Prediction method, device and equipment for replenishment quantity of office supplies, storage medium and program product

Abstract

The invention relates to the technical field of automatic management of office supplies, and provides a method, a device and equipment for predicting the replenishment amount of office supplies, a storage medium and a program product, which can automatically predict the replenishment amount of the office supplies. During the current prediction, obtaining an office supply receiving quantity sequence based on the current prediction moment and a plurality of office supply receiving quantity prediction models; the network architectures of the plurality of office supply receiving quantity prediction models are different; respectively inputting the office supply receiving quantity sequence into a plurality of office supply receiving quantity prediction models to obtain a plurality of current replenishment quantity prediction results; obtaining a weight corresponding to each current replenishment quantity prediction result according to the prediction accuracy of the office supply receiving quantity prediction model; the higher the accuracy is, the larger the weight is; and according to the weight, performing weighted summation on the plurality of current replenishment quantity prediction results to obtain the current replenishment quantity of the office supplies.

Description

Technical Field

[0001] The present application relates to the technical field of automated management of office supplies, and in particular to a method, device, computer equipment, storage medium and computer program product for predicting the replenishment quantity of office supplies. Background Art

[0002] Office supplies include printed materials, stationery, etc. used by employees in the office process. In order to ensure that employees can use office supplies normally, it is necessary to purchase office supplies in advance.

[0003] When purchasing office supplies, people generally rely on manual research and forecasting to formulate purchasing plans. This method is not only time-consuming and labor-intensive, but also easily affected by subjective factors, resulting in a disconnect between purchasing needs and actual conditions. Summary of the invention

[0004] Based on this, it is necessary to provide a method, device, computer equipment, storage medium and computer program product for predicting the replenishment quantity of office supplies in response to the above technical problems.

[0005] The present application provides a method for predicting the replenishment quantity of office supplies, the method comprising:

[0006] In the current prediction, the office supplies collection quantity sequence based on the current prediction moment and multiple office supplies collection quantity prediction models are obtained; the network architectures of the multiple office supplies collection quantity prediction models are different;

[0007] Inputting the office supply collection quantity sequence into multiple office supply collection quantity prediction models respectively to obtain multiple current replenishment quantity prediction results;

[0008] According to the prediction accuracy of the office supplies collection quantity prediction model, a weight corresponding to each current replenishment quantity prediction result is obtained; the higher the accuracy, the greater the weight;

[0009] According to the weights, a weighted sum is performed on multiple current replenishment quantity prediction results to obtain the current replenishment quantity of office supplies.

[0010] In one embodiment, the method further comprises:

[0011] Obtaining a first sub-prediction accuracy of the office supply collection quantity prediction model according to whether the historical replenishment quantity prediction result corresponding to the office supply collection quantity prediction model meets the office supply collection situation;

[0012] Obtaining a second sub-prediction accuracy of the office supplies collection quantity prediction model according to the parameter quantity included in the office supplies collection quantity prediction model;

[0013] The prediction accuracy of the office supplies collection quantity prediction model is obtained according to the first sub-prediction accuracy and the second sub-prediction accuracy.

[0014] In one embodiment, the prediction accuracy of the office supplies collection quantity prediction model is obtained according to the first sub-prediction accuracy and the second sub-prediction accuracy, including:

[0015] If the historical replenishment quantity prediction result corresponding to the office supplies collection quantity prediction model satisfies the office supplies collection situation, then the larger weight is determined as the first weight among the two weights;

[0016] If the parameter amount included in the office supply collection amount prediction model is a high parameter amount among the parameter amounts included in the plurality of office supply collection amount prediction models, then a large weight is determined as the second weight among the two weights;

[0017] The first sub-prediction accuracy is assigned to the first weight and the second sub-prediction accuracy is assigned to the second weight, and the first sub-prediction accuracy and the second sub-prediction accuracy are weighted summed to obtain the prediction accuracy of the office supplies collection quantity prediction model.

[0018] In one embodiment, the method further comprises:

[0019] Sorting the parameter quantities included in multiple office supplies collection quantity prediction models;

[0020] If the parameters are sorted from large to small, and the parameter quantity included in the office supplies collection quantity prediction model is ranked first, it is determined that the parameter quantity included in the office supplies collection quantity prediction model belongs to a high parameter quantity;

[0021] If the sorting is performed from small to large, and the parameter quantity included in the office supply collection quantity prediction model is sorted at the end, it is determined that the parameter quantity included in the office supply collection quantity prediction model belongs to the high parameter quantity.

[0022] In one embodiment, according to the prediction accuracy of the office supplies collection quantity prediction model, the weight corresponding to each current replenishment quantity prediction result is obtained, including:

[0023] Get the positive correlation function;

[0024] Inputting the prediction accuracy of the office supplies collection quantity prediction model into the positive correlation function to obtain an output result of the positive correlation function;

[0025] The output result of the positive correlation function is determined as the weight corresponding to the current replenishment quantity prediction result.

[0026] In one embodiment, the plurality of office supply collection quantity prediction models include a linear regression model, a decision tree model, and a neural network model.

[0027] The present application provides a device for predicting the replenishment quantity of office supplies, the device comprising:

[0028] The data and model acquisition module is used to obtain the office supply collection quantity sequence based on the current prediction time and multiple office supply collection quantity prediction models during the current prediction; the network architectures of the multiple office supply collection quantity prediction models are different;

[0029] A model prediction module, used to input the office supply collection quantity sequence into multiple office supply collection quantity prediction models respectively to obtain multiple current replenishment quantity prediction results;

[0030] A weight determination module, used to obtain a weight corresponding to each current replenishment quantity prediction result according to the prediction accuracy of the office supplies collection quantity prediction model; the higher the accuracy, the greater the weight;

[0031] The replenishment quantity determination module is used to perform weighted summation on multiple current replenishment quantity prediction results according to the weights to obtain the current replenishment quantity of office supplies.

[0032] The present application provides a computer device, including a memory and a processor, wherein the memory stores a computer program, and the processor executes the above method.

[0033] The present application provides a computer-readable storage medium having a computer program stored thereon, wherein the computer program is executed by a processor to execute the above method.

[0034] The present application provides a computer program product, on which a computer program is stored, and the computer program is executed by a processor to perform the above method.

[0035] The above-mentioned office supply replenishment quantity prediction method, device, computer equipment, storage medium and computer program product, when predicting the current time, obtains the office supply collection quantity sequence based on the current prediction moment and multiple office supply collection quantity prediction models; the network architectures of the multiple office supply collection quantity prediction models are different; the office supply collection quantity sequence is input into the multiple office supply collection quantity prediction models respectively to obtain multiple current replenishment quantity prediction results; according to the prediction accuracy of the office supply collection quantity prediction model, the weight corresponding to each current replenishment quantity prediction result is obtained; the higher the accuracy, the greater the weight; according to the weight, the weighted sum of the multiple current replenishment quantity prediction results is performed to obtain the current replenishment quantity of the office supplies. The scheme provided in the present application can automatically predict the replenishment quantity of office supplies without manual research and manual prediction, and makes predictions with the help of multiple office supply collection quantity prediction models with different network architectures. The higher the accuracy of the office supply collection quantity prediction model, the greater the weight corresponding to the corresponding current replenishment quantity prediction result, thereby improving the prediction accuracy of the office supply replenishment quantity. BRIEF DESCRIPTION OF THE DRAWINGS

[0036] In order to more clearly illustrate the technical solutions in the embodiments of the present application or the related technologies, the drawings required for use in the embodiments or the related technical descriptions are briefly introduced below. Obviously, the drawings described below are only some embodiments of the present application. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying creative work.

[0037] Figure 1 It is a flowchart of a method for predicting the replenishment quantity of office supplies in one embodiment;

[0038] Figure 2 It is a schematic diagram of the structure of multiple modules in one embodiment;

[0039] Figure 3 A normal distribution curve diagram related to the predicted value of replenishment quantity and safety stock in one embodiment;

[0040] Figure 4 It is a structural block diagram of a device for predicting the replenishment quantity of office supplies in one embodiment;

[0041] Figure 5 FIG. 4 is a diagram showing the internal structure of a computer device in one embodiment. DETAILED DESCRIPTION

[0042] In order to make the purpose, technical solution and advantages of the present application more clearly understood, the present application is further described in detail below in conjunction with the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are only used to explain the present application and are not used to limit the present application.

[0043] The office supplies replenishment quantity prediction method provided in the present application can be executed by a computer device, including: Figure 1 Steps shown.

[0044] Step S101, during the current prediction, obtain an office supply collection quantity sequence based on the current prediction moment and a plurality of office supply collection quantity prediction models.

[0045] For example, the current prediction time is April 10, and the daily office supply collection quantity in the past period since April 10 can be obtained, such as the daily office supply collection quantity in the past three months since April 10, thereby forming an office supply collection quantity sequence.

[0046] There are differences in the network architectures of multiple office supplies collection quantity prediction models.

[0047] Step S102: input the office supply collection quantity sequence into a plurality of office supply collection quantity prediction models respectively to obtain a plurality of current replenishment quantity prediction results.

[0048] Exemplarily, the office supply collection quantity sequence can be input into office supply collection quantity prediction model A to obtain the result output by office supply collection quantity prediction model A, which is the office supply collection prediction value; the current inventory of office supplies is subtracted from the office supply collection prediction value, and the result is added to the safety inventory, and the result is the current replenishment quantity prediction result; since the current replenishment quantity prediction result is obtained with the help of the office supply collection prediction value output by office supply collection quantity prediction model A, the current replenishment quantity prediction result corresponds to office supply collection quantity prediction model A.

[0049] Similarly, the office supplies collection quantity sequence can be input into the office supplies collection quantity prediction model B to obtain the result output by the office supplies collection quantity prediction model B, which is the office supplies collection prediction value; the current inventory of office supplies minus the office supplies collection prediction value, and then adding the safety inventory, the result obtained is the current replenishment quantity prediction result; since the current replenishment quantity prediction result is obtained with the help of the office supplies collection prediction value output by the office supplies collection quantity prediction model B, the current replenishment quantity prediction result corresponds to the office supplies collection prediction model B.

[0050] Step S103, according to the prediction accuracy of the office supplies collection quantity prediction model, obtain the weight corresponding to each current replenishment quantity prediction result; the higher the accuracy, the greater the weight.

[0051] Exemplarily, after obtaining the current replenishment quantity prediction result corresponding to office supply collection quantity prediction model A, the prediction accuracy of office supply collection quantity prediction model A can be obtained. The higher the prediction accuracy, the greater the weight of the current replenishment quantity prediction result corresponding to office supply collection quantity prediction model A.

[0052] As another example, after obtaining the current replenishment quantity prediction result corresponding to the office supply collection quantity prediction model B, the prediction accuracy of the office supply collection quantity prediction model B can be obtained. The higher the prediction accuracy, the greater the weight of the current replenishment quantity prediction result corresponding to the office supply collection quantity prediction model B.

[0053] Step S104 , performing weighted summation on multiple current replenishment quantity prediction results according to weights to obtain the current replenishment quantity of office supplies.

[0054] After obtaining the weights, each current replenishment quantity prediction result may be multiplied by the corresponding weight, and the multiple product results obtained may be summed to obtain the current replenishment quantity of office supplies.

[0055] In the above-mentioned office supply replenishment quantity prediction method, at the time of the current prediction, the office supply collection quantity sequence based on the current prediction moment and multiple office supply collection quantity prediction models are obtained; the network architectures of the multiple office supply collection quantity prediction models are different; the office supply collection quantity sequence is input into the multiple office supply collection quantity prediction models respectively to obtain multiple current replenishment quantity prediction results; according to the prediction accuracy of the office supply collection quantity prediction model, the weight corresponding to each current replenishment quantity prediction result is obtained; the higher the accuracy, the greater the weight; according to the weight, the weighted sum of the multiple current replenishment quantity prediction results is performed to obtain the current replenishment quantity of the office supplies. The solution provided in the present application can automatically predict the replenishment quantity of office supplies without manual research and manual prediction, and with the help of multiple office supply collection quantity prediction models with different network architectures for prediction, the higher the accuracy of the office supply collection quantity prediction model, the greater the weight corresponding to the corresponding current replenishment quantity prediction result, thereby improving the prediction accuracy of the office supply replenishment quantity.

[0056] In one embodiment, the method provided by the present application further includes:

[0057] The first sub-prediction accuracy of the office supply receipt quantity prediction model is obtained based on whether the historical replenishment quantity prediction results corresponding to the office supply receipt quantity prediction model meet the office supply receipt situation; the second sub-prediction accuracy of the office supply receipt quantity prediction model is obtained based on the number of parameters included in the office supply receipt quantity prediction model; the prediction accuracy of the office supply receipt quantity prediction model is obtained based on the first sub-prediction accuracy and the second sub-prediction accuracy.

[0058] For example, in the historical forecast, the historical replenishment quantity forecast results corresponding to the office supply collection quantity forecast model A can also be obtained, and the historical replenishment quantity forecast results corresponding to the office supply collection quantity forecast model B can also be obtained. The actual collection quantity of office supplies can be monitored later; if the inventory is greater than or equal to the actual collection quantity of office supplies after replenishment according to the historical replenishment quantity forecast results corresponding to the office supply collection quantity forecast model A, it indicates that the historical replenishment quantity forecast results corresponding to the office supply collection quantity forecast model A meet the subsequent office supply collection situation; if the inventory is less than the actual collection quantity of office supplies after replenishment according to the historical replenishment quantity forecast results corresponding to the office supply collection quantity forecast model A, it indicates that the historical replenishment quantity forecast results corresponding to the office supply collection quantity forecast model A do not meet the subsequent office supply collection situation.

[0059] According to whether the historical replenishment quantity prediction results corresponding to the office supply collection quantity prediction model A meet the office supply collection situation, the first sub-prediction accuracy of the office supply collection quantity prediction model A can be obtained.

[0060] The more parameters the office supply collection quantity prediction model includes, the higher the prediction accuracy. Accordingly, the second sub-prediction accuracy of the office supply collection quantity prediction model A can be obtained according to the parameters of the office supply collection quantity prediction model A.

[0061] By counting the first sub-prediction accuracy of office supply collection quantity prediction model A and the second sub-prediction accuracy of office supply collection quantity prediction model A, the prediction accuracy of office supply collection quantity prediction model A can be obtained.

[0062] Similarly, according to the above method, the first sub-prediction accuracy of office supply collection quantity prediction model B and the second sub-prediction accuracy of office supply collection quantity prediction model B can be obtained.

[0063] By counting the first sub-prediction accuracy of office supply collection quantity prediction model B and the second sub-prediction accuracy of office supply collection quantity prediction model B, the prediction accuracy of office supply collection quantity prediction model B can be obtained.

[0064] In one embodiment, the prediction accuracy of the office supplies collection quantity prediction model is obtained according to the first sub-prediction accuracy and the second sub-prediction accuracy, including:

[0065] If the historical replenishment quantity prediction results corresponding to the office supply collection quantity prediction model meet the office supply collection situation, then the larger weight is determined as the first weight among the two weights; if the parameter quantity included in the office supply collection quantity prediction model is a high parameter quantity among the parameter quantities included in multiple office supply collection quantity prediction models, then the larger weight is determined as the second weight among the two weights; the first sub-prediction accuracy is assigned to the first weight and the second sub-prediction accuracy is assigned to the second weight, and the weighted sum of the first sub-prediction accuracy and the second sub-prediction accuracy is performed to obtain the prediction accuracy of the office supply collection quantity prediction model.

[0066] Exemplarily, if the historical replenishment quantity prediction results corresponding to office supply collection quantity prediction model A meet the subsequent office supply collection situation, the larger weight can be determined as the first weight among the two weights; if the historical replenishment quantity prediction results corresponding to office supply collection quantity prediction model A do not meet the subsequent office supply collection situation, the smaller weight can be determined as the first weight among the two weights.

[0067] If the parameter quantity included in office supply collection quantity prediction model A is a high parameter quantity among the parameter quantities included in multiple office supply collection quantity prediction models, then the larger weight is determined as the second weight among the two weights; if the parameter quantity included in office supply collection quantity prediction model A is a low parameter quantity among the parameter quantities included in multiple office supply collection quantity prediction models, then the smaller weight is determined as the second weight among the two weights.

[0068] After determining the first weight and second weight of office supply collection quantity prediction model A, the first weight can be multiplied by the first sub-prediction accuracy of office supply collection quantity prediction model A, and the second weight can be multiplied by the second sub-prediction accuracy of office supply collection quantity prediction model A. The products are added together to obtain the prediction accuracy of office supply collection quantity prediction model A.

[0069] In the above manner, the prediction accuracy of office supplies collection quantity prediction model B can also be obtained.

[0070] In one embodiment, the method provided by the present application further includes:

[0071] The parameter quantities included in multiple office supply receipt prediction models are sorted; if they are sorted from large to small, and the parameter quantities included in the office supply receipt prediction model are sorted first, then it is determined that the parameter quantities included in the office supply receipt prediction model are high parameter quantities; if they are sorted from small to large, and the parameter quantities included in the office supply receipt prediction model are sorted last, then it is determined that the parameter quantities included in the office supply receipt prediction model are high parameter quantities.

[0072] After obtaining multiple office supply collection quantity prediction models, the parameter quantity of each office supply collection quantity prediction model can be obtained.

[0073] The parameter quantities included in the multiple office supplies collection quantity prediction models can be sorted from large to small; the parameter quantities ranked in the first N can be determined as high parameter quantities. N is a positive integer greater than or equal to 1.

[0074] Alternatively, the parameter quantities included in the multiple office supplies collection quantity prediction models may be sorted from small to large; the parameter quantities ranked last M may be determined as high parameter quantities. M is a positive integer greater than or equal to 1.

[0075] In one embodiment, according to the prediction accuracy of the office supplies collection quantity prediction model, the weight corresponding to each current replenishment quantity prediction result is obtained, including:

[0076] Obtain a positive correlation function; input the prediction accuracy of the office supplies collection quantity prediction model into the positive correlation function to obtain an output result of the positive correlation function; and determine the output result of the positive correlation function as a weight corresponding to the current replenishment quantity prediction result.

[0077] For example, the prediction accuracy of the office supplies collection quantity prediction model A can be used as an independent variable of the positive correlation function and input into the positive correlation function to obtain the output result of the positive correlation function. The output result of the positive correlation function can be determined as the weight corresponding to the current replenishment quantity prediction result.

[0078] In one embodiment, the plurality of office supply collection quantity prediction models include a linear regression model, a decision tree model, and a neural network model.

[0079] The network architectures of linear regression models, decision tree models, and neural network models are different.

[0080] The present application also provides an embodiment, which can perform real-time inventory management of low-value consumables such as office supplies through AI (Artificial Intelligence) algorithms, and realize real-time tracking and intelligent early warning of office supplies. This embodiment can automatically record the entry and exit of office supplies, monitor the inventory level of office supplies in real time, and automatically trigger replenishment reminders when the inventory of office supplies is lower than the safety inventory. In addition, this embodiment can predict the future inventory demand of office supplies based on inventory consumption trends and procurement cycles, providing strong support for enterprises to optimize inventory structure and reduce inventory costs.

[0081] This embodiment includes Figure 2 The basic data storage module, AI prediction module, inventory decision module and procurement management module are shown.

[0082] Among them, the basic data storage module is mainly used to store: core data such as product attributes (such as name, number, specification model) and safety inventory. The basic data storage module can also store keyword information such as whether office supplies are high-frequency materials or stagnant materials.

[0083] The AI ​​prediction module can predict the replenishment quantity d based on the data stored in the basic data storage module, the safety stock ss, the average delivery time (the average delivery time of the supplier) L and the service level Service Level. The calculation formula is as follows:

[0084] ;

[0085] Among them, Z is the confidence interval value corresponding to the service level, is the mean of the average delivery time, is the variance of demand, is the square of the mean of demand, is the variance of the average delivery time.

[0086] After predicting the replenishment quantity d, the inventory decision module can determine whether the current inventory is sufficient. If the inventory is insufficient, it is necessary to purchase goods, which can be achieved with the help of the procurement management module. In addition, inventory can also be allocated from other warehouses.

[0087] Reference Figure 3 , Figure 3The curve shown is a normal distribution curve. The forecast value of the replenishment quantity is located in the middle of the curve, indicating the expected average value of the replenishment quantity; Safety stock: The distance from the forecast value to one side of the curve indicates the amount of additional inventory retained to cope with uncertainties (such as demand fluctuations, supply delays, etc.). The setting of safety stock is to ensure that when actual demand exceeds the forecast value, there is still enough inventory to meet customer demand and avoid out-of-stock situations. Service level: usually refers to the probability of being able to meet customer demand within a certain period of time. Figure 3 In the context of a product, it may represent the service level that can be achieved with a specific level of safety stock. For example, a higher safety stock will generally correspond to a higher service level, meaning that it is more likely that customer orders will be met in a timely manner, but it will also increase inventory holding costs.

[0088] ‌Replenishment calculation formula‌:

[0089] Forecasted purchase quantity = inventory on order quantity - inventory balance - purchase on order quantity + minimum inventory‌.

[0090] Inventory on order quantity: Statistics on the order quantity of all effective orders associated with the material. If there is a purchase order with an order quantity of 100 and a shipped quantity of 40, the inventory on order quantity is 60.

[0091] ‌Inventory Balance‌: The current inventory quantity in the warehouse‌.

[0092] ‌Purchase quantity on order‌: Statistics the order quantity of all the effective purchase orders associated with the product. If there is a purchase order with an order quantity of 80 and the quantity in stock is 70, then the purchase quantity on order is 10‌.

[0093] ‌Minimum Inventory‌: Take the inventory warning value set in product management (general warehouse warning, sub-warehouse warning)‌.

[0094] Through these steps and formulas, intelligent replenishment decisions can be made effectively, inventory management can be optimized, and the risks of out-of-stock and excess inventory can be reduced.

[0095] It should be understood that, although the various steps in the flowcharts involved in the above-mentioned embodiments are displayed in sequence according to the indication of the arrows, these steps are not necessarily executed in sequence according to the order indicated by the arrows. Unless there is a clear explanation in this article, the execution of these steps does not have a strict order restriction, and these steps can be executed in other orders. Moreover, at least a part of the steps in the flowcharts involved in the above-mentioned embodiments can include multiple steps or multiple stages, and these steps or stages are not necessarily executed at the same time, but can be executed at different times, and the execution order of these steps or stages is not necessarily to be carried out in sequence, but can be executed in turn or alternately with other steps or at least a part of the steps or stages in other steps.

[0096] Based on the same inventive concept, the embodiment of the present application also provides a prediction device for office supplies replenishment quantity for implementing the above-mentioned prediction method for office supplies replenishment quantity. The implementation scheme for solving the problem provided by the device is similar to the implementation scheme recorded in the above-mentioned method, so the specific limitations in one or more embodiments of the prediction device for office supplies replenishment quantity provided below can refer to the limitations of the prediction method for office supplies replenishment quantity above, and will not be repeated here.

[0097] In one embodiment, Figure 4 As shown, a device for predicting the replenishment quantity of office supplies is provided, comprising:

[0098] The data and model acquisition module 401 is used to acquire the office supply collection quantity sequence based on the current prediction time and multiple office supply collection quantity prediction models during the current prediction; the network architectures of the multiple office supply collection quantity prediction models are different;

[0099] Model prediction module 402, used to input the office supply collection quantity sequence into multiple office supply collection quantity prediction models respectively to obtain multiple current replenishment quantity prediction results;

[0100] The weight determination module 403 is used to obtain the weight corresponding to each current replenishment quantity prediction result according to the prediction accuracy of the office supplies collection quantity prediction model; the higher the accuracy, the greater the weight;

[0101] The replenishment quantity determination module 404 is used to perform weighted summation on multiple current replenishment quantity prediction results according to the weights to obtain the current replenishment quantity of office supplies.

[0102] In one embodiment, the apparatus further comprises a prediction accuracy determination module, configured to:

[0103] The first sub-prediction accuracy of the office supply collection quantity prediction model is obtained based on whether the historical replenishment quantity prediction results corresponding to the office supply collection quantity prediction model meet the office supply collection situation; the second sub-prediction accuracy of the office supply collection quantity prediction model is obtained based on the parameter quantity included in the office supply collection quantity prediction model; the prediction accuracy of the office supply collection quantity prediction model is obtained based on the first sub-prediction accuracy and the second sub-prediction accuracy.

[0104] In one embodiment, the prediction accuracy determination module is further used to:

[0105] If the historical replenishment quantity prediction result corresponding to the office supply collection quantity prediction model satisfies the office supply collection situation, then the larger weight is determined as the first weight among the two weights; if the parameter quantity included in the office supply collection quantity prediction model is a high parameter quantity among the parameter quantities included in multiple office supply collection quantity prediction models, then the larger weight is determined as the second weight among the two weights; the first sub-prediction accuracy is assigned to the first weight and the second sub-prediction accuracy is assigned to the second weight, and the first sub-prediction accuracy and the second sub-prediction accuracy are weightedly summed to obtain the prediction accuracy of the office supply collection quantity prediction model.

[0106] In one embodiment, the prediction accuracy determination module is further used to:

[0107] Sort the parameter quantities included in multiple office supply receipt prediction models; if they are sorted from large to small, and the parameter quantities included in the office supply receipt prediction model are sorted first, then it is determined that the parameter quantities included in the office supply receipt prediction model are high parameter quantities; if they are sorted from small to large, and the parameter quantities included in the office supply receipt prediction model are sorted last, then it is determined that the parameter quantities included in the office supply receipt prediction model are high parameter quantities.

[0108] In one embodiment, the weight determination module 403 is further configured to:

[0109] Obtain a positive correlation function; input the prediction accuracy of the office supplies collection quantity prediction model into the positive correlation function to obtain an output result of the positive correlation function; and determine the output result of the positive correlation function as the weight corresponding to the current replenishment quantity prediction result.

[0110] In one embodiment, the plurality of office supply collection quantity prediction models include a linear regression model, a decision tree model, and a neural network model.

[0111] Each module in the above-mentioned prediction device for replenishment of office supplies can be implemented in whole or in part by software, hardware or a combination thereof. Each module can be embedded in or independent of a processor in a computer device in the form of hardware, or can be stored in a memory in a computer device in the form of software, so that the processor can call and execute the operations corresponding to each module.

[0112] In an exemplary embodiment, a computer device is provided, the internal structure of which can be shown as follows: Figure 5As shown. The computer device includes a processor, a memory, an input / output interface (Input / Output, referred to as I / O) and a communication interface. The processor, the memory and the input / output interface are connected through a system bus, and the communication interface is connected to the system bus through the input / output interface. The processor of the computer device is used to provide computing and control capabilities. The memory of the computer device includes a non-volatile storage medium and an internal memory. The non-volatile storage medium stores an operating system, a computer program and a database. The internal memory provides an environment for the operation of the operating system and the computer program in the non-volatile storage medium. The database of the computer device is used to store data involved in the above method. The input / output interface of the computer device is used to exchange information between the processor and an external device. The communication interface of the computer device is used to communicate with an external terminal through a network connection. When the computer program is executed by the processor, a method for predicting the replenishment of office supplies is implemented.

[0113] Those skilled in the art will understand that Figure 5 The structure shown in the figure is only a block diagram of a part of the structure related to the solution of the present application, and does not constitute a limitation on the computer device to which the solution of the present application is applied. The specific computer device may include more or fewer components than those shown in the figure, or combine certain components, or have a different arrangement of components.

[0114] In one embodiment, a computer device is provided, including a memory and a processor, wherein the memory stores a computer program, and the processor implements the steps in the above-mentioned various method embodiments when executing the computer program.

[0115] In one embodiment, a computer-readable storage medium is provided, on which a computer program is stored. When the computer program is executed by a processor, the steps in the above-mentioned method embodiments are implemented.

[0116] In one embodiment, a computer program product is provided, on which a computer program is stored, and the computer program is used by a processor to execute the steps in the above-mentioned various method embodiments.

[0117] It should be noted that the user information (including but not limited to user device information, user personal information, etc.) and data (including but not limited to data used for analysis, stored data, displayed data, etc.) involved in this application are all information and data authorized by the user or fully authorized by all parties, and the collection, use and processing of relevant data must comply with relevant regulations.

[0118] A person of ordinary skill in the art can understand that all or part of the processes in the above-mentioned embodiment method can be completed by instructing the relevant hardware through a computer program, and the computer program can be stored in a non-volatile computer-readable storage medium. When the computer program is executed, it can include the processes of the embodiments of the above-mentioned methods. Among them, any reference to the memory, database or other medium used in the embodiments provided in the present application can include at least one of non-volatile memory and volatile memory. Non-volatile memory can include read-only memory (ROM), magnetic tape, floppy disk, flash memory, optical memory, high-density embedded non-volatile memory, resistive random access memory (ReRAM), magnetic random access memory (MRAM), ferroelectric random access memory (FRAM), phase change memory (PCM), graphene memory, etc. Volatile memory can include random access memory (RAM) or external cache memory, etc. As an illustration and not limitation, RAM can be in various forms, such as static random access memory (SRAM) or dynamic random access memory (DRAM). The database involved in each embodiment provided in this application may include at least one of a relational database and a non-relational database. Non-relational databases may include distributed databases based on blockchains, etc., but are not limited to this. The processor involved in each embodiment provided in this application may be a general-purpose processor, a central processing unit, a graphics processor, a digital signal processor, a programmable logic device, a data processing logic device based on quantum computing, an artificial intelligence (AI) processor, etc., but are not limited to this.

[0119] The technical features of the above embodiments may be combined arbitrarily. To make the description concise, not all possible combinations of the technical features in the above embodiments are described. However, as long as there is no contradiction in the combination of these technical features, they should be considered to be within the scope of this application.

[0120] The above-described embodiments only express several implementation methods of the present application, and the descriptions thereof are relatively specific and detailed, but they cannot be understood as limiting the scope of the present application. It should be pointed out that, for a person of ordinary skill in the art, several variations and improvements can be made without departing from the concept of the present application, and these all belong to the protection scope of the present application. Therefore, the protection scope of the present application shall be subject to the attached claims.

Claims

1. A method for predicting the replenishment quantity of office supplies, characterized in that: The method comprises: In the current prediction, the office supplies collection quantity sequence based on the current prediction moment and multiple office supplies collection quantity prediction models are obtained; the network architectures of the multiple office supplies collection quantity prediction models are different; Inputting the office supply collection quantity sequence into multiple office supply collection quantity prediction models respectively to obtain multiple current replenishment quantity prediction results; According to the prediction accuracy of the office supplies collection quantity prediction model, a weight corresponding to each current replenishment quantity prediction result is obtained; the higher the accuracy, the greater the weight; According to the weights, a weighted sum is performed on multiple current replenishment quantity prediction results to obtain the current replenishment quantity of office supplies.

2. The method according to claim 1, characterized in that The method further comprises: Obtaining a first sub-prediction accuracy of the office supply collection quantity prediction model according to whether the historical replenishment quantity prediction result corresponding to the office supply collection quantity prediction model meets the office supply collection situation; Obtaining a second sub-prediction accuracy of the office supplies collection quantity prediction model according to the parameter quantity included in the office supplies collection quantity prediction model; The prediction accuracy of the office supplies collection quantity prediction model is obtained according to the first sub-prediction accuracy and the second sub-prediction accuracy.

3. The method according to claim 2, characterized in that The prediction accuracy of the office supplies collection quantity prediction model is obtained according to the first sub-prediction accuracy and the second sub-prediction accuracy, including: If the historical replenishment quantity prediction result corresponding to the office supplies collection quantity prediction model satisfies the office supplies collection situation, then the larger weight is determined as the first weight among the two weights; If the parameter amount included in the office supply collection amount prediction model is a high parameter amount among the parameter amounts included in the plurality of office supply collection amount prediction models, then a large weight is determined as the second weight among the two weights; The first sub-prediction accuracy is assigned to the first weight and the second sub-prediction accuracy is assigned to the second weight, and the first sub-prediction accuracy and the second sub-prediction accuracy are weighted summed to obtain the prediction accuracy of the office supplies collection quantity prediction model.

4. The method according to claim 3, characterized in that: The method further comprises: Sorting the parameter quantities included in multiple office supplies collection quantity prediction models; If the parameters are sorted from large to small, and the parameter quantity included in the office supplies collection quantity prediction model is ranked first, it is determined that the parameter quantity included in the office supplies collection quantity prediction model belongs to a high parameter quantity; If the sorting is performed from small to large, and the parameter quantity included in the office supply collection quantity prediction model is sorted at the end, it is determined that the parameter quantity included in the office supply collection quantity prediction model belongs to the high parameter quantity.

5. The method according to claim 1, characterized in that: According to the prediction accuracy of the office supplies collection quantity prediction model, the weight corresponding to each current replenishment quantity prediction result is obtained, including: Get the positive correlation function; Inputting the prediction accuracy of the office supplies collection quantity prediction model into the positive correlation function to obtain an output result of the positive correlation function; The output result of the positive correlation function is determined as the weight corresponding to the current replenishment quantity prediction result.

6. The method according to any one of claims 1 to 5, characterized in that: Multiple office supplies collection quantity prediction models include linear regression model, decision tree model and neural network model.

7. A device for predicting the replenishment quantity of office supplies, characterized in that: The device comprises: The data and model acquisition module is used to obtain the office supply collection quantity sequence based on the current prediction time and multiple office supply collection quantity prediction models during the current prediction; the network architectures of the multiple office supply collection quantity prediction models are different; A model prediction module, used to input the office supply collection quantity sequence into multiple office supply collection quantity prediction models respectively to obtain multiple current replenishment quantity prediction results; A weight determination module, used to obtain a weight corresponding to each current replenishment quantity prediction result according to the prediction accuracy of the office supplies collection quantity prediction model; the higher the accuracy, the greater the weight; The replenishment quantity determination module is used to perform weighted summation on multiple current replenishment quantity prediction results according to the weights to obtain the current replenishment quantity of office supplies.

8. A computer device comprising a memory and a processor, wherein the memory stores a computer program, wherein: When the processor executes the computer program, the method according to any one of claims 1 to 6 is implemented.

9. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, the method according to any one of claims 1 to 6 is implemented.

10. A computer program product, comprising a computer program, characterized in that When the computer program is executed by a processor, the method according to any one of claims 1 to 6 is implemented.

Images