Data processing method and device, electronic equipment, storage medium and product

Abstract

The embodiment of the invention discloses a data processing method and device, electronic equipment, a storage medium and a product, and the method comprises the steps: determining an effective spare part according to spare part receiving data within a preset time period; inputting the spare part attribute information of the at least one effective spare part into a pre-trained spare part prediction model to obtain predicted use information of the at least one effective spare part in the prediction time period; and for at least one effective spare part, performing inventory simulation processing on the predicted use information of the effective spare part through the supply chain simulation system, and determining a spare part acquisition plan corresponding to the effective spare part. According to the technical scheme, under the condition that the effective spare part prediction information is determined, the spare part prediction information is simulated based on the supply chain simulation system, and therefore the effect of obtaining plans corresponding to the effective spare parts is achieved.

Description

Technical Field

[0001] Embodiments of the present invention relate to the technical field of information processing, and in particular, to a data processing method, apparatus, electronic device, storage medium, and product. Background Art

[0002] In a large spare parts warehouse, different types of items can be stored. In order to reasonably manage and control the large spare parts warehouse, inventory management of spare parts is usually carried out.

[0003] Currently, the inventory management of large spare parts warehouses mainly includes: predicting the demand for spare parts through a machine learning prediction algorithm based on the historical usage data of spare parts, and replenishing the spare parts in the warehouse according to the prediction results.

[0004] When the inventors implemented the present technical solution based on the above method, they found the following problems:

[0005] However, the method of predicting the demand for spare parts using a simple machine learning prediction algorithm has the problem of low accuracy. Therefore, replenishing the spare parts inventory based on this may likely result in an incorrect spare parts procurement plan, leading to unreasonable spare parts procurement. Summary of the Invention

[0006] The present invention provides a data processing method, apparatus, electronic device, storage medium, and product, so as to simulate the spare parts prediction information based on a supply chain simulation system when determining effective spare parts prediction information, thereby achieving the effect of obtaining a plan corresponding to the effective spare parts.

[0007] In a first aspect, an embodiment of the present invention provides a data processing method, the method including:

[0008] Determining at least one effective spare part according to the spare part usage data within a preset time period;

[0009] Inputting the spare part attribute information of the at least one effective spare part into a pre-trained spare part prediction model to obtain the predicted usage information of the at least one effective spare part within a prediction time period;

[0010] For the at least one effective spare part, performing inventory simulation processing on the predicted usage information of the effective spare part through a supply chain simulation system to determine a spare part acquisition plan corresponding to the effective spare part, where the spare part acquisition plan at least includes the target inventory of the effective spare part and the warehousing information of the effective spare part under the target inventory.

[0011] Further, the method further includes:

[0012] Further, the determining at least one effective spare part according to the spare part usage data within a preset time period includes:

[0013] Determine the evaluation attributes of each item category in the spare part requisition data under the at least one pre-set evaluation dimension according to the spare part requisition data;

[0014] Determine the at least one effective spare part according to the evaluation attributes of each item category.

[0015] Further, the evaluation dimension includes a category relevance dimension and a usage dimension. The step of determining the evaluation attributes of each item category in the spare part requisition data under the at least one pre-set evaluation dimension includes:

[0016] Cluster the spare part requisition data of the same item category according to preset clustering conditions to obtain the to-be-used requisition data of the item category;

[0017] For the usage dimension, determine the first attribute corresponding to the usage dimension according to the normalized data corresponding to the to-be-used requisition data;

[0018] For the category relevance dimension, determine the second attribute of any two item categories according to the distribution accumulation function of any two item categories;

[0019] Determine the evaluation attributes of the item category according to the first attribute and the second attribute of the same item category.

[0020] Further, the step of determining the evaluation attributes of the item category according to the first attribute and the second attribute of the same item category includes:

[0021] Determine the first weight of the first attribute according to the first range to which the first attribute belongs; and determine the second weight of the second attribute according to the second range to which the second attribute belongs;

[0022] Determine the evaluation attributes of the item category according to the first attribute, the first weight, the second attribute, and the second weight.

[0023] Further, the supply chain simulation system includes: a warehousing structure building module, a multi-level warehouse network safety inventory optimization module, and an inventory simulation module;

[0024] Among them, the warehousing structure building module is used to construct warehousing topology information according to at least one warehousing area associated with the effective spare part, where the topology nodes in the warehousing topology information correspond to the warehousing areas, and the connection lines between the topology nodes correspond to the logistics information of two warehousing areas;

[0025] The multi-level warehouse network safety inventory optimization module is used to determine the inventory information of effective spare parts corresponding to the predicted usage information in at least one storage area according to the predicted usage information, warehouse topology information, and inventory cost control model;

[0026] The inventory simulation module is used to determine the target inventory and corresponding warehouse information according to the inventory information of the effective spare parts in at least one storage area, replenishment cycle, and custom processing cycle;

[0027] Wherein, the warehouse information is the inventory quantity stored in at least one storage area, and the sum of the at least one warehouse inventory quantity is the target inventory.

[0028] Further, the simulation processing of the predicted usage information of the effective spare parts is performed through the multi-level warehouse network safety inventory optimization module in the supply chain simulation system, including:

[0029] For the effective spare parts, according to the warehouse topology information, at least one transportation plan is determined, wherein the transportation plan includes each transportation node and the fulfillment time limit corresponding to two adjacent transportation nodes, and the transportation node corresponds to the storage area in the warehouse topology information;

[0030] According to the predicted usage information of the effective spare parts, the demand variance of the effective spare parts is determined, wherein the predicted usage information includes the spare part usage information within at least one usage cycle;

[0031] Based on the demand variance, current cycle service level, inventory cost corresponding to each storage area, and corresponding fulfillment time limit in the inventory cost control model, the inventory information of the effective spare parts in at least one storage area is determined.

[0032] Further, the inventory simulation processing of the predicted usage information of the effective spare parts is performed through the inventory simulation in the supply chain simulation system, including:

[0033] According to the inventory information, the theoretical demand quantity corresponding to the replenishment cycle, and the average demand quantity within the custom processing cycle, the highest replenishment information is determined;

[0034] According to the highest replenishment information, the predicted demand quantity corresponding to each usage cycle in the predicted usage information, the in-stock inventory, and the in-transit inventory, the target replenishment information is determined;

[0035] The target replenishment information is used as the target inventory of at least one storage area.

[0036] Further, after obtaining the spare part acquisition plan, the method further includes:

[0037] Perform multi - indicator verification on the target inventory;

[0038] The multi - indicator verification of the target inventory includes:

[0039] When the effective spare parts are the target inventory, determine the spare parts satisfaction rate index information based on the spare parts out - of - stock information within the target period;

[0040] Determine the cycle service level index information according to the number of cycles meeting the demand and the total number of cycles within the target period;

[0041] Determine the inventory turnover rate index information according to the total requisition data, demand quantity, and average inventory of the effective spare parts within the target period;

[0042] Determine the target acquisition plan according to the spare parts satisfaction rate index information, the cycle service level index information, the inventory turnover rate index information, and the expected information corresponding to the respective indicators;

[0043] Among them, the target acquisition plan is a plan in which the index information meets the expected information.

[0044] Furthermore, the method further includes:

[0045] In response to an event of adjusting the target content, perform code compilation on the target data corresponding to the target content based on a pre - created agent to obtain the target code corresponding to the target content, so as to process the corresponding data to be processed based on the updated target code.

[0046] Furthermore, the target content includes a spare parts prediction algorithm, and the data to be processed is spare parts attribute information; the target content includes any inventory control strategy in the supply chain simulation system, and the data to be processed is prediction usage information; the target content is the verification method corresponding to the verification index, and the data to be processed is the target inventory.

[0047] Furthermore, the method further includes: verifying the result of the target code; when the result verification meets the preset conditions, adjusting the target content based on the target code.

[0048] Furthermore, the method further includes: generating and displaying a target report based on the prediction usage information, the multi - indicator verification result, and the spare parts acquisition plan; where the spare parts requisition data at least includes at least one spare part and the usage information of each spare part, and the at least one effective spare part is the spare part among the at least one spare part.

[0049] In a second aspect, an embodiment of the present invention further provides a data processing device, and the device includes:

[0050] An effective spare part determination module, configured to determine at least one effective spare part according to the spare part requisition data within a preset time period;

[0051] A prediction information determination module, configured to input the spare part attribute information of the at least one effective spare part into a pre-trained spare part prediction model to obtain the predicted usage information of the at least one effective spare part within a prediction time period;

[0052] An inventory simulation module, configured to perform inventory simulation processing on the predicted usage information of the effective spare parts through a supply chain simulation system for the at least one effective spare part, and determine a spare part acquisition plan corresponding to the effective spare parts, where the spare part acquisition plan at least includes the target inventory of the effective spare parts and the warehousing information of the effective spare parts under the target inventory.

[0053] In a third aspect, an embodiment of the present invention provides a server, which includes:

[0054] One or more processors;

[0055] A memory, configured to store one or more programs;

[0056] When the one or more programs are executed by the one or more processors, the one or more processors implement the data processing method provided in any embodiment of the present invention.

[0057] In a fourth aspect, an embodiment of the present invention further provides a computer-readable storage medium, on which a computer program is stored, and when the program is executed by a processor, it implements the data processing method provided in any embodiment of the present invention.

[0058] In a fifth aspect, an embodiment of the present invention further provides a computer program product, including a computer program, characterized in that when the computer program is executed by a processor, it implements the data processing method according to any one of the embodiments of the present invention.

[0059] The technical solution of the embodiment of the present invention determines at least one effective spare part through the spare part requisition data within a preset time period. Furthermore, according to the spare part attribute information of the effective spare part and the pre-trained spare part prediction model, the predicted usage information of the effective spare part within the prediction time period is determined. Thus, the inventory simulation processing of the predicted usage information of the effective spare part can be carried out through the supply chain simulation system, and the spare part acquisition plan corresponding to the effective spare part is determined. In the technical solution provided in this embodiment, since the effective spare parts are obtained by screening a large number of spare parts through the spare part requisition data, the spare part attribute information of the effective spare parts has the characteristics of periodicity and trend. Therefore, the spare part prediction model predicts based on the spare part attribute information of the effective spare parts, and the predicted usage information of the effective spare parts obtained has higher accuracy and reliability. On this basis, the spare part prediction information is simulated based on the supply chain simulation system to obtain the acquisition plan corresponding to the effective spare part, improving the rationality of the spare part procurement plan. BRIEF DESCRIPTION OF THE DRAWINGS

[0060] In order to more clearly illustrate the technical solutions of the exemplary embodiments of the present invention, the drawings required for describing the embodiments will be briefly introduced below. Obviously, the introduced drawings are only the drawings of a part of the embodiments to be described in the present invention, rather than all the drawings. For those of ordinary skill in the art, other drawings can be obtained based on these drawings without creative efforts.

[0061] Figure 1 It is a schematic flowchart of a data processing method provided by an embodiment of the present invention;

[0062] Figure 2 It is a schematic diagram of the predicted usage information involved in an embodiment of the present invention;

[0063] Figure 3 It is a schematic diagram of the implementation process of determining the predicted usage information of effective spare parts according to the spare part prediction model involved in an embodiment of the present invention;

[0064] Figure 4 It is a schematic flowchart of another data processing method provided by an embodiment of the present invention;

[0065] Figure 5 It is a schematic diagram of the KS statistic matrix of all item categories involved in an embodiment of the present invention;

[0066] Figure 6 It is a comparison chart of the distribution cumulative functions of two item categories with a KS value < 0.3 involved in an embodiment of the present invention;

[0067] Figure 7 It is a schematic diagram of the implementation process of determining effective spare parts involved in an embodiment of the present invention;

[0068] Figure 8 Schematic diagram of the warehousing topology information involved in the embodiments of the present invention;

[0069] Figure 9 Schematic diagram of multiple transportation schemes involved in the embodiments of the present invention;

[0070] Figure 10 Flow schematic diagram of another data processing method provided by the embodiments of the present invention;

[0071] Figure 11 Implementation architecture schematic diagram of the data processing method provided by the embodiments of the present invention;

[0072] Figure 12 Flow schematic diagram of another data processing method provided by the embodiments of the present invention;

[0073] Figure 13 Implementation architecture schematic diagram of another data processing method provided by the embodiments of the present invention;

[0074] Figure 14 Schematic diagram of the implementation process of code update for the spare part prediction model involved in the embodiments of the present invention

[0075] Figure 15 Structure schematic diagram of a data processing device provided by the embodiments of the present invention;

[0076] Figure 16 Structure schematic diagram of an electronic device provided by the embodiments of the present invention. Detailed implementation manners

[0077] The present invention will be further described in detail below with reference to the accompanying drawings and embodiments. It can be understood that the specific embodiments described herein are only used to explain the present invention, rather than limiting the present invention. Additionally, it should be noted that for the sake of description, only parts related to the present invention are shown in the accompanying drawings rather than all structures.

[0078] Here, an overview of the concepts involved in this embodiment will be given first. A spare part refers to a module, component, and original part used to replace the original part, usually reserved for shortening the equipment repair downtime or for equipment maintenance and overhaul. Spare parts can be parts and components prepared for the more easily damaged parts in machines and instruments. In the process of maintenance and manufacturing, spare parts are items and spare parts prepared in advance and will be used in the near future.

[0079] Before introducing the technical solution, the application scenarios of the embodiments of the present invention can be described first. The technical solutions provided by the embodiments of the present invention can be applied to any scenario that requires spare part management. For example, for an auto repair company, during the process of vehicle repair services, multiple spare parts can be obtained in advance, and each spare part is a spare part. In this scenario, the method of the present invention can be used for spare part management to determine when and how much of a certain type of spare part needs to be purchased in a future time period. Another example is in the coal energy industry. For example, in the intelligent construction of coal mines, the spare parts of key equipment such as mining trucks, coal conveying systems, and ventilation systems, including engines, clutches, conveyor belts, and fans, are all spare parts. In this scenario, the method of the present invention can also be used for spare part management. Another example is in the power industry. All the spare parts that affect the normal operation of power equipment are spare parts, such as motor accessories including motor stators, motor rotors, stator windings, motor casings, end covers, motor fan blades, and bearings, as well as transformer accessories including transformer bushings, transformer moisture absorbers, transformer conducting rods, and transformer porcelain insulators. These spare parts need to be replaced immediately when the equipment is damaged to ensure the normal operation of the equipment. In this scenario, the method of the present invention can also be used for spare part management.

[0080] Figure 1 FIG. 4 is a schematic flowchart of a data processing method provided by an embodiment of the present invention. This embodiment is applicable to any situation that requires spare part management. This method can be executed by a data processing device, and the device can be implemented in the form of software and / or hardware. The hardware can be an electronic device, such as a mobile terminal, a PC, or a server, etc.

[0081] As Figure 1 shown, the data processing method includes:

[0082] S110. Determine at least one effective spare part according to the spare part requisition data within a preset time period.

[0083] Spare part requisition means that during the operation and maintenance of equipment, when the equipment fails or parts need to be replaced, the operator confirms the required spare part name, model, and quantity according to the demand and applies by filling out a spare part requisition form. After the application is approved, the operator goes to the spare part warehouse to pick up the spare parts, and returns the unused spare parts to the spare part warehouse after the equipment repair is completed or the use of the spare parts ends.

[0084] Among them, the preset time period is the preset time period length in the historical period. For example, the preset time period can be the time period of the first half of the year before the current time, the time period of the previous year before the current time, etc. The spare part requisition data is various records and statistical data regarding spare part requisition. The spare part requisition data includes at least one spare part and the corresponding spare part requisition information for each spare part. The spare part requisition information includes, but is not limited to, information such as the requisition frequency, requisition quantity, requisition time, requisition personnel, and department of the spare part.

[0085] Among them, an effective spare part is a spare part that requires attention for at least one spare part. Optionally, spare parts with higher usage frequencies and other conditions are used as effective spare parts. The spare part requisition data includes data on effective spare parts and ineffective spare parts. In order to improve the data processing effect or the fineness of data processing, the effective spare parts can be managed.

[0086] Specifically, at least one screening condition can be preset. For example, the preset screening conditions can include: the requisition frequency of a certain spare part within a preset time is less than or equal to a preset frequency threshold, the requisition quantity of a certain spare part within a preset time is less than or equal to a preset quantity threshold, the spare part model is a preset model, etc. Multidimensional screening is performed on the spare part requisition data within a preset time period according to the preset screening conditions, and the ineffective spare parts that do not meet the preset screening conditions are screened out to obtain one or more effective spare parts.

[0087] Exemplarily, the preset time period is one year, and the spare part requisition data involves the requisition information corresponding to 1000 spare parts. The requisition information of each spare part includes the requisition frequency of the spare part within one year, the daily requisition quantity, and other information. The spare part requisition data is screened and processed through the above preset screening conditions, and finally 450 ineffective spare parts are screened out, and the remaining 550 spare parts are effective spare parts.

[0088] S120. Input the spare part attribute information of at least one effective spare part into a pre-trained spare part prediction model to obtain the predicted usage information of at least one effective spare part within the prediction time period.

[0089] Among them, the spare part attribute information refers to various parameters and data that describe the characteristics of the spare part. The spare part attribute information includes the item category information of the effective spare part, the spare part requisition data, and the spare part inventory data. The item category information is used to characterize the category information to which a certain spare part belongs. For example, the item category information can include information such as the model, size, color, specifications, etc. of a certain effective spare part. The spare part inventory data refers to the beginning inventory quantity and the ending inventory quantity of a certain effective spare part in each warehouse over multiple time periods.

[0090] Among them, the spare part prediction model can be a pre-trained time series prediction model, which is used to process the spare part attribute information of the effective spare part and output the corresponding result. The output result can be the predicted usage information of the corresponding effective spare part. It should be particularly noted that time series prediction models with multiple different model structures can be pre-trained and integrated into a time series model library. In the specific application process, any time series prediction model can be selected from the time series model library.

[0091] In this embodiment, the predicted usage information refers to the usage information of a valid spare part in a future period. Optionally, the predicted usage information may be the predicted usage quantities corresponding to different usage cycles of the valid spare part within the predicted time period. Exemplarily, for the schematic diagram of the predicted usage information, see Figure 2 , such as Figure 2 shown. The predicted usage information of the valid spare part refers to the predicted usage quantities within each usage cycle (i.e., t0-t1, t1-t2, t2-t3, etc.) within the predicted time period T. For example, the predicted usage information of a certain valid spare part can be expressed as {t0-t1: predicted usage quantity x1; t1-t2: predicted usage quantity x2; t2-t3: predicted usage quantity x3;...}. It should be particularly noted that the predicted time period T and the time interval between adjacent usage cycles can be adjusted according to actual needs.

[0092] In practical applications, one or more spare part attribute information of valid spare parts can be used as input parameters of the spare part prediction model. The spare part prediction model can output the predicted usage quantities corresponding to different usage cycles of each valid spare part within the predicted time period, and these predicted usage quantities can be used as the predicted usage information. Exemplarily, for the schematic diagram of the implementation process of determining the predicted usage information of valid spare parts according to the spare part prediction model, see Figure 3 , the input parameters input to the spare part prediction model are: the spare part attribute information of valid spare part 1, valid spare part 2, valid spare part 3, etc. The output results of the spare part prediction model are: the predicted usage quantities of valid spare part 1, valid spare part 2, valid spare part 3,... and valid spare part n in the usage cycle of t0-t1, t1-t2, t2-t3,... within the predicted time period T.

[0093] S130. For at least one valid spare part, perform inventory simulation processing on the predicted usage information of the valid spare part through the supply chain simulation system to determine the spare part acquisition plan corresponding to the valid spare part.

[0094] Among them, the supply chain simulation system is a service system that uses program algorithms to simulate the operation process of spare parts in the supply chain. It better manages and plans the operation of the supply chain by simulating each link of the spare part supply chain. The spare part supply chain refers to the spare part logistics chain of multiple-level warehouses from the supplier's warehouse to the downstream service destination.

[0095] Among them, the spare part acquisition plan refers to a recommended plan for stocking spare parts of appropriate varieties and quantities at the right time and place to ensure the needs of equipment maintenance and repair, and to obtain the highest customer satisfaction with the lowest inventory investment. The spare part acquisition plan at least includes the target inventory of effective spare parts and the warehousing information of the effective spare parts under the target inventory. The target inventory refers to the inventory quantity of effective spare parts, and the warehousing information is used to characterize which warehouses the effective spare parts corresponding to the target inventory are located in.

[0096] It should be noted that the supply chain simulation system can perform inventory simulation processing on the predicted usage information of each effective spare part to obtain a spare part acquisition plan corresponding to each effective spare part. For the sake of clearly introducing this technical solution, one of the effective spare parts can be taken as an example for subsequent introduction. Correspondingly, the effective spare part currently being processed is regarded as the current effective spare part.

[0097] Specifically, the processing process of the supply chain simulation system for the current effective spare part may include: it is known which transit warehouses the current effective spare part needs to pass through in sequence from the supplier warehouse to the downstream service destination. Based on this, a topology map between these warehouses can be constructed; further, at least one warehousing distribution plan can be generated according to the predicted usage information of the current effective spare part and the topology map between the warehouses. Among them, each warehousing distribution plan includes: the total quantity of spare parts acquired corresponding to each usage cycle within the predicted time period (i.e., the target inventory) and the quantity of spare parts acquired at at least one transit warehouse (i.e., the warehousing information); thus, according to preset constraint conditions, such as safety inventory constraint conditions, minimum cost constraint conditions, etc., the target warehousing distribution plan can be screened from at least one warehousing distribution plan, and the target inventory and the corresponding warehousing information in this target warehousing distribution plan are determined as the spare part acquisition plan of the current effective spare part.

[0098] It should be noted that the acquisition, storage, use, processing, etc. of data in the technical solution of this application all comply with the relevant regulations of national laws and regulations. For example, intercept and process network requests with the authorization of the user.

[0099] The technical solution of the embodiment of the present invention determines at least one effective spare part through the spare part requisition data within a preset time period. Furthermore, according to the spare part attribute information of the effective spare part and the pre-trained spare part prediction model, the predicted usage information of the effective spare part within the prediction time period is determined. Thus, the inventory simulation processing can be performed on the predicted usage information of the effective spare part through the supply chain simulation system, and the spare part acquisition plan corresponding to the effective spare part can be determined. In the technical solution provided in this embodiment, since the effective spare parts are obtained by screening a large number of spare parts through the spare part requisition data, the spare part attribute information of the effective spare parts has the characteristics of periodicity and trend. Therefore, the spare part prediction model makes predictions based on the spare part attribute information of the effective spare parts, and the predicted usage information of the effective spare parts obtained has higher accuracy and reliability. On this basis, the spare part prediction information is simulated based on the supply chain simulation system to obtain the acquisition plan corresponding to the effective spare parts, which improves the rationality of the spare part procurement plan.

[0100] Figure 4 It is a schematic diagram of a data processing method provided by an embodiment of the present invention. On the basis of the foregoing embodiment, a detailed description is given of the specific implementation manner of determining at least one effective spare part according to the spare part requisition data within a preset time period. The specific implementation manner can refer to the technical solution of this embodiment. Among them, the same or corresponding technical terms as those in the above embodiment will not be described in detail here.

[0101] As Figure 4 shown, the method specifically includes the following steps:

[0102] S210. According to the spare part requisition data and at least one preset evaluation dimension, determine the evaluation attributes of each item category in the spare part requisition data under at least one evaluation dimension.

[0103] Among them, at least one evaluation dimension may include a category correlation dimension and a usage dimension. The category correlation dimension represents the dimension of the correlation between different spare parts in pairs. The usage dimension represents the dimension of the information related to the usage process of the spare parts. Each spare part corresponds to an item category.

[0104] In this embodiment, for each spare part, the first evaluation attribute of the spare part under the category correlation dimension and the second evaluation attribute of the spare part under the usage dimension can be determined according to the content corresponding to the spare part in the spare part requisition data.

[0105] Optionally, the specific implementation manner of determining the evaluation attributes of each item category in the spare part requisition data under at least one evaluation dimension according to the spare part requisition data and at least one preset evaluation dimension may include:

[0106] Cluster the spare part requisition data of the same item category according to the preset clustering conditions to obtain the to-be-used requisition data of the item category.

[0107] Among them, the preset clustering condition is a data clustering rule set in advance, which is used to determine how to cluster the spare part requisition data. The to-be-used requisition data is the data content for determining the evaluation attributes corresponding to a certain item category.

[0108] In this embodiment, the spare part requisition data obtained from the spare part requisition management department often includes discrete data at certain time points, and these data contents are not convenient to use directly. Therefore, it is necessary to first cluster the relevant data of the same item category in the spare part requisition data according to the preset clustering condition to obtain the corresponding to-be-used requisition data. Specifically, the preset clustering condition may include: aggregating the requisition frequency and / or requisition quantity of the same item category according to the preset unit time length. For example, the preset unit time length is 1 day. If the spare parts of a certain item category are requisitioned multiple times on the same day, the data volumes of the multiple requisition data can be superimposed, but the requisition frequency on that day is 1. On the basis of the above embodiment, if a certain item category is not requisitioned on a certain day, zero-filling processing can be performed on the spare part requisition data of that date. The specific processing process is as follows: after determining the start date and end date of the preset time length, there should be corresponding requisition data every day within this time period. If there is no data for a certain date in the original data indicating that the requisition is zero, then insert requisition data with a quantity of zero. Through this processing method, the consistency of the to-be-used requisition data for each item category is ensured.

[0109] For the usage dimension, based on the normalized data corresponding to the to-be-used requisition data, determine the first attribute corresponding to the usage dimension.

[0110] Among them, the usage dimension may include at least one of the usage frequency dimension, the usage quantity dimension, and the value dimension.

[0111] In this embodiment, the processing process for the to-be-used requisition data of each item category is the same. Here, any one of the item categories is used as the current item category, and the processing process of the to-be-used requisition data of the current item category is taken as an example for illustrative description.

[0112] For the frequency dimension, since multiple uses of the current item category on the same day are recorded as 1, the use frequency can be integrated in a superimposed form. The integrated use frequency is then normalized in order to scale the evaluation attribute values ​​of all item categories to a specified reasonable numerical range. Taking the maximum-minimum normalization method as an example, the principle of normalization is as follows: calculate the first frequency difference between the integrated use frequency of the current item category and the minimum use frequency of all item categories; calculate the second frequency difference between the maximum use frequency of all item categories and the minimum use frequency of all item categories; and use the ratio of the first frequency difference to the second frequency difference as the frequency evaluation attribute of the current item category.

[0113] For example, assuming there are 5 categories of items, and the integrated usage frequencies of the item categories are [100, 20, 10, 1, 1], then the frequency dimension evaluation attributes of each item category are [1, 0.19, 0.09, 0, 0] respectively.

[0114] For the usage quantity dimension, the daily collection quantity can be superimposed to obtain the integrated collection quantity, and then the integrated collection quantity can be normalized. The principle of normalization is as follows: calculate the first quantity difference between the integrated collection quantity of the current item category and the minimum collection quantity of all item categories; calculate the second quantity difference between the maximum collection quantity of all item categories and the minimum collection quantity of all item categories; and use the ratio of the first quantity difference to the second quantity difference as the quantity evaluation attribute of the current item category.

[0115] For the dimension of use value, on the basis of the integrated number of items used, the value of the current item category V = number of items used × unit price. The principle of normalizing the value data is as follows: calculate the first value difference between the integrated number of items used and the minimum number of items used across all item categories; calculate the second value difference between the maximum number of items used and the minimum number of items used across all item categories; and use the ratio of the first value difference to the second value difference as the value assessment attribute of the current item category.

[0116] In this embodiment, at least one of the frequency evaluation attribute, the frequency evaluation attribute, and the value evaluation attribute of the current item category may be used as the first attribute corresponding to the usage dimension.

[0117] For the category correlation dimension, the second attributes of any two item categories are determined based on the distribution accumulation function of any two item categories.

[0118] In this embodiment, the correlation of the distributions between any two item categories is evaluated by means of the Kolmogorov-Smirnov test (abbreviated as KS test). The cumulative distribution function corresponding to the item category can be determined according to the to-be-processed requisition data of the item category, and then the KS test is performed between two item categories according to the cumulative distribution function. The calculation method of the Kolmogorov-Smirnov statistic is as follows:

[0119] D n =|F 1 (x)-F 2 (x)|

[0120] where F 1 (x) and F 2 (x) are the cumulative distribution functions of two different item categories respectively.

[0121] In specific applications, two item categories with a KS statistic result less than 0.3 are taken as spare parts with similar requisition behaviors. Exemplarily, Figure 5 The schematic diagram of the KS statistic matrix of all item categories is shown. The matrix is presented in the form of a heat map (the redder the color, the greater the difference; conversely, the bluer the color, the smaller the difference. Less than 0.3 is reflected as being more blue). For the comparison diagram of the cumulative distribution functions of two item categories with a KS value < 0.3, see Figure 6 , as shown in Figure 6 (a) and Figure 6 (b). The cumulative distribution functions of "PVC tape_A000221_transparent" and "wire ear_A001798_SNBS1-4" are highly correlated. If the requisition behaviors of two item categories are similar, then the second attribute of these two item categories can be determined according to the KS statistic (i.e., D n ) of the two and the preset mapping relationship. For example, the larger the value of the KS statistic, the smaller the value of the second attribute of the two item categories; the smaller the value of the KS statistic, the larger the value of the second attribute of the two item categories.

[0122] Based on the first attribute and the second attribute of the same item category, the evaluation attribute of the item category is determined.

[0123] Specifically, the first evaluation value can be determined according to the first attribute and the corresponding weight, the second evaluation value can be determined according to the second attribute and the corresponding weight, and thus the evaluation attribute of the item category can be determined according to the first evaluation value and the second evaluation value.

[0124] Optionally, the specific implementation method for determining the evaluation attribute of an item category based on the first attribute and the second attribute of the same item category may include: determining the first weight of the first attribute according to the first range to which the first attribute belongs; and determining the second weight of the second attribute according to the second range to which the second attribute belongs; determining the evaluation attribute of the item category based on the first attribute, the first weight, the second attribute, and the second weight.

[0125] In this embodiment, since both the first attribute and the second attribute are normalized values, both of them are values between 0 and 1. Therefore, [0, 1] can be divided into multiple numerical ranges, and each numerical range corresponds to a different preset weight value. On this basis, the numerical range to which the first attribute belongs can be determined as the first range, and the preset weight value corresponding to the first range can be determined as the first weight; the numerical range to which the second attribute belongs can be determined as the second range, and the preset weight value corresponding to the second range can be determined as the second weight. Thus, based on the first weight and the second weight, a weighted sum processing is performed on the first attribute and the second attribute to obtain the evaluation attribute of the item category.

[0126] Exemplarily, [0, 1] can be divided into: the first numerical range [0, 0.25], corresponding to the preset weight W1; the second numerical range [0.25, 0.5], corresponding to the preset weight W2; the third numerical range [0.5, 0.75], corresponding to the preset weight W3; the fourth numerical range [0.75, 1], corresponding to the preset weight W4. If the first attribute is 0.19, then the first weight is W1, and if the second attribute is 0.67, then the first weight is W3. Based on this, the evaluation attribute S of the item category = W1×0.19 + W3×0.67. In this way, according to the numerical sizes of different evaluation dimensions, the corresponding weight values can be dynamically determined, making the determined evaluation attribute more objective and accurate.

[0127] S220. Determine at least one effective spare part according to the evaluation attribute of each item category.

[0128] In this embodiment, after obtaining the evaluation attribute of each item category, multiple item categories can be screened through the evaluation attribute. In this embodiment, screening the effective spare parts according to the multi-dimensional evaluation results improves the representativeness and objectivity of the effective spare parts.

[0129] Exemplarily, each evaluation attribute can be sorted in descending order, and the item categories ranked in the top preset positions can be determined as the target item categories, and the target item categories can be determined as the effective spare parts. It can also be that at least one effective spare part is determined according to the evaluation attributes of each item category and a preset attribute threshold. Among them, the preset attribute threshold can be calculated in advance through statistical analysis of data to obtain a reasonable value that can meet the business requirements. For example, the determination method of the preset attribute threshold target includes:

[0130] target = 0.8 * fscore 频率>50次 / 每年 + 0.4 * qscore 数量>客户认为数量"大”的阈值 + 0.8 * vscore 价值>客户认为价值"大”的阈值 + 0.5 * preset correlation threshold R

[0131] In addition, on the basis of determining the preset attribute threshold target, another schematic diagram of the implementation process for determining effective spare parts is shown in Figure 7 , the original data refers to the spare part requisition data within a preset time period. After the original data is preprocessed, the data to be used for requisition is obtained. Subsequently, the frequency evaluation attribute f-score, quantity evaluation attribute q-score, value evaluation attribute v-score, and distribution correlation R (i.e., the second evaluation attribute) of each item category are calculated according to the data to be used for requisition. The corresponding weight values are determined according to the numerical ranges to which each evaluation attribute belongs. Thus, according to the attribute values and the corresponding weight values, the corresponding evaluation attributes are determined; and then, according to the evaluation attributes and the preset attribute threshold target, effective spare parts are determined from multiple item categories.

[0132] S230. Input the spare part attribute information of at least one effective spare part into a pre-trained spare part prediction model to obtain the predicted usage information of at least one effective spare part within the prediction time period.

[0133] S240. For at least one effective spare part, perform inventory simulation processing on the predicted usage information of the effective spare part through a supply chain simulation system to determine a spare part acquisition plan corresponding to the effective spare part.

[0134] Among them, the spare part acquisition plan includes at least the target inventory of the effective spare part and the warehousing information of the effective spare part under the target inventory.

[0135] In the technical solution of the embodiment of the present invention, when determining effective spare parts, according to the spare part requisition data and at least one preset evaluation dimension, the evaluation attributes of each item category in the spare part requisition data under at least one evaluation dimension are determined. Thus, based on the evaluation attributes of each item category, at least one effective spare part is determined, and the effective spare parts are screened according to the multi-dimensional evaluation results, improving the representativeness and objectivity of the effective spare parts.

[0136] Based on the foregoing embodiments, the processing process of the supply chain simulation system can be further refined. For specific implementation manners, reference can be made to the detailed description of this embodiment. Technical terms that are the same as or corresponding to those in the above embodiments will not be elaborated herein. The method includes:

[0137] S310. Determine at least one effective spare part according to the spare part requisition data within a preset time period.

[0138] S320. Input the spare part attribute information of at least one effective spare part into a pre-trained spare part prediction model to obtain the predicted usage information of at least one effective spare part within a prediction time period.

[0139] S330. For at least one effective spare part, perform inventory simulation processing on the predicted usage information of the effective spare part through the supply chain simulation system to determine a spare part acquisition plan corresponding to the effective spare part.

[0140] Wherein, the spare part acquisition plan at least includes the target inventory of the effective spare part and the warehousing information of the effective spare part under the target inventory.

[0141] In this embodiment, the supply chain simulation system includes: a warehousing structure building module, a multi-level warehouse network safety inventory optimization module, and an inventory simulation module.

[0142] Specifically, the warehousing structure building module is used to construct warehousing topology information according to at least one warehousing area associated with the effective spare part.

[0143] Wherein, the warehousing area refers to a warehouse for storing and transferring spare parts. The topology nodes in the warehousing topology information correspond to the warehousing areas, and the connection lines between the topology nodes correspond to the logistics information between two warehousing areas.

[0144] In this embodiment, for any effective spare part, one or more warehousing areas associated with it are known, and the hierarchical relationship between multiple warehouses and the transportation duration between warehousing areas are also known. Based on this, each warehousing area can be used as a node. If there is a direct logistics relationship between two warehousing areas, a connection edge is generated between them, and the transportation duration between them is used as the attribute information of this connection edge, so that the warehousing topology information can be obtained.

[0145] Exemplarily, for a schematic diagram of the warehousing topology information, see Figure 8 , Figure 8 In, it is necessary to pass through three levels of warehousing areas in sequence from the supplier warehouse to the downstream service destination, namely the first warehouse, the second warehouse, and the third warehouse. The logistics duration between the supplier warehouse and the first warehouse is 4 weeks, the logistics duration between the first warehouse and the second warehouse is 3 weeks, and the logistics duration between the second warehouse and the third warehouse is 2 weeks.

[0146] The multi - level warehouse network safety inventory optimization module is used to determine the inventory information of effective spare parts corresponding to the predicted usage information in at least one warehousing area according to the predicted usage information, warehousing topology information, and inventory cost control model.

[0147] Among them, the inventory cost control model refers to a set of strategies, methods, and calculation formulas for managing inventory costs.

[0148] In this embodiment, the processing process of the multi - level warehouse network safety inventory optimization module for each effective spare part is the same. Here, any one of the effective spare parts is taken as the current effective spare part for illustration. According to the warehousing topology information of the current effective spare part, multiple transportation plans can be determined; and according to the spare part usage information of multiple usage cycles included in the predicted usage information of the current effective spare part, the demand variance corresponding to the current effective spare part can be obtained. Further, for each transportation plan, through numerical operations based on the demand variance and the inventory cost control model, an inventory cost index corresponding to each transportation plan can be obtained. Thus, the warehousing areas where the current effective spare parts involved in the transportation plan with the lowest inventory cost index should be placed and the inventory quantity of each warehousing area are used as the inventory information of the current effective spare part in at least one warehousing area.

[0149] Specifically, the specific implementation method of simulating the predicted usage information of effective spare parts through the multi - level warehouse network safety inventory optimization module in the supply chain simulation system may include:

[0150] For effective spare parts, according to the warehousing topology information, determine at least one transportation plan.

[0151] Among them, the transportation plan includes each transportation node and the fulfillment time limit corresponding to two adjacent transportation nodes, and the transportation node corresponds to the warehousing area in the warehousing topology information.

[0152] In this embodiment, since there are multiple logistics structures for the fixed warehouse location, multiple transportation plans can be determined according to the fixed warehousing topology structure. On the basis of the above example, for the schematic diagrams of multiple transportation plans, see Figure 9 , in the figure, the node with a white triangle inside a gray circle indicates that the warehousing area is included in the current transportation plan. There are 4 transportation plans in total in the figure. The first transportation plan is: {Supplier Warehouse --> First Warehouse --> Second Warehouse --> Third Warehouse --> Downstream Service Destination}, and the fulfillment time limit corresponding to each transportation node can be expressed as The second transportation plan is: {Supplier Warehouse --> Second Warehouse --> Third Warehouse --> Downstream Service Destination}, and the fulfillment time limit corresponding to each transportation node can be expressed as The third transportation plan is: {Supplier Warehouse --> First Warehouse --> Third Warehouse --> Downstream Service Destination}, and the fulfillment time limit corresponding to each transportation node can be expressed as The fourth transportation plan is: {Supplier Warehouse --> Third Warehouse --> Downstream Service Destination}, and the fulfillment time limit corresponding to each transportation node can be expressed as Specifically, when determining the fulfillment time limit corresponding to the last transportation node, the review period duration R (ReviewPeriod) needs to be added.

[0153] According to the predicted usage information of effective spare parts, determine the demand variance of effective spare parts.

[0154] Among them, the predicted usage information includes the spare part usage information within at least one usage cycle. Exemplarily, each usage cycle corresponds to Figure 2 t0 - t1, t1 - t2, t2 - t3... etc. in

[0155] In this embodiment, the predicted usage information includes the spare part usage information of multiple usage cycles. By performing a variance calculation on these spare part usage information, the demand variance corresponding to the current effective spare parts can be obtained.

[0156] Based on the demand variance, the current cycle service level, the inventory cost corresponding to each warehousing area, and the corresponding fulfillment time limit in the inventory cost control model, determine the inventory information of effective spare parts in at least one warehousing area.

[0157] Among them, the inventory cost control model can be expressed as: the inventory cost index C of the current transportation plan h is the total inventory cost of each warehousing area in the current transportation plan. The determination method of the inventory cost of each warehousing area is: the calculated value z of the current cycle service level α α = Φ -1 (α), the demand variance σ d the square root of the fulfillment time limit between the upper-level warehousing area i - 1 and the current warehousing area i of the current warehousing area and the product of the inventory cost of the current warehousing area i.

[0158] In this embodiment, for each transportation plan, the demand variance, the current cycle service level, the inventory cost corresponding to each storage area, and the corresponding fulfillment time limit can be substituted into the inventory cost control model for numerical operations to obtain the inventory cost index corresponding to each transportation plan. Then, the transportation plan corresponding to the lowest inventory cost index can be used as the target transportation plan, and the current effective spare parts involved in the target transportation plan and the inventory quantity of each storage area can be used as the inventory information of the current effective spare parts in at least one storage area.

[0159] An inventory simulation module, configured to determine the target inventory and the corresponding storage information according to the inventory information of the effective spare parts in at least one storage area, the replenishment cycle, and the custom processing cycle.

[0160] Among them, the storage information is the inventory quantity stored in at least one storage area, and the sum of the inventory quantities of at least one storage area is the target inventory. The replenishment cycle refers to the time interval between two replenishments. The custom processing cycle refers to the time interval of self-set processing or operations. Both the replenishment cycle and the custom processing cycle are parameter values that can be set by the user.

[0161] In this embodiment, according to the output result of the multi-level warehouse network safety inventory optimization module, it can be determined which storage areas the effective spare parts correspond to, that is, the storage information of the effective spare parts can be obtained. The replenishment cycle, the custom processing cycle, and the inventory information of the effective spare parts in at least one storage area can be used as the input parameters of the inventory simulation module to obtain the target replenishment information of each storage area in each usage cycle, so that the target replenishment information can be determined as the target inventory of at least one storage area.

[0162] Specifically, the specific implementation method of inventory simulation of the predicted usage information of effective spare parts through the inventory simulation in the supply chain simulation system may include:

[0163] Determine the highest replenishment information according to the inventory information, the theoretical demand quantity corresponding to the replenishment cycle, and the average demand quantity within the custom processing cycle.

[0164] Among them, the highest replenishment information refers to the upper limit of storing limited spare parts in the warehouse. When the inventory quantity reaches this limit, the replenishment will stop to avoid inventory backlog and cost increase.

[0165] In this embodiment, the average value μ of the spare parts demand under the custom time granularity can be preset according to historical experience d , so that the theoretical demand quantity d corresponding to the replenishment cycle R can be determined according to the average value μ of the spare parts demand d , the replenishment cycle, and the custom processing cycle R =μd *The average demand d within R and the custom processing period L L = μ d *L. Further, perform a summation operation on the total inventory information of the effective spare parts under at least one storage area, the theoretical demand corresponding to the replenishment cycle, and the average demand within the custom processing period to obtain the highest replenishment information.

[0166] Determine the target replenishment information based on the highest replenishment information, the predicted demand corresponding to each usage period in the predicted usage information, the on - hand inventory, and the in - transit inventory.

[0167] Among them, the target replenishment information refers to the replenishment quantity for each storage area. The on - hand inventory refers to the actual inventory goods stored in the warehouse. The in - transit inventory refers to the goods that have been shipped from the supplier or manufacturer but have not yet reached the destination (such as in the warehouse or in the hands of the customer), and these goods are in the process of transportation.

[0168] In this embodiment, the highest replenishment information, the predicted demand corresponding to each usage period in the predicted usage information, the on - hand inventory, and the in - transit inventory can be used as the input parameters of the replenishment quantity determination model to obtain the target replenishment information for each storage area in each usage period, so that the target replenishment information can be determined as the target inventory for at least one storage area.

[0169] Specifically, the replenishment quantity determination model is a set of a series of strategies, methods, and calculation formulas for determining the replenishment quantity. For example, the replenishment quantity determination model can be the (s, R) strategy, the (R, S) strategy, supply chain operations research, etc. Therefore, the analysis of the replenishment quantity calculation method in the simulation process will not be elaborated here. Only taking the commonly used method of the (R, S) strategy as an example of the replenishment quantity determination model, the replenishment quantity determination model can be expressed as: the target replenishment information Q t Is the difference between the highest replenishment information S and the on - hand inventory OH in the usage period t t The in - transit inventory IT in the usage period t t And the shortage quantity in the usage period t, where the shortage quantity in the usage period t is determined according to the predicted demand corresponding to the usage period t.

[0170] In this embodiment, through the warehouse structure building module, the multi - level warehouse network safety inventory optimization module, and the inventory simulation module in the supply chain simulation system, reasonable regulation and control of the spare parts inventory quantity and the spare parts storage warehouse can be achieved, avoiding excessive or insufficient inventory, so as to achieve the best utilization of warehouse resources and the minimization of the total inventory cost.

[0171] In the technical solution of the embodiment of the present invention, the supply chain simulation system includes: a warehousing structure building module, a multi-level warehouse network safety inventory optimization module, and an inventory simulation module; wherein, the warehousing structure building module is used to construct warehousing topology information according to at least one warehousing area associated with the effective spare parts, wherein the topology nodes in the warehousing topology information correspond to the warehousing areas, and the connection lines between the topology nodes correspond to the logistics information of two warehousing areas; the multi-level warehouse network safety inventory optimization module is used to determine the inventory information of the effective spare parts corresponding to the predicted usage information in the at least one warehousing area according to the predicted usage information, the warehousing topology information, and the inventory cost control model; the inventory simulation module is used to determine the target inventory and the corresponding warehousing information according to the inventory information of the effective spare parts in the at least one warehousing area, the replenishment cycle, and the custom processing cycle; wherein, the warehousing information is the inventory quantity stored in at least one warehousing area, and the sum of the at least one warehousing inventory quantities is the target inventory. In the technical solution provided in this embodiment, through the warehousing structure building module, the multi-level warehouse network safety inventory optimization module, and the inventory simulation module in the supply chain simulation system, reasonable regulation and control of the spare parts inventory quantity and the spare parts storage warehouse can be realized, avoiding excessive or insufficient inventory, so as to achieve the best utilization of warehouse resources and the minimization of the total inventory cost.

[0172] Figure 10 It is a schematic diagram of a data processing method provided by an embodiment of the present invention. On the basis of the foregoing embodiment, after obtaining the spare parts acquisition plan, multi-index verification can also be performed on the target inventory to obtain a multi-index verification result, and the specific implementation manner can refer to the technical solution of this embodiment. Wherein, the same or corresponding technical terms as those in the above embodiment will not be described in detail here.

[0173] As Figure 10 shown, the method specifically includes the following steps:

[0174] S410. Determine at least one effective spare part according to the spare part requisition data within a preset time period.

[0175] S420. Input the spare part attribute information of at least one effective spare part into a pre-trained spare part prediction model to obtain the predicted usage information of at least one effective spare part within the prediction time period.

[0176] S430. For at least one effective spare part, perform inventory simulation processing on the predicted usage information of the effective spare part through a supply chain simulation system to determine a spare part acquisition plan corresponding to the effective spare part.

[0177] Wherein, the spare part acquisition plan includes at least the target inventory of the effective spare part and the warehousing information of the effective spare part under the target inventory.

[0178] S440. Perform multi - index verification on the target inventory to obtain the multi - index verification results.

[0179] In this embodiment, it is possible to perform multi - index verification on the target inventory for fill rate, cycle service level, and inventory turnover rate, and obtain verification results under various indicators, so as to comprehensively evaluate and optimize the effect of spare - part inventory management, ensure the adequacy, timeliness, and economy of spare - part inventory, and ensure the smooth operation of the entire spare - part system and the improvement of customer satisfaction.

[0180] Optionally, the specific implementation method for performing multi - index verification on the target inventory may include:

[0181] When the effective spare parts are the target inventory, based on the spare - part out - of - stock information within the target period, determine the spare - part fill - rate index information.

[0182] Generally speaking, the spare - part fill rate is an important indicator to measure whether the spare - part inventory is sufficient. It is directly related to the maintenance efficiency of equipment, customer satisfaction, and operating costs. A high spare - part fill rate means that it is possible to respond more quickly to equipment failures, reduce downtime, and thus improve production efficiency. Therefore, the spare - part fill rate is one of the key indicators for evaluating the effect of inventory management.

[0183] In this embodiment, the determination method of the spare - part fill - rate index information β can be expressed as: 1 minus the ratio of the spare - part out - of - stock information to the replenishment quantity within the target period.

[0184] Based on the number of periods that meet the demand and the total number of periods within the target period, determine the cycle service - level index information.

[0185] The cycle service level reflects the ability of an organization to meet customer demand within a certain period. By monitoring the cycle service level, the organization can understand its own performance in meeting customer demand, and then adjust the inventory management strategy to improve customer satisfaction.

[0186] In this embodiment, the determination method of the cycle service - level index information α can be expressed as: the ratio of the number of periods that meet the demand within T periods (replenishment cycle or any custom - defined time period) to the total number of periods within T periods. For example, assuming the cycle is one month, and there are 2 months of out - of - stock situations in 12 months of a year, then the cycle service level is 2 / 12.

[0187] Based on the total usage data, demand quantity, and average inventory of effective spare parts within the target period, determine the inventory - turnover - rate index information.

[0188] Inventory turnover is an important indicator to measure the efficiency of inventory capital utilization. It reflects the flow rate and cash conversion ability of an organization's inventory materials. By improving inventory turnover, organizations can speed up capital turnover, reduce inventory costs, and thus improve overall operational efficiency. Inventory turnover is also important in spare parts inventory management. A reasonable inventory turnover rate can ensure the timely update and replenishment of spare parts inventory, avoiding obsolete or redundant spare parts occupying funds and resources.

[0189] In this embodiment, the inventory turnover rate indicator information τ can be determined as: the ratio of the total withdrawal and demand quantity in any time period T to the average inventory in the period T.

[0190] Determine the target acquisition plan based on the spare parts satisfaction rate indicator information, cycle service level indicator information, inventory turnover rate indicator information and the expected information corresponding to the corresponding indicators.

[0191] Among them, the target acquisition plan is a plan in which the indicator information meets the expected information.

[0192] In this embodiment, the expected information corresponding to each indicator can be obtained in advance, and the expected information is used to characterize the indicator level that the customer expects to achieve. For example, the expected information corresponding to the spare parts satisfaction rate indicator can be expressed as the satisfaction rate threshold A1, the expected information corresponding to the cycle service level indicator can be expressed as the cycle service level threshold A2, and the expected information corresponding to the inventory turnover rate indicator can be expressed as the inventory turnover rate threshold A3.

[0193] If the spare parts satisfaction rate index information, cycle service level index information, and inventory turnover rate index information corresponding to the spare parts acquisition plan all meet the expected information corresponding to the corresponding indicators, the spare parts acquisition plan can be determined as a target acquisition plan.

[0194] S460, generate and display a target report based on the predicted usage information, multi-indicator verification results, and spare parts acquisition plan.

[0195] The target report refers to a report file that summarizes various processing results obtained by the data processing method provided in this embodiment.

[0196] In this embodiment, the predicted usage information, multi-index verification results, and spare parts acquisition plan determined in the above steps can be summarized and a report file can be generated according to a preset report summary template. The report file is the target report. The target report can be displayed on any device with a display function. In this way, the user can clearly understand the inventory arrangement of various effective spare parts in the future time period.

[0197] For example, the implementation architecture diagram of the data processing method of this embodiment is shown in Figure 11, the architecture includes a spare part prediction algorithm package, a supply chain simulation system, an indicator management module, and a result management module. In the specific implementation process, according to the spare part requisition data within a preset time period, one or more effective spare parts can be screened out. Thus, the spare part attribute information of these effective spare parts can be processed according to the spare part prediction model in the spare part prediction algorithm package to obtain the predicted usage information of each effective spare part within the prediction time period. Furthermore, the predicted usage information of the effective spare parts can be input into the supply chain simulation system, and the supply chain simulation system performs inventory simulation processing on the predicted usage information of the effective spare parts to obtain the spare part acquisition plan corresponding to the effective spare parts. Further, the indicator management module can perform multi-indicator verification on the target inventory information in the spare part acquisition plan. In addition, the result management module can also generate report files such as an analysis report and a procurement plan according to the predicted usage information, multi-indicator verification results, and spare part acquisition plan generated in the above steps.

[0198] In the technical solution of the embodiment of the present invention, after obtaining the spare part acquisition plan, multi-indicator verification can also be performed on the target inventory. By performing multi-indicator verification on the satisfaction rate, cycle service level, and inventory turnover rate of the target inventory, verification results under multiple indicators can be obtained to comprehensively evaluate and optimize the effect of spare part inventory management, ensure the sufficiency, timeliness, and economy of spare part inventory, ensure the smooth operation of the entire spare part system, and improve customer satisfaction. In addition, a target report can also be generated and displayed based on the predicted usage information, multi-indicator verification results, and spare part acquisition plan, and users can clearly understand the inventory arrangements of various effective spare parts in the future time period.

[0199] Figure 12 It is a schematic diagram of a data processing method provided by an embodiment of the present invention. On the basis of the foregoing embodiment, target data corresponding to target content can also be compiled into code based on a pre-created intelligent agent to obtain target code corresponding to the target content, so as to process corresponding data to be processed based on the updated target code, and the target code can be verified. The specific implementation manner can refer to the technical solution of this embodiment. Technical terms that are the same or corresponding to the above embodiments will not be described in detail here.

[0200] As Figure 12 shown, the method specifically includes the following steps:

[0201] S510. Determine at least one effective spare part according to the spare part requisition data within a preset time period.

[0202] S520. Input the spare part attribute information of at least one effective spare part into a pre-trained spare part prediction model to obtain the predicted usage information of at least one effective spare part within the prediction time period.

[0203] S530. For at least one valid spare part, inventory simulation processing is performed on the predicted usage information of the valid spare part through a supply chain simulation system to determine a spare part acquisition plan corresponding to the valid spare part.

[0204] Among them, the spare part acquisition plan includes at least the target inventory of the valid spare part and the warehousing information of the valid spare part under the target inventory.

[0205] S540. In response to an event of adjusting target content, code compilation is performed on target data corresponding to the target content based on a pre-created agent to obtain target code corresponding to the target content, so as to process corresponding data to be processed based on the updated target code.

[0206] Among them, the event of adjusting target content refers to the event content of correcting or updating the target content. The data to be processed is the data content that needs to be processed by the target code. An agent can be understood as a module for generating program code that conforms to certain specifications and has certain functions. The target data is the data content corresponding to the target content. For example, the target data can be a piece of custom program code, a piece of descriptive text, etc. The target code refers to the program code compiled by the agent. The data to be processed is the data content that will be processed soon.

[0207] Optionally, the target content includes a spare part prediction algorithm, and the data to be processed is spare part attribute information; the target content includes any inventory control strategy in the supply chain simulation system, and the data to be processed is predicted usage information; the target content is the verification method corresponding to the verification index, and the data to be processed is the target inventory.

[0208] In this embodiment, the spare part prediction algorithm, the inventory control strategy in the supply chain simulation system, and the index verification method can all be updated. When it is necessary to update a certain target content, the user can trigger a preset control for updating the target content. At this time, the trigger operation can be responded to, the agent that has been designed and trained can be called, and the target data corresponding to the target content can be obtained. Thus, the agent can perform code compilation processing on the target data to obtain the target code. After obtaining the target code, the data to be processed corresponding to the target content can be processed according to the target code to obtain the corresponding processing result. In this embodiment, through the agent, the updated spare part prediction algorithm, inventory control strategy, and index verification method can be automatically converted into executable program code, reducing the algorithm update cost and being more easily customized and integrated according to the actual scenario.

[0209] Based on the above Figure 12 , refer to Figure 13 for the schematic diagram of the implementation architecture of the data processing method provided in this embodiment. The architecture also includes an agent module (Agent).

[0210] As shown Figure 13 When the user needs to update the algorithm model in the spare part prediction algorithm package, the target content is the spare part prediction algorithm, and the corresponding target data can be the custom code corresponding to the spare part prediction algorithm. The data to be processed is the spare part attribute information. When the user triggers the first preset control for updating the spare part prediction algorithm package, the intelligent agent can compile the custom code to obtain the target code, and thus can process the spare part attribute information according to the updated target code. When the user needs to update the inventory control strategy in the supply chain simulation system, the target content is the inventory control strategy, and the corresponding target data can be the custom code, description text, etc. corresponding to the inventory control strategy. The data to be processed is the prediction usage information. When the user triggers the second preset control for updating the inventory control strategy, the intelligent agent can compile the custom code, description text, etc. to obtain the target code, and thus can process the prediction usage information according to the updated target code. When the user needs to update the verification index in the index management module, the target content is the verification method corresponding to the verification index, and the corresponding target data can be the custom code, description text, etc. corresponding to the verification method. The data to be processed is the target inventory. When the user triggers the third preset control for updating the verification index, the intelligent agent can compile the custom code, description text, etc. to obtain the target code, and thus can process the target inventory according to the updated target code. In addition, the intelligent agent can also update the procurement plan template and analysis report template in the result management module.

[0211] S550. Verify the result of the target code, and when the result verification meets the preset conditions, adjust the target content based on the target code.

[0212] Among them, the preset condition is a rule set in advance for judging whether the processing result of the target code for the data to be processed is correct and reliable.

[0213] In this embodiment, in order to verify the correctness and reliability of the target code, based on the obtained target code, the target code can be verified. Specifically, if the code verification result is consistent with the expected result, it indicates that the target code is correct, and at this time, the target content can be adjusted according to the target code; if the code verification result is inconsistent with the expected result, it indicates that there is a problem with the target code. At this time, the intelligent agent needs to regenerate the target code corresponding to the target content and verify it until the generated target code meets the preset conditions, so as to ensure the correctness and reliability of the updated target content.

[0214] Next, a specific example is used to illustrate the agent execution process. The input parameter can be expressed as: "It is known that the formula for calculating the turnover rate is: Turnover Rate = (Total Issued Quantity D within Period T) / (Average Inventory Q within Period T), where D = sum(d_t) and Q = mean(q_t). d_t is the demand quantity at each time t within the period. q_t is the inventory quantity at each moment within the period. Then please rewrite this calculation method into Python code." The input parameter can be input into the agent, and the agent can compile target code that conforms to certain specifications by processing the input parameter. Further, the target code can be verified. The specific implementation process for verifying the target code can include: asking "Please determine whether {Generation} meets the format where the input parameter XXX is XXX and XXX is XXX? Is it consistent with the performance of the original code with input {input_test} and output {output_test}?" Here, Generation is the code generated above, and input_test and output_test are a test case that needs to be added to the custom algorithm module to verify whether the generated code can output the same output as the original code under the same input parameter. Finally, the generated target code will be automatically stored in the specified algorithm folder for the overall system to call.

[0215] For the case where the target content is the spare part prediction model, in this case, the schematic diagram of the implementation process for code updating of the spare part prediction model can be referred to Figure 14 , such as Figure 14 shown. The model files of the spare part prediction model that need to be newly added are divided into two categories: One category is that the model itself is developed according to the system requirements, and both the input and output conform to the system operation rules. This type of model can be directly used in the system. The other category is that the model is developed by a third party and is expected to be embedded in the system of the present invention. Then, code generation and verification need to be carried out by means of an agent. Only the model files that pass the verification will finally enter the model folder for the system to use.

[0216] The technical solution of the embodiment of the present invention can compile the target data corresponding to the target content into target code based on a pre-created agent, so as to process the corresponding data to be processed based on the updated target code. Through the agent, the updated spare part prediction algorithm, inventory control strategy, and index verification method can be automatically converted into executable program code, reducing the algorithm update cost and being more easily customized and adapted according to the actual scenario. And the target code can be verified to ensure the correctness and reliability of the updated target content.

[0217] The following is an embodiment of the data processing device provided by the embodiments of the present invention. This device and the data processing methods of the above embodiments belong to the same inventive concept. For the details not described in detail in the embodiment of the data processing device, reference may be made to the embodiments of the above data processing methods.

[0218] Figure 15 FIG. 4 is a schematic structural diagram of a data processing device provided by an embodiment of the present invention. The device specifically includes: a valid spare part determination module 610, a prediction information determination module 620, and an inventory simulation module 630.

[0219] Among them, the valid spare part determination module 610 is configured to determine at least one valid spare part according to the spare part requisition data within a preset time period.

[0220] The prediction information determination module 620 is configured to input the spare part attribute information of the at least one valid spare part into a pre-trained spare part prediction model to obtain the predicted usage information of the at least one valid spare part within a prediction time period.

[0221] The inventory simulation module 630 is configured to perform inventory simulation processing on the predicted usage information of the at least one valid spare part through a supply chain simulation system for the at least one valid spare part, and determine a spare part acquisition plan corresponding to the valid spare part. Wherein, the spare part acquisition plan at least includes the target inventory of the valid spare part and the warehousing information of the valid spare part under the target inventory.

[0222] The technical solution of the embodiment of the present invention determines at least one valid spare part according to the spare part requisition data within a preset time period. Furthermore, according to the spare part attribute information of the valid spare part and the pre-trained spare part prediction model, the predicted usage information of the valid spare part within the prediction time period is determined. Thus, inventory simulation processing can be performed on the predicted usage information of the valid spare part through a supply chain simulation system, and a spare part acquisition plan corresponding to the valid spare part is determined. In the technical solution provided by this embodiment, since the valid spare parts are obtained by screening a large number of spare parts through spare part requisition data, the spare part attribute information of the valid spare parts has the characteristics of periodicity and trend. Therefore, the spare part prediction model makes predictions based on the spare part attribute information of the valid spare parts, and the predicted usage information of the valid spare parts obtained has higher accuracy and reliability. On this basis, the spare part prediction information is simulated based on the supply chain simulation system to obtain an acquisition plan corresponding to the valid spare parts, improving the rationality of the spare part procurement plan.

[0223] Based on the above technical solution, the valid spare part determination module 610 includes:

[0224] An evaluation attribute determination unit for determining the evaluation attributes of each item category in the spare part requisition data under at least one preset evaluation dimension according to the spare part requisition data;

[0225] An effective spare part determination unit for determining the at least one effective spare part according to the evaluation attributes of each item category. The evaluation attribute determination unit

[0226] On the basis of the above technical solution, the evaluation dimension includes a category relevance dimension and a usage dimension. The evaluation attribute determination unit includes:

[0227] A to-be-used data determination unit for clustering the spare part requisition data of the same item category according to preset clustering conditions to obtain the to-be-used requisition data of the item category;

[0228] A first attribute determination subunit for determining the first attribute corresponding to the usage dimension according to the normalized data corresponding to the to-be-used requisition data for the usage dimension;

[0229] A second attribute determination subunit for determining the second attribute of any two item categories according to the distribution accumulation function of any two item categories for the category relevance dimension;

[0230] An evaluation attribute determination subunit for determining the evaluation attributes of the item category according to the first attribute and the second attribute of the same item category.

[0231] On the basis of the above technical solution, the evaluation attribute determination subunit is specifically configured to determine the first weight of the first attribute according to the first range to which the first attribute belongs; and determine the second weight of the second attribute according to the second range to which the second attribute belongs; determine the evaluation attributes of the item category according to the first attribute, the first weight, the second attribute, and the second weight.

[0232] On the basis of the above technical solution, the supply chain simulation system includes: a warehousing structure building module, a multi-level warehouse network safety inventory optimization module, and an inventory simulation module;

[0233] Among them, the warehousing structure building module is used to construct warehousing topology information according to at least one warehousing area associated with the effective spare parts, where the topology nodes in the warehousing topology information correspond to the warehousing areas, and the connection lines between the topology nodes correspond to the logistics information of two warehousing areas;

[0234] The multi-level warehouse network safety inventory optimization module is used to determine the inventory information of the effective spare parts corresponding to the predicted usage information in the at least one warehousing area according to the predicted usage information, the warehousing topology information, and the inventory cost control model;

[0235] The inventory simulation module is used to determine the target inventory and corresponding warehousing information according to the inventory information, replenishment cycle, and custom processing cycle of the effective spare parts under at least one warehousing area;

[0236] Wherein, the warehousing information is the inventory quantity stored in at least one warehousing area, and the sum of the at least one warehousing inventory quantities is the target inventory.

[0237] Based on the above technical solution, the inventory simulation module 630 includes:

[0238] The warehousing area determination unit is used to determine at least one transportation plan for the effective spare parts according to the warehousing topology information, wherein the transportation plan includes each transportation node and the fulfillment time limit corresponding to two adjacent transportation nodes, and the transportation node corresponds to the warehousing area in the warehousing topology information;

[0239] The demand variance determination unit is used to determine the demand variance of the effective spare parts according to the predicted usage information of the effective spare parts, wherein the predicted usage information includes the spare part usage information within at least one usage cycle;

[0240] The inventory information determination unit is used to determine the inventory information of the effective spare parts in at least one warehousing area based on the demand variance in the inventory cost control model, the current cycle service level demand variance determination unit, the inventory cost corresponding to each warehousing area, and the corresponding fulfillment time limit.

[0241] Based on the above technical solution, the inventory simulation module 630 further includes:

[0242] The highest replenishment information determination unit is used to determine the highest replenishment information according to the inventory information, the theoretical demand quantity corresponding to the replenishment cycle, and the average demand quantity within the custom processing cycle;

[0243] The target replenishment information determination unit is used to determine the target replenishment information according to the highest replenishment information, the predicted demand quantity corresponding to each usage cycle in the predicted usage information, the in-stock inventory, and the in-transit inventory;

[0244] The target inventory determination unit is used to use the target replenishment information as the target inventory of at least one warehousing area.

[0245] Based on the above technical solution, the data processing device further includes: an index verification module; the index verification module includes:

[0246] A satisfaction rate index determination unit, configured to determine spare part satisfaction rate index information according to spare part out-of-stock information within a target period when the effective spare parts are the target inventory;

[0247] A service level index determination unit, configured to determine cycle service level index information according to the number of cycles meeting demands and the total number of cycles within the target period;

[0248] An inventory turnover rate index determination unit, configured to determine inventory turnover rate index information according to the total requisition data, demand quantity, and average inventory of the effective spare parts within the target period;

[0249] An acquisition plan determination unit, configured to determine a target acquisition plan according to the spare part satisfaction rate index information, the cycle service level index information, the inventory turnover rate index information, and the expected information corresponding to the respective indexes; wherein, the target acquisition plan is a plan in which the index information meets the expected information.

[0250] Based on the above technical solution, the data processing device further includes: a content adjustment module;

[0251] An index verification module, configured to, in response to an event of adjusting a target content, perform code compilation on target data corresponding to the target content based on a pre-created agent to obtain target code corresponding to the target content, so as to process corresponding data to be processed based on the updated target code.

[0252] Based on the above technical solution, the target content includes a spare part prediction algorithm, and the data to be processed is spare part attribute information; the target content includes any inventory control strategy in a supply chain simulation system, and the data to be processed is prediction usage information; the target content is a verification method corresponding to a verification index, and the data to be processed is the target inventory.

[0253] Based on the above technical solution, the content adjustment module further includes: a code verification unit;

[0254] The code verification unit is configured to verify the result of the target code; when the result verification meets a preset condition, adjust the target content based on the target code.

[0255] Based on the above technical solution, the data processing device further includes: a target report generation module;

[0256] The target report generation module is configured to generate and display a target report based on the prediction usage information, multi-index verification results, and the spare part acquisition plan; wherein, the spare part requisition data includes at least one spare part and usage information of each spare part, and the at least one effective spare part is a spare part among the at least one spare part.

[0257] The data processing device provided by an embodiment of the present invention can execute the data processing method provided by any embodiment of the present invention, and has corresponding functional modules and beneficial effects for executing the data processing method.

[0258] It should be noted that in the above embodiment of the data processing device, the various units and modules included are only divided according to functional logic, but are not limited to the above division, as long as the corresponding functions can be realized; in addition, the specific names of the functional units are only for the convenience of mutual distinction and do not limit the protection scope of the present invention.

[0259] Figure 16 It is a schematic structural diagram of an electronic device provided by an embodiment of the present invention. Figure 16 It shows a block diagram of an exemplary electronic device 70 suitable for implementing the embodiment mode of the embodiment of the present invention. Figure 16 The shown electronic device 70 is only an example and should not bring any limitation to the functions and usage scope of the embodiment of the present invention.

[0260] As Figure 16 shown, the electronic device 70 is presented in the form of a general-purpose computing device. The components of the electronic device 70 may include but are not limited to: one or more processors or processing units 701, a system memory 702, and a bus 703 connecting different system components (including the system memory 702 and the processing unit 701).

[0261] The bus 703 represents one or more of several types of bus structures, including a memory bus or a memory controller, a peripheral bus, a graphics acceleration port, a processor, or a local bus using any bus structure in a variety of bus structures. For example, these architectures include but are not limited to Industry Standard Architecture (ISA) bus, Micro Channel Architecture (MAC) bus, Enhanced ISA bus, Video Electronics Standards Association (VESA) local bus, and Peripheral Component Interconnect (PCI) bus.

[0262] The electronic device 70 typically includes a variety of computer system readable media. These media can be any available media accessible by the electronic device 70, including volatile and non-volatile media, removable and non-removable media.

[0263] The system memory 702 may include computer system readable media in the form of volatile memory, such as random access memory (RAM) 704 and / or cache memory 705. The electronic device 70 may further include other removable / non-removable, volatile / non-volatile computer system storage media. By way of example only, the storage system 706 can be used for reading and writing non-removable, non-volatile magnetic media ( Figure 16not shown, and is typically referred to as a "hard disk drive"). Although Figure 16 not shown in Figure 16 , a disk drive for reading and writing to a removable non-volatile disk (such as a "floppy disk") and an optical disk drive for reading and writing to a removable non-volatile optical disk (such as a CD-ROM, DVD-ROM, or other optical medium) may be provided. In these cases, each drive may be connected to the bus 703 through one or more data medium interfaces. The memory 702 may include at least one program product having a set (such as at least one) of program modules configured to perform the functions of the embodiments of the present invention.

[0264] A program / utility 708 having a set (at least one) of program modules 707 may be stored, for example, in the memory 702. Such program modules 707 include, but are not limited to, an operating system, one or more application programs, other program modules, and program data. Each or some combination of these examples may include the implementation of a network environment. The program modules 707 generally perform the functions and / or methods in the embodiments described in the present invention.

[0265] The electronic device 70 may also communicate with one or more external devices 709 (such as a keyboard, a pointing device, a display 710, etc.), and may also communicate with one or more devices that enable a user to interact with the electronic device 70, and / or communicate with any device that enables the electronic device 70 to communicate with one or more other computing devices (such as a network card, a modem, etc.). Such communication may be through an input / output (I / O) interface 711. Also, the electronic device 70 may communicate with one or more networks (such as a local area network (LAN), a wide area network (WAN), and / or a public network, such as the Internet) through a network adapter 712. As shown in the figure, the network adapter 712 communicates with other modules of the electronic device 70 through the bus 703. It should be understood that although Figure 16 not shown in Figure 16 , other hardware and / or software modules may be used in conjunction with the electronic device 70, including but not limited to: microcode, device drivers, redundant processing units, external disk drive arrays, RAID systems, tape drives, and data backup storage systems, etc.

[0266] The processing unit 701 executes various functional applications and page processing by running programs stored in the system memory 702, such as implementing the data processing method provided by the embodiments of the present invention.

[0267] Embodiments of the present invention also provide a storage medium containing computer-executable instructions that, when executed by a computer processor, are used to execute a data processing method, the method including:

[0268] Determine at least one effective spare part according to the spare part requisition data within a preset duration;

[0269] Input the spare part attribute information of the at least one effective spare part into a pre-trained spare part prediction model to obtain the predicted usage information of the at least one effective spare part within a prediction time period;

[0270] For the at least one effective spare part, perform inventory simulation processing on the predicted usage information of the effective spare part through a supply chain simulation system to determine a spare part acquisition plan corresponding to the effective spare part, where the spare part acquisition plan at least includes the target inventory of the effective spare part and the warehousing information of the effective spare part under the target inventory.

[0271] The computer storage medium of the embodiments of the present invention may adopt any combination of one or more computer-readable media. The computer-readable media may be a computer-readable signal medium or a computer-readable storage medium. The computer-readable storage medium may be, for example, but not limited to, an electrical, magnetic, optical, electromagnetic, infrared, or semiconductor system, apparatus, or device, or any combination of the above. More specific examples (non-exhaustive list) of the computer-readable storage medium include: an electrical connection having one or more wires, 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), an 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 above. In this document, the computer-readable storage medium may be any tangible medium that contains or stores a program, and this program may be used by or in combination with an instruction execution system, apparatus, or device.

[0272] The computer-readable signal medium may include a data signal propagated in a baseband or as part of a carrier wave, which carries the computer-readable program code. Such a propagated data signal may take various forms, including but not limited to electromagnetic signals, optical signals, or any suitable combination of the above. The computer-readable signal medium may also be any computer-readable medium other than the computer-readable storage medium, and this computer-readable medium may send, propagate, or transmit a program for use by or in combination with an instruction execution system, apparatus, or device.

[0273] The program code contained on the computer-readable medium may be transmitted by any suitable medium, including but not limited to wireless, wire, optical cable, RF, etc., or any suitable combination of the above.

[0274] Computer program code for performing the operations of the embodiments of the present invention may be written in one or more programming languages or combinations thereof. The programming languages include object-oriented programming languages such as Java, Smalltalk, C++, and also include conventional procedural programming languages such as the "C" language or similar programming languages. The program code may be executed entirely on the user's computer, partially on the user's computer, executed as a stand-alone software package, partially on the user's computer and partially on a remote computer, or entirely on a remote computer or server. In the case of a remote computer, the remote computer may be connected to the user's computer through any type of network including a local area network (LAN) or a wide area network (WAN), or may be connected to an external computer (e.g., through the Internet using an Internet service provider).

[0275] Note that the above is only the preferred embodiment of the present invention and the technical principles applied. Those skilled in the art will understand that the present invention is not limited to the specific embodiments here. Various obvious changes, re-adjustments, and substitutions can be made by those skilled in the art without departing from the protection scope of the present invention. Therefore, although the present invention has been described in detail through the above embodiments, the present invention is not limited to the above embodiments. Without departing from the concept of the present invention, more other equivalent embodiments may be included, and the scope of the present invention is determined by the scope of the appended claims.

Claims

1. A data processing method, characterized in that: include: Determine at least one valid spare part based on spare parts requisition data within a preset period of time; Inputting the spare part attribute information of the at least one valid spare part into a pre-trained spare part prediction model to obtain predicted usage information of the at least one valid spare part within a predicted time period; For the at least one valid spare part, inventory simulation processing is performed on the predicted usage information of the valid spare part through the supply chain simulation system to determine a spare parts acquisition plan corresponding to the valid spare part, wherein the spare parts acquisition plan includes at least the target inventory of the valid spare part and the warehousing information of the valid spare part under the target inventory.

2. The method according to claim 1, characterized in that The step of determining at least one valid spare part according to the spare parts use data within a preset period of time includes: Determine, according to the spare parts requisition data and at least one pre-set evaluation dimension, an evaluation attribute of each item category in the spare parts requisition data under the at least one evaluation dimension; The at least one valid spare part is determined according to the evaluation attributes of each item category.

3. The method according to claim 2, characterized in that The evaluation dimension includes a category relevance dimension and a usage dimension, and determining the evaluation attribute of each item category in the spare parts requisition data under the at least one evaluation dimension according to the spare parts requisition data and at least one pre-set evaluation dimension includes: Clustering the spare parts requisition data of the same item category according to preset clustering conditions to obtain the requisition data to be used of the item category; For the usage dimension, determining a first attribute corresponding to the usage dimension according to the normalized data corresponding to the to-be-used collection data; For the category correlation dimension, determining the second attributes of any two item categories according to the distribution accumulation function of any two item categories; An evaluation attribute of the item category is determined based on a first attribute and a second attribute of the same item category.

4. The method according to claim 3, characterized in that Determining the evaluation attribute of the item category based on the first attribute and the second attribute of the same item category includes: Determine a first weight of the first attribute according to a first range to which the first attribute belongs; and determine a second weight of the second attribute according to a second range to which the second attribute belongs; An evaluation attribute of the item category is determined based on the first attribute, the first weight, the second attribute and the second weight.

5. The method according to claim 1, characterized in that The supply chain simulation system includes: a warehouse structure building module, a multi-level warehouse network safety inventory optimization module and an inventory simulation module; The storage structure building module is used to build storage topology information according to at least one storage area associated with the valid spare parts, wherein the topological nodes in the storage topology information correspond to storage areas, and the lines between the topological nodes correspond to the logistics information of the two storage areas; A multi-level warehouse network safety inventory optimization module, used to determine the inventory information of the valid spare parts corresponding to the predicted usage information in the at least one storage area according to the predicted usage information, the storage topology information and the inventory cost control model; The inventory simulation module is used to determine the target inventory and corresponding storage information according to the inventory information, replenishment cycle and custom processing cycle of the effective spare parts in the at least one storage area; The storage information is the inventory stored in at least one storage area, and the sum of the at least one storage inventory is the target inventory.

6. The method according to claim 5, characterized in that The predicted usage information of the effective spare parts is simulated by the multi-level warehouse network safety inventory optimization module in the supply chain simulation system, including: For the valid spare parts, at least one transportation plan is determined according to the storage topology information, wherein the transportation plan includes the performance time corresponding to each transportation node and two adjacent transportation nodes, and the transportation node corresponds to the storage area in the storage topology information; Determining the demand variance of the effective spare parts according to the predicted usage information of the effective spare parts, wherein the predicted usage information includes spare parts usage information within at least one usage cycle; Based on the demand variance, the current cycle service level, the inventory cost corresponding to each storage area and the corresponding fulfillment time in the inventory cost control model, the inventory information of the effective spare parts in the at least one storage area is determined.

7. The method according to claim 5, characterized in that The inventory simulation module in the supply chain simulation system performs inventory simulation processing on the forecast usage information of the effective spare parts, including: Determine the maximum replenishment information according to the inventory information, the theoretical demand corresponding to the replenishment cycle, and the average demand in the custom processing cycle; Determine target replenishment information according to the maximum replenishment information, the predicted demand corresponding to each usage cycle in the predicted usage information, the inventory in stock, and the inventory in transit; The target replenishment information is used as the target inventory of the at least one storage area.

8. The method according to claim 1, characterized in that After obtaining the spare parts acquisition plan, the method further includes: Performing multi-index verification on the target inventory; The multi-index verification of the target inventory includes: In the case where the effective spare parts are the target inventory, determining spare parts satisfaction rate index information according to spare parts shortage information within the target period; Determine cycle service level indicator information according to the number of cycles that meet the demand and the total number of cycles within the target cycle; Determine the inventory turnover rate indicator information according to the total requisition data, demand quantity and average inventory of the effective spare parts within the target period; A target acquisition plan is determined based on the spare parts satisfaction rate index information, the cycle service level index information, the inventory turnover rate index information and the expected information corresponding to the corresponding indicators; wherein the target acquisition plan is a plan in which the index information meets the expected information.

9. The method according to claim 1, characterized in that: The method further comprises: In response to an event of adjusting the target content, the target data corresponding to the target content is compiled based on a pre-created intelligent agent to obtain a target code corresponding to the target content, so as to process the corresponding data to be processed based on the updated target code.

10. The method according to claim 9, characterized in that The target content includes a spare parts prediction algorithm, and the data to be processed is spare parts attribute information; the target content includes any inventory control strategy in a supply chain simulation system, and the data to be processed is predicted usage information; the target content is a verification method corresponding to a verification indicator, and the data to be processed is a target inventory.

11. The method according to claim 9, characterized in that The method further comprises: Performing result verification on the target code; When the result verification satisfies a preset condition, the target content is adjusted based on the target code.

12. The method according to claim 1, characterized in that The method further comprises: A target report is generated and displayed based on the predicted usage information, the multi-indicator verification results and the spare parts acquisition plan.

13. A data processing device, characterized in that: include: An effective spare parts determination module, used to determine at least one effective spare part according to spare parts requisition data within a preset period of time; A prediction information determination module, used to input the spare part attribute information of the at least one valid spare part into a pre-trained spare part prediction model to obtain predicted usage information of the at least one valid spare part within a prediction time period; An inventory simulation module is used to perform inventory simulation processing on the predicted usage information of the at least one valid spare part through a supply chain simulation system, and determine a spare parts acquisition plan corresponding to the valid spare part, wherein the spare parts acquisition plan includes at least a target inventory of the valid spare part and the warehousing information of the valid spare part under the target inventory.

14. A server, characterized in that: The server includes: one or more processors; A memory for storing one or more programs; When the one or more programs are executed by the one or more processors, the one or more processors implement the data processing method according to any one of claims 1 to 12.

15. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the program is executed by a processor, the data processing method according to any one of claims 1 to 12 is implemented.

16. A computer program product comprising a computer program, characterized in that When the computer program is executed by a processor, the computer program implements the data processing method according to any one of claims 1 to 12.

Images