server 02 is configured to acquire vehicle position data, offline time, vehicle type, and vehicle identification code of the vehicle provided by a plurality of vehicle terminals 01, and perform calculation and output; the server 02 can be configured to execute the vehicle abnormal aggregation determination method provided by the embodiments, and the server 02 can include an input module 021, a processing module 022, and an output module 023, wherein the input module 021 is configured to acquire vehicle position data, offline time, vehicle type, and vehicle identification code of the vehicle, the processing module 022 is configured to process the acquired data, and the output module 023 is configured to output vehicle abnormal aggregation information; the input module 021 is in signal connection with the processing module 022, and the processing module 022 is in signal connection with the output module 023. In addition, the server 02 can further include a data storage module, configured to store the acquired data and the output vehicle abnormal aggregation information, so as to facilitate the processing module 022 to call. The user terminal 03 is a terminal used by a user to input parameters such as aggregation radius, first distance threshold, second distance threshold, and quantity threshold, and can be a computer device such as a tablet computer, a notebook computer, or a desktop computer. The user can log in to a task interface of the server 02 through the user terminal 03 to input parameters such as aggregation radius, first distance threshold, second distance threshold, and quantity threshold. The task interface can further provide a button component to enable or pause the processing process of the above method. In addition, the user terminal 03 can also acquire the vehicle abnormal aggregation information output by the output module 023 of the server 02, and intuitively display the vehicle abnormal aggregation information to the user in the form of a report and / or a map display interface.

[0089] It should be noted that the server 02 is used as an example to execute the above-mentioned vehicle abnormal aggregation determination method in the embodiments of the present application. In other embodiments, the server 02 can also be used to forward the vehicle position data, offline time, vehicle type, vehicle identification code and other data obtained from the vehicle terminal 01 to the user terminal 03, and execute the vehicle abnormal aggregation determination method provided by the present application through the user terminal 03.

[0090] Figure 3 A method flowchart of a vehicle abnormal aggregation determination method provided in the embodiments of the present application is shown in FIG. 3. Figure 3 The method includes the following steps:

[0091] Step 301: Obtain the aggregation radius, the first distance threshold, the second distance threshold, the quantity threshold, and the position data of a plurality of vehicles.

[0092] In the embodiments of the present application, the aggregation radius, the first distance threshold, the second distance threshold, and the quantity threshold can be input by the user on the task interface provided by the user terminal 03, and then can be obtained by the server 02. The position data of the vehicle can be obtained by the server 02 through the vehicle terminal 01 carried on each vehicle. Through the obtained aggregation radius, the first distance threshold, the second distance threshold, and the position data of a plurality of vehicles, the subsequent determination of vehicle abnormal aggregation is performed.

[0093] In some embodiments, the aggregation radius can be 500 m, the first distance threshold can be 100 m, and the second distance threshold can be 500 m. In this way, the number of operations can be reduced, and the accuracy of the obtained vehicle abnormal aggregation situation can be ensured.

[0094] In some embodiments, before determining a plurality of candidate position data according to a plurality of position data, the method further includes: preprocessing the position data of a plurality of vehicles.

[0095] In the embodiments of the present application, the preprocessing includes at least one of removing incomplete field data, removing abnormal value data, and removing empty row data.

[0096] The position data of the vehicle can be latitude and longitude coordinate data, wherein the latitude and longitude is a coordinate system composed of longitude and latitude, which is a spherical coordinate system that uses a spherical surface of a three-dimensional space to define the space on the earth, and can indicate any position on the earth. Alternatively, the user can predefine a target area related to the position data of a plurality of vehicles, and establish a local coordinate system in the target area. The position data of the vehicle can be coordinate data of the vehicle in the local coordinate system. The position data of the vehicle needs to meet a certain format, and preprocessing the position data of a plurality of vehicles can include removing the vehicle position data that does not meet the set format.

[0097] Exemplarily, the preset format of the position data can include a horizontal coordinate (or a longitude coordinate), a vertical coordinate (or a latitude coordinate), and an accuracy (for example, three decimal places). When the position data collected by the vehicle terminal 01 does not meet the accuracy in the preset format, the position data can be considered as incomplete data. When the position data is missing any one of the horizontal coordinate (or the longitude coordinate) or the vertical coordinate (or the latitude coordinate), the position data can be considered as empty row data. When the position indicated by the position data is out of the target area predefined by the user, the position data can be considered as numerical abnormal data. In the embodiments of the present application, before the position data of the plurality of vehicles is used to determine the vehicle abnormal aggregation information, the position data of the plurality of vehicles is preprocessed, so as to ensure the validity and accuracy of the position data, and further ensure the validity and accuracy of the finally determined vehicle abnormal aggregation information.

[0098] In some embodiments, the server 02 can implement the method for determining vehicle abnormal aggregation provided in the present application based on Flink and YARN. Flink is a high-throughput and low-latency distributed processing engine framework, which can perform data processing and calculation tasks, supports multiple data input and output characteristics, and supports writing and writing out of Elasticsearch database, Cassandra database, Mysql database and Hadoop distributed file system (HDFS). YARN is a platform that can realize unified management of resources, which can be used on demand to improve the resource utilization of the cluster. YARN is configured to start resources, wherein the start resources include drive memory, central processing unit, number of executors and executor memory. Flink on YARN is a deployment method, which makes the tasks in Flink execute on YARN. Before execution, configuration needs to be performed on YARN.

[0099] In some embodiments, the vehicle position data provided by the plurality of vehicle terminals 01, the offline time of the vehicle, the vehicle type and the vehicle identification code obtained by the server 02 can be stored in the HDFS, and the output vehicle abnormal aggregation information can be stored in the Elasticsearch database, the Cassandra database or the Mysql database.

[0100] In step 302, a plurality of candidate position data is determined according to the plurality of position data.

[0101] Each candidate position data satisfies: the average vector distance between the candidate position data and other position data in a set area is less than a first distance threshold, and the set area is an area with the position indicated by the candidate position data as the center and the aggregation radius as the radius.

[0102] The candidate position data is determined based on the plurality of position data, and represents a center position where the vehicles are likely to be concentrated, but is not necessarily the final determined position of the vehicle concentration. The candidate position data can be one of the plurality of position data obtained by the server 02, or can be a new position data calculated based on the plurality of position data, and the position indicated by the new position data actually has no vehicle parking. Each candidate position data represents a center position where the vehicles are concentrated in a set region where the vehicles are likely to be concentrated abnormally. When the average vector distance between the other position data in the set region and the candidate position data is less than the first distance threshold, it is indicated that the position indicated by the candidate position data is the center position where the vehicles are concentrated.

[0103] It should be noted that there can be multiple candidate position data in the target region, that is, there can be multiple positions where the vehicles are concentrated, and the real concentration position needs to be further determined from the multiple candidate position data.

[0104] The candidate position data can be determined in various ways. In some embodiments, the candidate position data can be determined by, for example, a Kmeans algorithm. In the embodiments of the present application, the step of determining the candidate position data can include the following sub-steps:

[0105] Step 3021, randomly selecting an initial position data from the plurality of position data.

[0106] Each candidate position data satisfies: the average vector distance between the other position data in the set region and the candidate position data is less than the first distance threshold, and the set region is a region with the position indicated by the candidate position data as the center and the concentration radius as the radius.

[0107] In the embodiments of the present application, the parameters input by the user can also include an offset threshold. When determining the candidate position data, after determining the average vector distance between the other position data in the set region and the position data, the offset amount can also be determined according to the average vector distance, and when the offset amount is less than the offset threshold, the data is determined as the candidate position data. Thus, each candidate position data can also satisfy: the offset amount determined based on the average vector distance between the other position data in the set region and the candidate position data is less than the offset threshold, and the set region is a region with the position indicated by the candidate position data as the center and the concentration radius as the radius.

[0108] Step 3022, determining an initial set based on the initial position data.

[0109] The first set is a set of position data whose positions are in a region with the position indicated by the initial position data as the center and the concentration radius as the radius.

[0110] Step 3023, determining an average vector distance between the initial position data and the other position data in the first set.

[0111] In this step, determining the average vector distance between the position data can include: calculating a vector sum of distances between the initial position data and the other position data in the first set; dividing a distance size of the vector sum by a number of the other position data in the first set, and taking a value obtained as a distance size of the average vector distance; and taking a direction of the vector sum as a direction of the average vector distance.

[0112] For example, the initial position O indicated by the initial position data and positions A, B and C indicated by the other position data in the first set can be on a straight line, where the position A is on the left side of the initial position O and has a distance of 10 from the initial position O, the position B is on the right side of the initial position O and has a distance of 10 from the initial position O, and the position C is on the right side of the initial position O and has a distance of 30 from the initial position O. In this case, the average vector distance between the positions A, B and C indicated by the other position data and the initial position O indicated by the initial position data has a size of 10=(10+30-10) / 3 and a direction of a direction from the initial position O to the position C.

[0113] In some embodiments, the vector distance between each other position data and the initial position data can be an Euclidean distance.

[0114] Step 3024, determining the offset based on the average vector distance.

[0115] In this step, determining the offset can include: determining a size of the offset based on the distance size of the average vector distance; and determining a direction of the offset based on the direction of the average vector distance.

[0116] In the embodiments of the present application, the size of the offset can be equal to the distance size of the average vector distance, or the size of the offset is in a multiple relationship with the distance size of the average vector distance, for example, the size of the offset can be 0.3 times, 0.4 times, 0.5 times or 0.6 times of the distance size of the average vector distance.

[0117] In some embodiments, the steps 3023 and 3024 of calculating the average vector distance can also not be performed, and the offset can be determined by the following manner: coordinate transformation is performed on the other position data and the initial position data, the longitude and latitude coordinates are converted into rectangular coordinates, the horizontal coordinate values of all the other position data having the rectangular coordinates are added and then divided by the number of the other position data to obtain a new horizontal coordinate value x, the vertical coordinate values of all the other position data having the rectangular coordinates are added and then divided by the number of the other position data to obtain a new vertical coordinate value y, thereby obtaining a new position data (x, y), and the Euclidean distance between the new position data and the initial position data having the rectangular coordinates is the size of the offset, and the direction from the new position data to the initial position data having the rectangular coordinates is the direction of the offset. In other words, in the i+1 iteration process, based on the i position data, after the i set is determined, the offset can be determined according to the other position data in the i set and the i position data; and then based on the offset, the i+1 position data is determined in the region corresponding to the i set.

[0118] In step 3025, it is determined whether the size of the offset is less than an offset threshold.

[0119] When the offset is not less than the offset threshold, it is determined that the initial position data is not the candidate position data, and the following step 3026 of further determining the candidate position data based on the initial position data is performed. When the offset is less than the offset threshold, it is determined that the initial position data is the candidate position data.

[0120] In step 3026, the first position data is determined in the region corresponding to the initial set based on the offset.

[0121] In this step, the position data obtained by increasing the distance corresponding to the size of the offset in the direction of the offset with the position indicated by the initial position data as the origin is taken as the first position data. In other words, the first position data can be the position data corresponding to the vector sum of the initial position data and the offset.

[0122] In the embodiments of the present application, the initial position data in the steps 3022 to 3025 is replaced by the first position data determined in this step, and the steps 3022 to 3025 are repeatedly performed until a candidate position data is determined.

[0123] In other words, in the embodiments of the present application, the determination of the plurality of candidate position data from the plurality of position data can include: randomly selecting the initial position data from the plurality of position data, and iteratively performing the following steps until a candidate position data is determined in response to the initial position data not being the candidate position data:

[0124] In response to the i-th position data determined in the i-th iteration not being the candidate position data, in the (i+1)-th iteration, based on the i-th position data, an i-th set is determined, wherein the i-th set is a set of position data located in a region with a center at the position indicated by the i-th position data and a radius of the gathering radius; an average vector distance between the other position data in the i-th set and the i-th position data is determined; based on the average vector distance, a shift amount is determined; and based on the shift amount, the (i+1)-th position data is determined in the region corresponding to the i-th set, wherein i is greater than or equal to 1 and is a positive integer, and the first position data determined in the first iteration is determined from the region corresponding to the initial position data.

[0125] In the embodiments of the present application, the average vector distance between the other position data in the i-th set and the i-th position data represents the distance between the position data of the vehicle gathered around the position and the position of the vehicle gathering.

[0126] Based on the shift amount, the (i+1)-th position data is determined in the region corresponding to the i-th set, so that the position indicated by the (i+1)-th position data is closer to the central position of the actual vehicle gathering than the position indicated by the i-th position data.

[0127] It should be noted that the above steps are repeatedly executed until the shift amount is less than the shift threshold, at which time the position data corresponding to the shift amount is very close to the central position of the vehicle gathering, so that a candidate position data can be obtained.

[0128] It should be noted that the determination of the candidate position data optimizes the Kmeans algorithm, which can only determine the position of the vehicle gathering in the case that the number of positions of the vehicle gathering in the specified target region is known, and cannot determine the position of the vehicle gathering without specifying the number of positions of the vehicle gathering in the target region. The determination method of the candidate position data provided in the embodiments of the present application does not need to determine the number of positions of the vehicle gathering in the target region as the Kmeans algorithm does, and thus is applicable to the case that the number of positions of the unknown vehicle gathering in the target region is unknown.

[0129] Considering that there can be multiple candidate position data in the target region, i.e., the position of the vehicle gathering can be multiple, the embodiments of the present application need to determine multiple candidate position data. Therefore, after determining one candidate position data, the user can re-execute the steps 3021 to 3026 to re-select the initial position data and determine the candidate position data.

[0130] In some embodiments, after determining one candidate position data, the initial position data is randomly selected from the plurality of position data, which can be implemented by the following method:

[0131] The initial position data is randomly selected from other position data outside the set corresponding to the determined candidate position data, to determine the next candidate position data.

[0132] The set corresponding to the determined candidate position data is a set of position data located in a region with the position indicated by the determined candidate position data as the center and the aggregation radius as the radius.

[0133] The position indicated by one candidate position data is one of the target regions of the multiple vehicle aggregation positions, and other multiple vehicle aggregation positions corresponding to candidate positions need to be determined until the position data of the multiple vehicles are all divided into the set corresponding to the determined candidate position data, which means that the position data of the multiple vehicles in the target region are all found in the corresponding vehicle aggregation position, thereby completing the determination of the candidate position data. In other words, in the embodiment of the application, one position data that has not been calculated is selected as the initial position data, and the candidate position data is determined based on the initial position data, until all position data are calculated, thereby determining multiple candidate position data.

[0134] Step 303, determining the vector distance between the multiple candidate position data.

[0135] In the embodiment of the application, similar to step 3023, the Euclidean distance between the multiple candidate position data can be calculated as the vector distance.

[0136] Determining the vector distance between the multiple candidate positions facilitates subsequent determination of abnormal position data.

[0137] Step 304, determining the abnormal position data according to the vector distance between the multiple candidate position data.

[0138] The vector distance between the abnormal position data is not less than the second distance threshold.

[0139] The vector distance between the abnormal position data is not less than the second distance threshold, which means that the position represented by the determined abnormal position data is not the same vehicle aggregation position, thereby avoiding multiple abnormal position data obtained from the vehicle position data around the same vehicle aggregation position.

[0140] In some embodiments, determining the abnormal position data can include the following sub-steps.

[0141] Step 3041, in response to the vector distance between the two candidate position data being less than the second distance threshold, merging the two candidate position data.

[0142] The vector distance between two candidate position data is less than the second distance threshold, which means that the two candidate position data represent the same vehicle gathering position or the distance between vehicle gathering positions is close, and thus needs to be merged.

[0143] In some embodiments, the merging manner can be: taking the average of the two candidate position data as the merged candidate position data, or respectively calculating the average vector distance of the position data of the plurality of vehicles in the region respectively centered at the two candidate position data and having the gathering radius as the radius, and taking the candidate position data corresponding to the smaller average vector distance as the merged candidate position data.

[0144] In step 3042, the updated vector distance between the merged candidate position data and other candidate position data or other merged candidate position data is determined.

[0145] The updated vector distance between the merged candidate position data and other candidate position data or other merged candidate position data is determined, so as to determine the abnormal position data.

[0146] In step 3043, the abnormal position data is determined based on the updated vector distance.

[0147] In this step, when there is a case that the updated vector distance is less than the second distance threshold, it means that the merged candidate position data and other candidate position data or other merged candidate position data can continue to be merged, and thus the above-mentioned step 3041 can be repeatedly executed until the vector distance between all candidate position data is less than the second distance threshold, at which time the existing candidate position data is determined as the abnormal position data.

[0148] In other words, in the embodiments of the present application, for a candidate position data, if the vector distance between the candidate position data and other surrounding candidate position data is not less than the second distance threshold, the candidate position data is directly determined as the abnormal position data; if the vector distance between the candidate position data and other surrounding candidate position data is less than the second distance threshold, the candidate position data and other candidate position data are merged until the vector distance between the candidate position data and other surrounding candidate position data is not less than the second distance threshold, and the merged candidate position data is determined as the abnormal position data. The determined abnormal position data is the vehicle gathering position.

[0149] In step 305, selected position data in the region corresponding to each abnormal position data is obtained.

[0150] The region corresponding to the abnormal position data is a region centered at the position indicated by the abnormal position data and having the gathering radius as the radius.

[0151] The abnormal position data can represent a central position where vehicles are gathered, and the abnormal position data can be one of the plurality of vehicle position data obtained by the server 02 or a new position data calculated according to the plurality of position data. The selected position data corresponding to the region of the abnormal position data represents the positions of the vehicles gathered around the central position. The selected position data corresponding to the region of each abnormal position data is obtained, so as to obtain the positions of the vehicles gathered around the central position of the vehicles.

[0152] In step 306, the vehicle abnormal gathering information is determined in response to the number of the selected position data being not less than the number threshold.

[0153] The vehicle abnormal gathering information includes the gathering position and the gathering number, the gathering position is the position indicated by the abnormal position data, and the gathering number is the total number of the selected position data.

[0154] When the number of the selected position data is not less than the number threshold, it indicates that the number of the vehicles in the region corresponding to the abnormal position data is greater than the number threshold, so that it is determined that the region corresponding to the abnormal position data exists the vehicle abnormal gathering situation, the position indicated by the abnormal position data is the position where the vehicle abnormal gathering exists, that is, the gathering position, and the total number of the selected position data is the actual gathering number of the vehicle abnormal gathering, that is, the gathering number.

[0155] In some embodiments, the number threshold can be 100 vehicles.

[0156] In some embodiments, the vehicle abnormal gathering information further includes at least one of the offline time, the vehicle type and the vehicle identification code of the vehicle corresponding to the abnormal position data and the selected position data, for subsequent statistics and intuitive display.

[0157] It should be noted that the offline time of the vehicle refers to the time when the vehicle terminal last communicates with the server.

[0158] In some embodiments, the offline time, the vehicle type and the vehicle identification code of the vehicle corresponding to the selected position data are written into the database.

[0159] In some embodiments, the database can be an Elasticsearch database, a Cassandra database and a Mysql database.

[0160] In step 307, the report and the map display interface are generated according to the vehicle abnormal gathering information.

[0161] The generated report and map display interface can enable the user to comprehensively master information such as abnormal position data, selected position data, offline time, vehicle type, and vehicle identification code, and can enable the user to intuitively obtain the position of vehicle abnormal aggregation in a target area and the distribution of vehicles around the position of vehicle abnormal aggregation, thereby monitoring the vehicles and investigating the safety hazards of the aggregated vehicles.

[0162] In some embodiments, after the Flink completes the determination task of vehicle abnormal aggregation, the user can obtain the task execution condition of the Flink, and the task execution condition includes the data quantity of the Flink and the execution log.

[0163] The determination method of vehicle abnormal aggregation provided in the embodiments of the present application can obtain the position of vehicle abnormal aggregation and the actual number of vehicle aggregation, so that the user knows the abnormal aggregation condition of the vehicles, thereby facilitating the user to monitor the vehicles.

[0164] In a second aspect, the embodiments of the present application provide another determination device of vehicle abnormal aggregation. Figure 4 For the structure diagram of another determination device of vehicle abnormal aggregation provided in the embodiments of the present application, refer to Figure 4 The determination device 400 of vehicle abnormal aggregation includes:

[0165] The first acquisition module 401 is configured to acquire the aggregation radius, the first distance threshold, the second distance threshold, the quantity threshold, and the position data of the plurality of vehicles.

[0166] The first determination module 402 is configured to determine a plurality of candidate position data from the plurality of position data, each candidate position data satisfying that the average vector distance between other position data in a set region and the candidate position data is less than the first distance threshold, and the set region is a region with the position indicated by the candidate position data as the center and the aggregation radius as the radius.

[0167] The second determination module 403 is configured to determine the vector distance between the plurality of candidate position data.

[0168] The third determination module 404 is configured to determine the abnormal position data according to the vector distance between the plurality of candidate position data, wherein the vector distance between the abnormal position data is not less than the second distance threshold.

[0169] The second acquisition module 405 is configured to acquire the selected position data in the region corresponding to each abnormal position data, and the region corresponding to the abnormal position data is a region with the position indicated by the abnormal position data as the center and the aggregation radius as the radius.

[0170] The fourth determining module 406 is configured to determine vehicle abnormal gathering information in response to the number of the selected position data being not less than the number threshold, wherein the vehicle abnormal gathering information comprises an abnormal gathering position and an abnormal gathering number, the abnormal gathering position is the position indicated by the abnormal position data, and the abnormal gathering number is the total number of the selected position data.

[0171] In some embodiments, the first determining module 402 comprises:

[0172] The first determining unit is configured to randomly select initial position data from the plurality of position data, and in response to the initial position data not being the candidate position data, iteratively perform the following steps until a candidate position data is determined:

[0173] The second determining unit is configured to, in response to the ith position data determined in the ith iteration not being the candidate position data, determine an ith set based on the ith position data in an (i+1)th iteration, wherein the ith set is a set of position data located in a region with the ith position data as the center and the gathering radius as the radius.

[0174] The third determining unit is configured to determine the average vector distance between the other position data in the ith set and the ith position data.

[0175] The fourth determining unit is configured to determine the offset based on the average vector distance.

[0176] The selecting unit is configured to determine the (i+1)th position data in the region corresponding to the ith set based on the offset.

[0177] Wherein i≥1, i is a positive integer, and the first position data determined in the first iteration is determined from the region corresponding to the initial position data.

[0178] In some embodiments, after determining a candidate position data, the initial position data is randomly selected from the plurality of position data, comprising:

[0179] The initial position data is randomly selected from the other position data outside the set corresponding to the determined candidate position data to determine the next candidate position data.

[0180] Wherein the set corresponding to the determined candidate position data is a set of position data located in a region with the position indicated by the determined candidate position data as the center and the gathering radius as the radius.

[0181] In some embodiments, the apparatus 400 further comprises:

[0182] The merging module is configured to merge two candidate position data in response to the vector distance between the two candidate position data being less than the second distance threshold.

[0183] a fifth determining module configured to determine an update vector distance between the merged candidate position data and other candidate position data or other merged candidate position data;

[0184] a sixth determining module configured to determine abnormal position data based on the update vector distance.

[0185] In some embodiments, the apparatus 400 further includes:

[0186] a preprocessing module configured to preprocess position data of a plurality of vehicles, the preprocessing including at least one of removing incomplete field data, removing abnormal value data, and removing empty row data.

[0187] In some embodiments, the apparatus 400 further includes:

[0188] a generating module configured to generate a report and a map display interface according to the vehicle abnormal aggregation information.

[0189] In some embodiments, the vehicle abnormal aggregation information further includes at least one of offline time, vehicle model, and vehicle identification code of the vehicle corresponding to the selected position data.

[0190] In summary, the vehicle abnormal aggregation determination apparatus provided by the embodiments of the present application can enable a user to obtain the abnormal aggregation of vehicles, so as to facilitate the user to monitor the vehicles.

[0191] In a third aspect, the embodiments of the present application provide an electronic device, which includes a memory and a processor, the memory being electrically connected with the processor.

[0192] The memory stores a computer program, and the computer program is executed by the processor to implement the vehicle abnormal aggregation determination method provided in the first aspect.

[0193] Those skilled in the art can understand that the electronic device provided by the embodiments of the present application can be specially designed and manufactured for the required purpose, or can also include known devices in a general-purpose computer. These devices have computer programs stored therein, which are selectively activated or reconfigured. Such computer programs can be stored in a device (for example, a computer) readable medium or any type of medium suitable for storing electronic instructions and respectively coupled to the bus.

[0194] The present application provides an electronic device in an optional embodiment, as shown in Figure 5 The electronic device 500 includes a memory 501 and a processor 502, and the memory 501 and the processor 502 are electrically connected, such as through a bus 503.

[0195] Optionally, the memory 501 is configured to store application codes for implementing the scheme of the present application, and the processor 502 is configured to control the execution. The processor 502 is configured to execute the application codes stored in the memory 501 to implement the method for determining vehicle abnormal aggregation provided by the embodiments of the present application.

[0196] The memory 501 can be a ROM (Read-Only Memory) or other type of static storage device that can store static information and instructions, can be a RAM (Random Access Memory) or other type of dynamic storage device that can store information and instructions, can be an EEPROM (Electrically Erasable Programmable Read-Only Memory), a CD-ROM (Compact Disc Read-Only Memory) or other optical disk storage, a magnetic disk storage medium or other magnetic storage device, or any other medium that can be used to carry or store desired program codes in the form of instructions or data structures and that can be accessed by a computer, but is not limited to this.

[0197] The processor 502 can be a CPU (Central Processing Unit), a general-purpose processor, a DSP (Digital Signal Processor), an ASIC (Application Specific Integrated Circuit), an FPGA (Field-Programmable Gate Array) or other programmable logic device, a transistor logic device, a hardware component or any combination thereof. It can implement or execute various exemplary logical blocks, modules and circuits described in combination with the disclosure. The processor 402 can also be a combination of computing functions, such as a combination of one or more microprocessors, a combination of DSP and microprocessor, etc.

[0198] The bus 503 can include a path for transmitting information between the above-mentioned components. The bus can be a PCI (Peripheral Component Interconnect) bus or an EISA (Extended Industry Standard Architecture) bus. The bus can be divided into an address bus, a data bus, a control bus, etc. For ease of representation, Figure 5Only one bus is shown for simplicity, but there can be more than one bus.

[0199] Optionally, the electronic device 500 can further include a transceiver 504. The transceiver 504 can be used for receiving and sending signals. The transceiver 504 can allow the electronic device 500 to communicate with other devices wirelessly or wired to exchange data. It should be noted that the transceiver 504 is not limited to one in actual application.

[0200] Optionally, the electronic device 500 can further include an input unit 505. The input unit 505 can be used to receive inputted digital, character, image and / or sound information, or to generate key signal input related to user settings and function control of the electronic device 500. The input unit 505 can include, but is not limited to, one or more of a touch screen, a physical keyboard, function keys (such as volume control buttons, on-off buttons, etc.), a trackball, a mouse, a joystick, a camera, a microphone, etc.

[0201] Optionally, the electronic device 500 can further include an output unit 506. The output unit 506 can be used to output or display information processed by the processor 502. The output unit 406 can include, but is not limited to, one or more of a display device, a speaker, a vibration device, etc.

[0202] Although Figure 5 The electronic device 500 is shown with various devices, but it should be understood that all of the illustrated devices are not required to practice or have the various embodiments. More or less devices can be implemented.

[0203] The electronic device provided by the embodiments of the present application has the same inventive concept as the above-described embodiments. The contents not shown in detail in the electronic device can refer to the above-described embodiments, and will not be described here again.

[0204] In a fourth aspect, a non-volatile computer readable storage medium is provided. The non-volatile computer readable storage medium stores a computer program. When the computer program is executed by a processor, the computer program implements the method for determining vehicle abnormal aggregation.

[0205] The non-volatile computer readable medium includes, but is not limited to, any type of disk (including floppy disks, hard disks, optical disks, CD-ROMs, and magneto-optical disks), ROMs, RAMs, EPROMs (Erasable Programmable Read-Only Memory), EEPROMs, flash memories, magnetic cards or optical cards. That is, the readable medium includes any medium that stores or transmits information in a form that can be read by a device (for example, a computer).

[0206] The nonvolatile computer readable storage medium provided by the embodiments of the present application has the same inventive concept as the above-mentioned embodiments. The content not specifically shown in the nonvolatile computer readable storage medium can refer to the above-mentioned embodiments, and will not be described here again.

[0207] In the present application, the terms "first" and "second" are only used for descriptive purposes and cannot be understood or implied to indicate or imply relative importance. The term "a plurality of" means two or more, unless otherwise expressly limited.

[0208] Other embodiments of the present application will be apparent to those skilled in the art from consideration of the specification and practice of the application disclosed herein. The present application is intended to cover any variations, uses or adaptive changes of this application following the general principles thereof and including the disclosures of common knowledge or conventional techniques in the art not disclosed in the present application. The specification and examples are only considered as exemplary.

[0209] It should be understood that the present application is not limited to the precise structures described above and shown in the drawings and that various modifications and changes can be made without departing from the scope thereof. The scope of the present application is only limited by the appended claims.

Claims

1. A method of determining an abnormal concentration of vehicles, characterized by, The method comprises: acquiring a gathering radius, a first distance threshold, a second distance threshold, a quantity threshold, and position data of a plurality of vehicles; determining a plurality of candidate position data according to the plurality of position data, each of the candidate position data satisfying: an average vector distance between other position data in a set region and the candidate position data is less than the first distance threshold, the set region being a region with a position indicated by the candidate position data as a center and the gathering radius as a radius; wherein the determining of the plurality of candidate position data according to the plurality of position data comprises: randomly selecting initial position data from the plurality of position data, and in response to the initial position data not being the candidate position data, iteratively performing the following steps until a candidate position data is determined: in response to i-th iteration determined i-th position data not being the candidate position data, determining an i-th set based on the i-th position data in an i+1-th iteration process, wherein the i-th set is a set of position data located in a region with a position indicated by the i-th position data as a center and the gathering radius as a radius; determining an average vector distance between other position data in the i-th set and the i-th position data; determining a displacement based on the average vector distance; determining i+1-th position data in a region corresponding to the i-th set based on the displacement, wherein i≥1, i is a positive integer, and a first position data determined in a first iteration is determined from a region corresponding to the initial position data; determining vector distances between the plurality of candidate position data; determining abnormal position data according to the vector distances between the plurality of candidate position data, wherein vector distances between the abnormal position data are not less than the second distance threshold; acquiring selected position data in a region corresponding to the abnormal position data, the region corresponding to the abnormal position data being a region with a position indicated by the abnormal position data as a center and the gathering radius as a radius; in response to a number of the selected position data not being less than the quantity threshold, determining vehicle abnormal gathering information, wherein the vehicle abnormal gathering information comprises a gathering position and a gathering quantity, the gathering position being a position indicated by the abnormal position data, and the gathering quantity being a total number of the selected position data.

2. The determination method according to claim 1, characterized in that, After determining one of the candidate position data, the randomly selecting of the initial position data from the plurality of position data comprises: randomly selecting the initial position data from other position data outside a set corresponding to the determined candidate position data to determine a next candidate position data, wherein the set corresponding to the determined candidate position data is a set of position data located in a region with a position indicated by the determined candidate position data as a center and the gathering radius as a radius.

3. The determination method according to claim 1 or 2, characterized in that, The method further comprises: in response to a vector distance between two of the candidate position data being less than the second distance threshold, merging the two of the candidate position data. determining an update vector distance between the merged candidate location data and other candidate location data or other merged candidate location data; determining the abnormal location data based on the update vector distance.

4. The determination method according to claim 1 or 2, characterized in that, Before the determining the plurality of candidate location data according to the plurality of location data, the method further comprises: preprocessing the location data of the plurality of vehicles, the preprocessing comprising at least one of removing incomplete field data, removing abnormal value data, and removing empty row data.

5. The determination method according to claim 1 or 2, characterized in that, After the determining the vehicle abnormal aggregation information, the method further comprises: generating a report and a map display interface according to the vehicle abnormal aggregation information.

6. The determination method according to claim 5, characterized in that, The vehicle abnormal aggregation information further comprises at least one of an offline time, a vehicle model, and a vehicle identification code of a vehicle corresponding to the selected location data.

7. An apparatus for determining an abnormal concentration of vehicles, characterized by The apparatus comprises: a first obtaining module, configured to obtain an aggregation radius, a first distance threshold, a second distance threshold, a quantity threshold, and location data of a plurality of vehicles; a first determining module, configured to determine a plurality of candidate location data according to the plurality of location data, each of the candidate location data satisfying that an average vector distance between other location data in a set region and the candidate location data is less than the first distance threshold, the set region being a region with a center at a location indicated by the candidate location data and a radius of the aggregation radius; wherein the determining the plurality of candidate location data according to the plurality of location data comprises: randomly selecting initial location data from the plurality of location data, and in response to the initial location data not being the candidate location data, iteratively performing the following steps until a candidate location data is determined: in response to i-th location data determined in i-th iteration not being the candidate location data, determining an i-th set based on the i-th location data in an (i+1)-th iteration, the i-th set being a set of location data located in a region with a center at the i-th location data and a radius of the aggregation radius; determining an average vector distance between other location data in the i-th set and the i-th location data; determining a displacement based on the average vector distance; determining (i+1)-th location data in a region corresponding to the i-th set based on the displacement, wherein i≥1, i is a positive integer, and a first location data determined in a first iteration is determined from a region corresponding to the initial location data; a second determining module, configured to determine vector distances between the plurality of candidate location data; a third determining module, configured to determine abnormal location data according to the vector distances between the plurality of candidate location data, wherein a vector distance between the abnormal location data is not less than the second distance threshold; a second obtaining module, configured to obtain selected location data in a region corresponding to each of the abnormal location data, the region corresponding to the abnormal location data being a region with a center at a location indicated by the abnormal location data and a radius of the aggregation radius; A fourth determining module, configured to determine vehicle abnormal gathering information in response to the number of the selected position data being not less than the number threshold, wherein the vehicle abnormal gathering information comprises a gathering position and a gathering number, the gathering position being the position indicated by the abnormal position data, and the gathering number being the total number of the selected position data.

8. An electronic device, comprising: The electronic device comprises: a memory; a processor electrically connected to the memory; the memory stores a computer program, and the computer program is executed by the processor to implement the method for determining vehicle abnormal gathering according to any one of claims 1-6.

9. A non-transitory computer readable storage medium, comprising: The non-volatile computer readable storage medium stores a computer program, and the computer program is executed by the processor to implement the method for determining vehicle abnormal gathering according to any one of claims 1-6.

Images