A vehicle model determination method and device based on an aggregation area stop

Abstract

The application relates to a vehicle model determination method and device based on an aggregation area parking. The method comprises the following steps: acquiring a plurality of aggregation areas where vehicles are parked; calculating vehicle data corresponding to the aggregation areas where the plurality of vehicles are parked within a preset time; determining the attributes of the aggregation areas based on the vehicle data; initializing a vehicle label of a known vehicle model in any aggregation area for an aggregation area with a strong vehicle model attribute and an aggregation area with a weak vehicle model attribute, calculating a vehicle model distribution vector of an unknown vehicle model in the aggregation area, and taking any unknown vehicle as a target vehicle; and transmitting the calculated vehicle model to all the aggregation areas associated with the target vehicle. The application can more accurately and completely determine the vehicle model, especially by determining the distribution of the vehicle through the association relationship between the aggregation area and the vehicle and making the determination of the vehicle model more rapid through the transmission of the vehicle model, so that subsequent data processing is more convenient, and the efficiency of data processing is improved as a whole. Therefore, the method has more application scenarios.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of data mining and data processing, and more particularly to a vehicle model determination method and device based on parking in aggregation areas. BACKGROUND

[0002] At present, with the development of logistics business, various vehicles, especially truck transportation, are more and more widely used, but because of long-distance transportation, they may be parked in various aggregation areas, such as when loading and unloading, when resting, when refueling, when congested, and so on. However, with the development of logistics business, there are also many cases of vehicle violations and even escape, so determining the vehicle model of each aggregation area can help the vehicle inspection work and the needs of many related application scenarios. SUMMARY

[0003] Based on the above technical problems, the present application aims to determine the aggregation area attribute of the parked vehicle first, and then calculate the vehicle model distribution vector of the unknown vehicle model in the strong vehicle model attribute aggregation area and the weak vehicle model attribute aggregation area, and transfer the calculated vehicle model to all aggregation areas associated with the target vehicle.

[0004] The first aspect of the present application provides a vehicle model determination method based on parking in aggregation areas, which comprises:

[0005] Obtaining a plurality of aggregation areas where vehicles are parked;

[0006] Calculating vehicle data corresponding to the plurality of aggregation areas where vehicles are parked within a preset time, wherein the vehicle data at least includes the total number of vehicles, the number of vehicles of known vehicle models, and the number of vehicles of unknown vehicle models;

[0007] Determining the attributes of each aggregation area based on the vehicle data, wherein the attributes of each aggregation area at least include a strong vehicle model attribute aggregation area, a weak vehicle model attribute aggregation area, and a no vehicle model attribute aggregation area;

[0008] Initializing the vehicle label of the known vehicle model in any aggregation area for the strong vehicle model attribute aggregation area and the weak vehicle model attribute aggregation area, calculating the vehicle model distribution vector of the unknown vehicle model in the aggregation area, and taking any vehicle of the unknown vehicle model as a target vehicle;

[0009] Transferring the calculated vehicle model to all aggregation areas associated with the target vehicle.

[0010] In some embodiments of the present application, the determination of the attributes of each aggregation area based on the vehicle data comprises:

[0011] Calculating the proportion of each vehicle model in each aggregation area according to the total number of vehicles, the number of vehicles of known vehicle models, and the number of vehicles of unknown vehicle models in each aggregation area.

[0012] Calculate the vehicle entropy value of each cluster area based on the proportion of each vehicle type in each cluster area;

[0013] The attributes of each cluster area are determined based on the vehicle entropy value of each cluster area.

[0014] In some embodiments of the present invention, the formula for calculating the vehicle entropy value of each cluster area is as follows:

[0015]

[0016] Where H(X) represents the entropy function, X = {x1, x2, ..., x} n} represents the various vehicle types within the cluster area, p(x i (x) represents the vehicle model. i The percentage of the cluster area, where n represents the total number of vehicle models.

[0017] In some embodiments of the present invention, the formula for transferring the calculated vehicle model to all clusters associated with the target vehicle is as follows:

[0018]

[0019] Where, p v (x i () indicates that the target vehicle model is x i The probability, This indicates that the vehicle model is x in the j-th cluster area where the target vehicle has stopped. i The probability is given by m, where m is the number of clusters where the target vehicle stops.

[0020] In some embodiments of the invention, after transmission to all gathering areas associated with the target vehicle, the method further includes:

[0021] Recalculate the vehicle proportion of the preset vehicle type in each cluster area;

[0022] The vehicle model label is updated based on the recalculated percentage.

[0023] In some embodiments of the present invention, the formula for calculating the proportion of preset vehicle types in each cluster area is as follows:

[0024]

[0025] Where, p a (x i () indicates that the vehicle model is x i The proportion of vehicles in any cluster area, N i For vehicles with a clearly defined model label and the label is x i The number of vehicles, N all This refers to the total number of vehicles within the cluster area. probability that the kth unlabeled vehicle model is x i n is the number of unlabeled vehicles whose model is x i

[0026] In some embodiments of the present application, updating the model label according to the recalculated proportion includes:

[0027] determining a probability value of the target vehicle belonging to a preset model according to the recalculated proportion;

[0028] when the probability value of belonging to the preset model exceeds a preset threshold, determining the preset model as the model label of the target vehicle.

[0029] The second aspect of the present application provides a vehicle model determination device based on an aggregation area parking, and the device includes:

[0030] an acquisition module for acquiring a plurality of aggregation areas where vehicles are parked;

[0031] a first calculation module for calculating vehicle data corresponding to the plurality of aggregation areas where vehicles are parked within a preset time, wherein the vehicle data at least includes a total number of vehicles, a number of vehicles of known models, and a number of vehicles of unknown models;

[0032] an attribute module for determining attributes of each aggregation area based on the vehicle data, wherein the attributes of each aggregation area at least include a strong model attribute aggregation area, a weak model attribute aggregation area, and a no model attribute aggregation area;

[0033] a second calculation module for initializing a vehicle label of a known model in any aggregation area, calculating a vehicle model distribution vector of an unknown model in the aggregation area, and taking any vehicle of the unknown model as a target vehicle, for the strong model attribute aggregation area and the weak model attribute aggregation area;

[0034] a transmission module for transmitting a calculated belonging model to all aggregation areas associated with the target vehicle.

[0035] The third aspect of the present application provides a computer device including a memory and a processor, the memory stores computer readable instructions, and the computer readable instructions are executed by the processor to make the processor execute the following steps:

[0036] acquiring a plurality of aggregation areas where vehicles are parked;

[0037] calculating vehicle data corresponding to the plurality of aggregation areas where vehicles are parked within a preset time, wherein the vehicle data at least includes a total number of vehicles, a number of vehicles of known models, and a number of vehicles of unknown models;

[0038] ​determine attributes of each cluster based on the vehicle data, wherein the attributes of each cluster at least include a strong vehicle attribute cluster, a weak vehicle attribute cluster and a no vehicle attribute cluster;

[0039] initialize a vehicle label of a known vehicle in any of the clusters, calculate a vehicle type distribution vector of an unknown vehicle in the cluster, and take the vehicle of any of the unknown vehicles as a target vehicle for the strong vehicle attribute cluster and the weak vehicle attribute cluster;

[0040] pass the calculated vehicle type to all clusters associated with the target vehicle.

[0041] The fourth aspect of the present application provides a computer readable storage medium, which stores a computer program, and the computer program is executed by a processor to implement the steps of:

[0042] obtain a plurality of clusters where vehicles are parked;

[0043] calculate vehicle data corresponding to the clusters where the plurality of vehicles are parked within a preset time, wherein the vehicle data at least includes a total number of vehicles, a number of vehicles of known vehicle types and a number of vehicles of unknown vehicle types;

[0044] determine attributes of each cluster based on the vehicle data, wherein the attributes of each cluster at least include a strong vehicle attribute cluster, a weak vehicle attribute cluster and a no vehicle attribute cluster;

[0045] initialize a vehicle label of a known vehicle in any of the clusters, calculate a vehicle type distribution vector of an unknown vehicle in the cluster, and take the vehicle of any of the unknown vehicles as a target vehicle for the strong vehicle attribute cluster and the weak vehicle attribute cluster;

[0046] pass the calculated vehicle type to all clusters associated with the target vehicle.

[0047] The technical scheme provided in the embodiments of the present application has at least the following technical effects or advantages:

[0048] The application first acquires a plurality of vehicle parking aggregation areas, calculates vehicle data corresponding to the plurality of vehicle parking aggregation areas within a preset time, wherein the vehicle data at least includes total number of vehicles, number of vehicles of known vehicle models and number of vehicles of unknown vehicle models, determines aggregation area attributes based on the vehicle data, wherein the aggregation area attributes at least include strong vehicle model attribute aggregation area, weak vehicle model attribute aggregation area and no vehicle model attribute aggregation area, initializes vehicle labels of known vehicle models in any aggregation area for the strong vehicle model attribute aggregation area and the weak vehicle model attribute aggregation area, calculates vehicle model distribution vectors of unknown vehicle models in the aggregation area, takes any unknown vehicle model as a target vehicle, and finally transmits the calculated vehicle model to all aggregation areas associated with the target vehicle, so as to more accurately and completely determine the vehicle model, especially by determining the distribution of vehicles through the association relationship between the aggregation area and the vehicle and making the determination of the vehicle model more efficient through the transmission of the vehicle model, thereby facilitating subsequent data processing and improving the efficiency of data processing as a whole, so that the method of the application will have more application scenarios.

[0049] It should be understood that the foregoing general description and the following detailed description are only exemplary and explanatory, and cannot limit the application. BRIEF DESCRIPTION OF DRAWINGS

[0050] Various other advantages and benefits will become apparent to those of ordinary skill in the art upon reading the following detailed description of the preferred embodiments. The accompanying drawings are included to provide a description of the preferred embodiments, and are not meant to limit the present application. Moreover, the same reference numerals in the attached drawings refer to the same or similar components throughout the several drawings. In the drawings:

[0051] Figure 1 A method for determining vehicle model based on aggregation area parking in an exemplary embodiment of the application is shown;

[0052] Figure 2 A relationship between aggregation area and vehicle in an exemplary embodiment of the application is shown;

[0053] Figure 3 A vehicle model transmission diagram in an exemplary embodiment of the application is shown;

[0054] Figure 4 A structure diagram of a device for determining vehicle model based on aggregation area parking in an exemplary embodiment of the application is shown;

[0055] Figure 5 A structure diagram of a computer device provided by an exemplary embodiment of the application is shown. DETAILED DESCRIPTION

[0056] Hereinafter, embodiments of the present application will be described with reference to the accompanying drawings. It is to be understood, however, that the description is merely exemplary of the present application, and is not intended to limit the scope of the present application. Also, in the following description, well-known functions or constructions are not described in detail since they would obscure the application in unnecessary detail. It is to be understood that the present application can be implemented without one or more of these details.

[0057] It is to be understood that the terms used herein are merely exemplary based on the embodiments of the present application, and are not intended to limit the scope of the exemplary embodiments of the present application. As used herein, the singular forms are intended to include the plural forms as well, unless the context clearly indicates otherwise. It will be further understood that the terms "comprises" and / or "has," when used herein, specify the presence of stated features, integers, steps, operations, elements, and / or components, but do not preclude the presence or addition of one or more other features, integers, steps, operations, elements, components, and / or any combinations thereof.

[0058] Now, exemplary embodiments according to the present application will be described in more detail with reference to the accompanying drawings. However, these exemplary embodiments can be implemented in various different forms, and should not be construed as limited to only the embodiments set forth herein. The drawings are not drawn to scale, in which some details can be exaggerated for the purpose of clarity and some details can be omitted. The shapes of various regions, layers, and relative sizes and positional relationships among them shown in the drawings are merely exemplary, and can be varied in actual implementation due to manufacturing tolerances or technical limitations, and can be designed in various shapes, sizes, and relative positions by those skilled in the art as needed.

[0059] The above-described exemplary embodiments of the present application can be applied to a variety of electronic devices. Hereinafter, a few exemplary embodiments will be described with reference to the accompanying drawings. Figure 1 - FIGS. Figure 5 Several embodiments will be given to describe exemplary implementations according to the present application. It is noted that the following application scenarios are merely shown to facilitate understanding of the spirit and principles of the present application, and the implementations of the present application are not limited in this respect. On the contrary, the implementations of the present application can be applied to any applicable scenario.

[0060] Embodiment 1:

[0061] This embodiment provides a vehicle model determination method based on aggregation area parking, as shown in the following formula (1): Figure 1 The method comprises the following steps:

[0062] S1, obtaining a plurality of aggregation areas where vehicles are parked;

[0063] S2, calculate vehicle data corresponding to the aggregation area where the plurality of vehicles stop within a preset time, wherein the vehicle data at least includes total number of vehicles, number of vehicles of known vehicle models, and number of vehicles of unknown vehicle models;

[0064] S3, determine attributes of each aggregation area based on the vehicle data, wherein the attributes of each aggregation area at least include strong vehicle model attribute aggregation area, weak vehicle model attribute aggregation area, and no vehicle model attribute aggregation area;

[0065] S4, initialize vehicle label of known vehicle models in any aggregation area for the strong vehicle model attribute aggregation area and the weak vehicle model attribute aggregation area, calculate vehicle model distribution vector of unknown vehicle models in the aggregation area, and take any vehicle of the unknown vehicle models as a target vehicle;

[0066] S5, transfer the calculated vehicle model to all aggregation areas associated with the target vehicle.

[0067] In a specific implementation, determining the attributes of each aggregation area based on the vehicle data comprises: calculating the proportion of each vehicle model in each aggregation area according to the total number of vehicles, the number of vehicles of known vehicle models, and the number of vehicles of unknown vehicle models in each aggregation area; calculating the vehicle model entropy value of each aggregation area according to the proportion of each vehicle model in each aggregation area; and determining the attributes of each aggregation area according to the vehicle model entropy value of each aggregation area.

[0068] In a specific implementation, the formula for calculating the vehicle model entropy value of each aggregation area is:

[0069]

[0070] wherein H(X) represents an entropy function, X={x1, x2, …, xn} represents various vehicle models in the aggregation area, p(x) is the proportion of the vehicle model x in the aggregation area, and n represents the total number of vehicle models. n} represents various vehicle models in the aggregation area, p(x i ) is the proportion of the vehicle model x i in the aggregation area, and n represents the total number of vehicle models.

[0071] In a specific implementation, the formula for transferring the calculated vehicle model to all aggregation areas associated with the target vehicle is:

[0072]

[0073] wherein p(x v ) represents the probability that the target vehicle is of the vehicle model x i , p(x i |Xj) represents the probability that the vehicle model is x i in the jth aggregation area where the target vehicle has stopped, and m is the number of aggregation areas where the target vehicle has stopped.

[0074] ​In a specific implementation, the method further comprises: recalculating the vehicle proportion of the preset vehicle model in each aggregation area; and updating the vehicle model label according to the recalculated proportion.

[0075] In a specific implementation, the formula for calculating the vehicle proportion of the preset vehicle model in each aggregation area is:

[0076]

[0077] wherein p a (x i ) represents the proportion of vehicles of the vehicle model x i in any aggregation area, N i represents the number of vehicles with a clear vehicle model label and the label is x i , N all represents the total number of vehicles in the aggregation area, pk represents the probability that the kth unlabeled vehicle is of the vehicle model x i , and n represents the number of unlabeled vehicles of the vehicle model x i .

[0078] In another specific implementation, updating the vehicle model label according to the recalculated proportion comprises: determining the probability value of the preset vehicle model to which the target vehicle belongs according to the recalculated proportion; and determining the preset vehicle model as the vehicle model label of the target vehicle when the probability value of the preset vehicle model exceeds a preset threshold.

[0079] It should be understood that the foregoing general description and the following detailed description are only exemplary and explanatory, and are not limiting to the present application.

[0080] Embodiment 2

[0081] The embodiment provides a vehicle model determination method based on aggregation area parking.

[0082] Firstly, a plurality of aggregation areas where vehicles are parked are obtained.

[0083] In a specific implementation, the plurality of aggregation areas where vehicles are parked can be found by grid search, such as gas stations, rest areas, express delivery and logistics parks, and self-unloading trucks near construction sites. The key to grid search for target positioning is to divide appropriate grids according to existing prior conditions and construct appropriate adaptive functions to calculate the adaptive value of each grid point. Grid search calculates point by point with a fixed step, which can avoid local optimization caused by multiple extreme values of the cost function, and thus can find the optimal solution.

[0084] The second step is to calculate the vehicle data corresponding to the cluster areas where the multiple vehicles stop within a preset time period. The vehicle data includes at least the total number of vehicles, the number of vehicles with known models, and the number of vehicles with unknown models.

[0085] The preset timeframe here can be one year, six months, three months, or one month. This refers to calculating vehicle data corresponding to multiple parking clusters, such as... Figure 2 As shown, this can be viewed as establishing a relationship network between two entities: clusters and vehicles, with each cluster corresponding to a list of vehicles. Figure 2 In the diagram, rectangles represent clusters, hexagons represent vehicles, and the edge between a vehicle and a cluster indicates that the vehicle has stopped in that cluster, meaning the two are related. Figure 2 In cluster A, known vehicle types include vehicles 1, 2, and 3, while unknown vehicle types include vehicles 4, 5, and 6. Of course, clusters B, C, and D also contain vehicle 5, indicating that vehicle 5 is associated with all three clusters—A, B, C, and D—meaning it has stopped in all of them. Alternatively, by clustering stop points, polygonal representations of cluster areas can be generated. By calculating the number of vehicles stopping in these areas within a specified timeframe (e.g., one year), a network relationship between vehicles and clusters can be established, yielding relevant data for both entities. This data includes at least the total number of vehicles, the number of vehicles with known vehicle types, the number of vehicles with unknown vehicle types, and the specific names of the known vehicle types.

[0086] The third step is to determine the attributes of each cluster area based on the vehicle data. The attributes of each cluster area include at least a cluster area with strong vehicle type attributes, a cluster area with weak vehicle type attributes, and a cluster area with no vehicle type attributes.

[0087] In one specific implementation, determining the attributes of each cluster area based on the vehicle data includes: calculating the proportion of each vehicle type in each cluster area based on the total number of vehicles in each cluster area, the number of vehicles with known vehicle types, and the number of vehicles with unknown vehicle types; calculating the vehicle type entropy value of each cluster area based on the proportion of each vehicle type in each cluster area; and determining the attributes of each cluster area based on the vehicle type entropy value of each cluster area. The formula for calculating the vehicle type entropy value of each cluster area is:

[0088]

[0089] Where H(X) represents the entropy function, X = {x1, x2, ..., x} n} represents the various vehicle types within the cluster area, p(x i (x) represents the vehicle model. i The proportion of vehicle types in a cluster, where n represents the total number of vehicle types. The more chaotic the vehicle types within a cluster, the higher its entropy value.

[0090] Based on the entropy values ​​of each cluster, clusters are divided into three categories: clusters with strong vehicle type attributes, clusters with weak vehicle type attributes, and clusters with no vehicle type attributes. Clusters with strong vehicle type attributes are those dominated by a single vehicle type, such as refrigerated trucks near fresh food markets, container trucks inside ports, vans in express delivery and logistics parks, and dump trucks near construction sites. Clusters with weak vehicle type attributes are those dominated by a few vehicle types, such as high-sided trucks and vans near farms. High entropy clusters are mostly areas with no freight demand, such as gas stations, rest areas, toll booths, roadside parking areas, and inspection stations, offering little help in vehicle type identification.

[0091] The fourth step involves initializing vehicle labels for known vehicle types in any of the strong vehicle type attribute clusters and weak vehicle type attribute clusters, calculating the vehicle type distribution vector for unknown vehicle types in the cluster, and taking any of the unknown vehicle types as the target vehicle.

[0092] Specifically, the vehicle type labels of the cluster area are initialized as a probability vector. <p a (x1),p a (x2)…p a (x z The vehicle model label is also represented as a probability vector. <p v (x1),p v (x2)…p v (x z The formula for calculating the vehicle model distribution vector of unknown models in this cluster is the same as the formula for calculating the entropy value, that is:

[0093]

[0094] Where X = {x1, x2, ..., x} n} represents the various vehicle types within the cluster area, p(x i (x) represents the vehicle model. i The proportion within the cluster, where n represents the total number of vehicle models. For example... Figure 3 As shown, cluster A transmits the vehicle model distribution to all vehicles of unknown models associated with it. Figure 3 Vehicle 5 in the middle is transferred to the gathering areas B, C and D where vehicle 5 has stopped.

[0095] The fifth step is to transfer the calculated vehicle model to all clusters associated with the target vehicle.

[0096] In a specific implementation, such as Figure 3 As shown, the formula for transferring the calculated vehicle model to all clusters associated with the target vehicle is:

[0097]

[0098] Where, p v (x i () indicates that the target vehicle model is x i The probability, This indicates that the vehicle model is x in the j-th cluster area where the target vehicle has stopped. i The probability is given by m, where m is the number of clusters where the target vehicle stops.

[0099] In one specific implementation, after transmitting the data to all clusters associated with the target vehicle, the method further includes: recalculating the proportion of preset vehicle models in each cluster; and updating the vehicle model label based on the recalculated proportion.

[0100] In one specific implementation, the formula for calculating the proportion of preset vehicle types in each cluster area is:

[0101]

[0102] Where, p a (x i () indicates that the vehicle model is x i The proportion of vehicles in any cluster area, N i For vehicles with a clearly defined model label and the label is x i The number of vehicles, N all This refers to the total number of vehicles within the cluster area. The vehicle model of the kth unlabeled vehicle is x. i The probability of x, where n is the vehicle model. i The number of vehicles not marked.

[0103] In another specific implementation, updating the vehicle model label based on the recalculated proportion includes: determining the probability value of the target vehicle belonging to a preset vehicle model based on the recalculated proportion; and when the probability value of belonging to the preset vehicle model exceeds a preset threshold, determining the preset vehicle model as the vehicle model label of the target vehicle. The formula for setting the preset threshold is as follows:

[0104]

[0105] Let x be the vehicle model calculated in the current iteration for the j-th vehicle. i The probability, The vehicle model calculated in the previous iteration for the j-th vehicle is x. i The probability is calculated as z, where z is the number of vehicle type categories and n is the total number of vehicles. The iteration continues until δ is reached. t Less than the given threshold ε.

[0106] In a preferred embodiment, a vehicle model label probability vector of the vehicle can be output, threshold values T0, T1 are set, and 1>T0>T1>0 is satisfied. When the probability of the vehicle model with the highest probability is higher than T0, the vehicle model is determined as the target vehicle model, and the confidence level is set as high. When the probability of the vehicle model with the highest probability is lower than T0 but higher than T1, the vehicle model is determined as the target vehicle model, and the confidence level is set as medium. When the probability of the vehicle model with the highest probability is lower than T1, it is determined that the target vehicle model is unknown.

[0107] The present application can more accurately and completely determine the vehicle model, especially by determining the distribution of the vehicle through the association relationship of the aggregation area and the vehicle and making the determination of the vehicle model faster through the transmission of the vehicle model, thereby facilitating subsequent data processing, and overall improving the efficiency of data processing. Therefore, the method of the present application will have more application scenarios.

[0108] It should be understood that the above general description and the following detailed description are only exemplary and explanatory, and cannot limit the present application.

[0109] Embodiment 3:

[0110] The present embodiment provides a vehicle model determination device based on aggregation area parking, as shown in Figure 4 The device comprises:

[0111] An acquisition module is configured to acquire a plurality of aggregation areas where vehicles are parked.

[0112] A first calculation module is configured to calculate vehicle data corresponding to the plurality of aggregation areas where vehicles are parked within a preset time, wherein the vehicle data at least includes a total number of vehicles, a number of vehicles of known vehicle models, and a number of vehicles of unknown vehicle models.

[0113] An attribute module is configured to determine attributes of each aggregation area based on the vehicle data, wherein the attributes of each aggregation area at least include a strong vehicle model attribute aggregation area, a weak vehicle model attribute aggregation area, and a vehicle model attribute-free aggregation area.

[0114] A second calculation module is configured to initialize a vehicle label of a known vehicle model in any aggregation area, calculate a vehicle model distribution vector of an unknown vehicle model in the aggregation area, and take any unknown vehicle as a target vehicle, for the strong vehicle model attribute aggregation area and the weak vehicle model attribute aggregation area.

[0115] A transmission module is configured to transmit the calculated vehicle model to all aggregation areas associated with the target vehicle.

[0116] It can be understood that the vehicle model determination device based on aggregation area parking can also include necessary hardware, such as locators and sensors, which are not limited here.

[0117] It should be further emphasized that the system provided in the embodiments of the present application can acquire and process relevant data based on artificial intelligence technology. Artificial intelligence (AI) is a theory, method, technology and application system for simulating, extending and expanding human intelligence by using a digital computer or a machine controlled by a digital computer, perceiving an environment, acquiring knowledge and using the knowledge to obtain optimal results. Artificial intelligence basic technologies generally include technologies such as sensors, special artificial intelligence chips, cloud computing, distributed storage, big data processing technology, operation / interaction systems, mechatronics, etc. Artificial intelligence software technologies mainly include computer vision technology, robot technology, biometric identification technology, speech processing technology, natural language processing technology, and machine learning / deep learning, etc.

[0118] Reference is made below to Figure 5 which shows a schematic diagram of a computer device provided by some embodiments of the present application. As shown in Figure 5 the computer device 2 includes a processor 200, a memory 201, a bus 202 and a communication interface 203, the processor 200, the communication interface 203 and the memory 201 are connected through the bus 202; the memory 201 stores a computer program executable on the processor 200, and the processor 200 executes the computer program to perform the vehicle model determination method based on the aggregation area stop provided by any of the preceding embodiments of the present application.

[0119] The memory 201 can include a high-speed random access memory (RAM) and can also include a non-volatile memory such as at least one disk memory. The communication between the system network element and at least one other network element is realized through at least one communication interface 203 (which can be wired or wireless), and the Internet, a wide area network, a local network, a metropolitan area network, etc. can be used.

[0120] The bus 202 can be an ISA bus, a PCI bus or an EISA bus, etc. The bus can be divided into an address bus, a data bus, a control bus, etc. The memory 201 is used to store programs, and the processor 200 executes the programs after receiving execution instructions. The vehicle model determination method based on the aggregation area stop disclosed in any of the preceding embodiments of the present application can be applied to the processor 200 or realized by the processor 200.

[0121] The processor 200 can be an integrated circuit chip with signal processing capability. In implementation, each step of the above method can be completed by integrated logic circuits or instructions in the form of software in the processor 200. The processor 200 described above can be a general-purpose processor, including a central processing unit (CPU), a network processor (NP), etc.; can also be a digital signal processor (DSP), an application-specific integrated circuit (ASIC), a ready programmable gate array (FPGA) or other programmable logic device, a discrete gate or transistor logic device, a discrete hardware component. Each method, step and logic block diagram disclosed in the embodiments of the present application can be implemented or executed. The general-purpose processor can be a microprocessor or the processor can also be any conventional processor. The steps of the method disclosed in combination with the embodiments of the present application can be directly embodied as a hardware code processor for execution, or a combination of hardware and software modules in the code processor for execution. The software module can be located in a random access memory, a flash memory, a read-only memory, a programmable read-only memory or an electrically erasable programmable memory, a register, etc. The storage medium in the art. The storage medium is located in the memory 201, and the processor 200 reads the information in the memory 201, and combines the hardware to complete the steps of the above method.

[0122] The embodiments of the present application also provide a computer readable storage medium corresponding to the vehicle type determination method based on the aggregation area parking provided by the foregoing embodiments, and a computer program is stored on the computer readable storage medium. When the processor runs, the computer program will execute the vehicle type determination method based on the aggregation area parking provided by any of the foregoing embodiments.

[0123] In addition, examples of the computer readable storage medium can also include, but are not limited to, a phase change memory (PRAM), a static random access memory (SRAM), a dynamic random access memory (DRAM), other types of random access memory (RAM), a read-only memory (ROM), an electrically erasable programmable read-only memory (EEPROM), a flash memory or other optical, magnetic storage medium, which will not be described one by one here.

[0124] The embodiment of the present application further provides a computer program product comprising a computer program which, when executed by a processor, implements the steps of the vehicle model determination method based on the parking of the aggregation area provided by any of the preceding embodiments, comprising: acquiring a plurality of aggregation areas where vehicles park; calculating vehicle data corresponding to the plurality of aggregation areas where vehicles park within a preset time, wherein the vehicle data at least comprises a total number of vehicles, a number of vehicles of known models and a number of vehicles of unknown models; determining attributes of each aggregation area based on the vehicle data, wherein the attributes of each aggregation area at least comprise a strong vehicle model attribute aggregation area, a weak vehicle model attribute aggregation area and a vehicle model attribute-free aggregation area; for the strong vehicle model attribute aggregation area and the weak vehicle model attribute aggregation area, initializing a vehicle label of a known model in any aggregation area, calculating a vehicle model distribution vector of an unknown model in the aggregation area, and taking any vehicle of the unknown model as a target vehicle; and transmitting the calculated vehicle model to all aggregation areas associated with the target vehicle.

[0125] It should be noted that the algorithms and displays presented herein are not inherently related to any particular computer, virtual apparatus, or other apparatus. Various general purpose systems can be used with these teachings, or with modifications thereof. The structure required to construct such systems is apparent from the description above. In addition, the present application is not described with reference to any particular programming language. It will be appreciated that a variety of programming languages can be used to implement the teachings of the application as described herein, and any references below to specific languages are provided for disclosure of enablement only. Numerous specific details are described above in order to provide a thorough understanding of the application. However, it will be recognized by one of ordinary skill that the application can be practiced without some or all of these specific details. In some instances, well known structures have not been described in detail in order to avoid obscuring the application.

[0126] Similarly, it is to be understood that the various features of the application described can sometimes be used to advantage together, but each of the features can be used independently of one another. In some instances, well-known methods, structures and techniques have not been described in detail in order to avoid obscuring the application. Other variations and embodiments of the application will occur to those skilled in the art once the nature of the application has been disclosed by the above description. The scope of the application should be determined with reference to the claims.

[0127] Those skilled in the art will appreciate that the modules in the apparatuses in the embodiments can be adapted and placed in one or more apparatuses other than the embodiments. The modules or units or components in the embodiments can be combined into one module or unit or component, and furthermore can be divided into multiple sub-modules or sub-units or sub-components. Any combination of all the features disclosed in the specification and any method or device disclosed in the specification can be adopted, except that at least some of such features and / or processes or units are mutually exclusive. Unless explicitly stated otherwise, each feature disclosed in the specification can be replaced by an alternative feature providing the same, equivalent or similar purpose.

[0128] Embodiments of various components of the present application can be implemented in hardware, or as software modules running in one or more processors, or in combinations thereof. Skilled persons in the art will appreciate that a microprocessor or a digital signal processor (DSP) can be used in practice to implement some or all of the functions of some or all of the components of the apparatus for creating a virtual machine according to embodiments of the present application. The present application can also be implemented as a program for executing part or all of the methods described herein on a device or apparatus. The program implementing the present application can be stored on a computer readable medium, or can have the form of one or more signals. Such signals can be downloaded from an Internet website, or provided on a carrier signal, or in any other form.

[0129] The above description is merely the preferred specific embodiments of the present application, but the scope of protection of the present application is not limited thereto. Any changes or replacements easily conceived by those skilled in the art within the technical scope of the present application should be encompassed within the scope of protection of the present application. Therefore, the scope of protection of the present application should be subject to the scope of protection of the claims.

Claims

1. A method for determining vehicle type based on parking in a cluster area, characterized in that, The method comprises: acquiring a plurality of vehicle parking aggregation areas; calculating vehicle data corresponding to the plurality of vehicle parking aggregation areas within a preset time, wherein the vehicle data at least comprises a total number of vehicles, a number of vehicles of known vehicle models, and a number of vehicles of unknown vehicle models; determining aggregation area attributes based on the vehicle data, wherein the aggregation area attributes at least comprise strong vehicle model attribute aggregation areas, weak vehicle model attribute aggregation areas, and no vehicle model attribute aggregation areas; for the strong vehicle model attribute aggregation areas and the weak vehicle model attribute aggregation areas, initializing vehicle labels of the known vehicle models in any aggregation area, calculating vehicle model distribution vectors of the unknown vehicle models in the aggregation area, and taking any vehicle of the unknown vehicle models as a target vehicle; transferring the calculated vehicle model to all aggregation areas associated with the target vehicle; the formula for transferring the calculated vehicle model to all aggregation areas associated with the target vehicle is: Where, p v (x i () indicates that the target vehicle model is x i The probability, This indicates that the vehicle model is x in the j-th cluster area where the target vehicle has stopped. i The probability is given by m, where m is the number of clusters where the target vehicle stops.

2. The cluster-based vehicle model determination method of claim 1, wherein, the determination of the aggregation area attributes based on the vehicle data comprises: calculating proportions of each vehicle model in each aggregation area according to the total number of vehicles, the number of vehicles of known vehicle models, and the number of vehicles of unknown vehicle models in each aggregation area; calculating vehicle model entropy values of each aggregation area according to the proportions of each vehicle model in each aggregation area; determining the aggregation area attributes according to the vehicle model entropy values of each aggregation area.

3. The cluster-based vehicle model determination method of claim 2, wherein, the formula for calculating the vehicle model entropy values of each aggregation area is: Where H(X) represents the entropy function, X = {x1, x2, …, x n} represents various vehicle types in the aggregation area, p(x i ) is the proportion of vehicle type x i in the aggregation area, and n represents the total number of vehicle types.

4. The cluster-based vehicle model determination method of claim 1, wherein, after being transferred to all aggregation areas associated with the target vehicle, it further comprises: recalculating vehicle proportions of a preset vehicle model in each aggregation area; updating the vehicle model label according to the recalculated proportions.

5. The cluster-based vehicle model determination method of claim 3, wherein, the formula for calculating the vehicle proportions of the preset vehicle model in each aggregation area is: Where, p a (x i () indicates that the vehicle model is x i The proportion of vehicles in any cluster area, N i For vehicles with a clearly defined model label and the label is x i The number of vehicles, N all This refers to the total number of vehicles within the cluster area. This indicates that the model of the kth unlabeled vehicle is x. i The probability of x, where n is the vehicle model. i The number of vehicles not marked.

6. The cluster-based vehicle model determination method of claim 4, wherein, the updating of the vehicle model label according to the recalculated proportions comprises: determining a probability value of a preset vehicle model to which the target vehicle belongs according to the recalculated proportions; when the probability value of the preset vehicle model exceeds a preset threshold, determining the preset vehicle model as the vehicle model label of the target vehicle.

7. A vehicle type determination device based on parking in a cluster area, characterized in that, The device comprises: an acquisition module configured to acquire a plurality of vehicle parking aggregation areas; a first calculation module configured to calculate vehicle data corresponding to the plurality of vehicle parking aggregation areas within a preset time, wherein the vehicle data at least comprises a total number of vehicles, a number of vehicles of known vehicle models, and a number of vehicles of unknown vehicle models; an attribute module configured to determine aggregation area attributes based on the vehicle data, wherein the aggregation area attributes at least comprise strong vehicle model attribute aggregation areas, weak vehicle model attribute aggregation areas, and no vehicle model attribute aggregation areas; a second calculation module configured to, for the strong vehicle model attribute aggregation areas and the weak vehicle model attribute aggregation areas, initialize vehicle labels of the known vehicle models in any aggregation area, calculate vehicle model distribution vectors of the unknown vehicle models in the aggregation area, and take any vehicle of the unknown vehicle models as a target vehicle; a transfer module configured to transfer the calculated vehicle model to all aggregation areas associated with the target vehicle; the formula for transferring the calculated vehicle model to all aggregation areas associated with the target vehicle is: Where, p v (x i () indicates that the target vehicle model is x i The probability, This indicates that the vehicle model is x in the j-th cluster area where the target vehicle has stopped. i The probability is given by m, where m is the number of clusters where the target vehicle stops. 8.A computer device, comprising a memory and a processor, and characterized in that, a memory stores computer readable instructions, and the computer readable instructions are executed by a processor to cause the processor to execute the method according to any one of claims 1-6.

9. A computer readable storage medium having stored thereon a computer program, characterized in that, The computer program is executed by a processor to implement the method according to any one of claims 1-6.

Images