An asset management method, system, device and storage medium

Abstract

Embodiments of the present application provide an asset management method, system, device and storage medium, relating to the technical field of Internet of Things data processing, the method comprising: generating a vehicle health fingerprint based on vehicle operation data and road surface data; obtaining vehicle location information and generating a vehicle expected income vector based on the vehicle location information; obtaining vehicle environment information and constructing a reward function according to the vehicle health fingerprint, the vehicle expected income vector and the vehicle environment information; and generating a vehicle scheduling instruction based on an output value corresponding to the reward function. The present application can balance vehicle income and vehicle life and make an optimal decision, thereby prolonging the life of the vehicle while ensuring the order income of the vehicle.

Description

Technical Field

[0001] This invention relates to the field of Internet of Things (IoT) data processing technology, and more specifically, to an asset management method, system, device, and storage medium. Background Technology

[0002] With the large-scale application of autonomous driving technology, robotaxis are becoming increasingly common. Unlike traditional ride-hailing services, the asset value of autonomous vehicles is highly dependent on the health status of their sensing hardware and their real-time operational profitability. However, existing technologies have significant shortcomings in vehicle asset assessment and management. First, the core components of autonomous vehicles include LiDAR, computing chips, and the vehicle chassis. Most existing vehicle management systems use a linear depreciation method based on mileage and years, which is unsuitable for assessing autonomous vehicles. Second, existing vehicle management systems often fail to balance the benefits of accepting orders with the impact of these orders on the vehicle's lifespan. Third, operational data is stored on operator servers, while hardware data is stored on the vehicle itself; the lack of a unified and reliable connection between the two makes them vulnerable to tampering. These shortcomings can easily lead to abnormal asset assessment and management of autonomous vehicles. Summary of the Invention

[0003] In view of this, the purpose of the present invention is to provide an asset management method, system, device and storage medium to solve at least some of the problems in the prior art.

[0004] To achieve the above objectives, the technical solution adopted by the present invention is as follows: In a first aspect, the present invention provides an asset management method applied to an asset management system, the method comprising: Vehicle health fingerprints are generated based on vehicle operation data and road surface data; Obtain vehicle location information and generate a vehicle expected revenue vector based on the vehicle location information; Obtain vehicle environment information, and construct a reward function based on the vehicle health fingerprint, the vehicle expected revenue vector, and the vehicle environment information; Vehicle dispatch instructions are generated based on the output value corresponding to the reward function.

[0005] In an optional implementation, the step of generating a vehicle health fingerprint based on vehicle operation data and road surface data includes: The optical attenuation coefficient of the lidar is calculated using the lidar data of the vehicle. The vehicle's vibration acceleration is obtained through the vehicle's inertial measurement unit; The vehicle obtains road surface data based on the positioning map, and the road surface data includes the road surface roughness coefficient. The chassis fatigue of the vehicle is calculated using the vibration acceleration and the road surface roughness coefficient. The vehicle health fingerprint is generated based on the light decay coefficient and the cumulative fatigue of the chassis.

[0006] In an optional implementation, the step of generating the vehicle's expected revenue vector based on vehicle location information includes: Generate a vehicle target area based on the vehicle location information; Obtain the current order information for the vehicle's target area, including order quantity, average order price, average waiting time, and weather. The expected revenue vector of the vehicle is calculated based on the order quantity, average order price, average waiting time, and weather conditions. The expected revenue vector of the vehicle includes expected revenue and average time.

[0007] In an optional implementation, the vehicle environment information includes the vehicle ambient temperature, and the step of constructing a reward function based on the vehicle health fingerprint, the vehicle expected revenue vector, and the vehicle environment information includes: The vehicle health fingerprint, the vehicle expected revenue vector, and the vehicle ambient temperature are input into a deep Q-network, and a reward function is constructed through the deep Q-network. The reward function is as follows:

[0008] in, For the expected return, The average time is... The light decay coefficient is... The fatigue level of the chassis. The ambient temperature of the vehicle. The safe threshold for ambient temperature. , , , and All are coefficients. It is an exponential function. This is an indicator function.

[0009] In an optional implementation, after the step of acquiring the vehicle's vibration acceleration via the vehicle's inertial measurement unit, the method further includes: If the vibration acceleration is greater than the acceleration threshold and the vehicle has not reported a collision, an interrupt signal is generated, which is used to suspend the vehicle's order-taking function. If the vehicle has reported a collision, then the vehicle's order-accepting function will be restored.

[0010] In an optional implementation, the lidar data includes point cloud echo distribution, and the step of calculating the lidar attenuation coefficient using the lidar data of the vehicle includes: Obtain the point cloud echo intensity distribution and reference distribution of the vehicle's lidar; The light decay coefficient was calculated using KL divergence:

[0011] in, Let X be the optical attenuation coefficient, and X be the discrete interval of the echo intensity. The point cloud echo intensity distribution This is the baseline distribution.

[0012] In an optional implementation, after the step of obtaining vehicle location information, the method further includes: If a vehicle information audit request is received from the auditing end, the vehicle operation compliance area is obtained; Commitments are generated based on the discrete logarithm problem using the vehicle location information and the vehicle's compliant operating area. A proof is generated based on the commitment using a proof generation algorithm, and the commitment and the proof are packaged and sent to the auditing end.

[0013] Secondly, the present invention provides an asset management system, comprising: The health fingerprint generation module is used to generate vehicle health fingerprints based on vehicle operation data and road surface data; The revenue vector generation module is used to obtain vehicle location information and generate a vehicle expected revenue vector based on the vehicle location information. The reward function construction module is used to obtain vehicle environment information and construct a reward function based on the vehicle health fingerprint, the vehicle expected revenue vector, and the vehicle environment information. The dispatch instruction generation module is used to generate vehicle dispatch instructions based on the output value corresponding to the reward function.

[0014] Thirdly, the present invention provides an electronic device including a processor and a memory, the memory storing machine-executable instructions executable by the processor, the processor executing the machine-executable instructions to implement the asset management method described in the first aspect.

[0015] Fourthly, the present invention provides a computer-readable storage medium having a computer program stored thereon, wherein the computer program, when executed by a processor, implements the asset management method described in the first aspect.

[0016] This invention provides an asset management method, system, device, and storage medium that generates vehicle health fingerprints by collecting vehicle operation data and road surface data to achieve a multi-faceted assessment of vehicle health. Then, a reward function is constructed using the vehicle health fingerprint, the vehicle's expected revenue vector, and vehicle environmental information. Based on the reward function, vehicle dispatch instructions are generated, thereby achieving a balance between vehicle revenue and vehicle lifespan and making optimal decisions. This extends vehicle lifespan while ensuring vehicle order-taking revenue.

[0017] To make the above-mentioned objects, features and advantages of the present invention more apparent and understandable, preferred embodiments are described below in detail with reference to the accompanying drawings. Attached Figure Description

[0018] To more clearly illustrate the technical solutions of the embodiments of the present invention, the accompanying drawings used in the embodiments will be briefly introduced below. It should be understood that the following drawings only show some embodiments of the present invention and should not be regarded as a limitation on the scope. For those skilled in the art, other related drawings can be obtained based on these drawings without creative effort.

[0019] Figure 1 A schematic diagram of the framework structure of an asset management system provided by an embodiment of the present invention is shown; Figure 2 A block diagram of a cloud server provided by an embodiment of the present invention is shown; Figure 3 A flowchart illustrating an asset management method provided by an embodiment of the present invention is shown; Figure 4 The diagram illustrates a functional module diagram of an asset management system provided by an embodiment of the present invention.

[0020] icon: 100-Cloud Server; 200-Vehicle Terminal; 300-Audit Terminal; 210-Storage; 220-Processor; 230-Communication Module; 400-Asset Management System; 410-Health Fingerprint Generation Module; 420-Revenue Vector Generation Module; 430-Reward Function Construction Module; 440-Schedule Instruction Generation Module. Detailed Implementation

[0021] The technical solutions of the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of the present invention, and not all embodiments. The components of the embodiments of the present invention described and shown in the accompanying drawings can generally be arranged and designed in various different configurations.

[0022] Therefore, the following detailed description of the embodiments of the invention provided in the accompanying drawings is not intended to limit the scope of the claimed invention, but merely to illustrate selected embodiments of the invention. All other embodiments obtained by those skilled in the art based on the embodiments of the invention without inventive effort are within the scope of protection of the invention.

[0023] It should be noted that relational terms such as "first" and "second" are used merely to distinguish one entity or operation from another, and do not necessarily require or imply any such actual relationship or order between these entities or operations. Furthermore, the terms "comprising," "including," or any other variations thereof are intended to cover non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements includes not only those elements but also other elements not expressly listed, or elements inherent to such a process, method, article, or apparatus. Without further limitations, an element defined by the phrase "comprising one..." does not exclude the presence of other identical elements in the process, method, article, or apparatus that includes said element.

[0024] Existing technologies present significant technical challenges in vehicle asset management and evaluation: 1. Mismatch between static depreciation models and dynamic losses: Existing fleet management systems mostly use the linear depreciation method of "mileage + years". However, the photoelectric degradation of sensors and the aging of domain controller computing power in autonomous vehicles have a non-linear relationship with "power-on time" and "road bump frequency". Traditional models cannot quantify such micro-physical losses, resulting in distorted asset valuation.

[0025] 2. Decision-making conflict between operational revenue and asset protection: Fleet dispatching systems often pursue "maximizing order revenue," while asset management systems pursue "maximizing hardware lifespan." Under a monolithic control architecture, it is difficult to balance the multi-objective game problem of "whether to sacrifice hardware lifespan (such as operating in high-temperature environments) for high-priced orders" in real time at the millisecond level.

[0026] 3. Lack of Trust Anchors Due to Data Silos: Operational data (transaction logs) are stored on the operator's servers, while hardware data (wear and tear) is stored on the vehicle itself, lacking a unified and trustworthy connection between the two. In financial risk control scenarios (ABS financing, insurance loss assessment), investors cannot verify whether the operator is manipulating sensor data to embellish asset statements.

[0027] 4. "Action omission" in single-threaded models under complex events: When a vehicle simultaneously uploads "minor collision alarm" and "high-value order request", the traditional single-threaded control model is prone to "only processing orders and ignoring risk evidence" due to competition for computing resources or confusion in logical priorities, resulting in asset risk exposure.

[0028] To address the aforementioned technical challenges, this invention provides an asset management system.

[0029] Please refer to Figure 1 , Figure 1 This is a schematic diagram of the framework structure of an asset management system provided in this embodiment.

[0030] The asset management system 400 mainly includes a cloud server 100, a vehicle terminal 200, and an audit terminal 300. The cloud server 100, the vehicle terminal 200, and the audit terminal 300 communicate and connect with each other.

[0031] The cloud server, vehicle-side, and auditing end can each consist of one or more intelligent agents. The vehicle-side agent is installed on the vehicle to collect its physical characteristics, such as LiDAR echo intensity and inertial measurement unit vibration spectrum, and generate a vehicle health fingerprint. The cloud server agent receives and stores the vehicle health fingerprint and various vehicle data sent by the vehicle-side agent. The auditing end agent monitors and audits the vehicle data to prevent data tampering.

[0032] Please refer to Figure 2 , Figure 2 This is a block diagram of a cloud server provided in this embodiment. The cloud server 100 includes a memory 210, a processor 220, and a communication module 230. The memory 210, processor 220, and communication module 230 are electrically connected to each other directly or indirectly to realize data transmission or interaction. For example, these components can be electrically connected to each other through one or more communication buses or signal lines.

[0033] The memory 210 is used to store programs or data. The memory 210 may be, but is not limited to, random access memory (RAM), read-only memory (ROM), programmable read-only memory (PROM), erasable programmable read-only memory (EPROM), electrically erasable programmable read-only memory (EEPROM), etc.

[0034] The processor 220 is used to read / write data or programs stored in the memory 210 and to perform corresponding functions.

[0035] The communication module 230 is used to establish a communication connection between the cloud server 100 and other communication terminals through the network, and to send and receive data through the network.

[0036] It should be understood that, Figure 2 The structure shown is only a schematic diagram of the cloud server 100. The cloud server 100 may also include components that are larger than... Figure 2 The more or fewer components shown, or having the same Figure 2 The different configurations shown. Figure 2 The components shown can be implemented using hardware, software, or a combination thereof.

[0037] Please refer to Figure 3 , Figure 3 An asset management method provided in this embodiment includes: S310: Generate vehicle health fingerprints based on vehicle operation data and road surface data.

[0038] Vehicle health fingerprints are primarily used to assess vehicle wear and tear. The core components of autonomous vehicles mainly include LiDAR (Light Detection and Ranging) and the vehicle's suspension system, i.e., the chassis. Therefore, vehicle operating data mainly includes sensing data from the onboard LiDAR. Chassis wear and tear can be assessed using two types of data: vehicle vibration data and road surface data. The vibration of the same vehicle varies depending on road conditions; for example, vibration on flat ground is significantly lower than on gravel roads. Similarly, vehicles with different degrees of chassis aging may exhibit different vibration patterns on the same road surface. For instance, vehicles with more aged chassis typically experience higher vibration levels than those with more worn chassis. Therefore, a comprehensive assessment of chassis aging can be achieved by combining vibration and road surface data. Then, a vehicle health fingerprint can be generated based on the onboard LiDAR sensing data and the overall chassis aging condition.

[0039] S320. Obtain vehicle location information and generate a vehicle expected revenue vector based on the vehicle location information.

[0040] To provide real-time, regionalized economic value for vehicle dispatching decisions, it is necessary to calculate the expected revenue of a vehicle per unit time based on its current location information and market data. This will enable the generated vehicle dispatching decisions to balance the relationship between vehicle aging and economic benefits.

[0041] S330. Obtain vehicle environment information, and construct a reward function based on the vehicle health fingerprint, the vehicle expected revenue vector, and the vehicle environment information.

[0042] Vehicle environmental information can include temperature, climate, and other data for different areas within the vehicle's operating range. Extreme weather conditions such as high temperatures, low temperatures, heavy rain, or other extreme weather can accelerate vehicle aging and wear. Aging and wear are also part of the cost of accepting orders. Therefore, while some orders may be more expensive, they cannot be accepted blindly due to the potential for accelerated vehicle aging and wear. For example, accepting orders for vehicles operating in high-temperature areas may yield higher short-term profits, but it could lead to premature vehicle scrapping.

[0043] Therefore, in order to make a scientific and reasonable vehicle scheduling strategy, it is necessary to use vehicle health fingerprint, vehicle expected revenue vector and vehicle environmental information as influencing factors to construct the reward function.

[0044] S340. Generate vehicle dispatch instructions based on the output value corresponding to the reward function.

[0045] After constructing the reward function, the collected current vehicle health fingerprint, vehicle expected revenue vector, and vehicle environment information are input into the reward function to obtain the corresponding output value. Then, vehicle dispatch instructions are generated based on the output value, and vehicle operation is controlled through the vehicle dispatch instructions.

[0046] This embodiment generates a vehicle health fingerprint by using vehicle operation data and road surface data to achieve a multi-faceted assessment of vehicle health. Then, a reward function is constructed by using the vehicle health fingerprint, the vehicle expected revenue vector, and vehicle environmental information. Based on the reward function, vehicle dispatch instructions are generated, thereby achieving a balance between vehicle revenue and vehicle lifespan and making optimal decisions. This extends vehicle lifespan while ensuring vehicle order-taking revenue.

[0047] In one implementation, the step of generating a vehicle health fingerprint based on vehicle operation data and road surface data includes: The optical attenuation coefficient of the lidar is calculated using the lidar data of the vehicle. The vehicle's vibration acceleration is obtained through the vehicle's inertial measurement unit; The vehicle obtains road surface data based on the positioning map, and the road surface data includes the road surface roughness coefficient. The chassis fatigue of the vehicle is calculated using the vibration acceleration and the road surface roughness coefficient. The vehicle health fingerprint is generated based on the light decay coefficient and the cumulative fatigue of the chassis.

[0048] The lidar data includes point cloud echo distribution, and the step of calculating the lidar attenuation coefficient using the vehicle's lidar data includes: Obtain the point cloud echo intensity distribution and reference distribution of the vehicle's lidar; The light decay coefficient was calculated using KL divergence:

[0049] in, Let X be the optical attenuation coefficient, and X be the discrete interval of the echo intensity. The point cloud echo intensity distribution This is the baseline distribution.

[0050] The fatigue level of a vehicle's chassis can be assessed using an improved model based on Miner's linear cumulative damage theory, combined with vibration acceleration data collected by the vehicle-mounted inertial measurement unit. Road surface roughness coefficient of high-precision map To calculate:

[0051] in, The cumulative fatigue amount from time 0 to t. For calibration coefficients, This represents the ultimate fatigue life constant of the suspension system. This is a fatigue index to ensure that the microscopic wear and tear on vehicles on bumpy roads can be accurately analyzed and recorded.

[0052] After obtaining the light decay coefficient and the cumulative fatigue of the chassis, the corresponding vehicle health fingerprint can be calculated by the onboard intelligent agent and sent to the cloud server.

[0053] The transmission strategies for sending the vehicle's health fingerprint to the cloud server can be divided into three types: Heartbeat Mode: During normal vehicle operation, the vehicle-side agent uploads a structured health fingerprint package only once every 60 seconds. {vin: "xxx", health_vector: [0.98, 0.02], status: " normal"} Each single data transfer consumes less than 1KB.

[0054] Event-Trigger Mode: In response to a sudden change in the loss index (such as vibration value > 5G or a sudden rise in battery temperature), the vehicle-side agent automatically captures raw sensor data slices for 30 seconds before and after the event, generates a hash digest, and uploads it to the cloud server for future reference.

[0055] Audit Mode (On-Demand Mode): In response to a deep audit command issued by the cloud server (such as before the settlement of financial assets), the vehicle agent calls the historical logs stored locally and uploads a full data statistical report for the specified time period.

[0056] This embodiment calculates the light decay coefficient and chassis cumulative fatigue degree in different ways according to the actual situation of autonomous vehicles. Then, the vehicle health fingerprint is generated by the light decay coefficient and chassis cumulative fatigue degree. This can significantly reduce the error of vehicle residual value prediction and significantly improve the financial accuracy of asset loss assessment. Moreover, by selecting different methods to send the vehicle health fatigue fingerprint to the cloud server at different times, the communication bandwidth cost is reduced and the commercial feasibility of large-scale fleet operation is greatly improved.

[0057] In one implementation, the step of generating a vehicle expected revenue vector based on vehicle location information includes: Generate a vehicle target area based on the vehicle location information; Obtain the current order information for the vehicle's target area, including order quantity, average order price, average waiting time, and weather. The expected revenue vector of the vehicle is calculated based on the order quantity, average order price, average waiting time, and weather conditions. The expected revenue vector of the vehicle includes expected revenue and average time.

[0058] The vehicle sends its real-time coordinates to the cloud server. The cloud server then divides the area around the vehicle's current location, for example, a three-kilometer radius around the vehicle, into the vehicle's target area. It then obtains information such as the number of orders currently being called within the target area, the average order price, the average waiting time, the weather, and whether it is during peak hours or other special periods. Based on this information, it calculates the vehicle's average future revenue.

[0059] For example, area A has an expected revenue of 13 yuan in the next ten minutes, but road conditions are poor, resulting in higher vehicle power consumption. Area B has an expected revenue of 10 yuan in the next ten minutes, but vehicle power consumption is lower. The system can make appropriate dispatch instructions based on the actual situation of the vehicles.

[0060] In one implementation, the vehicle environment information includes the vehicle ambient temperature, and the step of constructing a reward function based on the vehicle health fingerprint, the vehicle expected return vector, and the vehicle environment information includes: The vehicle health fingerprint, the vehicle expected revenue vector, and the vehicle ambient temperature are input into a deep Q-network, and a reward function is constructed through the deep Q-network. The reward function is as follows:

[0061] in, For the expected return, The average time is... The light decay coefficient is... The fatigue level of the chassis. The ambient temperature of the vehicle. The safe threshold for ambient temperature. , , , and All are coefficients. It is an exponential function. This is an indicator function.

[0062] In the future, to maximize profits while protecting assets, a reward function can be constructed based on expected profits and vehicle wear and tear.

[0063] in, The exponential function property ensures that when the loss index and When approaching a critical value, the penalty value increases exponentially to ensure that the vehicle responds promptly when wear and tear is high.

[0064] Indicator functions can impose additional hard penalties when the ambient temperature exceeds a safety threshold, but no penalty is imposed if the ambient temperature does not exceed the safety threshold.

[0065] When the final calculated output value of the reward function If the value is less than 0, it means that continuing to accept orders will not only fail to generate revenue, but will also cause irreversible damage to the vehicle's value. In this case, a command to stop accepting orders can be generated and sent to the vehicle.

[0066] When the output value of the reward function When the value is ≥0, it means that the order can generate revenue and will not cause damage to the vehicle. The cloud server can select the order with the highest revenue from multiple orders to accept the order, so as to ensure the revenue of the vehicle.

[0067] In one embodiment, after the step of acquiring the vibration acceleration of the vehicle via the vehicle's inertial measurement unit, the method further includes: If the vibration acceleration is greater than the acceleration threshold and the vehicle has not reported a collision, an interrupt signal is generated, which is used to suspend the vehicle's order-taking function. If the vehicle has reported a collision, then the vehicle's order-accepting function will be restored.

[0068] To ensure that vehicle risk events, such as collisions and alarms, are not missed, a separate auditing terminal can be set up. The auditing terminal asynchronously monitors the input and output of all vehicles. Once a risk event is found to be unreported or unresponsive, an interrupt signal is immediately generated. The interrupt signal from the auditing terminal has a high priority. Once an interrupt signal is issued, the vehicle must suspend the event it is currently executing, thus minimizing the possibility of risk events being missed due to confusion in the business logic priorities of the vehicle or cloud server.

[0069] In one embodiment, after the step of obtaining vehicle location information, the method further includes: If a vehicle information audit request is received from the auditing end, the vehicle operation compliance area is obtained; Commitments are generated based on the discrete logarithm problem using the vehicle location information and the vehicle's compliant operating area. A proof is generated based on the commitment using a proof generation algorithm, and the commitment and the proof are packaged and sent to the auditing end.

[0070] When the auditing end needs to prove that the vehicle is driving in a restricted area or that the battery wear does not exceed the threshold, in order to protect the privacy of operating routes and asset information, the vehicle end or cloud server end does not directly send the original location information and voltage information to the auditing end. Instead, it generates zero-knowledge proof credentials based on the location information and voltage information.

[0071] Let the vehicle's actual coordinates be... The compliant operating area is First, commitments are generated based on the discrete logarithm problem:

[0072] in, A large prime number is used to define the finite field Z. p (mold The multiplication group (where all operations are performed within this group, and the result is guaranteed to be [1, p).) Integers within the range of 1] For the finite field Z p The primitive element (generator), that is, the power of g, can traverse Zp. All non-zero elements in For public key components, This is the random blinding factor.

[0073] Then, the proof is output through the generation algorithm Prove. This ensures that the Verify verification algorithm satisfies the following logic:

[0074] Proof can be generated locally on the cloud server or in the vehicle using an automotive-grade encryption chip. and commitment And will prove and commitment The data is sent to the auditing end, which can verify whether the vehicle is operating within the compliant operating area without obtaining the vehicle's specific coordinates and voltage, thus achieving financial-grade privacy auditing of the data.

[0075] To perform the corresponding steps in the above embodiments and various possible methods, an implementation of an asset management system is given below. Please refer to [link / reference]. Figure 4 , Figure 4 This is a functional block diagram of an asset management system provided in an embodiment of the present invention. It should be noted that the asset management system provided in this embodiment has the same basic principles and technical effects as those in the above embodiments. For the sake of brevity, any parts not mentioned in this embodiment can be referred to the corresponding content in the above embodiments. The asset management system 400 includes: The health fingerprint generation module 410 is used to generate vehicle health fingerprints based on vehicle operation data and road surface data. The revenue vector generation module 420 is used to acquire vehicle location information and generate a vehicle expected revenue vector based on the vehicle location information. The reward function construction module 430 is used to obtain vehicle environment information and construct a reward function based on the vehicle health fingerprint, the vehicle expected revenue vector and the vehicle environment information. The dispatch instruction generation module 440 is used to generate vehicle dispatch instructions based on the output value corresponding to the reward function.

[0076] Optionally, the above modules can be stored in the form of software or firmware. Figure 2 The memory shown may be stored in or embedded in the operating system (OS) of the asset management system, and may be used by... Figure 1 The processor executes the commands. Meanwhile, the data and program code required to execute these modules can be stored in memory.

[0077] In the several embodiments provided in this application, it should be understood that the disclosed apparatus and methods can also be implemented in other ways. The apparatus embodiments described above are merely illustrative; for example, the flowcharts and block diagrams in the accompanying drawings illustrate the architecture, functionality, and operation of possible implementations of apparatus, methods, and computer program products according to various embodiments of the present invention. In this regard, each block in a flowchart or block diagram may represent a module, segment, or portion of code containing one or more executable instructions for implementing a specified logical function. It should also be noted that in some alternative implementations, the functions marked in the blocks may occur in a different order than those marked in the drawings. For example, two consecutive blocks may actually be executed substantially in parallel, and they may sometimes be executed in reverse order, depending on the functions involved. It should also be noted that each block in a block diagram and / or flowchart, and combinations of blocks in block diagrams and / or flowcharts, can be implemented using a dedicated hardware-based system that performs the specified function or action, or using a combination of dedicated hardware and computer instructions.

[0078] In addition, the functional modules in the various embodiments of the present invention can be integrated together to form an independent part, or each module can exist independently, or two or more modules can be integrated to form an independent part.

[0079] If the aforementioned functions are implemented as software functional modules and sold or used as independent products, they can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of this invention, or the part that contributes to the prior art, or a portion of the technical solution, can be embodied in the form of a software product. This computer software product is stored in a storage medium and includes several instructions to cause a computer device (which may be a personal computer, server, or network device, etc.) to execute all or part of the steps of the methods described in the various embodiments of this invention. The aforementioned storage medium includes various media capable of storing program code, such as USB flash drives, portable hard drives, read-only memory (ROM), random access memory (RAM), magnetic disks, or optical disks.

[0080] The above description is merely a preferred embodiment of the present invention and is not intended to limit the invention. Various modifications and variations can be made to the present invention by those skilled in the art. Any modifications, equivalent substitutions, improvements, etc., made within the spirit and principles of the present invention should be included within the scope of protection of the present invention.

Claims

1. An asset management method, characterized in that, Applied to an asset management system, the method includes: Vehicle health fingerprints are generated based on vehicle operation data and road surface data; Obtain vehicle location information and generate a vehicle expected revenue vector based on the vehicle location information; Obtain vehicle environment information, and construct a reward function based on the vehicle health fingerprint, the vehicle expected revenue vector, and the vehicle environment information; Vehicle dispatch instructions are generated based on the output value corresponding to the reward function.

2. The asset management method according to claim 1, characterized in that, The step of generating a vehicle health fingerprint based on vehicle operation data and road surface data includes: The optical attenuation coefficient of the lidar is calculated using the lidar data of the vehicle. The vehicle's vibration acceleration is obtained through the vehicle's inertial measurement unit; The vehicle obtains road surface data based on the positioning map, and the road surface data includes the road surface roughness coefficient. The chassis fatigue of the vehicle is calculated using the vibration acceleration and the road surface roughness coefficient. The vehicle health fingerprint is generated based on the light decay coefficient and the cumulative fatigue of the chassis.

3. The asset management method according to claim 2, characterized in that, The step of generating the vehicle's expected revenue vector based on vehicle location information includes: Generate a vehicle target area based on the vehicle location information; Obtain the current order information for the vehicle's target area, including order quantity, average order price, average waiting time, and weather. The expected revenue vector of the vehicle is calculated based on the order quantity, average order price, average waiting time, and weather conditions. The expected revenue vector of the vehicle includes expected revenue and average time.

4. The asset management method according to claim 3, characterized in that, The vehicle environment information includes the vehicle ambient temperature. The step of constructing a reward function based on the vehicle health fingerprint, the vehicle expected revenue vector, and the vehicle environment information includes: The vehicle health fingerprint, the vehicle expected revenue vector, and the vehicle ambient temperature are input into a deep Q-network, and a reward function is constructed through the deep Q-network. The reward function is as follows: in, For the aforementioned expected returns, The average time is... The light decay coefficient is... The fatigue level of the chassis. The ambient temperature of the vehicle. The safe threshold for ambient temperature. , , , and All are coefficients. It is an exponential function. This is an indicator function.

5. The asset management method according to claim 2, characterized in that, After the step of obtaining the vehicle's vibration acceleration through the vehicle's inertial measurement unit, the method further includes: If the vibration acceleration is greater than the acceleration threshold and the vehicle has not reported a collision, an interrupt signal is generated, which is used to suspend the vehicle's order-taking function. If the vehicle has reported a collision, then the vehicle's order-accepting function will be restored.

6. The asset management method according to claim 2, characterized in that, The lidar data includes point cloud echo distribution, and the step of calculating the lidar attenuation coefficient using the lidar data from the vehicle includes: Obtain the point cloud echo intensity distribution and reference distribution of the vehicle's lidar; The light decay coefficient was calculated using KL divergence: in, Let X be the optical attenuation coefficient, and X be the discrete interval of the echo intensity. The point cloud echo intensity distribution This is the baseline distribution.

7. The asset management method according to claim 1, characterized in that, After the step of obtaining vehicle location information, the method further includes: If a vehicle information audit request is received from the auditing end, the vehicle operation compliance area is obtained; Commitments are generated based on the discrete logarithm problem using the vehicle location information and the vehicle's compliant operating area. A proof is generated based on the commitment using a proof generation algorithm, and the commitment and the proof are packaged and sent to the auditing end.

8. An asset management system, characterized in that, include: The health fingerprint generation module is used to generate vehicle health fingerprints based on vehicle operation data and road surface data; The revenue vector generation module is used to obtain vehicle location information and generate a vehicle expected revenue vector based on the vehicle location information. The reward function construction module is used to obtain vehicle environment information and construct a reward function based on the vehicle health fingerprint, the vehicle expected revenue vector, and the vehicle environment information. The dispatch instruction generation module is used to generate vehicle dispatch instructions based on the output value corresponding to the reward function.

9. An electronic device, characterized in that, It includes a processor and a memory, the memory storing machine-executable instructions that can be executed by the processor to implement the asset management method according to any one of claims 1-7.

10. A computer-readable storage medium having a computer program stored thereon, characterized in that, When the computer program is executed by the processor, it implements the asset management method as described in any one of claims 1-7.

Images