Vehicle management method and device, equipment, storage medium and program product

Abstract

The invention relates to a vehicle management method and device, equipment, a storage medium and a program product, and relates to the technical field of computers. The method comprises the steps that cloud equipment receives a vehicle identification result sent by edge equipment; the vehicle identification result is a result obtained by the edge device calling a vehicle identification model to identify the vehicle image of the target vehicle; calling a large model to perform semantic analysis on the vehicle identification result to obtain an analysis result; if the analysis result indicates that the target vehicle is legally parked, judging whether the target vehicle conforms to a current parking strategy or not through a rule engine; and if the current parking strategy is met, parking charging is carried out on the target vehicle. By adopting the method, the accuracy of vehicle management can be improved.

Description

Technical Field

[0001] This application relates to the field of computer technology, and in particular to a vehicle management method, apparatus, device, storage medium, and program product. Background Technology

[0002] With the continuous growth of urban vehicle ownership, parking management and charging systems have become a key component of smart urban management. Currently, most systems rely on a single technical model to achieve parking space status recognition and charging calculation, such as solutions based on traditional image processing or simple sensor networks. However, such methods face significant challenges in complex scenarios: environmental factors such as changes in lighting, occlusion, and interference from multiple vehicle types can easily lead to detection errors, resulting in low accuracy in vehicle management. Summary of the Invention

[0003] Therefore, it is necessary to provide a vehicle management method, device, equipment, storage medium, and program product that can improve the accuracy of vehicle management in response to the above-mentioned technical problems.

[0004] In a first aspect, this application provides a vehicle management method applied to a cloud device; the method includes:

[0005] Receive vehicle recognition results sent by the edge device; the vehicle recognition results are obtained by the edge device calling the vehicle recognition model to recognize the vehicle image of the target vehicle;

[0006] The large model is invoked to perform semantic analysis on the vehicle recognition results, and the analysis results are obtained.

[0007] If the analysis results indicate that the target vehicle is legally parked, the rule engine will determine whether the target vehicle complies with the current parking strategy.

[0008] If the target vehicle meets the current parking policy, parking fees will be charged.

[0009] In one embodiment, the method further includes:

[0010] The parking billing records of the target vehicle are stored in the model context protocol service database;

[0011] At each first preset time interval, a profile analysis and fare evasion prediction are performed based on the parking billing records in the model context protocol service database.

[0012] In one embodiment, the method further includes:

[0013] The vehicle identification results are stored in the Model Context Protocol Service database;

[0014] Every second preset time interval, the vehicle recognition results in the model context protocol service database are reviewed;

[0015] If the vehicle recognition result is verified to be abnormal, a recognition correction process is triggered to obtain a corrected vehicle recognition result.

[0016] The vehicle recognition model is updated based on the corrected vehicle recognition results.

[0017] In one embodiment, the method further includes:

[0018] The analysis results are stored in the Model Context Protocol Service database;

[0019] Every third preset time interval, the analysis results in the model context protocol service database are reviewed;

[0020] If the analysis results are found to be abnormal, an analysis correction process is triggered to obtain corrected analysis results.

[0021] Based on the revised analysis results, the large model is updated.

[0022] In one embodiment, the method further includes:

[0023] If the analysis results indicate that the target vehicle is illegally parked, an alarm message is generated;

[0024] The alarm information is pushed to the management device corresponding to the administrator.

[0025] Secondly, this application provides a vehicle management device applied to a cloud-based device; the device includes:

[0026] The receiving module is used to receive vehicle recognition results sent by the edge device; the vehicle recognition results are the results obtained by the edge device calling the vehicle recognition model to recognize the vehicle image of the target vehicle;

[0027] The analysis module is used to call a large model to perform semantic analysis on the vehicle recognition results and obtain the analysis results;

[0028] The judgment module is used to determine whether the target vehicle conforms to the current parking strategy by means of a rule engine if the analysis result indicates that the target vehicle is legally parked.

[0029] The billing module is used to charge parking fees for the target vehicle if it meets the current parking policy.

[0030] In one embodiment, the apparatus further includes:

[0031] The storage module is used to store the parking billing records of the target vehicle into the model context protocol service database; at each first preset time interval, it performs profile analysis and fare evasion prediction based on the parking billing records in the model context protocol service database.

[0032] In one embodiment, the apparatus further includes:

[0033] The storage module is used to store the vehicle recognition results to the model context protocol service database; at every second preset time interval, the vehicle recognition results in the model context protocol service database are reviewed; if the vehicle recognition results are found to be abnormal, a recognition correction process is triggered to obtain the corrected vehicle recognition results; based on the corrected vehicle recognition results, the vehicle recognition model is updated.

[0034] In one embodiment, the apparatus further includes:

[0035] The storage module is used to store the analysis results in the model context protocol service database; every third preset time interval, the analysis results in the model context protocol service database are reviewed; if the analysis results are found to be abnormal, an analysis correction process is triggered to obtain the corrected analysis results; based on the corrected analysis results, the large model is updated.

[0036] In one embodiment, the apparatus further includes:

[0037] The alarm module is used to generate alarm information if the analysis results indicate that the target vehicle is illegally parked; and to push the alarm information to the management device corresponding to the management personnel.

[0038] Thirdly, this application provides a cloud device, including a memory and a processor, wherein the memory stores a computer program, and the processor executes the computer program to implement the steps in the various method embodiments of this application.

[0039] Fourthly, this application provides a computer-readable storage medium storing a computer program that, when executed by a processor, implements the steps in the various method embodiments of this application.

[0040] Fifthly, this application provides a computer program product, including a computer program that, when executed by a processor, implements the steps in the various method embodiments of this application.

[0041] The aforementioned vehicle management method, device, equipment, storage medium, and program product receive vehicle recognition results sent by an edge device. These vehicle recognition results are obtained by the edge device using a vehicle recognition model to identify the target vehicle's image. A larger model is then used to perform semantic analysis on the vehicle recognition results to obtain the analysis results. If the analysis results indicate that the target vehicle is legally parked, a rule engine determines whether the target vehicle conforms to the current parking policy. If it conforms to the current parking policy, parking fees are charged for the target vehicle. Compared to traditional vehicle management methods, this application uses a small model (i.e., a vehicle recognition model) for vehicle recognition on the edge device side and a large model for semantic analysis on the cloud device side. This collaboration between the small and large models balances semantic understanding and execution efficiency. Furthermore, the combination with a rule engine ensures zero-illusion execution of parking policies and rules, improving the accuracy of vehicle management. Attached Figure Description

[0042] To more clearly illustrate the technical solutions in the embodiments of this application or related technologies, the drawings used in the description of the embodiments of this application or related technologies will be briefly introduced below. Obviously, the drawings described below are only some embodiments of this application. For those skilled in the art, other related drawings can be obtained based on these drawings without creative effort.

[0043] Figure 1 This is a flowchart illustrating a vehicle management method in one embodiment;

[0044] Figure 2 This is a flowchart illustrating the vehicle management method in another embodiment;

[0045] Figure 3 This is a structural block diagram of a vehicle management device in one embodiment;

[0046] Figure 4 This is an internal structure diagram of a cloud device in one embodiment. Detailed Implementation

[0047] To make the objectives, technical solutions, and advantages of this application clearer, the following detailed description is provided in conjunction with the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are merely illustrative and not intended to limit the scope of this application.

[0048] In one embodiment, such as Figure 1 As shown, a vehicle management method is provided, which can be applied to cloud devices. The method includes the following steps:

[0049] Step 102: Receive the vehicle recognition result sent by the edge device; the vehicle recognition result is the result obtained by the edge device calling the vehicle recognition model to recognize the vehicle image of the target vehicle.

[0050] The vehicle recognition model is a small model, meaning it's a lightweight model used to perform vehicle recognition tasks. The vehicle recognition results include license plate recognition and vehicle location information.

[0051] In one embodiment, an edge device can capture images of a target vehicle using a camera. The edge device can then use a vehicle recognition model to identify the vehicle image, obtain a vehicle recognition result, and upload the result to a cloud device. The cloud device can receive the vehicle recognition result sent by the edge device.

[0052] Step 104: Call the large model to perform semantic analysis on the vehicle recognition results and obtain the analysis results.

[0053] Among them, large models refer to large-scale language models with capabilities such as semantic understanding, task planning, and intent recognition, such as GPT-type models.

[0054] In one embodiment, the cloud device can call a large model to perform semantic analysis on the vehicle recognition results and obtain the analysis results. That is, the cloud device can call a large model to determine whether the target vehicle is legally parked. It can be understood that the analysis results include whether the target vehicle is legally parked or illegally parked.

[0055] Step 106: If the analysis results indicate that the target vehicle is legally parked, then the rule engine determines whether the target vehicle conforms to the current parking strategy.

[0056] The rule engine is a system that makes judgments based on a knowledge base and logical rules, and is used to ensure the controllability and consistency of business logic.

[0057] In one embodiment, if the cloud device can call a large model to determine that the target vehicle is legally parked, the cloud device can call a rule engine to determine whether the target vehicle conforms to the current parking policy, such as whether parking is allowed and the billing rules.

[0058] Step 108: If the current parking policy is met, then parking fees will be charged for the target vehicle.

[0059] In the aforementioned vehicle management method, the system receives vehicle recognition results sent by an edge device. These results are obtained by the edge device using a vehicle recognition model to identify the target vehicle's image. A larger model is then used to perform semantic analysis on the vehicle recognition results, yielding an analysis result. If the analysis result indicates that the target vehicle is legally parked, a rule engine determines whether the target vehicle conforms to the current parking policy. If it conforms to the current parking policy, parking fees are charged for the target vehicle. Compared to traditional vehicle management methods, this application uses a smaller model (the vehicle recognition model) for vehicle recognition on the edge device side and a larger model for semantic analysis on the cloud device side. This collaboration between the smaller and larger models balances semantic understanding and execution efficiency. Furthermore, the rule engine ensures zero-illusion execution of parking policies and rules, improving the accuracy of vehicle management.

[0060] In one embodiment, the method further includes: storing the parking billing records of the target vehicle in the Model Context Protocol Service Database; and performing profile analysis and fare evasion prediction based on the parking billing records in the Model Context Protocol Service Database at first preset intervals.

[0061] Among them, the Model Context Protocol service, or MCP service, refers to a service module used to store the processing results of edge devices and cloud devices, and to provide long-term memory and tool invocation capabilities.

[0062] In one embodiment, the cloud device can store the parking billing records of the target vehicle in the Model Context Protocol Service (MCP) database. Every first preset time interval, such as every week, the cloud device can perform profile analysis and fare evasion prediction on the target vehicle based on the parking billing records in the MCP database.

[0063] In the above embodiments, by periodically integrating historical parking billing data to construct dynamic vehicle behavior profiles, proactive prediction and early warning of parking fee evasion risks are achieved. This transforms reactive, post-event collection into precise, pre-event prevention, significantly improving the parking fee collection rate.

[0064] In one embodiment, the method further includes: storing the vehicle recognition result in a model context protocol service database; reviewing the vehicle recognition result in the model context protocol service database at second preset intervals; if the vehicle recognition result is found to be abnormal, triggering a recognition correction process to obtain the corrected vehicle recognition result; and updating the vehicle recognition model based on the corrected vehicle recognition result.

[0065] In one embodiment, the cloud device can store vehicle recognition results in a Model Context Protocol Service (MCP) database. Every second preset time interval, such as every 10 days, the cloud device can review the vehicle recognition results in the MCP database. If the review finds that the vehicle recognition results are abnormal, it indicates that the vehicle recognition model has made an error and its recognition accuracy needs to be improved. At this time, a recognition correction process can be triggered to obtain corrected vehicle recognition results. Based on the corrected vehicle recognition results, the vehicle recognition model is updated to improve its recognition accuracy.

[0066] In the above embodiments, by continuously storing vehicle recognition data and establishing a periodic review mechanism, recognition anomalies can be effectively detected and corrected. The correction process provides timely feedback, driving the dynamic updating and optimization of the vehicle recognition model, gradually improving recognition accuracy and adaptability. This closed-loop system achieves self-monitoring and continuous learning of the model, enhancing the long-term stability and reliability of the system, reducing manual maintenance costs, and can be widely applied in intelligent transportation and security scenarios.

[0067] In one embodiment, the method further includes: storing the analysis results in a model context protocol service database; reviewing the analysis results in the model context protocol service database every third preset time interval; if the analysis results are found to be abnormal, triggering an analysis correction process to obtain corrected analysis results; and updating the large model based on the corrected analysis results.

[0068] In one embodiment, the cloud device can store the analysis results in the Model Context Protocol Service (MCP) database. Every three preset time intervals, such as every 15 days, the cloud device can review the analysis results in the MCP database. If the review finds an anomaly in the analysis results, it indicates that there is an error in the semantic analysis of the large model, and the accuracy of the semantic analysis of the large model needs to be improved. At this time, an analysis correction process can be triggered to obtain the corrected analysis results, and based on the corrected analysis results, the large model is updated to improve the semantic analysis accuracy of the large model.

[0069] In the above embodiments, an analytical closed loop for continuous optimization of a large model is constructed. By periodically reviewing and correcting historical analysis results in the database, the system can proactively identify and correct model biases. Based on the corrected, high-quality data, the model is updated, enabling it to continuously adapt to new situations and correct inherent errors, thereby achieving a spiral improvement in performance. This not only significantly improves the model's accuracy, reliability, and generalization ability but also greatly reduces the cost of manual supervision and iteration, ensuring the system's stability and intelligent evolution during long-term operation.

[0070] In one embodiment, the method further includes: if the analysis results indicate that the target vehicle is illegally parked, generating an alarm message; and pushing the alarm message to the management device corresponding to the management personnel.

[0071] In one embodiment, if the analysis results indicate that the target vehicle is illegally parked, for example, if the target vehicle is not parked in a designated area, the cloud device can generate an alarm message and push the alarm message to the management device corresponding to the manager, so that the manager can perform the corresponding vehicle management, such as notifying the owner of the target vehicle to move the vehicle or pay the fine.

[0072] In the above embodiments, by automatically identifying illegal parking and issuing real-time alerts, traffic violations can be detected and processed immediately. This significantly improves the response speed and enforcement efficiency of management personnel, reducing reliance on manual patrols. Systematic alert push notifications ensure accountability, strengthen violation control capabilities, and help maintain good traffic order.

[0073] In one embodiment, such as Figure 2 As shown, the cloud device receives vehicle recognition results sent by the edge device. These results are obtained by the edge device using a vehicle recognition model to identify the target vehicle's image. The cloud device then uses a large model to perform semantic analysis on the vehicle recognition results. If the analysis indicates the target vehicle is illegally parked, an alarm is generated and pushed to the corresponding management device. If the analysis indicates the target vehicle is legally parked, a rule engine determines whether the target vehicle conforms to the current parking policy. If it does, parking fees are charged. The parking fee records for the target vehicle are stored in the model context protocol service database. Every first preset time interval, a profile analysis and fee evasion prediction are performed based on the parking fee records in the model context protocol service database. The vehicle recognition results are stored in the model context protocol service database. Every second preset time interval, the vehicle recognition results in the model context protocol service database are reviewed. If an anomaly is detected, a correction process is triggered to obtain a corrected vehicle recognition result. Based on the corrected vehicle recognition result, the vehicle recognition model is updated. The analysis results are stored in the Model Context Protocol Service database; every third preset time interval, the analysis results in the Model Context Protocol Service database are reviewed; if the analysis results are found to be abnormal, the analysis correction process is triggered to obtain the corrected analysis results; based on the corrected analysis results, the large model is updated.

[0074] It should be understood that although the steps in the flowcharts of the above embodiments are shown sequentially, these steps are not necessarily executed in that order. Unless otherwise expressly stated herein, there is no strict order restriction on the execution of these steps, and they can be executed in other orders. Moreover, at least some of the steps in the above embodiments may include multiple sub-steps or multiple stages. These sub-steps or stages are not necessarily completed at the same time, but can be executed at different times. The execution order of these sub-steps or stages is not necessarily sequential, but can be performed alternately or in turn with other steps or at least a portion of the sub-steps or stages of other steps.

[0075] Based on the same inventive concept, this application also provides a vehicle management device for implementing the vehicle management method described above. The solution provided by this device is similar to the solution described in the above method; therefore, the specific limitations in one or more vehicle management device embodiments provided below can be found in the limitations of the vehicle management method described above, and will not be repeated here.

[0076] In one embodiment, such as Figure 3 As shown, a vehicle management device 300 is provided, which is applied to cloud devices; the device specifically includes:

[0077] The receiving module 302 is used to receive the vehicle recognition result sent by the edge device; the vehicle recognition result is the result obtained by the edge device calling the vehicle recognition model to recognize the vehicle image of the target vehicle;

[0078] Analysis module 304 is used to call the large model to perform semantic analysis on the vehicle recognition results and obtain the analysis results;

[0079] The judgment module 306 is used to determine whether the target vehicle conforms to the current parking strategy if the analysis result indicates that the target vehicle is legally parked.

[0080] The billing module 308 is used to bill the target vehicle for parking if it meets the current parking policy.

[0081] In one embodiment, the apparatus further includes:

[0082] The storage module is used to store the parking billing records of the target vehicle into the model context protocol service database; every first preset time interval, it performs profile analysis and fare evasion prediction based on the parking billing records in the model context protocol service database.

[0083] In one embodiment, the apparatus further includes:

[0084] The storage module is used to store vehicle recognition results to the model context protocol service database; at every second preset time interval, the vehicle recognition results in the model context protocol service database are reviewed; if the vehicle recognition result is found to be abnormal, the recognition correction process is triggered to obtain the corrected vehicle recognition result; based on the corrected vehicle recognition result, the vehicle recognition model is updated.

[0085] In one embodiment, the apparatus further includes:

[0086] The storage module is used to store the analysis results to the Model Context Protocol Service database; every third preset time interval, the analysis results in the Model Context Protocol Service database are reviewed; if the analysis results are found to be abnormal, the analysis correction process is triggered to obtain the corrected analysis results; based on the corrected analysis results, the large model is updated.

[0087] In one embodiment, the apparatus further includes:

[0088] The alarm module is used to generate alarm information if the analysis results indicate that the target vehicle is illegally parked; and push the alarm information to the corresponding management device of the management personnel.

[0089] The aforementioned vehicle management device receives vehicle recognition results sent by an edge device. These results are obtained by the edge device using a vehicle recognition model to identify the target vehicle's image. A larger model is then used to perform semantic analysis on the vehicle recognition results, yielding an analysis result. If the analysis result indicates that the target vehicle is legally parked, a rule engine determines whether the target vehicle conforms to the current parking policy. If it conforms to the current parking policy, parking fees are charged for the target vehicle. Compared to traditional vehicle management methods, this application uses a smaller model (the vehicle recognition model) for vehicle recognition on the edge device side and a larger model for semantic analysis on the cloud device side. This collaboration between the smaller and larger models balances semantic understanding and execution efficiency. Furthermore, the rule engine ensures zero-illusion execution of parking policies and rules, improving the accuracy of vehicle management.

[0090] Each module in the aforementioned vehicle management device can be implemented entirely or partially through software, hardware, or a combination thereof. These modules can be embedded in hardware within or independently of the processor in the cloud device, or stored in software within the memory of the cloud device, so that the processor can invoke and execute the corresponding operations of each module.

[0091] In one embodiment, a cloud device is provided, which may be a server, and its internal structure diagram may be as follows: Figure 4As shown, the cloud device includes a processor, memory, input / output (I / O) interfaces, and a communication interface. The processor, memory, and I / O interfaces are connected via a system bus, and the communication interface is also connected to the system bus via the I / O interfaces. The processor provides computing and control capabilities. The memory includes non-volatile storage media and internal memory. The non-volatile storage media stores the operating system, computer programs, and databases. The internal memory provides the environment for the operating system and computer programs stored in the non-volatile storage media. The I / O interfaces are used for exchanging information between the processor and external devices. The communication interface is used for communicating with external terminals via a network connection. When the computer program is executed by the processor, it implements a vehicle management method.

[0092] Those skilled in the art will understand that Figure 4 The structure shown is merely a block diagram of a portion of the structure related to the solution of this application and does not constitute a limitation on the cloud device on which the solution of this application is applied. The specific cloud device may include more or fewer components than shown in the figure, or combine certain components, or have different component arrangements.

[0093] In one embodiment, a cloud device is also provided, including a memory and a processor, wherein the memory stores a computer program, and the processor executes the computer program to perform the following steps:

[0094] Receive vehicle recognition results sent by the edge device; the vehicle recognition results are the results obtained by the edge device calling the vehicle recognition model to recognize the vehicle image of the target vehicle;

[0095] The large model is invoked to perform semantic analysis on the vehicle recognition results, and the analysis results are obtained.

[0096] If the analysis results indicate that the target vehicle is legally parked, the rule engine will determine whether the target vehicle complies with the current parking strategy.

[0097] If the vehicle meets the current parking policy, parking fees will be charged.

[0098] In one embodiment, a cloud device is also provided, including a memory and a processor, wherein the memory stores a computer program, and the processor, when executing the computer program, further performs the following steps:

[0099] Store the parking billing records of the target vehicle in the model context protocol service database;

[0100] At each preset interval, a profile analysis and fare evasion prediction are performed based on parking billing records in the model context protocol service database.

[0101] In one embodiment, a cloud device is also provided, including a memory and a processor, wherein the memory stores a computer program, and the processor, when executing the computer program, further performs the following steps:

[0102] The vehicle recognition results are stored in the Model Context Protocol Service database;

[0103] Every second preset time interval, the vehicle recognition results in the Model Context Protocol Service Database are reviewed;

[0104] If the vehicle recognition result is found to be abnormal, the recognition correction process will be triggered to obtain the corrected vehicle recognition result.

[0105] The vehicle recognition model is updated based on the corrected vehicle recognition results.

[0106] In one embodiment, a cloud device is also provided, including a memory and a processor, wherein the memory stores a computer program, and the processor, when executing the computer program, further performs the following steps:

[0107] The analysis results are stored in the Model Context Protocol Service database;

[0108] Every third preset time interval, the analysis results in the Model Context Protocol Service Database are reviewed;

[0109] If the analysis results are found to be abnormal, the analysis correction process will be triggered to obtain the corrected analysis results.

[0110] The large model is updated based on the revised analysis results.

[0111] In one embodiment, a cloud device is also provided, including a memory and a processor, wherein the memory stores a computer program, and the processor, when executing the computer program, further performs the following steps:

[0112] If the analysis results indicate that the target vehicle is illegally parked, an alarm message will be generated;

[0113] Alarm information will be pushed to the corresponding management device of the administrator.

[0114] In one embodiment, a computer-readable storage medium is provided storing a computer program that, when executed by a processor, implements the steps in the above method embodiments.

[0115] In one embodiment, a computer program product is provided, including a computer program that, when executed by a processor, implements the steps in the above method embodiments.

[0116] It should be noted that the user information (including but not limited to user device information, user personal information, etc.) and data (including but not limited to data used for analysis, data stored, data displayed, etc.) involved in this application are all information and data authorized by the user or fully authorized by all parties, and the collection, use and processing of related data must comply with the relevant laws, regulations and standards of the relevant countries and regions.

[0117] Those skilled in the art will understand that all or part of the processes in the methods of the above embodiments can be implemented by a computer program instructing related hardware. The computer program can be stored in a non-volatile computer-readable storage medium, and when executed, it can include the processes of the embodiments of the above methods. Any references to memory, databases, or other media used in the embodiments provided in this application can include at least one of non-volatile memory and volatile memory. Non-volatile memory can include read-only memory (ROM), magnetic tape, floppy disk, flash memory, optical memory, high-density embedded non-volatile memory, resistive random access memory (ReRAM), magnetic random access memory (MRAM), ferroelectric random access memory (FRAM), phase change memory (PCM), graphene memory, etc. Volatile memory can include random access memory (RAM) or external cache memory, etc. By way of illustration and not limitation, RAM can take many forms, such as Static Random Access Memory (SRAM) or Dynamic Random Access Memory (DRAM). The databases involved in the embodiments provided in this application may include at least one type of relational database and non-relational database. Non-relational databases may include, but are not limited to, blockchain-based distributed databases. The processors involved in the embodiments provided in this application may be general-purpose processors, central processing units, graphics processing units, digital signal processors, programmable logic devices, quantum computing-based data processing logic devices, artificial intelligence (AI) processors, etc., and are not limited to these.

[0118] The technical features of the above embodiments can be combined in any way. For the sake of brevity, not all possible combinations of the technical features in the above embodiments are described. However, as long as there is no contradiction in the combination of these technical features, they should be considered to be within the scope of this application.

[0119] The embodiments described above are merely illustrative of several implementation methods of this application, and while the descriptions are specific and detailed, they should not be construed as limiting the scope of this patent application. It should be noted that those skilled in the art can make various modifications and improvements without departing from the concept of this application, and these all fall within the protection scope of this application. Therefore, the protection scope of this application should be determined by the appended claims.

Claims

1. A vehicle management method, characterized in that, Applied to cloud devices; the method includes: Receive vehicle recognition results sent by the edge device; the vehicle recognition results are obtained by the edge device calling the vehicle recognition model to recognize the vehicle image of the target vehicle; The large model is invoked to perform semantic analysis on the vehicle recognition results, and the analysis results are obtained. If the analysis results indicate that the target vehicle is legally parked, the rule engine will determine whether the target vehicle complies with the current parking strategy. If the target vehicle meets the current parking policy, parking fees will be charged.

2. The method according to claim 1, characterized in that, The method further includes: The parking billing records of the target vehicle are stored in the model context protocol service database; At each first preset time interval, a profile analysis and fare evasion prediction are performed based on the parking billing records in the model context protocol service database.

3. The method according to claim 1, characterized in that, The method further includes: The vehicle identification results are stored in the Model Context Protocol Service database; Every second preset time interval, the vehicle recognition results in the model context protocol service database are reviewed; If the vehicle recognition result is verified to be abnormal, a recognition correction process is triggered to obtain a corrected vehicle recognition result. The vehicle recognition model is updated based on the corrected vehicle recognition results.

4. The method according to claim 1, characterized in that, The method further includes: The analysis results are stored in the Model Context Protocol Service database; Every third preset time interval, the analysis results in the model context protocol service database are reviewed; If the analysis results are found to be abnormal, an analysis correction process is triggered to obtain corrected analysis results. Based on the revised analysis results, the large model is updated.

5. The method according to claim 1, characterized in that, The method further includes: If the analysis results indicate that the target vehicle is illegally parked, an alarm message is generated; The alarm information is pushed to the management device corresponding to the administrator.

6. A vehicle management device, characterized in that, Applied to cloud devices; the device includes: The receiving module is used to receive vehicle recognition results sent by the edge device; the vehicle recognition results are the results obtained by the edge device calling the vehicle recognition model to recognize the vehicle image of the target vehicle; The analysis module is used to call a large model to perform semantic analysis on the vehicle recognition results and obtain the analysis results; The judgment module is used to determine whether the target vehicle conforms to the current parking strategy by means of a rule engine if the analysis result indicates that the target vehicle is legally parked. The billing module is used to charge parking fees for the target vehicle if it meets the current parking policy.

7. The apparatus according to claim 6, characterized in that, The device further includes: The storage module is used to store the parking billing records of the target vehicle into the model context protocol service database; at each first preset time interval, it performs profile analysis and fare evasion prediction based on the parking billing records in the model context protocol service database.

8. A cloud device comprising a memory and a processor, wherein the memory stores a computer program, characterized in that, When the processor executes the computer program, it implements the steps of the method according to any one of claims 1 to 5.

9. A computer-readable storage medium storing a computer program, characterized in that, When the computer program is executed by a processor, it implements the steps of the method according to any one of claims 1 to 5.

10. A computer program product, comprising a computer program, characterized in that, When the computer program is executed by a processor, it implements the steps of the method according to any one of claims 1 to 5.

Images