Vehicle spare part stock quantity determination method and related equipment

Abstract

The invention provides a vehicle spare part stock quantity determination method and related equipment, and relates to the technical field of artificial intelligence. The method comprises the steps that the inventory data of a target vehicle model is acquired, the target vehicle model is a vehicle model using a target spare part, and the inventory data comprises the total sales volume of the target vehicle model in different periods; according to the inventory data of the target vehicle model, the sales volume of the target vehicle model in the current period is obtained; calculating a cumulative distribution function value of the target vehicle according to the current period and the cumulative distribution function; and determining the stock quantity of the target spare parts in the current period according to the sales volume and the cumulative distribution function value of the target vehicle type in the target vehicle type in the current period and the average replacement quantity of the target spare parts, the method and the device are more suitable for long-term prediction and better conform to the application scene of damaged replacement of the vehicle spare parts, and therefore, on the premise of effectively utilizing the vehicle data, the vehicle replacement efficiency is improved. The vehicle spare parts are predicted more accurately, and the inventory and storage cost is reduced.

Description

Background Art

[0002] In the auto parts procurement industry, due to the poor liquidity and long shelf life of parts, when purchasing parts, it is usually necessary to choose a one-time purchase of large quantities, especially for certain specific parts that can only be used on certain models, because after the model is delisted, the parts will no longer be produced. Therefore, when the model is about to be delisted, the automaker needs to purchase enough parts at one time to cope with the current number of parts on the market for the maintenance and replacement needs of the owners of the model in the future. However, the related technology has problems such as low accuracy, waste of inventory and cost for large-scale procurement and long-term prediction.

[0003] It should be noted that the information disclosed in the above background technology section is only used to enhance the understanding of the background of the present disclosure, and therefore may include information that does not constitute the prior art known to ordinary technicians in the field. Summary of the invention

[0004] The present disclosure provides a method for determining the inventory quantity of vehicle spare parts and related equipment, which at least to a certain extent overcomes the problems of low accuracy, waste of inventory and cost in large-scale procurement and long-term prediction in related technologies.

[0005] Other features and advantages of the present disclosure will become apparent from the following detailed description, or may be learned in part by the practice of the present disclosure.

[0006] According to one aspect of the present disclosure, there is provided a method for determining the inventory of vehicle spare parts, comprising: obtaining ownership data of a target vehicle model, the target vehicle model being a vehicle model using target spare parts, the ownership data comprising the total sales volume of the target vehicle model in different cycles; obtaining the sales volume of the target vehicle model in a current cycle based on the ownership data of the target vehicle model; calculating a cumulative distribution function value of the target vehicle based on the current cycle and a cumulative distribution function; and determining the inventory volume of the target spare parts in the current cycle based on the sales volume of the target vehicle model in the current cycle, the cumulative distribution function value and the average replacement volume of the target spare parts.

[0007] In one embodiment of the present disclosure, the cumulative distribution function is trained based on the historical sales data of the target spare parts, the ownership data of the target vehicle model and the average replacement amount of the target spare parts; the cumulative distribution function is a probability density function of the attenuated gamma distribution.

[0008] In one embodiment of the present disclosure, the cumulative distribution function is trained in the following manner: initializing the parameter value of the cumulative distribution function to be trained; training the cumulative distribution function to be trained based on the ownership data of the target vehicle model and the average replacement quantity of the target spare parts to obtain the predicted inventory of the target spare parts within the target period; obtaining the loss function value based on the historical sales data and the predicted inventory; adjusting the parameter value of the cumulative distribution function to be trained to minimize the loss function value to obtain the cumulative distribution function.

[0009] In one embodiment of the present disclosure, gradient descent fitting is used to obtain the target parameter group of the cumulative distribution function so as to minimize the loss function value.

[0010] In one embodiment of the present disclosure, the stock quantity of the target spare parts in the current cycle is determined based on the sales volume of the target vehicle model in the current cycle, the cumulative distribution function value and the average replacement volume of the target spare parts, including: determining the product of the sales volume of the target vehicle model in the current cycle, the cumulative distribution function value and the average replacement volume of the target spare parts as the stock quantity of the target spare parts in the current cycle.

[0011] In one embodiment of the present disclosure, when the target vehicle model includes multiple vehicle models, determining the stock quantity of the target spare parts in the current cycle includes: determining the stock quantity of the target spare parts for each vehicle model in the current cycle; accumulating the stock quantity of the target spare parts for each vehicle model in the current cycle to obtain the stock quantity of the target spare parts in the current cycle.

[0012] In one embodiment of the present disclosure, the method further includes: determining the stock quantity of the target spare part in at least one cycle; and determining the total stock quantity of the target spare part in the entire life cycle based on the stock quantity of the target spare part in the at least one cycle.

[0013] According to another aspect of the present disclosure, a device for determining the inventory quantity of vehicle spare parts is also provided, including: a data acquisition module, used to obtain the inventory data of a target vehicle model, the target vehicle model is a vehicle model using target spare parts, and the inventory data includes the total sales volume of the target vehicle model in different cycles; a first determination module, used to obtain the sales volume of the target vehicle model in a current cycle based on the inventory data of the target vehicle model; a second determination module, used to calculate the cumulative distribution function value of the target vehicle based on the current cycle and the cumulative distribution function; and a third determination module, used to determine the inventory quantity of the target spare parts in the current cycle based on the sales volume of the target vehicle model in the current cycle, the cumulative distribution function value and the average replacement volume of the target spare parts.

[0014] According to another aspect of the present disclosure, an electronic device is provided, comprising: a processor; and a memory for storing executable instructions of the processor; wherein the processor is configured to execute the above-mentioned method for determining the inventory quantity of vehicle spare parts by executing the executable instructions.

[0015] According to another aspect of the present disclosure, a computer-readable storage medium is provided, on which a computer program is stored, and when the computer program is executed by a processor, the above-mentioned method for determining the inventory quantity of vehicle spare parts is implemented.

[0016] According to another aspect of the present disclosure, a computer program product is provided, the computer program product comprising a computer program or computer instructions, the computer program or the computer instructions being loaded and executed by a processor so that a computer implements the above-mentioned method for determining the inventory quantity of vehicle spare parts.

[0017] In the embodiment of the present disclosure, the ownership data of the target vehicle model is obtained, the target vehicle model is a vehicle model using the target spare parts, and the ownership data includes the total sales volume of the target vehicle model in different periods; based on the ownership data of the target vehicle model, the sales volume of the target vehicle model in the current period is obtained; based on the current period and the cumulative distribution function, the cumulative distribution function value of the target vehicle is calculated; based on the sales volume of the target vehicle model in the current period, the cumulative distribution function value and the average replacement volume of the target spare parts, the stock volume of the target spare parts in the current period is determined. The present disclosure is more suitable for long-term prediction and is more in line with the application scenario of replacement of damaged vehicle spare parts, so that on the premise of effectively utilizing vehicle data, more accurate prediction of vehicle spare parts can be made, thereby reducing inventory and storage costs.

[0018] It is to be understood that the foregoing general description and the following detailed description are exemplary and explanatory only and are not restrictive of the present disclosure. BRIEF DESCRIPTION OF THE DRAWINGS

[0019] The accompanying drawings herein are incorporated into the specification and constitute a part of the specification, illustrate embodiments consistent with the present disclosure, and together with the specification are used to explain the principles of the present disclosure. Obviously, the accompanying drawings described below are only some embodiments of the present disclosure, and for ordinary technicians in this field, other accompanying drawings can be obtained based on these accompanying drawings without creative work.

[0020] Figure 1 The following is an architecture diagram of a vehicle dispatching system provided by an embodiment of the present disclosure;

[0021] Figure 2 A flow chart of a method for determining the inventory quantity of vehicle spare parts provided by an embodiment of the present disclosure is shown;

[0022] Figure 3A flow chart of a cumulative distribution function training method provided by an embodiment of the present disclosure is shown;

[0023] Figure 4 A schematic diagram of a cumulative distribution function training process provided by an embodiment of the present disclosure is shown;

[0024] Figure 5 A flow chart of another method for determining the inventory quantity of vehicle spare parts provided by an embodiment of the present disclosure is shown;

[0025] Figure 6 A flowchart showing another example of a method for determining the inventory quantity of vehicle spare parts provided by an embodiment of the present disclosure is shown;

[0026] Figure 7 A schematic diagram showing the structure of a device for determining the inventory quantity of vehicle spare parts provided by an embodiment of the present disclosure is shown;

[0027] Figure 8 A structural block diagram of an electronic device provided by an embodiment of the present disclosure is shown. DETAILED DESCRIPTION

[0028] Example embodiments will now be described more fully with reference to the accompanying drawings. However, example embodiments can be implemented in a variety of forms and should not be construed as limited to the examples set forth herein; rather, these embodiments are provided so that the disclosure will be more comprehensive and complete and to fully convey the concepts of the example embodiments to those skilled in the art. The described features, structures, or characteristics may be combined in any suitable manner in one or more embodiments.

[0029] In addition, the accompanying drawings are only schematic illustrations of the present disclosure and are not necessarily drawn to scale. The same reference numerals in the figures represent the same or similar parts, and their repeated description will be omitted. Some of the block diagrams shown in the accompanying drawings are functional entities and do not necessarily correspond to physically or logically independent entities. These functional entities can be implemented in software form, or implemented in one or more hardware modules or integrated circuits, or implemented in different networks and / or processor devices and / or microcontroller devices.

[0030] For ease of understanding, before introducing the embodiments of the present disclosure, several terms involved in the embodiments of the present disclosure are first explained as follows:

[0031] Gamma distribution: Gamma distribution is a continuous probability distribution in statistics. The parameter α in the Gamma distribution is called the shape parameter, and β is called the scale parameter. It can usually be used in scenarios involving the probability distribution of time variables and the probability distribution of quantity variables.

[0032] Probability density function: The probability density function is a function that describes the probability of the output value of a random variable near a certain value point. For a distribution, its horizontal axis represents the value of the distribution variable, and the vertical axis represents the probability of the variable appearing at its corresponding horizontal axis value.

[0033] Cumulative distribution function: The cumulative distribution function is the integral of the probability density function, which can fully describe the probability distribution of a real random variable. In the case of a scalar continuous distribution, it gives the area under the probability density function from negative infinity to x. For a distribution, its abscissa represents the value of the distribution variable, and the ordinate represents the probability that the variable is less than or equal to its corresponding abscissa value.

[0034] Figure 1 An exemplary system architecture 100 is shown to which a method for determining a vehicle spare parts inventory quantity or an apparatus for determining a vehicle spare parts inventory quantity according to an embodiment of the present disclosure can be applied.

[0035] like Figure 1 As shown, the system architecture 100 may include a terminal device 110 , a network 120 and a server 130 .

[0036] The network 120 is used to provide a medium for a communication link between the terminal device 110 and the server 130, and may be a wired network or a wireless network. The network 120 may include various connection types, such as wired or wireless communication links or optical fiber cables.

[0037] The user may use the terminal device 110 to interact with the server 130 through the network 120 to receive or send messages.

[0038] The terminal device 110 may be any electronic device that has a voice acquisition device and supports web browsing, including but not limited to a smart phone, a tablet computer, a display screen, and a desktop computer.

[0039] Various communication client applications can be installed on the terminal device 110, such as shopping applications, web browser applications, search applications, instant messaging tools, email clients, social platform software, etc., and historical shipment data can be obtained through the communication client applications.

[0040] It should be noted that the client of the application installed on the terminal device 110 is the same, or the client of the same type of application based on different operating systems. Based on the different terminal platforms, the specific form of the client of the application can also be different, for example, the application client can be a mobile client, a PC client, etc.

[0041] The server 130 may be a server that provides various services, such as a background management server that provides support for web browsing websites browsed by users using the terminal device 110. The background server may obtain the ownership data of the target vehicle model, the target vehicle model is a vehicle model that uses the target spare parts, and the ownership data includes the total sales of the target vehicle model in different cycles; according to the ownership data of the target vehicle model, the sales of the target vehicle model in the current cycle are obtained; according to the current cycle and the cumulative distribution function, the cumulative distribution function value of the target vehicle is calculated. It is also possible to perform analysis and other processing based on the sales volume of the target vehicle model in the current cycle, the cumulative distribution function value, and the average replacement amount of the target spare parts, etc., and obtain the processing results (such as the stock of the target spare parts in the current cycle, the total stock of the target spare parts in the entire life cycle, etc.) and feed them back to the terminal device 110.

[0042] Optionally, server 130 can be an independent physical server, or a server cluster or distributed system composed of multiple physical servers, or a cloud server that provides basic cloud computing services such as cloud services, cloud databases, cloud computing, cloud functions, cloud storage, network services, cloud communications, middleware services, domain name services, security services, CDN (Content Delivery Network), as well as big data and artificial intelligence platforms.

[0043] Those skilled in the art will know that Figure 1 The number of terminal devices, networks and servers in the embodiment is only for illustration, and any number of terminal devices, networks and servers may be provided according to actual needs, and the embodiments of the present disclosure do not limit this.

[0044] During the vehicle sales process, when a model is about to be discontinued, the vehicle's spare parts will no longer be produced. The manufacturer needs to purchase enough spare parts at one time to cope with the current number of spare parts of this model on the market, in order to meet the vehicle maintenance and replacement needs in the future.

[0045] For the application scenario of large-scale procurement and long-term forecasting of vehicle spare parts, a forecasting method is needed to ensure the accuracy of the forecast, so as to accurately purchase the spare parts inventory, so as not to fail to meet the demand due to insufficient procurement, and not to waste inventory and costs due to excessive procurement.

[0046] Vehicle spare parts forecasting has the following characteristics: first, there is a strong correlation between demand and vehicle sales or vehicle ownership, and the current ownership of the corresponding model on the market will directly determine the demand; second, the purchase of spare parts usually has a long time interval, and is purchased in the form of batches of orders. In other words, the number of spare parts purchased each time will be the demand for a long time in the future, rather than a shorter time unit, such as 10 years. Third, the full life cycle forecast is obviously different from the general form of parts forecasting. The required forecast period is usually in years, such as 10 years or even longer, while the general parts forecast is in days and months, and the required forecast length is at most one year or slightly longer. Therefore, there are many problems in using conventional forecasting methods for ultra-long cycle forecasts.

[0047] In the related art, expert evaluation methods, time series forecasting methods, and forecasting methods based on sales and maintenance data can be used to forecast vehicle spare parts inventory.

[0048] For the expert evaluation method, based on the experience of the experts responsible for managing inventory and historical data, the demand for all spare parts in the next cycle is evaluated and purchased. In the case of stable vehicle ownership and short-term prediction scenarios, experts can maintain a high accuracy rate with their rich experience. However, when faced with long-term estimation scenarios and scenarios where a large number of spare parts demand needs to be estimated, the expert evaluation method has problems such as inaccurate estimation and lack of energy to make one-to-one predictions, and is difficult to apply to scenarios with large inventory management.

[0049] The time series prediction method is a prediction method based on historical data. It predicts future demand by analyzing and modeling the historical data of vehicle spare parts demand. The time series prediction method includes stationary time series prediction method and non-stationary time series prediction method. When there is more data, this method can more intelligently and accurately dig out the rules behind the changes in demand, effectively solve a large number of inventory management prediction scenarios, and can perform daily periodic training and prediction through scripts and scheduling. It can achieve the prediction demand of a large amount of inventory without human intervention, and has a high accuracy rate in short-term prediction effects. However, when faced with life cycle level predictions, such as 10 years or even longer predictions, this method cannot accurately fit the future spare parts inventory trend, which limits the prediction of life cycle spare parts demand.

[0050] For the prediction method based on efficiency and maintenance data, the prediction is made using the time series method based on the historical demand data of spare parts, and the number of maintenance replacement parts and the number of fault replacement parts are estimated in combination with the known maintenance data, and the larger value of the two predictions is used as the estimate of the number of demand parts. However, in the prediction at the life cycle level, the prediction method combined with maintenance data also hits a wall. When the prediction cycle exceeds a certain threshold, the probability of replacing parts for each vehicle must be 1, and it will not increase after a longer period of time. The demand for spare parts caused by the growth of future vehicle sales is not considered. This method requires the maintenance work order data of all sold vehicles to make accurate predictions, which requires extremely high data costs and requirements and cannot be applied to long-term predictions at the life cycle level.

[0051] In order to at least partially solve the above technical problems, it is urgent to design a method that can be applied to the long-term prediction of vehicle spare parts.

[0052] The present invention provides a method for determining the inventory quantity of vehicle spare parts, which can be applied to the demand forecasting scenario of vehicle spare parts at the future full life cycle level, thereby helping vehicle users to make more accurate forecasts and conduct reasonable purchases to meet demand while minimizing procurement and warehousing costs.

[0053] In addition, it can also be applied to other long-term forecasting scenarios to achieve accurate demand forecasting at the life cycle level.

[0054] The present disclosure provides a method for determining the inventory of vehicle spare parts, which obtains the inventory data of a target vehicle model, where the target vehicle model is a vehicle model that uses target spare parts, and the inventory data includes the total sales volume of the target vehicle model in different cycles; based on the inventory data of the target vehicle model, the sales volume of the target vehicle model in the current cycle is obtained; based on the current cycle and the cumulative distribution function, the cumulative distribution function value of the target vehicle is calculated; based on the sales volume of the target vehicle model in the current cycle, the cumulative distribution function value and the average replacement volume of the target spare parts, the inventory volume of the target spare parts in the current cycle is determined. The present disclosure is more suitable for long-term prediction and is more in line with the application scenario of replacement of damaged vehicle spare parts, so that on the premise of effectively using vehicle data, more accurate prediction of vehicle spare parts can be made, thereby reducing inventory and storage costs.

[0055] It should be pointed out that the embodiments of the present invention and the technical features therein may be combined with each other without conflict.

[0056] The present exemplary implementation is described in detail below with reference to the accompanying drawings and embodiments.

[0057] First, a method for determining the stock quantity of vehicle spare parts is provided in an embodiment of the present disclosure, and the method can be executed by any system with computing and processing capabilities. The method for determining the stock quantity of vehicle spare parts provided in an embodiment of the present disclosure can be executed by a server, for example, by a vehicle spare parts stock quantity determination device configured on the server.

[0058] Figure 2 A flow chart of a method for determining the inventory quantity of vehicle spare parts provided in an embodiment of the present disclosure is shown as follows: Figure 2 As shown, the method for determining the vehicle spare parts inventory provided in the embodiment of the present disclosure includes the following steps:

[0059] S202. Acquire ownership data of a target vehicle model, where the target vehicle model is a vehicle model using a target spare part, and the ownership data includes total sales of the target vehicle model in different periods.

[0060] The target spare parts can be understood as parts that need to be repaired or replaced for the vehicle, such as air conditioning filters, engine cylinder heads, cylinder blocks, pistons, intake valves, exhaust valves, tires, tire mounting screws, etc. The above-mentioned target vehicle models refer to at least one vehicle model that uses the target spare parts. It should be noted that a target spare part can be applied to one vehicle model or to multiple vehicle models.

[0061] In the present disclosure, the above cycle can be predicted in months. The ownership data of the target model is the total number of target models put on the market in different cycles. For example, there is one target model corresponding to the target spare part, and the ownership data of the target model is obtained as shown in Table 1.

[0062] Table 1. Ownership data of target models

[0063]

[0064]

[0065] As shown in Table 1, taking June 2021 as an example, the number of vehicles in the current month is 310, of which 30 are from April 2021, 60 are from May 2021, and 220 are from June 2021. That is, the number of vehicles in the target model is the sum of the sales in the current month and all the months before the current month. It should be noted that the target model will be delisted in 2023, so the number of vehicles in October and November 2023 will remain the same and will not change.

[0066] S204. Obtain the sales volume of the target model in the current cycle according to the ownership data of the target model.

[0067] In one embodiment, with continued reference to Table 1, the sales volume of the target model in the current cycle is obtained based on the total sales volume of the target model in the current cycle and the total sales volume of the target model in the previous cycle.

[0068] For example, by subtracting the target model ownership in May 2021 from the target model ownership in June 2021 in Table 1, we can get the sales volume of the target model in June 2021, that is, 330-90=220 (units).

[0069] S206. Calculate the cumulative distribution function value of the target vehicle according to the current cycle and the cumulative distribution function.

[0070] In one embodiment, the cumulative distribution function is a probability density function of a decaying gamma distribution, and the cumulative distribution function is constructed on the basis of a gamma distribution.

[0071] The probability density function p(t) of the Gamma distribution is expressed as follows:

[0072]

[0073] Wherein, t is a variable. In the present disclosure, t is the number of cycles from the current cycle, or the number of months from the current month. α is a shape parameter that determines the shape of the distribution curve, β is an inverse scale parameter that mainly determines the steepness of the curve, and Γ(·) is a gamma function.

[0074] Gamma distribution can describe the distribution of time occurrence and can be used to express the probability distribution of fault occurrence time.

[0075] On the basis of Gamma distribution, a new parameter d is added, d≤1, and d is used to characterize the time decay coefficient. The probability density function p′(t) of the decaying gamma distribution is expressed by the following formula:

[0076]

[0077] By increasing the time decay coefficient d, in the current long-cycle spare parts replacement scenario, when spare parts are damaged after long-term use, car owners prefer to replace the whole vehicle instead of spare parts, which leads to a lower overall probability of spare parts replacement. Decay-Gamma (α, β, d) is used to represent a decaying Gamma distribution. It should be noted that the probability density function of the above decaying Gamma distribution is a trained function, that is, the above parameters α, β, d are optimal values.

[0078] In one embodiment, the cycle number corresponding to the current cycle can be substituted into the probability density function of the above-mentioned attenuated Gamma distribution to obtain the cumulative distribution function value of the target vehicle, which is the difference between the cumulative distribution function value of the current month and the cumulative distribution function value of the previous month.

[0079] S208. Determine the stock quantity of the target spare parts in the current cycle according to the sales volume of the target vehicle model, the cumulative distribution function value, and the average replacement quantity of the target spare parts in the current cycle.

[0080] In one embodiment, the average replacement quantity of the target spare parts is the average replacement quantity of the target spare parts during the life cycle of each vehicle model, which may be provided by the vehicle manufacturer.

[0081] In S208, the product of the sales volume of the target vehicle model in the current cycle, the cumulative distribution function value, and the average replacement quantity of the target spare parts is determined as the stock quantity of the target spare parts in the current cycle.

[0082] In the embodiment of the present disclosure, the ownership data of the target vehicle model is obtained, the target vehicle model is a vehicle model using the target spare parts, and the ownership data includes the total sales volume of the target vehicle model in different periods; based on the ownership data of the target vehicle model, the sales volume of the target vehicle model in the current period is obtained; based on the current period and the cumulative distribution function, the cumulative distribution function value of the target vehicle is calculated; based on the sales volume of the target vehicle model in the current period, the cumulative distribution function value and the average replacement volume of the target spare parts, the stock volume of the target spare parts in the current period is determined. The present disclosure is more suitable for long-term prediction and is more in line with the application scenario of replacement of damaged vehicle spare parts, so that on the premise of effectively utilizing vehicle data, more accurate prediction of vehicle spare parts can be made, thereby reducing inventory and storage costs.

[0083] In one embodiment, the cumulative distribution function is trained based on the historical sales data of the target spare parts, the target vehicle model's inventory data, and the average replacement amount of the target spare parts. Among them, the historical sales data of the target spare parts and the target vehicle model's inventory data need to be refined to data per month, and the average replacement amount of the target spare parts for each vehicle model can be a measured value. The historical sales data of the target spare parts used by the target vehicles in Table 1 from April 2021 to November 2023 are shown in Table 2.

[0084] Table 2 Historical sales data of target spare parts

[0085] time Sales 2021-04 1 2021-05 1 2021-06 2 2021-07 3 2021-08 4 ··· ··· 2023-10 78 2023-11 81

[0086] Figure 3 FIG. 2 shows a flow chart of a cumulative distribution function training method provided by an embodiment of the present disclosure. Figure 3As shown, in one embodiment, the cumulative distribution function is obtained by training in the following manner:

[0087] S302, initializing the parameter value of the cumulative distribution function to be trained;

[0088] S304, training the cumulative distribution function to be trained according to the ownership data of the target vehicle model and the average replacement quantity of the target spare parts, to obtain the predicted stock quantity of the target spare parts in the target period;

[0089] S306. Obtain a loss function value based on historical sales data and predicted inventory quantities;

[0090] S308. Adjust the parameter value of the cumulative distribution function to be trained to minimize the loss function value and obtain the cumulative distribution function.

[0091] When training the cumulative distribution function, first initialize the parameter values ​​of the cumulative distribution function to be trained. For example, assume that the initial parameter values ​​of the probability density function of the Decay-Gamma distribution are α=1.5, β=100, d=0.95, and then calculate the predicted inventory quantity E of the target spare parts for each month.

[0092] The predicted inventory quantity E can be expressed by the following formula:

[0093] E=Q(t)×p'(t)×A (Formula 3)

[0094] Among them, Q(t) is the sales volume of the target model in the current cycle, p'(t) is the cumulative distribution function value, A is the average replacement amount, and t is the current cycle number.

[0095] E0 is used to represent the historical sales data of the target spare parts, and the loss function value can be calculated based on the predicted inventory quantity E and the historical sales data.

[0096] In one embodiment, the loss function may adopt a mean square error loss function or an average error loss function, where the mean square error loss function is used to measure the average difference between the predicted value and the true value of the cumulative distribution function.

[0097] For example, the loss function value is calculated based on the mean square error loss function n is the number of samples, and in the present disclosure, n=1.

[0098] After obtaining the loss function value, the goal is to continuously minimize the loss function value by adjusting the parameters of the probability density function of the Decay-Gamma distribution.

[0099] In one embodiment, the optimizer uses gradient descent fitting to obtain a target parameter set of the cumulative distribution function so as to minimize the loss function value.

[0100] The target parameter group is the parameter value corresponding to the minimum loss function value, which is the optimal or near-optimal parameter group.

[0101] In the present disclosure, the target spare parts inventory in the future period can be predicted by fitting the probability density function of the decaying gamma distribution. In the scenario where the target spare parts need long-term prediction, the corresponding target model is generally no longer on the market, so the estimate of the future model inventory can be the inventory value of the last month of the current available data. Through calculation, the spare parts sales value for each month in the future for a long period of time can be obtained.

[0102] Figure 4 A schematic diagram of a cumulative distribution function training process provided by an embodiment of the present disclosure is shown as follows: Figure 4 As shown, the cumulative distribution function training process is as follows:

[0103] The optimizer initializes the probability density function of the Decay-Gamma distribution;

[0104] According to the vehicle ownership data and the probability density function of the Decay-Gamma distribution, the predicted value of spare parts inventory is obtained;

[0105] According to the historical sales data of spare parts and the predicted value of inventory, the loss function value is obtained;

[0106] The optimizer performs parameter iteration based on the gradient descent method of the loss function to minimize the loss function value and obtain the optimal or near-optimal parameter value. At this point, the training of the probability density function of the Decay-Gamma distribution is completed.

[0107] In the disclosed embodiment, the cumulative distribution function is trained by using historical sales data of target spare parts, ownership data of target vehicle models and average replacement quantity of target spare parts, thereby improving the prediction accuracy of the cumulative distribution function and making the target spare parts inventory obtained by the cumulative distribution function closer to the actual inventory.

[0108] Figure 5 A flow chart of another method for determining the inventory quantity of vehicle spare parts provided by an embodiment of the present disclosure is shown as follows: Figure 5 As shown, when the target vehicle model includes multiple vehicle models, the determination of the stock quantity of the target spare parts in the current cycle in the above S208 includes:

[0109] S502, determining the stock quantity of target spare parts for each vehicle model in the current cycle;

[0110] S504. Accumulate the target spare parts stocking quantity of each vehicle model in the current cycle to obtain the target spare parts stocking quantity in the current cycle.

[0111] In one embodiment, when the target spare parts are applied to multiple vehicle models, a cumulative distribution function can be used to predict the stock quantity of the target spare parts for each vehicle model in the current cycle, and then the stock quantities of multiple vehicle models are accumulated to obtain the stock quantity of the target spare parts in the current cycle.

[0112] In addition, the cumulative distribution function can be trained based on the ownership data of multiple models, the historical sales data of target spare parts, and the average replacement quantity to directly obtain the inventory of target spare parts corresponding to multiple models in the current period.

[0113] In the disclosed embodiment, the target spare parts stock quantity in the current cycle is obtained by accumulating the target spare parts stock quantity of multiple vehicle models in the current cycle, thereby improving the prediction accuracy of the target spare parts demand.

[0114] Figure 6 A flowchart of another example of a method for determining the inventory quantity of vehicle spare parts provided by an embodiment of the present disclosure is shown. Figure 6 As shown, in one embodiment, the method further includes:

[0115] S602, determining the stock quantity of the target spare parts within at least one cycle;

[0116] S604: Determine the total stock quantity of the target spare part in the entire life cycle according to the stock quantity of the target spare part in at least one cycle.

[0117] In one embodiment, the at least one period is at least one predicted period in the future, which refers to a period that has not yet occurred, such as the next 10 years.

[0118] In one embodiment, the stock quantity of target spare parts in at least one future cycle can be predicted separately. By accumulating the stock quantity of target spare parts in at least one future cycle, the total stock quantity of target spare parts in the entire life cycle can be obtained, thereby guiding vehicle manufacturers to stock the target spare parts, enabling merchants to make the most reasonable procurement plan and reduce inventory costs.

[0119] In order to deepen the understanding of the method for determining the inventory quantity of vehicle spare parts disclosed in the present invention, it is explained below with reference to specific examples.

[0120] Based on the data obtained from Table 1 and Table 2, the cumulative distribution function training process is as follows:

[0121] The average replacement of target spare parts is 1.5.

[0122] Initialize the Decay-Gamma distribution with initial parameter values ​​α=1.5, β=100, d=0.95.

[0123] Calculate the forecast value of spare parts inventory for each month. Taking June 2021 as an example, the vehicle inventory is 310, of which 30 are from April 2021, 60 are from May 2021, and 220 are from June 2021. The forecast value of spare parts inventory in June 2021 is E = (p'(1) × 30 + p'(2) × 60) × 1.5 = 1.352.

[0124] The historical sales data of the target spare parts in June 2021 is 2, then the loss function value MSE = (1.352-2) 2 =0.419.

[0125] The optimizer is selected to minimize the loss function value by adjusting the parameter values ​​of the Decay-Gamma distribution. For example, stochastic gradient descent is used to achieve the optimization effect by continuously adjusting the negative gradient of the forward parameter value, and the suboptimal parameters of the three parameters are obtained: α=1.28, β=102.53, d=0.985.

[0126] Based on the cumulative distribution function obtained through training, the ownership data of the target vehicle model, and the average replacement volume of the target spare parts, the inventory volume (i.e., predicted sales volume) of the target spare parts in the next ten years can be predicted, as shown in Table 3.

[0127] Table 3

[0128] Time (year dimension) Forecast sales 2024 928 2025 759 2026 605 2027 475 2028 369 ··· ··· 2034 31 2035 24

[0129] For a spare part of a certain car model, the corresponding model has been discontinued and the spare part will be discontinued in the near future, so the merchant needs to make sufficient purchases in stages to meet the demand for the spare part in the next ten years. A ten-year demand forecast for this spare part is required.

[0130] Table 4 shows the predicted sales volume of target spare parts obtained by the deep learning method DeepAR and the attenuated gamma distribution fitting method disclosed in the present invention.

[0131] Table 4

[0132]

[0133] It can be seen from Table 4 that when the traditional deep learning method is used, its prediction results in the recent period are close to the attenuated gamma distribution fitting method disclosed in this disclosure, which is relatively close to the actual results and has a fair accuracy. However, once the time period is extended, due to the characteristics of the model itself, in the absence of long-term actual data, its predicted value will tend to the mean and eventually stay at a constant that does not conform to the actual situation. If we purchase according to this prediction, the only result will be a large backlog of inventory, resulting in excessive inventory storage costs, and ultimately the cost of the inventory itself that cannot be sold will also need to be borne.

[0134] However, when the attenuated gamma distribution fitting method disclosed in the present invention is used, its long-term prediction value will converge, and its actual situation is consistent with basic cognition. Although there is no actual data in the future period to calculate the accuracy, it can be clearly seen that its predicted results are consistent with the trend of the spare parts sales life cycle. The prediction results disclosed in the present invention are used to guide automotive industry customers to make purchases, and a procurement strategy that is closer to the actual situation is adopted. The inventory is fully utilized, and the inventory cost of customers is reduced as much as possible while ensuring that the spare parts demand is met, and finally the cost reduction for merchants is achieved.

[0135] Based on the same inventive concept, the embodiments of the present disclosure also provide a vehicle spare parts inventory determination device and a vehicle spare parts inventory determination device, such as the following embodiments. Since the principle of solving the problem in the device embodiment is similar to that in the above method embodiment, the implementation of the device embodiment can refer to the implementation of the above method embodiment, and the repeated parts will not be repeated.

[0136] Figure 7 FIG. 2 is a schematic diagram of a vehicle spare parts inventory determination device provided by an embodiment of the present disclosure. Figure 7 As shown, the vehicle spare parts inventory determination device of this embodiment includes a data acquisition module 710, a first determination module 720, a second determination module 730 and a third determination module 740. Among them:

[0137] The data acquisition module 710 is used to acquire the ownership data of the target vehicle model, where the target vehicle model is a vehicle model using the target spare parts, and the ownership data includes the total sales volume of the target vehicle model in different periods;

[0138] The first determination module 720 is used to obtain the sales volume of the target model in the current period according to the ownership data of the target model;

[0139] The second determination module 730 is used to calculate the cumulative distribution function value of the target vehicle according to the current cycle and the cumulative distribution function;

[0140] The third determination module 740 is used to determine the stock quantity of the target spare parts in the current cycle according to the sales volume of the target vehicle model, the cumulative distribution function value and the average replacement quantity of the target spare parts in the current cycle.

[0141] It should be noted that the cumulative distribution function is obtained by training based on the historical sales data of the target spare parts, the ownership data of the target vehicle models and the average replacement volume of the target spare parts; the cumulative distribution function is the probability density function of the attenuated gamma distribution.

[0142] In one embodiment, the device also includes a model training module not shown in the accompanying drawings, and the model training module is used to train the cumulative distribution function in the following manner: initialize the parameter value of the cumulative distribution function to be trained; train the cumulative distribution function to be trained according to the ownership data of the target vehicle model and the average replacement quantity of the target spare parts to obtain the predicted inventory of the target spare parts within the target period; obtain the loss function value based on the historical sales data and the predicted inventory; adjust the parameter value of the cumulative distribution function to be trained to minimize the loss function value and obtain the cumulative distribution function.

[0143] In one embodiment, the model training module is used to obtain a target parameter set of the cumulative distribution function by using gradient descent fitting to minimize the loss function value.

[0144] In one embodiment, the third determination module 740 is used to determine the product of the sales volume of the target vehicle model, the cumulative distribution function value and the average replacement quantity of the target spare parts in the current cycle as the stock quantity of the target spare parts in the current cycle.

[0145] In one embodiment, the third determination module 740 is also used to determine the target spare parts inventory of each model in the current cycle when the target model includes multiple models; accumulate the target spare parts inventory of each model in the current cycle to obtain the target spare parts inventory in the current cycle.

[0146] In one embodiment, the third determination module 740 is further used to determine the stock quantity of the target spare part in at least one cycle; and determine the total stock quantity of the target spare part in the entire life cycle according to the stock quantity of the target spare part in at least one cycle.

[0147] In the embodiment of the present disclosure, the ownership data of the target vehicle model is obtained, the target vehicle model is a vehicle model using the target spare parts, and the ownership data includes the total sales volume of the target vehicle model in different periods; based on the ownership data of the target vehicle model, the sales volume of the target vehicle model in the current period is obtained; based on the current period and the cumulative distribution function, the cumulative distribution function value of the target vehicle is calculated; based on the sales volume of the target vehicle model in the current period, the cumulative distribution function value and the average replacement volume of the target spare parts, the stock volume of the target spare parts in the current period is determined. The present disclosure is more suitable for long-term prediction and is more in line with the application scenario of replacement of damaged vehicle spare parts, so that on the premise of effectively utilizing vehicle data, more accurate prediction of vehicle spare parts can be made, thereby reducing inventory and storage costs.

[0148] It will be appreciated by those skilled in the art that various aspects of the present invention may be implemented as a system, method or program product. Therefore, various aspects of the present invention may be specifically implemented in the following forms, namely: a complete hardware implementation, a complete software implementation (including firmware, microcode, etc.), or a combination of hardware and software, which may be collectively referred to herein as a "circuit", "module" or "system".

[0149] Refer to the following Figure 8 An electronic device 800 according to this embodiment of the present invention will be described. Figure 8 The electronic device 800 shown is only an example and should not bring any limitation to the functions and scope of use of the embodiments of the present invention.

[0150] like Figure 8 As shown, the electronic device 800 is in the form of a general computing device. The components of the electronic device 800 may include but are not limited to: at least one processing unit 810, at least one storage unit 820, and a bus 830 connecting different system components (including the storage unit 820 and the processing unit 810).

[0151] The storage unit stores program codes, which can be executed by the processing unit 810, so that the processing unit 810 performs the steps of various exemplary embodiments of the present invention described in the above “Exemplary Method” section of this specification. For example, the processing unit 810 can perform the following steps: Figure 2 As shown in , the ownership data of the target vehicle model is obtained, the target vehicle model is the vehicle model using the target spare parts, and the ownership data includes the total sales of the target vehicle model in different cycles; according to the ownership data of the target vehicle model, the sales volume of the target vehicle model in the current cycle is obtained; according to the current cycle and the cumulative distribution function, the cumulative distribution function value of the target vehicle is calculated; according to the sales volume of the target vehicle model in the current cycle, the cumulative distribution function value and the average replacement volume of the target spare parts, the stock quantity of the target spare parts in the current cycle is determined.

[0152] The storage unit 820 may include a readable medium in the form of a volatile storage unit, such as a random access memory unit (RAM) 8201 and / or a cache memory unit 8202 , and may further include a read-only memory unit (ROM) 8203 .

[0153] The storage unit 820 may also include a program / utility 8204 having a set (at least one) of program modules 8205, such program modules 8205 including but not limited to: an operating system, one or more application programs, other program modules and program data, each of which or some combination may include the implementation of a network environment.

[0154] Bus 830 may represent one or more of several types of bus structures, including a memory unit bus or memory unit controller, a peripheral bus, an accelerated graphics port, a processing unit, or a local bus using any of a variety of bus architectures.

[0155] The electronic device 800 may also communicate with one or more external devices 840 (e.g., keyboards, pointing devices, Bluetooth devices, etc.), one or more devices that enable a user to interact with the system, and / or any device that enables the electronic device 800 to communicate with one or more other computing devices (e.g., routers, modems, etc.). Such communication may be performed via an input / output (I / O) interface 850. Furthermore, the system may also communicate with one or more networks (e.g., a local area network (LAN), a wide area network (WAN), and / or a public network, such as the Internet) via a network adapter 860. Figure 8 As shown, the network adapter 860 communicates with other modules of the electronic device 800 via the bus 830. It should be understood that although Figure 8 Not shown, other hardware and / or software modules may be used in conjunction with electronic device 800, including but not limited to: microcode, device drivers, redundant processing units, external disk drive arrays, RAID systems, tape drives, and data backup storage systems.

[0156] Through the description of the above implementation, it is easy for those skilled in the art to understand that the example implementation described here can be implemented by software, or by software combined with necessary hardware. Therefore, the technical solution according to the implementation of the present disclosure can be embodied in the form of a software product, which can be stored in a non-volatile storage medium (which can be a CD-ROM, a USB flash drive, a mobile hard disk, etc.) or on a network, including several instructions to enable a computing device (which can be a personal computer, a server, a terminal device, or a network device, etc.) to execute the method according to the implementation of the present disclosure.

[0157] In an exemplary embodiment of the present disclosure, a computer-readable storage medium is also provided, which may be a readable signal medium or a readable storage medium. In an exemplary embodiment of the present disclosure, a computer program product is also provided, which includes a computer program or a computer instruction, and the computer program or the computer instruction is loaded and executed by a processor to enable the computer to implement the steps of the method disclosed in the above embodiment.

[0158] More specific examples of computer-readable storage media in the present disclosure may include, but are not limited to, an electrical connection having one or more conductors, a portable computer disk, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), optical fiber, a portable compact disk read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the foregoing.

[0159] In the present disclosure, a computer readable storage medium may include a data signal propagated in baseband or as part of a carrier wave, wherein a readable program code is carried. Such propagated data signals may take a variety of forms, including but not limited to electromagnetic signals, optical signals, or any suitable combination of the above. A readable signal medium may also be any readable medium other than a readable storage medium, which may send, propagate, or transmit a program for use by or in conjunction with an instruction execution system, apparatus, or device.

[0160] Alternatively, the program code contained on the computer-readable storage medium may be transmitted using any appropriate medium, including but not limited to wireless, wired, optical cable, RF, etc., or any suitable combination of the foregoing.

[0161] In a specific implementation, the program code for performing the operations of the present disclosure may be written in any combination of one or more programming languages, including object-oriented programming languages ​​such as Java, C++, etc., and conventional procedural programming languages ​​such as "C" or similar programming languages. The program code may be executed entirely on the user computing device, partially on the user device, as a separate software package, partially on the user computing device and partially on a remote computing device, or entirely on a remote computing device or server. In the case of a remote computing device, the remote computing device may be connected to the user computing device through any type of network, including a local area network (LAN) or a wide area network (WAN), or may be connected to an external computing device (e.g., using an Internet service provider to connect through the Internet).

[0162] It should be noted that, although several modules or units of the device for action execution are mentioned in the above detailed description, this division is not mandatory. In fact, according to the embodiments of the present disclosure, the features and functions of two or more modules or units described above can be embodied in one module or unit. On the contrary, the features and functions of one module or unit described above can be further divided into multiple modules or units to be embodied.

[0163] In addition, although the steps of the method in the present disclosure are described in a specific order in the drawings, this does not require or imply that the steps must be performed in this specific order, or that all the steps shown must be performed to achieve the desired results. Additionally or alternatively, some steps may be omitted, multiple steps may be combined into one step, and / or one step may be decomposed into multiple steps, etc.

[0164] Through the description of the above implementation, it is easy for those skilled in the art to understand that the example implementation described here can be implemented by software, or by software combined with necessary hardware. Therefore, the technical solution according to the implementation of the present disclosure can be embodied in the form of a software product, which can be stored in a non-volatile storage medium (which can be a CD-ROM, a USB flash drive, a mobile hard disk, etc.) or on a network, including several instructions to enable a computing device (which can be a personal computer, a server, a mobile terminal, or a network device, etc.) to execute the method according to the implementation of the present disclosure.

[0165] Those skilled in the art will readily appreciate other embodiments of the present disclosure after considering the specification and practicing the invention disclosed herein. The present disclosure is intended to cover any variations, uses or adaptations of the present disclosure, which follow the general principles of the present disclosure and include common knowledge or customary techniques in the art that are not disclosed in the present disclosure. The description and examples are intended to be exemplary only, and the true scope and spirit of the present disclosure are indicated by the appended claims.

Claims

1. A method for determining the stock quantity of vehicle spare parts, characterized in that: include: Acquire the ownership data of the target vehicle model, where the target vehicle model is a vehicle model using the target spare parts, and the ownership data includes the total sales volume of the target vehicle model in different periods; According to the ownership data of the target vehicle model, the sales volume of the target vehicle model in the current cycle is obtained; Calculating a cumulative distribution function value of the target vehicle according to the current cycle and the cumulative distribution function; The stock quantity of the target spare parts in the current cycle is determined according to the sales volume of the target vehicle model in the current cycle, the cumulative distribution function value and the average replacement quantity of the target spare parts.

2. The method for determining the vehicle spare parts inventory according to claim 1, characterized in that: The cumulative distribution function is obtained by training based on the historical sales data of the target spare part, the ownership data of the target vehicle model and the average replacement amount of the target spare part; The cumulative distribution function is a probability density function of a decaying gamma distribution.

3. The method for determining the vehicle spare parts inventory according to claim 2, characterized in that: The cumulative distribution function is trained in the following way: Initialize the parameter value of the cumulative distribution function to be trained; The cumulative distribution function to be trained is trained according to the ownership data of the target vehicle model and the average replacement quantity of the target spare parts to obtain the predicted stock quantity of the target spare parts within the target period; Obtaining a loss function value according to the historical sales data and the predicted inventory quantity; The parameter values ​​of the cumulative distribution function to be trained are adjusted to minimize the loss function value, thereby obtaining the cumulative distribution function.

4. The method for determining the vehicle spare parts inventory according to claim 3, characterized in that: The target parameter set of the cumulative distribution function is obtained by gradient descent fitting to minimize the loss function value.

5. The method for determining the vehicle spare parts inventory according to claim 1, characterized in that: Determining the stock quantity of the target spare parts in the current cycle according to the sales volume of the target vehicle model in the current cycle, the cumulative distribution function value, and the average replacement quantity of the target spare parts includes: The product of the sales volume of the target vehicle model in the current cycle, the cumulative distribution function value and the average replacement quantity of the target spare part is determined as the stock quantity of the target spare part in the current cycle.

6. The method for determining the vehicle spare parts inventory according to claim 5, characterized in that: When the target vehicle model includes multiple vehicle models, determining the stock quantity of the target spare parts in the current cycle includes: Determine the stock quantity of target spare parts for each vehicle model in the current cycle; The stock quantity of the target spare parts for each vehicle type in the current cycle is accumulated to obtain the stock quantity of the target spare parts in the current cycle.

7. The method for determining the vehicle spare parts inventory according to any one of claims 1 to 6, characterized in that: The method further comprises: Determining the stock quantity of the target spare part in at least one cycle; According to the stock quantity of the target spare part in the at least one cycle, the total stock quantity of the target spare part in the entire life cycle is determined.

8. A device for determining the stock quantity of vehicle spare parts, characterized in that: include: A data acquisition module, used to acquire the ownership data of a target vehicle model, wherein the target vehicle model is a vehicle model using a target spare part, and the ownership data includes the total sales volume of the target vehicle model in different periods; A first determination module is used to obtain the sales volume of the target model in the current period according to the ownership data of the target model; A second determination module is used to calculate a cumulative distribution function value of the target vehicle according to the current cycle and the cumulative distribution function; The third determination module is used to determine the stock quantity of the target spare parts in the current cycle according to the sales volume of the target vehicle model in the current cycle, the cumulative distribution function value and the average replacement quantity of the target spare parts.

9. An electronic device, characterized in that: include: processor; and a memory for storing executable instructions of the processor; wherein the processor is configured to execute the vehicle spare parts inventory determination method according to any one of claims 1 to 7 by executing the executable instructions.

10. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, the method for determining the vehicle spare parts inventory quantity according to any one of claims 1 to 7 is implemented.

11. A computer program product, characterized in that The computer program product includes a computer program or computer instructions, and the computer program or computer instructions are loaded and executed by a processor to enable a computer to implement the method for determining the vehicle spare parts inventory quantity according to any one of claims 1 to 7.

Images