Vehicle part inventory adjusting method, electronic equipment and vehicle

Abstract

The invention relates to the field of data processing, and provides a vehicle part inventory adjustment method, an electronic device and a vehicle, and the method comprises the steps: obtaining the part type of a target part of a target vehicle and vehicle driving data, inputting the part type and the vehicle driving data into a pre-trained fault prediction model, outputting the fault time of the target part through the fault prediction model; the initial demand quantity of the target part is obtained, the initial demand quantity and the fault time are input into a pre-trained inventory demand prediction model, the target inventory quantity of the target part is obtained through processing of the inventory demand prediction model, and the initial demand quantity is the demand quantity of the target part required corresponding to the fault time; the inventory of the target parts is adjusted according to the target inventory, it is guaranteed that when the target parts break down and need to be replaced, enough inventory is provided for replacement, meanwhile, the problem of inventory overstock of the parts is avoided, and inventory management is optimized.

Description

Technical Field

[0001] The present disclosure relates to the field of data processing, and in particular to a method for adjusting vehicle parts inventory, an electronic device, and a vehicle. Background Art

[0002] With the rapid development of vehicle technology, vehicles have become an important means of transportation in people's daily lives. As vehicles are used, parts in them are worn to varying degrees and need to be replaced. Accordingly, in order to meet the demand for replacement of vehicle parts, it is necessary to have sufficient inventory of parts.

[0003] The current management of vehicle parts inventory usually only judges the replacement time of parts based on the maintenance personnel's experience, and then increases the inventory of parts when they think they need to be replaced. This can easily lead to inventory backlogs or insufficient inventory of parts due to inaccurate judgments or other emergencies. Summary of the invention

[0004] In view of this, the purpose of the present disclosure is to propose a vehicle parts inventory adjustment method, electronic equipment and vehicle, so as to solve the current management of vehicle parts inventory. Usually, the replacement time of parts is judged only based on the experience of maintenance personnel, and the inventory of parts is increased when it is considered that replacement is needed. This is prone to the problem of inventory backlog or insufficient inventory of parts due to inaccurate judgment or other emergencies.

[0005] Based on the above purpose, a first aspect of the present disclosure provides a method for adjusting the inventory of vehicle parts, the method comprising:

[0006] Obtaining a component type and vehicle driving data of a target component of a target vehicle, inputting the component type and the vehicle driving data into a pre-trained fault prediction model, and outputting a fault time of the target component via the fault prediction model;

[0007] Obtaining an initial demand for a target component, inputting the initial demand and the failure time into a pre-trained inventory demand forecasting model, and processing the inventory demand forecasting model to obtain a target inventory of the target component, wherein the initial demand is the demand for the target component required for the failure time;

[0008] The inventory of the target component is adjusted according to the target inventory quantity.

[0009] Based on the same inventive concept, the second aspect of the present disclosure proposes a vehicle parts inventory adjustment device, comprising:

[0010] a failure time prediction module configured to obtain a component type and vehicle driving data of a target component of a target vehicle, input the component type and the vehicle driving data into a pre-trained failure prediction model, and output a failure time of the target component via the failure prediction model;

[0011] An inventory determination module is configured to obtain an initial demand for a target component, input the initial demand and the failure time into a pre-trained inventory demand forecasting model, and obtain a target inventory of the target component through processing by the inventory demand forecasting model, wherein the initial demand is the demand for the target component required for the failure time;

[0012] The inventory adjustment module is configured to adjust the inventory of the target component according to the target inventory quantity.

[0013] Based on the same inventive concept, the third aspect of the present disclosure proposes an electronic device, comprising a memory, a processor, and a computer program stored on the memory and executable by the processor, wherein the processor implements the vehicle parts inventory adjustment method as described above when executing the computer program.

[0014] Based on the same inventive concept, the fourth aspect of the present disclosure proposes a non-transitory computer-readable storage medium, which stores computer instructions, and the computer instructions are used to enable a computer to execute the vehicle parts inventory adjustment method as described above.

[0015] Based on the same inventive concept, the fifth aspect of the present disclosure provides a vehicle, including the vehicle parts inventory adjustment device described in the second aspect or the electronic device described in the third aspect or the storage medium described in the fourth aspect.

[0016] As can be seen from the above, the present disclosure proposes a vehicle parts inventory adjustment method, electronic device and vehicle, obtains the part type and vehicle driving data of the target part of the target vehicle, inputs the part type and the vehicle driving data into a pre-trained fault prediction model, and outputs the fault time of the target part through the fault prediction model. Considering the vehicle driving data when predicting the parts, that is, considering the impact of the actual driving on the parts, and then predicting the fault time of the parts is more accurate, and the demand for parts is accurately predicted. The initial demand for the target parts is obtained, wherein the initial demand is the demand for the target parts corresponding to the fault time, and the initial demand and the fault time are input into a pre-trained inventory demand prediction model, and processed by the inventory demand prediction model to obtain the target inventory of the target parts. The target inventory of the target parts is output using the trained inventory demand prediction model, and the target inventory obtained is more accurate. The target inventory is the actual quantity of the target parts in the subsequent process. The inventory of the target parts is adjusted according to the target inventory so that the inventory quantity of the target parts meets the demand of the target inventory, ensuring that when the target parts fail and need to be replaced, there is enough inventory for replacement. At the same time, the inventory of target parts is adjusted according to the target inventory quantity to avoid the problem of parts inventory backlog caused by replenishing too much inventory at one time, thereby optimizing inventory management. BRIEF DESCRIPTION OF THE DRAWINGS

[0017] In order to more clearly illustrate the technical solutions in the present disclosure or related technologies, the drawings required for use in the embodiments or related technical descriptions are briefly introduced below. Obviously, the drawings described below are only embodiments of the present disclosure. For ordinary technicians in this field, other drawings can be obtained based on these drawings without creative work.

[0018] Figure 1 A flowchart of a vehicle parts inventory adjustment method according to an embodiment of the present disclosure;

[0019] Figure 2 It is a structural block diagram of a vehicle parts inventory adjustment device according to an embodiment of the present disclosure;

[0020] Figure 3 It is a schematic diagram of the structure of an electronic device according to an embodiment of the present disclosure. DETAILED DESCRIPTION

[0021] In order to make the objectives, technical solutions and advantages of the present disclosure more clearly understood, the present disclosure is further described in detail below in combination with specific embodiments and with reference to the accompanying drawings.

[0022] It should be noted that, unless otherwise defined, the technical terms or scientific terms used in the embodiments of the present disclosure should be understood by people with ordinary skills in the field to which the present disclosure belongs. The "first", "second" and similar words used in the embodiments of the present disclosure do not indicate any order, quantity or importance, but are only used to distinguish different components. "Including" or "comprising" and similar words mean that the elements or objects appearing before the word cover the elements or objects listed after the word and their equivalents, without excluding other elements or objects. "Connect" or "connected" and similar words are not limited to physical or mechanical connections, but can include electrical connections, whether direct or indirect. "Up", "down", "left", "right" and the like are only used to indicate relative positional relationships. When the absolute position of the described object changes, the relative positional relationship may also change accordingly.

[0023] The terms used in this disclosure are explained as follows:

[0024] DQN: Deep Q network (DQN) is an algorithm used to solve reinforcement learning problems.

[0025] DDPG: DDPG (Deep Deterministic Policy Gradient) is an off-policy algorithm and can only be used in continuous action space.

[0026] PPO: Proximal Policy Optimization (PPO) algorithm.

[0027] TRPO: Trust region policy optimization (TRPO).

[0028] A3C: Reinforcement learning algorithm (Asynchronous Advantage Actor-Critic, A3C).

[0029] SAC: SAC is a maximum entropy-based policy learning method (Soft Actor-Critic, SAC), which improves learning speed and stability by adding entropy terms and randomization strategies.

[0030] DMS: Dealer Management System, an information system used to manage dealers' inventory, sales, maintenance services and other business processes.

[0031] With the rapid development of vehicle technology, vehicles have become an important means of transportation in people's daily lives. As vehicles are used, parts in them are worn to varying degrees and need to be replaced. Accordingly, in order to meet the demand for replacement of vehicle parts, it is necessary to have sufficient inventory of parts.

[0032] The current management of vehicle parts inventory usually only judges the replacement time of parts based on the maintenance personnel's experience, and then increases the inventory of parts when they think they need to be replaced. This can easily lead to inventory backlogs or insufficient inventory of parts due to inaccurate judgments or other emergencies.

[0033] Based on the above description, this embodiment proposes a vehicle parts inventory adjustment method, such as Figure 1 As shown, the method includes:

[0034] Step 101, obtaining the component type and vehicle driving data of a target component of a target vehicle, inputting the component type and the vehicle driving data into a pre-trained fault prediction model, and outputting the failure time of the target component through the fault prediction model.

[0035] In a specific implementation, the component type and vehicle driving data of the target component of the target vehicle are obtained, wherein the vehicle driving data refers to the data when the vehicle is driving, which can directly or indirectly reflect the usage of the component, and the vehicle driving data can specifically include the usage time of the component, the maintenance history of the component, the mileage of the vehicle, the driving behavior, etc. The maintenance history of the component refers to the historical record of the repair or replacement of the component, and the driving behavior refers to the behavior operation when driving the vehicle, such as sudden acceleration, sudden braking, deceleration, steering, etc.

[0036] In this embodiment, driving behaviors include both regular driving behaviors and special driving behaviors that cause significant damage to vehicle parts. The regular driving behaviors refer to behaviors corresponding to normal vehicle driving, and the special driving behaviors refer to behaviors that cause significant damage to vehicle parts, such as sudden braking, sharp turns, and sudden acceleration. In this embodiment, regular driving behaviors are acquired at regular intervals at preset time periods, and special driving behaviors are acquired in real time. For example, regular driving behaviors are acquired every 5 minutes, and special driving behaviors are acquired immediately as long as they exist.

[0037] The initial fault prediction model is trained in advance, and a fault prediction model is obtained after the training is completed, wherein the initial fault prediction model is a model using a neural network structure, including at least one of the following: DQN model, DDPG model, PPO model, TRPO model, A3C model, SAC model, which is not specifically limited in this embodiment.

[0038] The component type and vehicle driving data are input into the fault prediction model, and the fault prediction model processes and outputs the failure time of the target component. Since the component type is taken into account when determining the failure time, the obtained failure time fits the characteristics of the component itself. At the same time, the vehicle driving data is taken into account when determining the failure time, which corresponds to the actual use of the vehicle, and the predicted failure time is more accurate.

[0039] Step 102, obtaining the initial demand for the target component, inputting the initial demand and the failure time into a pre-trained inventory demand forecasting model, and processing the inventory demand forecasting model to obtain the target inventory of the target component, wherein the initial demand is the demand for the target component required corresponding to the failure time.

[0040] In specific implementation, the initial demand quantity of the target component is obtained, and the initial demand quantity indicates the demand quantity of the target component required corresponding to the failure time. The initial demand quantity may be the demand quantity preset by the vehicle manufacturer, and can be directly obtained in this embodiment.

[0041] For example, the current time is June 22, the failure time is October 22, and the target component is brake pads. The initial demand for brake pads is the pre-set demand that needs to be prepared in October 22.

[0042] The initial inventory demand forecasting model is trained in advance, and the inventory demand forecasting model is obtained after the training is completed, wherein the initial inventory demand forecasting model is a model using a neural network structure, including at least one of the following: DQN model, DDPG model, PPO model, TRPO model, A3C model, SAC model, which is not specifically limited in this embodiment.

[0043] The initial demand and failure time are input into the inventory demand forecasting model, and the target inventory of the target component is obtained through processing by the inventory demand forecasting model. The target inventory can ensure both the initial demand corresponding to the failure time and the demand when the target component fails and needs to be replaced, so as to meet the needs of different scenarios.

[0044] Step 103: adjusting the inventory of the target component according to the target inventory quantity.

[0045] During specific implementation, the inventory of the target parts is adjusted according to the target inventory quantity.

[0046] Specifically, the actual inventory of the target parts can be obtained. If the actual inventory is less than the target inventory, it means that replenishment is needed, and prompt information can be output to prompt the management personnel to replenish in time before the failure time. The prompt information includes at least one of the following: voice broadcast, screen display, etc. The content form of the prompt content includes at least one of the following: text, picture, rich text, etc.

[0047] Exemplarily, the content of the prompt is in the form of text, and the prompt information is in the form of voice broadcast. When the actual inventory of the target component is less than the target inventory, the prompt information "Insufficient inventory, please replenish before XX month of XX year" is output.

[0048] At the same time, when the actual inventory is less than the target inventory, the actual inventory of the target parts can be monitored in real time, and a preset frequency can be set for reminders to remind users to replenish the stock until the actual inventory is greater than or equal to the target inventory.

[0049] Furthermore, when the actual inventory is less than the target inventory, a replenishment order can be directly generated and output, and the replenishment order can be sent to the parts supplier so that the parts supplier can send the target parts according to the replenishment order to achieve the replenishment of the target parts, reduce manual intervention, and improve the response speed.

[0050] If the actual inventory is greater than the target inventory, it means that no replenishment is required. At the same time, the actual inventory of the target parts can be monitored in real time. When the actual inventory is less than the target inventory, a prompt message is output to prompt the management staff to replenish the stock in time before the failure time. The prompt message includes at least one of the following: voice broadcast, screen display, etc. The content of the prompt content includes at least one of the following: text, picture, rich text, etc.

[0051] Furthermore, if the actual inventory is greater than the target inventory, the actual inventory can be further compared with the target inventory to determine whether the actual inventory is greater than a preset multiple of the target inventory. If the actual inventory is less than or equal to the first preset multiple of the target inventory, only the actual inventory of the target component is monitored.

[0052] If the actual inventory is greater than the target inventory by the second preset multiple, and the first preset multiple is less than the second preset multiple, it indicates that there may be inventory accumulation of parts, so a prompt message is output to remind the user of the inventory accumulation of parts. At the same time, the rated demand for the target parts at every preset time period can also be obtained, and the target time corresponding to when the inventory of the target parts is less than the first preset multiple is calculated based on the rated demand and the actual inventory, and a prompt message is output based on the target time to remind the user to replenish the stock.

[0053] Exemplarily, the first preset multiple is 1.5 times, the second preset multiple is 3 times, the preset duration is one month, and the current time is June 22. The target inventory is 1000, and the actual inventory is 3200, that is, the actual inventory is greater than the target inventory of the second preset multiple. At this time, the rated demand of the target parts for each month is obtained, that is, the rated demand in July 22 is 500, the rated demand in August 22 is 700, and the rated demand in September 22 is 600. It can be calculated that when it is October 22, the actual inventory is 1400, which is less than the target inventory of the first preset multiple, so the target time is determined to be October 22. Output prompt information to prompt the user to replenish in October 22. At the same time, a replenishment order can also be automatically sent to the parts supplier in October 22 to achieve automatic replenishment.

[0054] Through the above scheme, the component type and vehicle driving data of the target component of the target vehicle are obtained, the component type and the vehicle driving data are input into a pre-trained fault prediction model, and the fault time of the target component is output through the fault prediction model. When predicting the components, the vehicle driving data is considered, that is, the influence of the actual driving on the components is considered, so that the failure time of the components is predicted more accurately, and the demand for components is accurately predicted. The initial demand for the target component is obtained, wherein the initial demand is the demand for the target component corresponding to the failure time, the initial demand and the failure time are input into a pre-trained inventory demand prediction model, and the target inventory of the target component is obtained through the inventory demand prediction model. The target inventory of the target component is output using the trained inventory demand prediction model, and the target inventory obtained is more accurate. The target inventory is the actual quantity required for the target component in the subsequent process. The inventory of the target component is adjusted according to the target inventory so that the inventory quantity of the target component meets the demand of the target inventory, ensuring that there is sufficient inventory for replacement when the target component fails and needs to be replaced. At the same time, the inventory of the target component is adjusted according to the target inventory to avoid the problem of overstocking of components due to excessive inventory replenishment at one time, thereby optimizing inventory management.

[0055] In some embodiments, the fault prediction model includes a component wear prediction model and a fault time prediction model, that is, step 101 specifically includes:

[0056] Step 1011: input the component type and the vehicle driving data into a pre-trained component wear prediction model, and use the component wear prediction model to analyze the component type and the vehicle driving data to obtain the wear degree of the target component.

[0057] In specific implementation, the fault prediction model may specifically include a component wear prediction model and a failure time prediction model, that is, first predicting the degree of component wear, and then predicting the component failure time based on the degree of wear.

[0058] The initial component wear prediction model is trained in advance, and the component wear prediction model is obtained after the training is completed, wherein the initial component wear prediction model is a model using a neural network structure, including at least one of the following: DQN model, DDPG model, PPO model, TRPO model, A3C model, SAC model, which is not specifically limited in this embodiment.

[0059] The component type and vehicle driving data are input into the pre-trained component wear prediction model, and the component wear prediction model outputs the degree of wear of the component. In this embodiment, the degree of wear of the component can be expressed in percentage form, such as the degree of wear of the brake pad is 30%.

[0060] Exemplarily, the vehicle driving data includes the usage time of the parts, the maintenance history of the parts, the mileage of the vehicle, and the driving behavior, that is, the input quantity input into the parts wear prediction model at this time includes the usage time of the parts, the maintenance history of the parts, the mileage of the vehicle, the driving behavior, and the type of parts. The specific training process of the parts wear prediction model is described in detail in the subsequent steps of this disclosure.

[0061] Step 1012, obtaining environmental information, inputting the environmental information and the degree of wear into a pre-trained failure time prediction model, and outputting the failure time of the target component through the failure time prediction model.

[0062] During the specific implementation, the initial failure time prediction model is trained in advance, and the failure time prediction model is obtained after the training is completed, wherein the initial failure time prediction model is a model using a neural network structure, including at least one of the following: DQN model, DDPG model, PPO model, TRPO model, A3C model, SAC model, which is not specifically limited in this embodiment.

[0063] Environmental information is obtained, and the environmental information indicates the environmental information of the target vehicle, and the environmental information includes environmental temperature, road condition information, vehicle location, etc. The environmental information and the degree of wear of the components output by the component wear prediction model are input into the failure time prediction model, and the failure time of the target component is output through the failure time prediction model.

[0064] Through the above scheme, the degree of wear of the parts is first predicted, and then the failure time of the parts is predicted based on the degree of wear, so that the degree of wear of the parts is fully considered when predicting the failure time, and the predicted failure time is more accurate. At the same time, the degree of wear and failure time of the parts are predicted using the trained model, which makes the prediction of the degree of wear and failure time of the parts more accurate.

[0065] Considering that other vehicles of the same model and the same production period as the target vehicle may have the problem of target component failure at about the same time as the target vehicle, more stocks of target components may be prepared to ensure replacement of other vehicles. Therefore, in some embodiments, step 103 specifically includes:

[0066] Step 1031, obtaining the vehicle model of the target vehicle and the installation time of the target component.

[0067] Step 1032, determining a first quantity of first target vehicles corresponding to the target component having the same installation time as the other vehicles having the same vehicle model as the vehicle.

[0068] Step 1033, determining a second number of second target vehicles in which the target component has been replaced among the first target vehicles.

[0069] Step 1034: Adjust the inventory of the target component according to the first quantity, the second quantity, and the target inventory.

[0070] In a specific implementation, the vehicle model of the target vehicle and the installation time of the target component are obtained, and the first target vehicles corresponding to the target component with the same installation time are obtained among other vehicles with the same vehicle model, and the number of the first target vehicles is counted as the first quantity.

[0071] From the first target vehicles, determine whether each first target vehicle has replaced the target component. Count the number of second target vehicles corresponding to the replacement of the target component as the second number. Adjust the inventory of the target component according to the first number, the second number and the target inventory.

[0072] For example, the target component is a shock absorber, the vehicle model of the target vehicle is model A, the shock absorber is installed in October 21, and the target inventory is 200. Find all vehicles of the same model A, and find all vehicles with shock absorbers installed in October 21 from all vehicles of model A as the first target vehicles, and count the first number of the first target vehicles as 50.

[0073] Determine whether each of the 50 first target vehicles has had its shock absorber replaced. Count the second number of second target vehicles that have had their shock absorbers replaced, which is 30. Adjust the inventory of shock absorbers according to the first number, the second number, and the target inventory.

[0074] Through the above scheme, considering that other vehicles of the same model and the same production period as the target vehicle may have the problem of target parts failure at about the same time as the target vehicle, the inventory of target parts is adjusted according to the above first quantity, second quantity and target inventory. The second quantity is the number of vehicles that may have the problem of target parts failure at about the same time as the target vehicle. When adjusting the target parts inventory, the second quantity is taken into account to ensure that other vehicles have sufficient target parts for replacement when failures occur, thereby meeting the needs of both the target vehicle and other vehicles.

[0075] In some embodiments, based on the specific scheme described in steps 1031 to 1034, step 1034 specifically includes:

[0076] Step 10341, performing a difference processing on the first quantity and the second quantity to obtain an inventory adjustment value.

[0077] Step 10342, adding the target inventory level and the preset multiple of the inventory level adjustment value to obtain a new target inventory level.

[0078] Step 10343, using the new target inventory to adjust the inventory of the target parts.

[0079] In specific implementation, the first quantity is the number of first target vehicles corresponding to the target parts with the same installation time among other vehicles of the same vehicle model, and the second quantity is the number of second target vehicles among the first target vehicles in which the target parts have been replaced. The first quantity and the second quantity are subtracted to obtain the inventory adjustment value.

[0080] The target inventory quantity and the inventory quantity adjustment value of the preset multiple are added together, and the summed value is the new target inventory quantity, and the inventory of the target component is adjusted using the new target inventory quantity. In this embodiment, the preset multiple is a value greater than 1.

[0081] Based on the example of step 1031 to step 1034, the preset multiple is 1.1, the first quantity is 50, the second quantity is 30, and the target inventory is 200. The inventory adjustment value calculated by the first quantity and the second quantity is 20, and the inventory adjustment value of the preset multiple is 22. The target inventory and the inventory adjustment value of the preset multiple are added together, that is, the new target inventory is 222.

[0082] Through the above scheme, in addition to considering that other vehicles of the same model and the same production period as the target vehicle may have the problem of target parts failure at about the same time as the target vehicle, an extra portion of inventory is reserved so that when some vehicles suddenly need to replace target parts, there are still abundant target parts for replacement, avoiding the shortage of target parts and ensuring sufficient inventory of target parts.

[0083] In some embodiments, the training process of the component wear prediction model includes:

[0084] Step 10A: acquiring a first component type and historical vehicle driving data corresponding to the first component type, and determining an actual wear degree corresponding to the first component type.

[0085] Step 10B: labeling the first component type and the historical vehicle driving data using the actual wear degree to obtain a target data set, wherein the target data set includes a first training data set.

[0086] Step 10C, obtaining an initial component wear prediction model, using the first training data set to train the initial component wear prediction model, determining whether a first preset training end condition is met, and obtaining a component wear prediction model.

[0087] In a specific implementation, a first component type and historical vehicle driving data corresponding to the first component type are obtained, an actual degree of wear corresponding to the first component type is determined, and the first component type and the historical vehicle driving data are marked using the actual degree of wear to obtain a target data set, wherein the target data set includes a first training data set, and the actual degree of wear is used to correct the obtained training results.

[0088] An initial component wear prediction model is obtained. In this embodiment, the initial component wear prediction model is a neural network artificial intelligence model. The initial component wear prediction model is trained using the first training data set. When the initial component wear prediction model meets the first preset training end condition, the training ends and the component wear prediction model is obtained.

[0089] The first preset training end condition includes at least one of the following: determining that all data in the first training data set are input into the initial component wear prediction model for training, determining that the loss function of the initial component wear prediction model converges to a first preset convergence threshold, or determining that the initial component wear prediction model is iteratively trained to a first preset number of iterations.

[0090] Exemplarily, the first preset training end condition is to determine that all data in the first training data set are input into the initial component wear prediction model for training:

[0091] There are a total of fifty groups of data in the training data set, each group of data includes a first component type, historical vehicle driving data and actual wear degree. The first preset training end condition is to determine that all data in the first training data set are input into the initial component wear prediction model for training, that is, when the fifty groups of data are all input into the initial component wear prediction model, there is no training data in the first training data set that has not been input into the initial component wear prediction model, and it is determined that the initial component wear prediction model training is completed, and the component wear prediction model is obtained.

[0092] In another example, the first preset training end condition is to determine that the first loss function of the initial component wear prediction model converges to a first preset convergence threshold:

[0093] Input the training data in the training data set into the initial component wear prediction model for training, and output a first training result. Determine a first loss function based on the first training result and the actual wear degree. The type of the first loss function includes at least one of the following: mean square error loss function, cross entropy loss function, logarithmic loss function, exponential loss function, square loss function or absolute value loss function, etc. When the first loss function converges to a first preset convergence threshold, it is determined that the first preset training end condition is met, and a component wear prediction model is obtained.

[0094] In another example, the first preset training end condition is to determine that the initial component wear prediction model is iteratively trained to a first preset number of iterations.

[0095] The training data in the training data set is input into the initial component wear prediction model for iterative training, the number of iterations is recorded, and when it is determined that the number of iterations is equal to the first preset number of iterations, the first preset training end condition is met to obtain the component wear prediction model.

[0096] Through the above scheme, the training data in the training data set includes the first component type, historical vehicle driving data and actual wear degree. The training data in the training data set is used to train the initial component wear prediction model until the first preset training end condition is met, and the component wear prediction model is obtained, so that the component wear prediction model can be used to output the wear degree corresponding to the component type and vehicle driving data in the subsequent process, and the wear degree can be determined more accurately.

[0097] In some embodiments, the target data set also includes a test data set, the first preset training end condition is to determine that the first loss function of the initial component wear prediction model converges to a first preset convergence threshold, and the training process of the component wear prediction model further includes:

[0098] Step 10D: input the test data set into the initial component wear prediction model to obtain the test results.

[0099] Step 10E: Obtain a preset target weight value corresponding to the test data set, and calculate a first loss function based on the test result and the target weight value.

[0100] Step 10F, updating the model parameters of the component wear prediction model until the first loss function converges to obtain an optimized component wear prediction model.

[0101] Step 10G: Obtain a component wear prediction model according to the model parameters corresponding to the optimized component wear prediction model.

[0102] In a specific implementation, a test data set in the target data set is input into the component wear prediction model, and a test result is output via the component wear prediction model, wherein the test result includes a first weight value corresponding to the test data.

[0103] A target weight value corresponding to the test data is pre-set, and a first loss function is obtained by calculating according to the target weight value and the first weight value included in the test result. The first loss function may be a logarithmic loss function, a hinge loss function, an exponential loss function, a cross entropy loss function, a square error loss function, an absolute value loss function, and a 0-1 loss function.

[0104] Based on the first loss function obtained in the above steps, the model parameters of the component wear prediction model are updated by the gradient descent method until the first loss function converges to obtain an optimized component wear prediction model. The gradient descent method is to solve the minimum value along the direction of gradient descent.

[0105] When the first loss function converges, the optimization of the component wear prediction model is completed, and the component wear prediction model is obtained based on the model parameters corresponding to the optimized component wear prediction model.

[0106] Through the above scheme, the trained component wear prediction model is tested using the test data in the target data set to determine the result error of the attribute prediction model. Based on the first loss function calculated based on the test result and the target weight value, the model is optimized until the first loss function converges, so that the wear value of the target component predicted by the component wear prediction model is more accurate, thereby improving the prediction accuracy of the component wear prediction model.

[0107] In some embodiments, the initial component wear prediction model comprises an input layer, a hidden layer, and an output layer. Step 10B uses the first training data set to train the initial component wear prediction model, specifically including:

[0108] Step 10B1, inputting the first component type, historical vehicle driving data and actual wear degree into the initial component wear prediction model through the input layer.

[0109] Step 10B2, storing the first component type in the type database of the initial component wear prediction model, and using the hidden layer to process the historical vehicle driving data and the actual wear degree to obtain a processing result;

[0110] Step 10B3, calling the type database according to the processing result, and matching the actual wear degree corresponding to the first component type;

[0111] Step 10B4: input the actual wear degree and historical environmental information corresponding to the first component type into the hidden layer for processing to generate a first training result.

[0112] Step 10B5: output the first training result from the initial component wear prediction model using an output layer.

[0113] In specific implementation, the initial component wear prediction model includes an input layer, a hidden layer and an output layer. The input layer is used to input the first component type, historical vehicle driving data and actual wear degree into the initial component wear prediction model.

[0114] The first component type is stored in a type database of an initial component wear prediction model, so that the wear degree corresponding to the first component type can be retrieved from the type database later. The historical vehicle driving data and the actual wear degree are processed by a hidden layer to obtain a processing result, which indicates the actual wear degree corresponding to the historical vehicle driving data.

[0115] According to the processing result, the type database is retrieved to match the actual wear degree corresponding to the first component type. The actual wear degree and historical environmental information corresponding to the first component type are input into the hidden layer for processing to generate a first training result. The first training result is output from the initial component wear prediction model through the output layer.

[0116] In some embodiments, the input layer includes at least one input interface, each input interface corresponds to the type of component, that is, the wear degree of each type of component corresponds to an input interface, such as the wear degree of the brake pad and the wear degree of the shock absorber correspond to different input interfaces. The wear degree is input into the initial component wear prediction model through the corresponding input interface. The wear degree of each type of component corresponds to a different hidden layer, and the input interface corresponding to the wear degree of each type of component is connected to the hidden layer corresponding to the wear degree of each type of component. The output layer includes at least one output interface, and the hidden layer corresponding to the wear degree of each type of component is connected to an output interface.

[0117] In some embodiments, the training process of the failure time prediction model includes:

[0118] Step 10a, obtaining historical environmental information of the component and the historical wear degree corresponding to the historical environmental information, and determining the actual failure time corresponding to the historical environmental information.

[0119] Step 10b: Use the actual failure time to mark the historical environmental information and the historical wear degree to obtain a second training data set.

[0120] Step 10c, obtaining an initial failure time prediction model, using the second training data set to train the initial failure time prediction model, determining whether a second preset training end condition is met, and obtaining a failure time prediction model.

[0121] In specific implementation, historical environmental information of the component and the historical wear degree corresponding to the historical environmental information are obtained, the actual failure time corresponding to the historical environmental information is determined, the historical environmental information and the historical wear degree are marked using the actual failure time, and a second training data set is obtained. The actual failure time is used to correct the obtained training results.

[0122] An initial failure time prediction model is obtained. In this embodiment, the initial failure time prediction model is a neural network artificial intelligence model. The initial failure time prediction model is trained using the second training data set. When the initial failure time prediction model meets the second preset training end condition, the training ends and the failure time prediction model is obtained.

[0123] The second preset training end condition includes at least one of the following: determining that all data in the second training data set are input into the initial failure time prediction model for training, determining that the loss function of the initial failure time prediction model converges to a second preset convergence threshold, or determining that the initial failure time prediction model is iteratively trained to a second preset number of iterations.

[0124] Exemplarily, the second preset training end condition is to determine that all data in the second training data set are input into the initial failure time prediction model for training:

[0125] There are a total of fifty groups of data in the training data set, each group of data includes historical environmental information, historical wear and tear, and actual failure time. The second preset training end condition is to determine that all data in the second training data set are input into the initial failure time prediction model for training, that is, when the fifty groups of data are all input into the initial failure time prediction model, there is no training data in the second training data set that has not been input into the initial failure time prediction model, and the initial failure time prediction model training is determined to be completed, and the failure time prediction model is obtained.

[0126] In another example, the second preset training end condition is to determine that the second loss function of the initial failure time prediction model converges to a second preset convergence threshold:

[0127] Input the training data in the training data set into the initial fault time prediction model for training, and output a second training result. Determine a second loss function based on the second training result and the actual fault time. The type of the second loss function includes at least one of the following: mean square error loss function, cross entropy loss function, logarithmic loss function, exponential loss function, square loss function or absolute value loss function, etc. When the second loss function converges to a second preset convergence threshold, it is determined that the second preset training end condition is met, and a fault time prediction model is obtained.

[0128] In another example, the second preset training end condition is to determine that the initial failure time prediction model is iteratively trained to a second preset number of iterations.

[0129] The training data in the training data set is input into the initial failure time prediction model for iterative training, the number of iterations is recorded, and when it is determined that the number of iterations is equal to a second preset number of iterations, the second preset training end condition is met to obtain the failure time prediction model.

[0130] Through the above scheme, the training data in the training data set includes historical environmental information, historical wear levels and actual failure time. The initial failure time prediction model is trained using the training data in the training data set until the second preset training end condition is met, and a failure time prediction model is obtained. The failure time prediction model can be used for subsequent use to output the failure time corresponding to the environmental information and wear level. The failure time is determined more accurately, and the subsequent determination of the target inventory of the target parts based on the failure time is more accurate.

[0131] In some embodiments, the training process of the inventory demand forecasting model includes:

[0132] Step A, obtaining the historical demand and historical failure time of parts, and determining the actual inventory corresponding to the historical failure time.

[0133] Step B: using the actual inventory to mark the historical demand and the historical failure time to obtain a third training data set.

[0134] Step C, obtaining an initial inventory demand forecasting model, using the third training data set to train the initial inventory demand forecasting model, determining whether a third preset training end condition is met, and obtaining an inventory demand forecasting model.

[0135] In specific implementation, the historical demand and historical failure time of parts are obtained, the actual inventory corresponding to the historical failure time is determined, and the historical demand and the historical failure time are marked using the actual inventory to obtain a third training data set. The actual inventory is used to correct the obtained training results.

[0136] An initial inventory demand forecasting model is obtained. In this embodiment, the initial inventory demand forecasting model is a neural network artificial intelligence model. The initial inventory demand forecasting model is trained using the third training data set. When the initial inventory demand forecasting model meets the third preset training end condition, the training ends and the inventory demand forecasting model is obtained.

[0137] The third preset training end condition includes at least one of the following: determining that all data in the third training data set are input into the initial inventory demand forecasting model for training, determining that the loss function of the initial inventory demand forecasting model converges to a third preset convergence threshold, or determining that the initial inventory demand forecasting model is iteratively trained to a third preset number of iterations.

[0138] Exemplarily, the third preset training end condition is to determine that all data in the third training data set are input into the initial inventory demand forecasting model for training:

[0139] There are a total of fifty groups of data in the training data set, each group of data includes historical demand, historical failure time and actual inventory. The third preset training end condition is to determine that all data in the third training data set are input into the initial inventory demand forecasting model for training, that is, when the fifty groups of data are input into the initial inventory demand forecasting model, there is no training data in the third training data set that has not been input into the initial inventory demand forecasting model, and the initial inventory demand forecasting model training is determined to be completed, and the inventory demand forecasting model is obtained.

[0140] In another example, the third preset training end condition is to determine that the third loss function of the initial inventory demand forecasting model converges to a third preset convergence threshold:

[0141] Input the training data in the training data set into the initial inventory demand forecasting model for training, and output a third training result. Determine a third loss function according to the third training result and the actual inventory. The type of the third loss function includes at least one of the following: mean square error loss function, cross entropy loss function, logarithmic loss function, exponential loss function, square loss function or absolute value loss function, etc. When the third loss function converges to a third preset convergence threshold, it is determined that the third preset training end condition is met, and the inventory demand forecasting model is obtained.

[0142] In another example, the third preset training end condition is to determine that the initial inventory demand forecasting model is iteratively trained to a third preset number of iterations.

[0143] The training data in the training data set is input into the initial inventory demand forecasting model for iterative training, the number of iterations is recorded, and when it is determined that the number of iterations is equal to a third preset number of iterations, the third preset training end condition is met, and the inventory demand forecasting model is obtained.

[0144] Through the above scheme, the training data in the training data set includes historical demand, historical failure time and actual inventory. The initial inventory demand prediction model is trained using the training data in the training data set until the third preset training end condition is met, and the inventory demand prediction model is obtained. The inventory demand prediction model can be used for subsequent use to output the target inventory corresponding to the initial demand and failure time, and the target inventory is determined more accurately.

[0145] In this embodiment, the parts wear prediction model, the failure time prediction model and the inventory demand prediction model can be further trained according to usage during use, and the model can be continuously optimized to improve the accuracy of model prediction.

[0146] Based on the same inventive concept, another embodiment of the present disclosure provides a method for adjusting the inventory of vehicle parts, comprising:

[0147] Collect historical maintenance records for each vehicle, including parts replacement time, fault type, mileage, etc. Integrate data from different models and years to form a comprehensive historical fault database. Real-time vehicle status monitoring, using Internet of Vehicles technology to collect real-time vehicle operation data, such as engine condition, battery status, sensor data, etc. Obtain information such as vehicle mileage, driving habits (frequency of sudden acceleration and sudden braking). Collect vehicle environment data, such as climate, road conditions, etc., which may affect parts wear, and user usage habit data, such as daily commuting routes, long-distance driving frequency, etc.

[0148] The component wear prediction model, failure time prediction model and inventory demand prediction model are established respectively. Specifically, the input features of the component wear prediction model are vehicle model, mileage, driving behavior (frequency of sudden acceleration and sudden braking), ambient temperature, component usage time and maintenance history. The historical data set is divided into training set and test set in chronological order, where the test set reflects the latest wear situation. According to the replacement record and usage time of the parts, the degree of wear or remaining life is defined as the target variable. The model is trained using the training set data, and the latest wear situation is confirmed through continuous verification. According to the current mileage and driving behavior of different models, the degree of wear of key components is predicted to provide a basis for preventive maintenance. For example, frequent sudden braking may accelerate the wear of brake pads and brake discs.

[0149] The input features of the failure time prediction model are vehicle sensor data (such as vibration, temperature, pressure), driving behavior, environmental factors (road conditions), and historical component failure records. Such as the average value and standard deviation over a period of time, as well as the statistical characteristics of driving behavior. Organize the sensor data before the historical failure and mark them as abnormal samples, and the non-fault period as normal samples. Train the anomaly detection model to identify normal and abnormal patterns; predict future trends and identify prediction results that deviate from expectations as early warning signals. Monitor vehicle sensor data in real time, apply the model for online analysis, and trigger an early warning immediately once an abnormality is detected.

[0150] For example, by continuously monitoring the engine vibration data, abnormal increases in vibration levels can be detected early, indicating possible engine failure. For example, frequent driving on bumpy roads or in dusty environments can affect the life of components such as filters and shock absorbers.

[0151] The input features of the inventory demand forecasting model are historical demand for parts, vehicle model, mileage, season, region, historical fault records, and user habits. Consider seasonal and holiday effects and construct corresponding dummy variables. Sort out historical sales and replacement records, and handle missing values ​​and outliers. Use historical data to train the model. Predict the demand for each part in the future, and distinguish seasonal demand fluctuations and regional differences.

[0152] Dynamically adjust inventory based on forecast results, maintain a safe inventory of high-demand parts, and reduce capital occupation of low-demand parts. For example, based on the forecasted growth in demand for air-conditioning system repairs in high-temperature areas in summer, increase the inventory of related parts in advance to ensure a quick response to customer needs.

[0153] Based on the forecast results, the dealer's parts inventory level is automatically adjusted to ensure sufficient supply of high-demand parts, while reducing the inventory of low-demand parts to prevent capital occupation. At the same time, an intelligent replenishment mechanism is implemented to automatically trigger a purchase order when the inventory drops to a preset threshold, reducing manual intervention and improving response speed.

[0154] By sharing forecast data with parts suppliers through DMS, suppliers can plan production in advance and shorten the delivery cycle. Realize real-time sharing of upstream and downstream information in the supply chain, enhance the flexibility and resilience of the supply chain, and effectively respond to market fluctuations. At the same time, collect comparison data between actual failures and forecast results, and continuously optimize the model. Consider after-sales service feedback and customer satisfaction, and continuously adjust algorithms and strategies to better meet actual needs.

[0155] It should be noted that the method of the embodiment of the present disclosure can be performed by a single device, such as a computer or a server. The method of the present embodiment can also be applied in a distributed scenario and completed by multiple devices cooperating with each other. In the case of such a distributed scenario, one of the multiple devices can only perform one or more steps in the method of the embodiment of the present disclosure, and the multiple devices will interact with each other to complete the described method.

[0156] It should be noted that the above describes some embodiments of the present disclosure. Other embodiments are within the scope of the appended claims. In some cases, the actions or steps recorded in the claims can be performed in an order different from that in the above embodiments and still achieve the desired results. In addition, the processes depicted in the accompanying drawings do not necessarily require the specific order or continuous order shown to achieve the desired results. In some embodiments, multitasking and parallel processing are also possible or may be advantageous.

[0157] Based on the same inventive concept, corresponding to any of the above-mentioned embodiment methods, the present disclosure also provides a vehicle parts inventory adjustment device.

[0158] refer to Figure 2 , Figure 2 The vehicle parts inventory adjustment device of the embodiment includes:

[0159] The failure time prediction module 201 is configured to obtain a component type and vehicle driving data of a target component of a target vehicle, input the component type and the vehicle driving data into a pre-trained failure prediction model, and output a failure time of the target component via the failure prediction model;

[0160] The inventory determination module 202 is configured to obtain an initial demand for a target component, input the initial demand and the failure time into a pre-trained inventory demand prediction model, and obtain a target inventory of the target component through processing by the inventory demand prediction model, wherein the initial demand is the demand for the target component required for the failure time;

[0161] The inventory adjustment module 203 is configured to adjust the inventory of the target component according to the target inventory quantity.

[0162] In some embodiments, the fault prediction model includes a component wear prediction model and a fault time prediction model, and the fault time prediction module 201 specifically includes:

[0163] a wear degree prediction unit configured to input the component type and the vehicle driving data into a pre-trained component wear prediction model, and analyze the component type and the vehicle driving data using the component wear prediction model to obtain the wear degree of the target component;

[0164] The failure time prediction unit is configured to obtain environmental information, input the environmental information and the wear degree into a pre-trained failure time prediction model, and output the failure time of the target component through the failure time prediction model.

[0165] In some embodiments, the inventory adjustment module 203 specifically includes:

[0166] A data acquisition unit is configured to acquire a vehicle model of a target vehicle and an installation time of a target component;

[0167] A first quantity determination unit is configured to determine a first quantity of first target vehicles corresponding to the target component having the same installation time among other vehicles having the same vehicle model as the vehicle;

[0168] A second quantity determination unit is configured to determine a second quantity of second target vehicles in which the target component has been replaced among the first target vehicles;

[0169] The inventory adjustment unit is configured to adjust the inventory of the target component according to the first quantity, the second quantity and the target inventory amount.

[0170] In some embodiments, the inventory adjustment unit is specifically configured to:

[0171] Subtract the first quantity from the second quantity to obtain an inventory adjustment value;

[0172] Adding the target inventory quantity and the preset multiple of the inventory quantity adjustment value to obtain a new target inventory quantity;

[0173] The inventory of the target component is adjusted using the new target inventory amount.

[0174] In some embodiments, the device includes a component wear prediction model training module, and the component wear prediction model training module is specifically configured as follows:

[0175] Acquire a first component type and historical vehicle driving data corresponding to the first component type, and determine an actual degree of wear corresponding to the first component type;

[0176] Using the actual wear degree to mark the first component type and the historical vehicle driving data to obtain a target data set, wherein the target data set includes a first training data set;

[0177] An initial component wear prediction model is obtained, and the initial component wear prediction model is trained using the first training data set to determine whether a first preset training end condition is met, thereby obtaining a component wear prediction model.

[0178] In some embodiments, the device includes a failure time prediction model training module, and the failure time prediction model training module is specifically configured to:

[0179] Obtain historical environmental information of the component and the historical wear degree corresponding to the historical environmental information, and determine the actual failure time corresponding to the historical environmental information;

[0180] Using the actual failure time to mark the historical environmental information and the historical wear degree to obtain a second training data set;

[0181] An initial failure time prediction model is obtained, and the initial failure time prediction model is trained using the second training data set to determine whether a second preset training end condition is met to obtain a failure time prediction model.

[0182] In some embodiments, the device includes an inventory demand forecasting model training module, and the inventory demand forecasting model training module is specifically configured to:

[0183] Obtain the historical demand and failure time of parts, and determine the actual inventory corresponding to the historical failure time;

[0184] Using the actual inventory to mark the historical demand and the historical failure time, to obtain a third training data set;

[0185] An initial inventory demand forecasting model is obtained, and the initial inventory demand forecasting model is trained using the third training data set to determine whether a third preset training end condition is met to obtain an inventory demand forecasting model.

[0186] In some embodiments, the device further includes a prompt module, and the prompt module is specifically configured to:

[0187] Obtaining the actual inventory of the target component;

[0188] In response to the actual inventory being less than the target inventory, outputting a prompt message, wherein the prompt message is used to prompt information that the target component is insufficient in stock;

[0189] Generate and output a replenishment order so that the component supplier can replenish the target components according to the replenishment order.

[0190] For the convenience of description, the above device is described by dividing it into various modules according to its functions. Of course, when implementing the present disclosure, the functions of each module can be implemented in the same or multiple software and / or hardware.

[0191] The device of the above embodiment is used to implement the corresponding vehicle parts inventory adjustment method in any of the above embodiments, and has the beneficial effects of the corresponding method embodiment, which will not be repeated here.

[0192] Based on the same inventive concept, corresponding to any of the above-mentioned embodiments, the present disclosure also provides an electronic device, including a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein when the processor executes the program, the vehicle parts inventory adjustment method described in any of the above embodiments is implemented.

[0193] Figure 3 A more specific schematic diagram of the hardware structure of an electronic device provided in this embodiment is shown, and the device may include: a processor 1010, a memory 1020, an input / output interface 1030, a communication interface 1040, and a bus 1050. The processor 1010, the memory 1020, the input / output interface 1030, and the communication interface 1040 are connected to each other through the bus 1050 in the device.

[0194] The processor 1010 can be implemented by a general-purpose CPU (Central Processing Unit), a microprocessor, an application-specific integrated circuit (ASIC), or one or more integrated circuits, and is used to execute relevant programs to implement the technical solutions provided in the embodiments of this specification.

[0195] The memory 1020 may be implemented in the form of ROM (Read Only Memory), RAM (Random Access Memory), static storage device, dynamic storage device, etc. The memory 1020 may store an operating system and other application programs. When the technical solutions provided in the embodiments of this specification are implemented by software or firmware, the relevant program codes are stored in the memory 1020 and are called and executed by the processor 1010.

[0196] The input / output interface 1030 is used to connect the input / output module to realize information input and output. The input / output module can be configured in the device as a component (not shown in the figure), or it can be externally connected to the device to provide corresponding functions. The input device may include a keyboard, a mouse, a touch screen, a microphone, various sensors, etc., and the output device may include a display, a speaker, a vibrator, an indicator light, etc.

[0197] The communication interface 1040 is used to connect a communication module (not shown) to realize communication interaction between the device and other devices. The communication module can realize communication through a wired mode (such as USB, network cable, etc.) or a wireless mode (such as mobile network, WIFI, Bluetooth, etc.).

[0198] The bus 1050 includes a path that transmits information between the various components of the device (eg, the processor 1010, the memory 1020, the input / output interface 1030, and the communication interface 1040).

[0199] It should be noted that, although the above device only shows the processor 1010, the memory 1020, the input / output interface 1030, the communication interface 1040 and the bus 1050, in the specific implementation process, the device may also include other components necessary for normal operation. In addition, it can be understood by those skilled in the art that the above device may also only include the components necessary for implementing the embodiments of the present specification, and does not necessarily include all the components shown in the figure.

[0200] The electronic device of the above embodiment is used to implement the corresponding vehicle parts inventory adjustment method in any of the above embodiments, and has the beneficial effects of the corresponding method embodiment, which will not be repeated here.

[0201] Based on the same inventive concept, corresponding to any of the above-mentioned embodiment methods, the present disclosure also provides a non-transitory computer-readable storage medium, wherein the non-transitory computer-readable storage medium stores computer instructions, and the computer instructions are used to enable the computer to execute the vehicle parts inventory adjustment method as described in any of the above embodiments.

[0202] The computer-readable medium of this embodiment includes permanent and non-permanent, removable and non-removable media, and information storage can be implemented by any method or technology. Information can be computer-readable instructions, data structures, modules of programs, or other data. Examples of computer storage media include, but are not limited to, phase change memory (PRAM), static random access memory (SRAM), dynamic random access memory (DRAM), other types of random access memory (RAM), read-only memory (ROM), electrically erasable programmable read-only memory (EEPROM), flash memory or other memory technology, read-only compact disk read-only memory (CD-ROM), digital versatile disk (DVD) or other optical storage, magnetic cassettes, magnetic tape magnetic disk storage or other magnetic storage devices or any other non-transmission media that can be used to store information that can be accessed by a computing device.

[0203] The computer instructions stored in the storage medium of the above embodiment are used to enable the computer to execute the vehicle parts inventory adjustment method described in any of the above embodiments, and have the beneficial effects of the corresponding method embodiments, which will not be repeated here.

[0204] Based on the same inventive concept, corresponding to any of the above-mentioned embodiments and methods, the present application also provides a vehicle, including the vehicle parts inventory adjustment device in the above-mentioned embodiments, the electronic device in the above-mentioned embodiments, and the computer-readable storage medium in the above-mentioned embodiments, and the vehicle equipment implements the vehicle parts inventory adjustment method described in any of the above embodiments.

[0205] The vehicle of the above-mentioned embodiment is used to implement the vehicle parts inventory adjustment method described in any of the above-mentioned embodiments, and has the beneficial effects of the corresponding method embodiments, which will not be repeated here.

[0206] It is understandable that before using the technical solutions of each embodiment of the present disclosure, the type, scope of use, usage scenarios, etc. of the personal information involved will be informed to the user in an appropriate manner, and the user's authorization will be obtained.

[0207] For example, in response to receiving an active request from a user, a prompt message is sent to the user to clearly remind the user that the operation requested to be performed will require obtaining and using the user's personal information. Thus, the user can independently choose whether to provide personal information to software or hardware such as an electronic device, application, server, or storage medium that performs the operation of the technical solution of the present disclosure according to the prompt message.

[0208] As an optional but non-limiting implementation, in response to receiving the user's active request, the prompt information may be sent to the user in the form of a pop-up window, in which the prompt information may be presented in text form. In addition, the pop-up window may also carry a selection control for the user to choose "agree" or "disagree" to provide personal information to the electronic device.

[0209] It is understandable that the above notification and the process of obtaining user authorization are merely illustrative and do not constitute a limitation on the implementation of the present disclosure. Other methods that meet relevant laws and regulations may also be applied to the implementation of the present disclosure.

[0210] Those skilled in the art should understand that the discussion of any of the above embodiments is merely illustrative and is not intended to imply that the scope of the present disclosure is limited to these examples. Based on the concept of the present disclosure, the technical features in the above embodiments or different embodiments may be combined, the steps may be implemented in any order, and there are many other variations of the different aspects of the embodiments of the present disclosure as described above, which are not provided in detail for the sake of simplicity.

[0211] In addition, to simplify the description and discussion, and in order not to make the embodiments of the present disclosure difficult to understand, the known power / ground connections to the integrated circuit (IC) chips and other components may or may not be shown in the provided figures. In addition, the device can be shown in the form of a block diagram to avoid making the embodiments of the present disclosure difficult to understand, and this also takes into account the fact that the details of the implementation of these block diagram devices are highly dependent on the platform on which the embodiments of the present disclosure will be implemented (that is, these details should be fully within the scope of understanding of those skilled in the art). Where specific details (e.g., circuits) are set forth to describe exemplary embodiments of the present disclosure, it is apparent to those skilled in the art that the embodiments of the present disclosure can be implemented without these specific details or with changes in these specific details. Therefore, these descriptions should be considered illustrative rather than restrictive.

[0212] Although the present disclosure has been described in conjunction with specific embodiments of the present disclosure, many replacements, modifications and variations of these embodiments will be apparent to those skilled in the art from the foregoing description. For example, other memory architectures (e.g., dynamic RAM (DRAM)) may use the embodiments discussed.

[0213] The embodiments of the present disclosure are intended to cover all such substitutions, modifications and variations that fall within the broad scope of the present application. Therefore, any omissions, modifications, equivalent substitutions, improvements, etc. made within the spirit and principles of the embodiments of the present disclosure should be included in the scope of protection of the present disclosure.

Claims

1. A method for adjusting the inventory of vehicle parts, characterized in that: include: Obtaining a component type and vehicle driving data of a target component of a target vehicle, inputting the component type and the vehicle driving data into a pre-trained fault prediction model, and outputting a fault time of the target component via the fault prediction model; Obtaining an initial demand for a target component, inputting the initial demand and the failure time into a pre-trained inventory demand forecasting model, and processing the inventory demand forecasting model to obtain a target inventory of the target component, wherein the initial demand is the demand for the target component required for the failure time; The inventory of the target component is adjusted according to the target inventory quantity.

2. The method according to claim 1, characterized in that The fault prediction model includes a component wear prediction model and a fault time prediction model; The step of inputting the component type and the vehicle driving data into a pre-trained fault prediction model and outputting the fault time of the target component via the fault prediction model includes: Inputting the component type and the vehicle driving data into a pre-trained component wear prediction model, and using the component wear prediction model to analyze the component type and the vehicle driving data to obtain the wear degree of the target component; Environmental information is obtained, and the environmental information and the degree of wear are input into a pre-trained failure time prediction model, and the failure time of the target component is output through the failure time prediction model.

3. The method according to claim 2, characterized in that The step of adjusting the inventory of the target component according to the target inventory quantity includes: Obtaining the vehicle model of the target vehicle and the installation time of the target parts; Determine a first quantity of first target vehicles corresponding to the target component having the same installation time among other vehicles having the same vehicle model as the vehicle; Determine a second number of second target vehicles in which the target component has been replaced among the first target vehicles; The inventory of the target component is adjusted according to the first quantity, the second quantity and the target inventory amount.

4. The method according to claim 3, characterized in that The step of adjusting the inventory of the target component according to the first quantity, the second quantity and the target inventory includes: Subtract the first quantity from the second quantity to obtain an inventory adjustment value; Adding the target inventory quantity and the preset multiple of the inventory quantity adjustment value to obtain a new target inventory quantity; The inventory of the target component is adjusted using the new target inventory amount.

5. The method according to claim 2, characterized in that: The training process of the component wear prediction model includes: Acquire a first component type and historical vehicle driving data corresponding to the first component type, and determine an actual degree of wear corresponding to the first component type; Using the actual wear degree to mark the first component type and the historical vehicle driving data to obtain a target data set, wherein the target data set includes a first training data set; An initial component wear prediction model is obtained, and the initial component wear prediction model is trained using the first training data set to determine whether a first preset training end condition is met, thereby obtaining a component wear prediction model.

6. The method according to claim 2, characterized in that The training process of the failure time prediction model includes: Obtain historical environmental information of the component and the historical wear degree corresponding to the historical environmental information, and determine the actual failure time corresponding to the historical environmental information; Using the actual failure time to mark the historical environmental information and the historical wear degree to obtain a second training data set; An initial failure time prediction model is obtained, and the initial failure time prediction model is trained using the second training data set to determine whether a second preset training end condition is met to obtain a failure time prediction model.

7. The method according to claim 1, characterized in that The training process of the inventory demand forecasting model includes: Obtain the historical demand and failure time of parts, and determine the actual inventory corresponding to the historical failure time; Using the actual inventory to mark the historical demand and the historical failure time, to obtain a third training data set; An initial inventory demand forecasting model is obtained, and the initial inventory demand forecasting model is trained using the third training data set to determine whether a third preset training end condition is met to obtain an inventory demand forecasting model.

8. The method according to claim 1, characterized in that After adjusting the inventory of the target component according to the target inventory quantity, the method further includes: Obtaining the actual inventory of the target component; In response to the actual inventory being less than the target inventory, outputting a prompt message, wherein the prompt message is used to prompt information that the target component is insufficient in stock; Generate and output a replenishment order so that the component supplier can replenish the target components according to the replenishment order.

9. An electronic device, comprising a memory, a processor, and a computer program stored in the memory and running on the processor, wherein the processor implements the method according to any one of claims 1 to 8 when executing the program.

10. A vehicle, characterized in that: An electronic device comprising the electronic device described in claim 9.

Images