A method, device, medium and equipment for identifying a nature of a fleet customer

Abstract

The application provides a fleet property identification method, device, medium and equipment. Vehicle information of a target fleet is obtained. Based on the vehicle information of each vehicle, a gathering point of the corresponding vehicle is determined. Based on the gathering point of each vehicle, a distribution distance between any two vehicles in the target fleet is calculated. Based on the distribution distance, the similarity between the two vehicles is determined. Based on the similarity between all vehicles in the target fleet and the vehicle information of all vehicles, the vehicle attribute of each vehicle in the target fleet is determined. Based on the vehicle attribute of all vehicles in the target fleet, the property of the target fleet is determined. According to the distance between the parking point distribution of the vehicles in the fleet, the difference and similarity between the vehicles are determined, thereby distinguishing the attributes of the vehicles in the fleet, and then determining the property of the fleet. The route information of the actual operation of the vehicles in the fleet determines the attributes, which can accurately identify the vehicle attributes and accurately identify the property of the fleet.

Description

Technical Field

[0001] This application relates to the field of vehicle identification technology, specifically to a method, device, medium, and equipment for identifying fleet operators. Background Technology

[0002] In the commercial vehicle transportation industry, based on differences in vehicle ownership and operation management models, vehicle owners are mainly divided into two categories: individual owners and company owners (i.e., fleets). Individual owners are often referred to as small-scale operators, who own a small number of vehicles and operate on a limited scale. In contrast, fleets refer to large-scale freight companies that own dozens to thousands of commercial vehicles. Their operation model is more complex and they are an important part of the industry's transportation capacity. The vehicle composition of a fleet typically includes two types: self-owned vehicles and affiliated vehicles. Self-owned vehicles are purchased and directly owned by the fleet itself, and their operation scheduling, cargo transportation planning, and daily management are all organized and implemented by the fleet. Affiliated vehicles, on the other hand, are actually owned by individuals. The vehicle owners register and affiliate their vehicles to qualified transportation companies to undertake specific transportation business needs (e.g., transportation projects requiring enterprise qualification, long-term contract waybills on fixed routes, etc.). Under this model, although affiliated vehicles legally or formally belong to the fleet, their actual operation management and transportation task arrangement are often still dominated by the individual vehicle owner, and the fleet's direct control is weak.

[0003] In practical operations, accurately determining the true nature of a fleet's business is crucial when assessing its transportation capacity, analyzing credit risk, or regulating the industry. This nature not only affects operational stability but also directly relates to the actual scale of controllable transportation resources. Currently, the industry typically only obtains the total number of vehicles registered under a fleet's name, making it difficult to effectively distinguish the specific number and proportion of self-owned and affiliated vehicles. Assessing solely based on the total number of vehicles often overestimates a fleet's actual ability to dispatch and control transportation capacity. This is especially true for fleets with a high proportion of affiliated vehicles, where their true level of scale and intensive operation may be significantly lower than their nominal size.

[0004] Current technologies lack an effective method for identifying and quantifying the composition of self-owned and affiliated vehicles in a fleet, leading to significant errors in assessing the fleet's actual transport capacity, operational stability, and the nature of its operators. Therefore, a precise and reliable technical solution is urgently needed to distinguish the actual ownership and management model of vehicles, thereby providing accurate data support for vehicle capacity assessment, industry management, and related decision-making. Summary of the Invention

[0005] To address the aforementioned technical problems, this application is proposed. Embodiments of this application provide a method, apparatus, medium, and device for identifying the nature of a fleet operator.

[0006] According to one aspect of this application, a method for identifying the business nature of a fleet is provided, comprising: acquiring all vehicle information of a target fleet; wherein the vehicle information includes the operation information of the corresponding vehicles; determining multiple aggregation points of the corresponding vehicles based on the vehicle information of each vehicle; wherein the aggregation points represent the parking points of the corresponding vehicles; calculating the distribution distance between any two vehicles in the target fleet based on the aggregation points of each vehicle; wherein the distribution distance represents the distribution difference between the aggregation points of the two vehicles; determining the similarity between the corresponding two vehicles based on the distribution distance; determining the vehicle attributes of each vehicle in the target fleet based on the similarity between all vehicles in the target fleet and all vehicle information; wherein the vehicle attributes include self-owned vehicles and affiliated vehicles; and determining the business nature of the target fleet based on the vehicle attributes of all vehicles in the target fleet.

[0007] In one embodiment, determining multiple cluster points for a corresponding vehicle based on the vehicle information of each vehicle includes: determining all parking spots of the corresponding vehicle within a set time period based on the vehicle information of each vehicle; clustering all parking spots of a single vehicle to obtain multiple cluster center points; and selecting the cluster center point of the multiple clusters containing the highest number of parking spots as the cluster point.

[0008] In one embodiment, calculating the distribution distance between any two vehicles in the target convoy based on the aggregation point of each vehicle includes: calculating the distance between any two aggregation points between the two vehicles based on the latitude and longitude information of the aggregation point of each vehicle; and calculating the distribution distance between the two vehicles based on the distance between all aggregation points between the two vehicles.

[0009] In one embodiment, calculating the distribution distance between the two vehicles based on the distance values ​​between all aggregation points between the two vehicles includes: solving for the minimum cost to reach all aggregation points of the other vehicle from all aggregation points of one vehicle based on the distance values ​​between all aggregation points of the two vehicles; and using the minimum cost as the distribution distance between the two vehicles.

[0010] In one embodiment, determining the similarity between two corresponding vehicles based on the distribution distance includes: calculating the median of the distribution distances between all vehicles in the target fleet; and calculating the similarity between two corresponding vehicles based on the distribution distances between the two vehicles and the median.

[0011] In one embodiment, determining the vehicle attributes of each vehicle in the target fleet based on the similarity between all vehicles in the target fleet and all vehicle information includes: inputting the similarity between all vehicles in the target fleet and all vehicle information into a trained neural network model to obtain the vehicle attributes of each vehicle in the target fleet.

[0012] In one embodiment, determining the business nature of the target fleet based on the vehicle attributes of all vehicles in the target fleet includes: determining the business nature of the target fleet based on the proportion of various vehicle attributes in the target fleet.

[0013] According to another aspect of this application, a device for identifying the business nature of a fleet is provided, comprising: a vehicle information acquisition module for acquiring all vehicle information of a target fleet; wherein the vehicle information includes the operation information of the corresponding vehicle; a cluster point determination module for determining multiple cluster points of a corresponding vehicle based on the vehicle information of each vehicle; wherein the cluster point represents the parking point of the corresponding vehicle; a distribution distance calculation module for calculating the distribution distance between any two vehicles in the target fleet based on the cluster points of each vehicle; wherein the distribution distance represents the distribution difference between the cluster points of the two vehicles; a similarity determination module for determining the similarity between corresponding two vehicles based on the distribution distance; a vehicle attribute determination module for determining the vehicle attribute of each vehicle in the target fleet based on the similarity between all vehicles in the target fleet and all vehicle information; wherein the vehicle attribute includes self-owned vehicles and affiliated vehicles; and a business nature determination module for determining the business nature of the target fleet based on the vehicle attributes of all vehicles in the target fleet.

[0014] According to another aspect of this application, a computer-readable storage medium is provided, the storage medium storing a computer program for performing any of the methods described above.

[0015] According to another aspect of this application, an electronic device is provided, comprising: a processor; a memory for storing processor-executable instructions; the processor being configured to perform any of the methods described above.

[0016] This application provides a method, apparatus, medium, and equipment for identifying the business nature of a fleet. The method involves acquiring all vehicle information of a target fleet, including the corresponding vehicle's operational information; determining multiple aggregation points for each vehicle based on its information; each aggregation point representing a parking spot; calculating the distribution distance between any two vehicles in the target fleet based on their aggregation points; the distribution distance representing the distribution difference between the aggregation points of the two vehicles; determining the similarity between the two vehicles based on the distribution distance; determining the vehicle attributes of each vehicle in the target fleet based on the similarity between all vehicles and all vehicle information; vehicle attributes including self-owned vehicles and affiliated vehicles; determining the business nature of the target fleet based on the vehicle attributes of all vehicles in the target fleet; and determining the difference and similarity between vehicles based on the distance between their parking spots, thereby distinguishing the attributes of vehicles in the fleet and determining the business nature of the fleet. The attributes are determined by the actual route information of the vehicles in the fleet, which accurately identifies vehicle attributes and thus accurately identifies the business nature of the fleet. Attached Figure Description

[0017] The above and other objects, features, and advantages of this application will become more apparent from the more detailed description of the embodiments of this application in conjunction with the accompanying drawings. The drawings are provided to further illustrate the embodiments of this application and form part of the specification. They are used together with the embodiments of this application to explain this application and do not constitute a limitation thereof. In the drawings, the same reference numerals generally represent the same components or steps.

[0018] Figure 1 This is a flowchart illustrating a method for identifying the nature of a fleet operator provided in an exemplary embodiment of this application.

[0019] Figure 2 This is a schematic diagram of the structure of a vehicle fleet operator identification device provided in an exemplary embodiment of this application.

[0020] Figure 3 This is a structural diagram of an electronic device provided in an exemplary embodiment of this application. Detailed Implementation

[0021] Hereinafter, exemplary embodiments according to this application will be described in detail with reference to the accompanying drawings. Obviously, the described embodiments are merely some embodiments of this application, and not all embodiments of this application. It should be understood that this application is not limited to the exemplary embodiments described herein.

[0022] Figure 1 This is a flowchart illustrating a method for identifying the nature of a fleet operator according to an exemplary embodiment of this application. Figure 1 As shown, the method for identifying the business nature of this fleet includes the following steps:

[0023] Step 110: Obtain information on all vehicles in the target fleet.

[0024] The vehicle information includes the corresponding vehicle's operational information. Specifically, the vehicle's operational information includes the vehicle's VIN, data collection time, longitude, latitude, and cumulative mileage. This application uses vehicle-to-everything (V2X) big data to obtain the operational information of all vehicles in the target fleet within a certain period (e.g., one month), as a data basis for determining the fleet's business nature.

[0025] Step 120: Based on the vehicle information of each vehicle, determine multiple aggregation points for the corresponding vehicle.

[0026] In this context, the aggregation point represents the parking spot of the corresponding vehicle. Specifically, this application determines a parking spot if the distance a vehicle travels within a time range (e.g., 9 minutes) is less than a length range (e.g., 30 meters).

[0027] Step 130: Based on the aggregation point of each vehicle, calculate the distribution distance between any two vehicles in the target convoy.

[0028] The distribution distance represents the degree of difference in the distribution between the aggregation points of the two vehicles. Typically, the working position of the vehicle (loading or unloading) is the aggregation point. This application determines the difference between the working positions or layouts of the two vehicles by calculating the distribution distance between them.

[0029] Step 140: Determine the similarity between two corresponding vehicles based on the distribution distance.

[0030] Based on the distribution distance, the similarity between the corresponding two vehicles is determined, specifically the degree of similarity in the operating status of the two vehicles, thereby determining whether the two vehicles are of the same type.

[0031] Step 150: Based on the similarity between all vehicles in the target fleet and all vehicle information, determine the vehicle attributes of each vehicle in the target fleet.

[0032] The vehicle attributes include self-owned vehicles and affiliated vehicles. This application determines the vehicle attributes of each vehicle in the target fleet based on the similarity between all vehicles in the target fleet and all vehicle information.

[0033] Step 160: Determine the business nature of the target fleet based on the vehicle attributes of all vehicles in the target fleet.

[0034] After determining the vehicle attributes of all vehicles in the target fleet, the business nature of the target fleet is determined based on the vehicle attributes of all vehicles.

[0035] This application provides a method for identifying the business nature of a fleet, which involves obtaining information on all vehicles in a target fleet, including their operational information; determining multiple aggregation points for each vehicle based on their information, where each aggregation point represents a parking spot; calculating the distribution distance between any two vehicles in the target fleet based on their aggregation points, where the distribution distance represents the distribution difference between the aggregation points of the two vehicles; determining the similarity between the two vehicles based on the distribution distance; determining the vehicle attributes of each vehicle in the target fleet based on the similarity between all vehicles in the target fleet and all vehicle information, where vehicle attributes include self-owned vehicles and affiliated vehicles; determining the business nature of the target fleet based on the vehicle attributes of all vehicles in the target fleet; and determining the difference and similarity between vehicles based on the distance between their parking spots, thereby distinguishing the attributes of vehicles in the fleet and determining the business nature of the fleet. The method also uses the actual route information of the vehicles in the fleet to determine their attributes, which can accurately identify vehicle attributes and thus accurately identify the business nature of the fleet.

[0036] In one embodiment, step 120 can be implemented as follows: based on the vehicle information of each vehicle, determine all parking spots of the corresponding vehicle within a set time period; cluster all parking spots of a single vehicle to obtain multiple cluster center points; select the cluster center point of multiple clusters with the highest number of parking spots as the aggregation point.

[0037] This application clusters all parking spots of vehicles within a set time period (e.g., one month) to obtain multiple clusters and corresponding cluster center points. Each cluster contains multiple parking spots. This application sorts the clusters according to the number of parking spots contained in each cluster from most to least, and selects the cluster center points of the top-ranked clusters (e.g., the top 5) as cluster points. At the same time, relevant data of the cluster points are extracted, including vehicle VIN, cluster point ID, longitude, latitude, number of parking spots, etc.

[0038] In one embodiment, step 130 can be implemented as follows: based on the latitude and longitude information of the aggregation point of each vehicle, calculate the distance between any two aggregation points between the two vehicles; based on the distance between all aggregation points between the two vehicles, calculate the distribution distance between the two vehicles.

[0039] Based on the latitude and longitude information of each vehicle's aggregation point, the distance between any two aggregation points between the two vehicles is calculated. Furthermore, based on the distances between all aggregation points between the two vehicles, the distribution distance between them is calculated. Specifically, the aggregation point data for vehicles A and B includes the number of parking spots at each aggregation point and the corresponding latitude and longitude. Let the number of parking spots at aggregation points for vehicles A and B be: and Correspondingly, the latitude and longitude of the aggregation points for vehicle A and vehicle B are as follows: and Preferably, this application normalizes the number of parking points for vehicle A and vehicle B respectively, using the following normalization formula: , ,in, and The first i The result is the normalized number of parking spots at each aggregation point, and calculations are performed based on the normalized data.

[0040] In one embodiment, step 130 can be implemented as follows: based on the distance between all aggregation points of the two vehicles, calculate the minimum cost to reach all aggregation points of the other vehicle from all aggregation points of one vehicle; and use the minimum cost as the distribution distance between the two vehicles.

[0041] Specifically, the formula for calculating the distance between all aggregation points between two vehicles is as follows:

[0042] ;

[0043] in, This is the distance function.

[0044] This application calculates the distance between all aggregation points of two vehicles in a target convoy, and uses the minimum cost to reach all aggregation points of the other vehicle from all aggregation points of one vehicle as the distribution distance between the two vehicles. Specifically, this application assumes that the five aggregation points of vehicle A and vehicle B are each represented by five mounds of earth. The distribution distance between vehicle A and vehicle B is achieved by transferring soil from the five mounds of vehicle A to the five mounds of vehicle B to achieve the same distribution as the five mounds of vehicle B. The decision variable... The first vehicle representing vehicle A i The soil needs to be moved to vehicle B. j Record the amount of soil piled up. This problem, which represents the cost of transportation, is transformed into a linear programming problem, i.e., solving... The minimum value of the expression, where, m That is the number of mounds of dirt belonging to vehicle A. n Let be the number of mounds of earth for vehicle B, for example, set to 5. Since all the mounds of earth for vehicle A need to be moved, and the mounds of earth for vehicle B are also just filled, the above linear programming problem must satisfy the following constraints:

[0045] , ;

[0046] The linear programming problem described above is:

[0047] ;

[0048] in, To minimize costs, Let be a vector consisting of the distance values ​​between the aggregation points of any two vehicles in the convoy. As constraints, For example, a constant term. .

[0049] In one embodiment, step 140 can be implemented by: calculating the median of the distribution distances between all vehicles in the target fleet; and calculating the similarity between two vehicles based on the distribution distances and the median between them.

[0050] Specifically, the formula for calculating the similarity between two vehicles is:

[0051] ;

[0052] in, The similarity between vehicle A and vehicle B. The median is the distribution distance between all vehicles in the convoy. The smaller the distribution distance between two vehicles, the greater their similarity, which is closer to 1. If the distribution distance is large, the similarity will quickly decay to close to 0.

[0053] After calculating the similarity between every two vehicles, an adjacency matrix for the target fleet is constructed based on the similarity between all vehicles in the fleet, specifically:

[0054] .

[0055] In one embodiment, step 150 can be implemented by inputting the similarity between all vehicles in the target fleet and all vehicle information into the trained neural network model to obtain the vehicle attributes of each vehicle in the target fleet.

[0056] The neural network model trained in this application is a three-layer graph convolutional neural network. Specifically, the output dimensions of the three convolutional layers are 32, 32, and 8, respectively. The output of each convolutional layer is: , , yes The degree matrix, Yes E A symmetric normalization was performed. For the first The layer's weight parameter matrix, The activation function is non-linear; the output dimension of the neural network model is 2 (self-owned or affiliated). This application inputs the similarity between all vehicles in the fleet (i.e., the adjacency matrix of the target fleet) and all vehicle information (feature matrix) into the neural network model to obtain the vehicle attributes of each vehicle in the target fleet. The feature matrix is ​​obtained by concatenating the static information of the vehicles after one-hot encoding. The static information of the vehicles includes static parameters such as vehicle type, brand, fuel type, horsepower range, and vehicle age. This application uses the feature matrix as the embedding vector of the vehicle nodes, and together with the adjacency matrix, it is input into the neural network model.

[0057] In one embodiment, step 160 can be implemented by determining the business nature of the target fleet based on the proportion of various vehicle attributes in the target fleet.

[0058] After determining the attributes of all vehicles in the target fleet, the business type of the target fleet is determined based on the proportion of each vehicle attribute. Specifically, if the proportion of self-owned vehicles in the target fleet is greater than 80%, the business type of the target fleet is determined to be self-owned; if the proportion of self-owned vehicles in the target fleet is between 30% and 80%, the business type of the target fleet is determined to be self-owned plus affiliated; if the proportion of self-owned vehicles in the target fleet is less than 30%, the business type of the target fleet is determined to be affiliated.

[0059] Figure 2 This is a schematic diagram of the structure of a vehicle fleet operator identification device provided in an exemplary embodiment of this application. For example... Figure 2 As shown, the vehicle fleet identification device 20 includes: a vehicle information acquisition module 21, used to acquire all vehicle information of the target fleet; wherein, the vehicle information includes the corresponding vehicle's operating information; a cluster point determination module 22, used to determine multiple cluster points of the corresponding vehicle based on the vehicle information of each vehicle; wherein, the cluster point represents the parking point of the corresponding vehicle; a distribution distance calculation module 23, used to calculate the distribution distance between any two vehicles in the target fleet based on the cluster points of each vehicle; wherein, the distribution distance represents the distribution difference between the cluster points of the two vehicles; a similarity determination module 24, used to determine the similarity between corresponding two vehicles based on the distribution distance; a vehicle attribute determination module 25, used to determine the vehicle attribute of each vehicle in the target fleet based on the similarity between all vehicles in the target fleet and all vehicle information; wherein, the vehicle attribute includes self-owned vehicles and affiliated vehicles; and a fleet nature determination module 26, used to determine the fleet nature of the target fleet based on the vehicle attributes of all vehicles in the target fleet.

[0060] This application provides a vehicle fleet operator identification device. The device acquires all vehicle information of the target fleet through a vehicle information acquisition module 21, whereby the vehicle information includes the corresponding vehicle's operational information. A cluster point determination module 22 determines multiple cluster points for each vehicle based on its vehicle information, where each cluster point represents a parking point of the corresponding vehicle. A distribution distance calculation module 23 calculates the distribution distance between any two vehicles in the target fleet based on the cluster points of each vehicle, where the distribution distance represents the distribution difference between the cluster points of the two vehicles. A similarity determination module 24 determines the similarity between two corresponding vehicles based on the distribution distance. The vehicle attribute determination module 25 determines the vehicle attributes of each vehicle in the target fleet based on the similarity between all vehicles and all vehicle information; the vehicle attributes include self-owned vehicles and affiliated vehicles. The business nature determination module 26 determines the business nature of the target fleet based on the vehicle attributes of all vehicles in the target fleet; it determines the difference and similarity between vehicles based on the distance between the parking points of vehicles in the fleet, thereby distinguishing the attributes of vehicles in the fleet and determining the business nature of the fleet. The attributes are determined by the actual route information of the vehicles in the fleet, which can accurately identify vehicle attributes and thus accurately identify the business nature of the fleet.

[0061] In one embodiment, the above-mentioned cluster point determination module 22 can be further configured to: determine all parking points of the corresponding vehicle within a set time period based on the vehicle information of each vehicle; cluster all parking points of a single vehicle to obtain multiple cluster center points; and select the cluster center point of multiple clusters containing the highest number of parking points as the cluster point.

[0062] In one embodiment, the above-mentioned distribution distance calculation module 23 can be further configured to: calculate the distance between any two aggregation points between two vehicles based on the latitude and longitude information of the aggregation point of each vehicle; and calculate the distribution distance between the two vehicles based on the distance between all aggregation points between the two vehicles.

[0063] In one embodiment, the above-mentioned distribution distance calculation module 23 can be further configured to: calculate the minimum cost from all the aggregation points of one vehicle to all the aggregation points of the other vehicle based on the distance values ​​between all the aggregation points of the two vehicles; and use the minimum cost as the distribution distance between the two vehicles.

[0064] In one embodiment, the similarity determination module 24 can be further configured to: calculate the median of the distribution distance between all vehicles in the target fleet; and calculate the similarity between two corresponding vehicles based on the distribution distance and the median between the two vehicles.

[0065] In one embodiment, the vehicle attribute determination module 25 can be further configured to input the similarity between all vehicles in the target fleet and all vehicle information into the trained neural network model to obtain the vehicle attributes of each vehicle in the target fleet.

[0066] In one embodiment, the aforementioned business type determination module 26 can be further configured to: determine the business type of the target fleet based on the proportion of various vehicle attributes in the target fleet.

[0067] Below, for reference Figure 3 This application describes an electronic device according to embodiments thereof. The electronic device may be either or both of a first device and a second device, or a standalone device independent of them, which may communicate with the first device and the second device to receive acquired input signals from them.

[0068] Figure 3 A block diagram of an electronic device according to an embodiment of this application is illustrated.

[0069] like Figure 3 As shown, the electronic device 10 includes one or more processors 11 and memory 12.

[0070] The processor 11 may be a central processing unit (CPU) or other form of processing unit with data processing capabilities and / or instruction execution capabilities, and may control other components in the electronic device 10 to perform desired functions.

[0071] The memory 12 may include one or more computer program products, which may include various forms of computer-readable storage media, such as volatile memory and / or non-volatile memory. The volatile memory may include, for example, random access memory (RAM) and / or cache memory. The non-volatile memory may include, for example, read-only memory (ROM), hard disk, flash memory, etc. One or more computer program instructions may be stored on the computer-readable storage medium, and the processor 11 may execute the program instructions to implement the methods of the various embodiments of this application described above and / or other desired functions. Various contents such as input signals, signal components, and noise components may also be stored in the computer-readable storage medium.

[0072] In one example, the electronic device 10 may also include an input device 13 and an output device 14, which are interconnected via a bus system and / or other forms of connection mechanism (not shown).

[0073] When the electronic device is a standalone device, the input device 13 can be a communication network connector for receiving the collected input signals from the first device and the second device.

[0074] In addition, the input device 13 may also include, for example, a keyboard, a mouse, etc.

[0075] The output device 14 can output various information to the outside, including determined distance information, direction information, etc. The output device 14 may include, for example, a display, a speaker, a printer, and a communication network and its connected remote output devices, etc.

[0076] Of course, for the sake of simplicity, Figure 3 Only some of the components of the electronic device 10 relevant to this application are shown in this illustration; components such as buses, input / output interfaces, etc., are omitted. In addition, the electronic device 10 may include any other suitable components depending on the specific application.

[0077] In addition to the methods and apparatus described above, embodiments of this application may also be computer program products, which include computer program instructions that, when executed by a processor, cause the processor to perform the steps in the methods according to various embodiments of this application described in the "Exemplary Methods" section above.

[0078] The computer program product can be written in any combination of one or more programming languages ​​to perform the operations of the embodiments of this application. The programming languages ​​include object-oriented programming languages ​​such as Java and C++, as well as conventional procedural programming languages ​​such as C or similar languages. The program code can be executed entirely on the user's computing device, partially on the user's computing device, as a standalone software package, partially on the user's computing device and partially on a remote computing device, or entirely on a remote computing device or server.

[0079] Furthermore, embodiments of this application may also be computer-readable storage media storing computer program instructions thereon, which, when executed by a processor, cause the processor to perform the steps in the methods according to various embodiments of this application described in the "Exemplary Methods" section above.

[0080] The computer-readable storage medium may be any combination of one or more readable media. A readable medium may be a readable signal medium or a readable storage medium. A readable storage medium may be, for example, an electrical, magnetic, optical, electromagnetic, infrared, or semiconductor system, apparatus, or device, or any combination thereof. More specific examples of readable storage media (a non-exhaustive list) include: an electrical connection having one or more wires, a portable disk, a hard disk, random access memory (RAM), read-only memory (ROM), erasable programmable read-only memory (EPROM or flash memory), optical fiber, portable compact disk read-only memory (CD-ROM), optical storage device, magnetic storage device, or any suitable combination thereof.

[0081] The basic principles of this application have been described above with reference to specific embodiments. However, it should be noted that the advantages, benefits, and effects mentioned in this application are merely examples and not limitations, and should not be considered as essential features of each embodiment of this application. Furthermore, the specific details disclosed above are for illustrative and facilitative purposes only, and are not limitations. These details do not limit the application to the necessity of employing the aforementioned specific details for implementation.

[0082] The block diagrams of devices, apparatuses, devices, and systems involved in this application are merely illustrative examples and are not intended to require or imply that they must be connected, arranged, or configured in the manner shown in the block diagrams. As those skilled in the art will recognize, these devices, apparatuses, devices, and systems can be connected, arranged, and configured in any manner. Words such as “comprising,” “including,” “having,” etc., are open-ended terms meaning “including but not limited to,” and are used interchangeably with them. The terms “or” and “and” as used herein refer to the terms “and / or,” and are used interchangeably with them unless the context clearly indicates otherwise. The term “such as” as used herein refers to the phrase “such as but not limited to,” and is used interchangeably with it.

[0083] It should also be noted that in the apparatus, equipment, and methods of this application, the components or steps can be disassembled and / or recombined. These disassemblies and / or recombinations should be considered as equivalent solutions of this application.

[0084] The above description of the disclosed aspects is provided to enable any person skilled in the art to make or use this application. Various modifications to these aspects will be readily apparent to those skilled in the art, and the general principles defined herein can be applied to other aspects without departing from the scope of this application. Therefore, this application is not intended to be limited to the aspects shown herein, but rather to be accorded the widest scope consistent with the principles and novel features disclosed herein.

[0085] The above description has been given for purposes of illustration and description. Furthermore, this description is not intended to limit the embodiments of this application to the forms disclosed herein. Although numerous exemplary aspects and embodiments have been discussed above, those skilled in the art will recognize certain variations, modifications, alterations, additions, and sub-combinations thereof.

Claims

1. A method for identifying the nature of a fleet operator, characterized in that, include: Obtain all vehicle information of the target fleet; wherein, the vehicle information includes the corresponding vehicle's operating information; Based on the vehicle information of each vehicle, multiple gathering points for the corresponding vehicle are determined; wherein, the gathering point represents the parking point of the corresponding vehicle. Based on the aggregation point of each vehicle, the distribution distance between any two vehicles in the target convoy is calculated; wherein, the distribution distance represents the distribution difference between the aggregation points of the two vehicles. Based on the distribution distance, the similarity between the corresponding two vehicles is determined; Based on the similarity between all vehicles in the target fleet and all vehicle information, the vehicle attributes of each vehicle in the target fleet are determined; wherein, the vehicle attributes include self-owned vehicles and affiliated vehicles; Based on the vehicle attributes of all vehicles in the target fleet, the business nature of the target fleet is determined.

2. The method for identifying the nature of fleet operators according to claim 1, characterized in that, The process of determining multiple aggregation points for a corresponding vehicle based on the vehicle information of each vehicle includes: Based on the vehicle information of each vehicle, determine all parking spots for the corresponding vehicle within a set time period; Cluster all parking spots of a single vehicle to obtain multiple cluster centers; The cluster center of the cluster containing the top-ranked clusters in terms of the number of parking spots is selected as the aggregation point.

3. The method for identifying the nature of fleet operators according to claim 1, characterized in that, The calculation of the distribution distance between any two vehicles in the target convoy, based on the aggregation point of each vehicle, includes: Based on the latitude and longitude information of the aggregation point of each vehicle, calculate the distance between any two aggregation points between two vehicles. Calculate the distribution distance between the two vehicles based on the distance values ​​between all aggregation points between the two vehicles.

4. The method for identifying the nature of fleet operators according to claim 3, characterized in that, The calculation of the distribution distance between the two vehicles based on the distance values ​​between all aggregation points between them includes: Based on the distances between all aggregation points of the two vehicles, find the minimum cost to reach all aggregation points of the other vehicle from all aggregation points of one vehicle. The minimum cost is taken as the distribution distance between the two vehicles.

5. The method for identifying the nature of fleet operators according to claim 1, characterized in that, Determining the similarity between two corresponding vehicles based on the distribution distance includes: Calculate the median of the distribution distances between all vehicles in the target convoy; The similarity between two vehicles is calculated based on the distribution distance between them and the median.

6. The method for identifying the nature of fleet operators according to claim 1, characterized in that, The process of determining the vehicle attributes of each vehicle in the target fleet based on the similarity between all vehicles in the target fleet and all vehicle information includes: The similarity between all vehicles in the target fleet and all vehicle information are input into the trained neural network model to obtain the vehicle attributes of each vehicle in the target fleet.

7. The method for identifying the nature of fleet operators according to claim 1, characterized in that, The determination of the business nature of the target fleet based on the vehicle attributes of all vehicles in the target fleet includes: Based on the proportion of various vehicle attributes in the target fleet, the business nature of the target fleet is determined.

8. A device for identifying the nature of a fleet operator, characterized in that, include: The vehicle information acquisition module is used to acquire all vehicle information of the target fleet; wherein, the vehicle information includes the operation information of the corresponding vehicle; The aggregation point determination module is used to determine multiple aggregation points for each vehicle based on the vehicle information of each vehicle; wherein, the aggregation point represents the parking point of the corresponding vehicle. The distribution distance calculation module is used to calculate the distribution distance between any two vehicles in the target fleet based on the aggregation point of each vehicle; wherein the distribution distance represents the distribution difference between the aggregation points of the two vehicles. A similarity determination module is used to determine the similarity between two corresponding vehicles based on the distribution distance; The vehicle attribute determination module is used to determine the vehicle attributes of each vehicle in the target fleet based on the similarity between all vehicles in the target fleet and all vehicle information; wherein, the vehicle attributes include self-owned vehicles and affiliated vehicles; The business type determination module is used to determine the business type of the target fleet based on the vehicle attributes of all vehicles in the target fleet.

9. A computer-readable storage medium, characterized in that, The storage medium stores a computer program for performing the method described in any one of claims 1-7.

10. An electronic device, characterized in that, include: processor; Memory used to store the processor's executable instructions; The processor is used to execute the method described in any one of claims 1-7.

Images