Inventory prediction method and device, storage medium and electronic equipment

Abstract

The invention discloses an inventory prediction method and device, a storage medium and electronic equipment. The method comprises the following steps: acquiring historical demand data of materials in a historical period; obtaining a target prediction strategy, and performing prediction processing on the historical demand data of the material based on the target prediction strategy to obtain prediction demand data of the material in a prediction period; determining initial replenishment data based on the predicted demand data of the material; and determining correction parameters based on the historical prediction demand data and the actual demand data of the historical period, and determining target replenishment data based on the correction parameters and the initial replenishment data. Prediction processing is performed on historical demand data of a material in a historical period to obtain predicted demand data. Under the condition that the initial replenishment data is determined based on the predicted demand data, the initial replenishment data is corrected by setting the correction parameter, and the accuracy of the target replenishment data is improved.

Description

Technical Field

[0001] The present invention relates to the field of intelligent supply chain technology, and in particular to an inventory forecasting method, device, storage medium and electronic equipment. Background Art

[0002] In the equipment maintenance scenario, the timeliness requirements of maintenance business are guaranteed by the stock of spare parts and other materials. The lack of materials cannot guarantee the timeliness of maintenance, and material redundancy leads to high material costs. Therefore, material inventory forecasting has a positive significance for maintenance scenarios.

[0003] In the process of implementing the present invention, it is found that there are at least the following technical problems in the prior art: the regularity of material inventory planning is poor, resulting in poor inventory forecasting accuracy. Summary of the invention

[0004] The present invention provides an inventory forecasting method, device, storage medium and electronic equipment to improve the accuracy of inventory forecasting.

[0005] According to one aspect of the present invention, there is provided an inventory forecasting method, comprising:

[0006] Obtain historical demand data for materials within the historical period;

[0007] Acquire a target forecasting strategy, and perform forecasting processing on the historical demand data of the material based on the target forecasting strategy to obtain forecast demand data of the material in the forecasting period;

[0008] Determining initial replenishment data based on the forecast demand data of the material;

[0009] A correction parameter is determined based on the historical forecast demand data and the actual demand data of the historical period, and a target replenishment data is determined based on the correction parameter and the initial replenishment data.

[0010] According to another aspect of the present invention, there is provided an inventory forecasting device, comprising:

[0011] The historical data acquisition module is used to obtain the historical demand data of materials in the historical period;

[0012] A demand forecasting module is used to obtain a target forecasting strategy, and to forecast the historical demand data of the material based on the target forecasting strategy to obtain forecast demand data of the material in the forecasting period;

[0013] An initial replenishment data determination module, used to determine initial replenishment data based on the forecast demand data of the material;

[0014] The target replenishment data determination module is used to determine correction parameters based on the historical forecast demand data and actual demand data of the historical period, and determine target replenishment data based on the correction parameters and the initial replenishment data.

[0015] According to another aspect of the present invention, an electronic device is provided, the electronic device comprising:

[0016] at least one processor; and

[0017] a memory communicatively connected to the at least one processor; wherein,

[0018] The memory stores a computer program executable by the at least one processor, and the computer program is executed by the at least one processor so that the at least one processor can execute the inventory forecasting method described in any embodiment of the present invention.

[0019] According to another aspect of the present invention, a computer-readable storage medium is provided, wherein the computer-readable storage medium stores computer instructions, and the computer instructions are used to enable a processor to implement the inventory forecasting method described in any embodiment of the present invention when executed.

[0020] The technical solution of the embodiment of the present invention obtains predicted demand data by predicting and processing the historical demand data of the material in the historical period. When the initial replenishment data is determined based on the predicted demand data, the initial replenishment data is corrected by setting correction parameters to improve the accuracy of the target replenishment data.

[0021] It should be understood that the contents described in this section are not intended to identify the key or important features of the embodiments of the present invention, nor are they intended to limit the scope of the present invention. Other features of the present invention will become easily understood through the following description. BRIEF DESCRIPTION OF THE DRAWINGS

[0022] In order to more clearly illustrate the technical solutions in the embodiments of the present invention, the following briefly introduces the drawings required for use in the description of the embodiments. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without creative work.

[0023] Figure 1 is a flow chart of an inventory forecasting method provided by an embodiment of the present invention;

[0024] Figure 2 It is a structural schematic diagram of an inventory forecasting device provided by an embodiment of the present invention;

[0025] Figure 3 It is a structural schematic diagram of an electronic device provided by an embodiment of the present invention. DETAILED DESCRIPTION

[0026] In order to enable those skilled in the art to better understand the scheme of the present invention, the technical scheme in the embodiments of the present invention will be clearly and completely described below in conjunction with the drawings in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work should fall within the scope of protection of the present invention.

[0027] It should be noted that the terms "first", "second", etc. in the specification and claims of the present invention and the above-mentioned drawings are used to distinguish similar objects, and are not necessarily used to describe a specific order or sequence. It should be understood that the data used in this way can be interchanged where appropriate, so that the embodiments of the present invention described herein can be implemented in an order other than those illustrated or described herein. In addition, the terms "including" and "having" and any variations thereof are intended to cover non-exclusive inclusions, for example, a process, method, system, product or device that includes a series of steps or units is not necessarily limited to those steps or units that are clearly listed, but may include other steps or units that are not clearly listed or inherent to these processes, methods, products or devices.

[0028] Figure 1 This is a flow chart of an inventory forecasting method provided by an embodiment of the present invention. This embodiment is applicable to the case of forecasting material inventory. The method can be executed by an inventory forecasting device. The inventory forecasting device can be implemented in the form of hardware and / or software. The inventory forecasting device can be configured in electronic devices such as computers, mobile phones, servers, etc. Figure 1 As shown, the method includes:

[0029] S110. Obtain historical demand data for materials within a historical period.

[0030] S120: Acquire a target forecasting strategy, and perform forecasting processing on the historical demand data of the material based on the target forecasting strategy to obtain forecast demand data of the material in a forecasting period.

[0031] S130: Determine initial replenishment data based on the predicted demand data of the material.

[0032] S140: Determine correction parameters based on the historical forecast demand data and actual demand data of the historical period, and determine target replenishment data based on the correction parameters and the initial replenishment data.

[0033] The materials in this embodiment are materials required for equipment maintenance, and the materials may be accessory materials. The specific types of materials are not limited here and can be determined according to the equipment maintenance requirements. The materials here can be stored in multiple material warehouses. When there is a demand for materials, an application can be made to the material warehouse in the form of a material document. Among them, the material document may include but is not limited to one or more of the application time information, material warehouse identification, material category, material brand, material code, application material quantity, document type, etc. The information in the above-mentioned material documents can be stored in a database, which is convenient for summarizing the demand data based on the information in the above-mentioned material documents. For example, when each material warehouse receives a material document, it uploads the above-mentioned material document to the database.

[0034] Historical demand data is obtained by summarizing the demand information on the material documents. The demand information on the material documents can be summarized based on multiple dimensions such as material library identification, time information, material code, etc. to obtain summary data. Exemplarily, the summary data may include demand data for material library identification A and material code m in time information 1. On the basis of the above-mentioned summary data, inquiries and further summaries can be performed on the dimensions of material library, time and material code, for example, summary data within a certain time range can be determined on the time dimension, such as weekly dimension or monthly dimension. Optionally, the summary data of each historical period, i.e., historical demand data, is determined according to the period length of the historical period. The period length of the historical period can be one month or half a month, etc.

[0035] On the basis of the above embodiment, the historical demand data of materials in the historical period is obtained, including: counting the original demand data of each material in each material library, and determining the original demand data of each material in the historical period based on the time information of the demand data; based on the preset hit rate of the material library and the original demand data of each material in the historical period, determining the historical demand data of materials in the historical period.

[0036] The original demand data of each material in the historical period may be the summary data of the materials in the historical period. Since the material library pre-sets a preset hit rate, the preset hit rate is the material library's ability to meet material demand. The preset hit rate is a data value greater than zero and less than or equal to 1. For example, the preset hit rate of a certain material library may be 90%. For any material library, based on the preset hit rate of the material library and the original demand data of each material in the material library in the historical period, the historical demand data of the material in each historical period of the material library is determined. Specifically, the original demand data of each material in each historical period in the material library may be multiplied by the preset hit rate to obtain the historical demand data of each material in each historical period in the material library.

[0037] Based on the above embodiment, the document type of the material document can be an application type and a borrowing type, wherein the application type can be a document type formed by applying for materials from the material library and directly used for equipment maintenance, and the borrowing type can be a document type formed by a material library requesting materials from another material library. Correspondingly, the historical demand data of materials includes work order demand data and attachment demand data, wherein the work order demand data can be obtained by summarizing the material documents of the application type and processing them with the preset hit rate of the material library, and the attachment demand data can be obtained by summarizing the material documents of the borrowing type and processing them with the preset hit rate of the material library.

[0038] In some embodiments, for the specific preset hit rate of the material library, it can be determined that the materials with local demand cannot meet the demand. After determining the original demand data of each material in the historical period based on the time information of the demand data, the total original demand data corresponding to all material codes in the same material library can be counted, and the total historical demand data of the material library can be determined based on the total original demand data and the preset hit rate of the material library. Sort multiple materials based on the original demand data of each material (for example, it can be the application quantity), for example, it can be sorted from large to small based on the original demand data of each material. Determine the material that meets the total historical demand data based on the sorting, and determine the historical demand data of the material in the historical period. Exemplarily, it may be possible to determine in order of sorting whether the cumulative demand data at each material meets the original total demand data. When the material code is at position n in the sorting, determine whether the cumulative demand data of all materials at position n and before position n in the sorting meet the original total demand data. If not, determine the material at position n in the sorting as a historical demand material, mark the material, and continue to determine the next sorted material until the cumulative demand data at a certain sorted material meets the original total demand data. Then stop determining subsequent materials and discard them.

[0039] The historical demand data of the marked materials in the historical period are counted to obtain the historical demand data of the materials in the material library in the historical period, wherein the historical demand data includes related information such as material code, demand data and historical period range.

[0040] On the basis of the above embodiment, based on the historical demand data of the material in the historical period, each material is forecasted to obtain the forecast demand data of each material in the forecast period. The forecast period can be the same as the historical period, for example, one month. By determining the forecast demand data of the material in the forecast period, a basis is provided for material replenishment.

[0041] In this embodiment, multiple candidate forecasting strategies can be pre-set, and a target forecasting strategy can be determined from the multiple candidate forecasting strategies to forecast the demand for materials. Specifically, the historical forecast demand data of the candidate forecasting strategies for the historical period and the actual demand data of the historical period are obtained; the forecast confidence of the candidate forecasting strategy is determined based on the historical forecast demand data and the actual demand data corresponding to the historical period; and the target forecasting strategy is determined based on the forecast confidence of the candidate forecasting strategy.

[0042] For any candidate prediction strategy, obtain the historical prediction demand data and actual demand data corresponding to a preset number of historical periods under the candidate prediction strategy, determine the absolute value of the difference between the historical prediction demand data and the actual demand data for each historical period, and the absolute value of the difference represents the prediction accuracy of the candidate prediction strategy in the historical period. Based on one or more of the sum, mean, and weighted data of the absolute values ​​of the differences of the candidate prediction strategy in multiple historical periods, determine the prediction confidence of the candidate prediction strategy, and the prediction confidence is negatively correlated with the sum, mean, or weighted data of the absolute values ​​of the differences of multiple historical periods.

[0043] The candidate prediction strategy with the highest prediction confidence is determined as the target prediction strategy. By presetting multiple candidate prediction strategies, the diversity of prediction strategies is improved. The target prediction strategy with the highest prediction confidence is screened from multiple candidate prediction strategies to improve prediction accuracy and prediction precision.

[0044] In some embodiments, the candidate prediction strategies include a first prediction strategy and a second prediction strategy; accordingly, the target prediction process is the first prediction strategy or the second prediction strategy.

[0045] Among them, the first prediction strategy is: based on the historical demand data, weight data and seasonal parameters of each of the historical periods, the first prediction item of the historical period is determined, and the predicted demand data of the prediction period is determined based on the first prediction items of the historical periods of multiple historical periods and the seasonal parameters of the prediction period. Different historical periods correspond to different weight data and seasonal parameters, and the longer the interval between the historical period and the current moment, the smaller the weight data. The seasonal parameters of the historical period can be determined by the historical demand data of the historical period, for example, they can be positively correlated with the historical demand data. Among them, the first prediction item of the historical period can be determined based on the product of the historical demand data of the historical period and the weight data, and the quotient of the product and the seasonal parameter. The predicted demand data of the prediction period is determined based on the sum of the first prediction items of the historical periods of multiple historical periods and the product of the seasonal parameters of the prediction period.

[0046] The first forecasting strategy can be a forecasting strategy based on a weighted moving average algorithm, which is used to forecast future time period demand data based on historical data in a preset time period before the current moment. The weighted moving average algorithm is suitable for spot forecasting, which can effectively eliminate random fluctuations in the forecast and is suitable for forecasting when the material is neither growing nor declining rapidly and there are no seasonal factors.

[0047] Exemplarily, the first forecasting strategy can be represented by the following formula: Dn+1=[(Dn*w1) / mn+(Dn-1*w2) / mn-1+(Dn-2*w3) / mn-2+…]*mn+1, where Dn+1 is the forecast demand data for forecast period n+1, Dn, Dn-1, Dn-2, …: refer to the historical demand data of materials in the nth period, n-1 period and other historical periods; w1, w2, w3… are the weight data of the historical period, and mn+1, mn, mn-1, … refer to the seasonal parameters of the forecast period and each historical period. The seasonal parameters need to be determined based on the historical demand data of more than 12 historical periods in the past, and it is more accurate to determine them based on the historical demand data of 24 historical periods. Among them, the data range of n period is between 3-6, that is, the values ​​of the past 3-6 months are selected for calculation. For example, July demand = (June demand × W1 / M6 + May demand × W2 / M5 + April demand × W3 / M4 + March demand × W4 / M3 + February demand × W5 / M2 + January demand × W6 / M1) × M7, W1 refers to the first cycle, and by analogy, it refers to the weight ratio of the nth cycle.

[0048] Optionally, the second forecasting strategy is: determine the average forecast item of the historical period and the trend item of the forecast period based on multiple historical demand data and seasonal parameters of the historical periods, and determine the forecast demand data of the forecast period based on the average forecast item and the trend item.

[0049] Among them, by determining the quotient of the historical demand data of each historical period and the seasonal parameter, and determining the average prediction item of the historical period based on the average of the above quotient values ​​corresponding to multiple historical periods, the trend item of the prediction period can be determined based on the ratio of the average prediction item of the first local historical period and the average prediction item of the second local historical period. For example, all historical periods can be divided into two parts, namely the first local historical period and the second local historical period, and the time interval between the first local historical period and the current moment is smaller than the time interval between the second local historical period and the current moment.

[0050] The second forecasting strategy can be a forecasting strategy based on the trend moving average algorithm, which is a forecasting strategy based on the simple moving average method and adds the influence of the demand change trend to obtain the forecasting data of the future. Compared with the weighted moving average algorithm, it can be more sensitive to the turning points of rapid demand growth and rapid demand drop.

[0051] Exemplarily, the second prediction strategy can be expressed by the following formula: Dn+1=E(Dn / mn+Dn-1 / mn-1+…+Dn-5 / mn-5)*mn+1*a, wherein E() is the average value, a is the trend item of the prediction period, and the trend item can be determined based on the trend parameter am. The trend parameter can be determined as: am=E(Dn / mn+Dn-1 / mn-1+Dn-2 / mn-2) / E(Dn-3 / mn-3+Dn-4 / mn-4+Dn-5 / mn-5), wherein Dn, Dn-1 and Dn-2 are the first local historical period, and Dn-3, Dn-4 and Dn-5 are the second local historical period. Here, the number of the first local historical period and the second local historical period are 3 respectively, which is only an example. In other embodiments, it can be divided and determined according to the total data of the historical period.

[0052] The trend item of the forecast period has a corresponding relationship with the trend parameter, and the mapping range of the trend parameter is preset. Taking the mapping range as (n, m) as an example, when the trend parameter am is between the mapping range (n, m), the trend item can be a fixed value, and the fixed value can be the center value of the trend range, that is, the mean of n and m. When the trend parameter am is less than n, the trend item can be the same as the trend parameter, that is, a=am; when the trend parameter am is greater than m, the trend item can be obtained by pre-processing the trend parameter, for example, a=aqrt(am).

[0053] Taking the demand forecast for July as an example, July demand = E(June demand / M6+May demand / M5+April demand / M4+March demand / M3+February demand / M2+January demand / M1)×M7×a, where a is the trend item of the forecast period, and the trend item can be determined based on the trend parameter am. When 0.8≤am≤1.2, a=1.0; when am<0.8, a=am; when am>1.2, a=aqrt(am). Among them, the above 0.8 and 1.2 are examples of trend range boundary values ​​n and m, respectively, which can be set as needed. Correspondingly, am=(June demand / M6+May demand / M5+April demand / M4) / (March demand / M3+February demand / M2+January demand / M1).

[0054] On the basis of the above embodiment, the candidate prediction strategy may also include a neural network prediction model, which is used to predict the historical demand data of any material in multiple historical periods to obtain the predicted demand data of the material in the prediction period. The neural network prediction model can be trained based on historical demand sample data and prediction labels, and the type of neural network prediction model is not limited here. The above-mentioned first prediction strategy, second prediction strategy and neural network prediction model can be judged by prediction confidence to determine the target prediction strategy. It can be understood that the parameters included in the first prediction strategy, the second prediction strategy and the neural network prediction model can be continuously updated according to the historical prediction demand data and actual demand data of the newly added historical period to improve the prediction accuracy of each candidate prediction strategy.

[0055] In some embodiments, based on the prediction confidence of the candidate prediction strategy, the weight of the candidate prediction strategy is set. Correspondingly, the target prediction strategy is multiple candidate prediction strategies and the weights of the candidate prediction strategies. Demand forecasting is performed based on each candidate prediction strategy respectively, and the prediction results obtained by the candidate prediction strategies are weighted based on the weights of the candidate prediction strategies to obtain predicted demand data.

[0056] Based on the above embodiment, the forecast demand data of each material in the forecast period is obtained, and the initial replenishment data is determined according to the forecast demand data of the material in the forecast period. Optionally, for any material, the initial replenishment data may be the difference between the forecast demand data and the current inventory data. Optionally, the initial replenishment data for the current time may be determined according to the estimated number of replenishments in the forecast period and the difference between the forecast demand data and the current inventory data.

[0057] In some embodiments, the current inventory data may be determined, and a replenishment operation may be triggered when the current inventory data is less than or equal to the safety inventory data, where the safety inventory data is the minimum inventory data to ensure normal operation of the maintenance scenario.

[0058] When the initial replenishment data is determined, the initial replenishment data is updated based on the correction parameter to obtain the target replenishment data, and the product of the initial replenishment data and the correction parameter is determined as the target replenishment data. The correction parameter is determined based on the historical forecast demand data and the actual demand data of the historical cycle, and the correction parameter can be determined by the ratio of the actual demand data to the historical forecast demand data. Optionally, the correction parameter can be determined based on the ratio of the actual demand data to the historical forecast demand data of the previous historical cycle; optionally, the correction parameter can be determined based on the average of the ratios of the actual demand data to the historical forecast demand data of multiple historical cycles. The correction parameter is updated sequentially over time to improve the accuracy of the correction parameter and further improve the accuracy of the target replenishment data.

[0059] Exemplarily, the data of historical months are calculated, and the historical forecast demand data and actual demand data are compared to obtain the correction parameter X, and the initial replenishment data of the current month*X=the target replenishment data of the current month. At the end of the current month, the actual demand data of the current month is compared with the initial replenishment data*X to update the correction parameter X.

[0060] The technical solution provided in this embodiment obtains predicted demand data by predicting the historical demand data of the material in the historical period. When the initial replenishment data is determined based on the predicted demand data, the initial replenishment data is corrected by setting correction parameters to improve the accuracy of the target replenishment data.

[0061] In some embodiments, in view of the characteristic that the material warehouse has a preset hit rate, when determining the predicted demand data for each material in the material warehouse, the supply list of materials of the material warehouse, that is, the supply material set, is determined based on the preset hit rate. The materials in the supply material set are the supply materials of the material warehouse, and the materials that do not belong to the supply material set are not supplied in the material warehouse.

[0062] Optionally, a supply material set is determined based on a preset hit rate and the predicted demand data of each of the materials, and the material set includes the supply materials. Specifically, the total predicted demand data corresponding to the predicted demand data of each of the materials is counted, that is, the sum of the predicted demand data of each of the materials. The stock quantity is determined based on the total predicted demand data and the preset hit rate. For example, the product of the total predicted demand data and the preset hit rate can be used as the stock quantity. The materials are sorted based on the quantity and / or value of each of the materials, and a supply material set is determined based on the stock quantity and the sorting. Optionally, the material brand dimension is summarized based on the predicted demand data of each of the materials, and the quantity and / or value are sorted based on the summarized data of each brand dimension. Optionally, the quantity and / or value are sorted based on the predicted demand data of each material.

[0063] Taking quantity sorting as an example, for the summary data of the brand dimension or the forecast demand data corresponding to the material, the materials are sorted based on the size of the demand quantity. For materials with the same demand quantity, they can be sorted based on the material unit value. For materials with the same quantity and material unit value, they can be sorted based on the material code to obtain the material sorting. The above sorting is from large to small.

[0064] Taking value sorting as an example, for the summary data of the brand dimension or the predicted demand data corresponding to the material, the purchase value of the material is determined based on the demand quantity and the unit value of the material, and sorting is performed based on the unit value of the material, for example, sorting from small to large based on the purchase value.

[0065] Taking the sorting of quantity and value as an example, for any material, weighted processing is performed based on the order of quantity sorting and the order of value sorting, and then the order of the overall sorting is obtained to form the material sorting.

[0066] Based on the above sorting, the materials in the sorting are marked in turn, and the marked materials are determined as supply materials until the cumulative quantity of the supply materials meets the stock quantity, and the marking is stopped. The marked materials form a supply material set. The supply material set can be displayed in the form of a material list, which is not limited here.

[0067] Accordingly, when any supply material meets the inventory replenishment condition, the initial replenishment data of the supply material is determined based on the predicted demand data of the supply material. The inventory replenishment condition includes: the inventory of the supply material is less than or equal to the replenishment threshold data. The inventory of the supply material in the material warehouse can be determined in real time, and when it is less than or equal to the replenishment threshold data, the replenishment operation of the supply material is triggered. Alternatively, the inventory of the supply material in the material warehouse can be determined regularly, and when it is less than or equal to the replenishment threshold data, the replenishment operation of the supply material is triggered.

[0068] Optionally, the method for determining replenishment threshold data includes: determining a determination coefficient based on the preset hit rate, and determining safety stock data based on the determination coefficient and preset data parameters of the historical period; determining unit time demand data based on the predicted demand data, and determining replenishment threshold data based on the safety stock data and the unit time demand data.

[0069] Among them, the determination coefficient may be positively correlated with the preset hit rate, and the determination method of the determination coefficient is not limited. The preset data parameters of the historical period include but are not limited to the standard deviation, variance, etc. of the forecast demand data of multiple historical periods. Taking the preset data parameters of the historical period as the standard deviation of the forecast demand data of multiple historical periods as an example, the safety stock data can be determined based on the determination coefficient and the standard deviation of the historical period. Exemplarily, the safety stock data is the determination coefficient * the standard deviation of the historical period * sqrt (LT / 30), where LT is a system pre-configured parameter.

[0070] The unit time demand data is determined by the forecast demand data of the forecast period and the duration of the forecast period. For example, the unit time can be 1 day. Correspondingly, the unit time demand data is the average daily demand data, which is determined by the forecast demand data of the forecast period and the number of days in the forecast period. Specifically, the average daily demand data = forecast demand data / number of days in the forecast period.

[0071] The replenishment threshold data may be determined based on the safety stock data and the unit time demand data, for example, it may be safety stock data+LT*unit time demand data.

[0072] In some embodiments, determining initial replenishment data based on predicted demand data for the supply material includes: determining current expected data based on the predicted demand data, and determining initial replenishment data based on one or more of currently available data, replenishable data, and currently missing data and the expected data.

[0073] Optionally, the current expected data may be determined by the ratio of the forecast demand data to the planned replenishment times. Optionally, the current expected data may be determined by the safety stock data, the unit time demand data, and the periodic trigger interval, wherein the periodic trigger interval may be the time interval for periodic determination of the material library. For example, the current expected data may be safety stock data + C * periodic trigger interval * unit time demand data, wherein the parameter C and the periodic trigger interval may be system configuration parameters.

[0074] Among them, the currently available data is the available inventory data in the material library, the replenishable data is the material data that is in the process of replenishment and has not entered the material library, and the currently missing data is the shortage of the material library. Correspondingly, the initial replenishment data = the current expected data - the current available data - the replenishable data + the current missing data.

[0075] On the basis of the above embodiment, the above initial replenishment data is corrected by using correction parameters to obtain target replenishment data.

[0076] Generate replenishment tasks according to target replenishment data to realize material replenishment. Replenishment tasks include purchasing tasks and transfer tasks. When the replenishment material warehouse is not the main warehouse material warehouse, the replenishment task can be a transfer task, such as transferring materials from other material warehouses; when the replenishment material warehouse is the main warehouse material warehouse, the replenishment task can be a purchasing task.

[0077] In some embodiments, the initial replenishment data can be determined based on the QR model. For example, the inventory can be maintained daily. When the inventory is lower than the replenishment threshold data, the order quantity Q is triggered, that is, the expected data for the current time. The data required for the QR model to determine the initial replenishment data is shown in Table 1 below.

[0078] Table 1

[0079]

[0080]

[0081] In some embodiments, the initial replenishment data may be determined based on the QT model, for example, by regularly checking the inventory, and when the sum of the available inventory and the in-transit inventory is less than the replenishment threshold data, the order quantity Q is triggered. The data required for the QT model to determine the initial replenishment data is shown in Table 2 below.

[0082] Table 2

[0083]

[0084] In the above QR model and QT model, the unit time is taken as one day as an example. Correspondingly, the unit time demand data Ed is the average daily demand, and the replenishment threshold data ROP is determined based on the safety stock data ss + system pre-configured parameters LT * unit time demand data Ed.

[0085] Initial replenishment data = current expected data Q - current available data (i.e. available inventory) - replenishable data (i.e. in-transit data and quantity of replenishment requests) + current missing data (i.e. out-of-stock quantity). Optionally, the current expected data Q can be determined based on safety inventory data ss, unit time demand data Ed, and regular trigger interval c; optionally, the current expected data can also be determined by the ratio of predicted demand data to planned replenishment times.

[0086] On the basis of the above-mentioned embodiment, real-time material detection is performed on the material warehouse, and a stock-out alarm is generated when there is a shortage of materials; and a redundancy alarm is generated when there is a material redundancy.

[0087] The technical solution of this embodiment determines the supply material set of the material library based on the preset hit rate of the material library, and performs replenishment processing when any material in the supply material set meets the inventory replenishment conditions, thereby ensuring timely replenishment of materials and avoiding material shortages. At the same time, the initial replenishment quantity is determined based on the predicted demand data, thereby improving the accuracy of replenishment prediction.

[0088] Figure 2 Schematic diagram of the structure of an inventory forecasting device provided by an embodiment of the present invention. Figure 2 As shown, the device comprises:

[0089] The historical data acquisition module 210 is used to acquire the historical demand data of materials in the historical period;

[0090] The demand forecasting module 220 is used to obtain a target forecasting strategy, and to forecast the historical demand data of the material based on the target forecasting strategy to obtain forecast demand data of the material in the forecasting period;

[0091] An initial replenishment data determination module 230, configured to determine initial replenishment data based on the forecast demand data of the material;

[0092] The target replenishment data determination module 240 is used to determine correction parameters based on the historical forecast demand data and actual demand data of the historical period, and determine target replenishment data based on the correction parameters and the initial replenishment data.

[0093] The technical solution of this embodiment obtains predicted demand data by predicting the historical demand data of the material in the historical period. When the initial replenishment data is determined based on the predicted demand data, the initial replenishment data is corrected by setting correction parameters to improve the accuracy of the target replenishment data.

[0094] Based on the above embodiment, optionally, the historical data acquisition module 210 is used to:

[0095] The original demand data of each material in each material library is counted, and the original demand data of each material in the historical period is determined based on the time information of the demand data; the historical demand data of the material in the historical period is determined based on the preset hit rate of the material library and the original demand data of each material in the historical period.

[0096] Based on the above embodiment, optionally, the demand forecasting module 220 is used to: obtain historical forecast demand data of candidate forecasting strategies for historical periods and actual demand data of the historical periods; determine the forecast confidence of the candidate forecasting strategies based on the historical forecast demand data and actual demand data corresponding to the historical periods; and determine the target forecasting strategy based on the forecast confidence of the candidate forecasting strategies.

[0097] Optionally, the candidate prediction strategies include a first prediction strategy and a second prediction strategy;

[0098] The first forecasting strategy is used to: determine the first forecast item of the historical period based on the historical demand data, weight data and seasonal parameters of each of the historical periods, and determine the forecast demand data of the forecast period based on the first forecast items of the historical periods of multiple historical periods and the seasonal parameters of the forecast period;

[0099] The second forecasting strategy is used to determine the average forecast item of the historical period and the trend item of the forecasting period based on the historical demand data of multiple historical periods and seasonal parameters, and determine the forecast demand data of the forecasting period based on the average forecast item and the trend item.

[0100] Based on the above embodiment, the initial replenishment data determination module 230 is further used to:

[0101] Before determining the initial replenishment data based on the predicted demand data of the materials, determining a supply material set based on a preset hit rate and the predicted demand data of each of the materials, wherein the supply material is included in the material set;

[0102] And, in the case where the supply material meets the inventory replenishment condition, initial replenishment data is determined based on the forecast demand data of the supply material.

[0103] Optionally, the supply material determination module 230 is further used for:

[0104] The total predicted demand data corresponding to the predicted demand data of each of the materials is counted, and the stock quantity is determined based on the total predicted demand data and a preset hit rate; the materials are sorted based on the quantity and / or value of each of the materials, and the supply material set is determined based on the stock quantity and the sorting.

[0105] Based on the above embodiment, optionally, the inventory replenishment condition includes: the inventory quantity of the supply material is less than or equal to the replenishment threshold data;

[0106] The replenishment data determination module 240 is used to:

[0107] Determine a determination coefficient based on the preset hit rate, determine safety stock data based on the determination coefficient and preset data parameters of the historical period; determine unit time demand data based on the predicted demand data, and determine replenishment threshold data based on the safety stock data and the unit time demand data.

[0108] Optionally, the replenishment data determination module 240 is further configured to:

[0109] The current expected data is determined based on the predicted demand data, and the initial replenishment data is determined based on one or more items of currently available data, replenishable data and currently missing data and the expected data.

[0110] Based on the above embodiment, optionally, the replenishment data determination module 240 is further used to: determine correction parameters based on the historical forecast demand data and actual demand data of the historical period; and update the replenishment data based on the correction parameters.

[0111] The inventory forecasting device provided in the embodiment of the present invention can execute the inventory forecasting method provided in any embodiment of the present invention, and has the corresponding functional modules and beneficial effects of the execution method.

[0112] Figure 3 1 is a schematic diagram of the structure of an electronic device provided by an embodiment of the present invention. The electronic device 10 is intended to represent various forms of digital computers, such as laptop computers, desktop computers, workstations, personal digital assistants, servers, blade servers, mainframe computers, and other suitable computers. The electronic device may also represent various forms of mobile devices, such as personal digital processing, cellular phones, smart phones, wearable devices (such as helmets, glasses, watches, etc.) and other similar computing devices. The components shown herein, their connections and relationships, and their functions are merely examples and are not intended to limit the implementation of the present invention described and / or required herein.

[0113] like Figure 3As shown, the electronic device 10 includes at least one processor 11, and a memory connected to the at least one processor 11, such as a read-only memory (ROM) 12, a random access memory (RAM) 13, etc., wherein the memory stores a computer program that can be executed by at least one processor, and the processor 11 can perform various appropriate actions and processes according to the computer program stored in the read-only memory (ROM) 12 or the computer program loaded from the storage unit 18 to the random access memory (RAM) 13. In the RAM 13, various programs and data required for the operation of the electronic device 10 can also be stored. The processor 11, the ROM 12, and the RAM 13 are connected to each other through a bus 14. An input / output (I / O) interface 15 is also connected to the bus 14.

[0114] A number of components in the electronic device 10 are connected to the I / O interface 15, including: an input unit 16, such as a keyboard, a mouse, etc.; an output unit 17, such as various types of displays, speakers, etc.; a storage unit 18, such as a disk, an optical disk, etc.; and a communication unit 19, such as a network card, a modem, a wireless communication transceiver, etc. The communication unit 19 allows the electronic device 10 to exchange information / data with other devices through a computer network such as the Internet and / or various telecommunication networks.

[0115] The processor 11 may be a variety of general and / or special processing components with processing and computing capabilities. Some examples of the processor 11 include, but are not limited to, a central processing unit (CPU), a graphics processing unit (GPU), various special artificial intelligence (AI) computing chips, various processors running machine learning model algorithms, a digital signal processor (DSP), and any appropriate processor, controller, microcontroller, etc. The processor 11 executes the various methods and processes described above, such as the inventory forecasting method.

[0116] In some embodiments, the inventory prediction method may be implemented as a computer program, which is tangibly contained in a computer-readable storage medium, such as a storage unit 18. In some embodiments, part or all of the computer program may be loaded and / or installed on the electronic device 10 via the ROM 12 and / or the communication unit 19. When the computer program is loaded into the RAM 13 and executed by the processor 11, one or more steps of the inventory prediction method described above may be performed. Alternatively, in other embodiments, the processor 11 may be configured to execute the inventory prediction method in any other appropriate manner (e.g., by means of firmware).

[0117] Various implementations of the systems and techniques described above herein can be implemented in digital electronic circuit systems, integrated circuit systems, field programmable gate arrays (FPGAs), application specific integrated circuits (ASICs), application specific standard products (ASSPs), systems on chips (SOCs), load programmable logic devices (CPLDs), computer hardware, firmware, software, and / or combinations thereof. These various implementations can include: being implemented in one or more computer programs that can be executed and / or interpreted on a programmable system including at least one programmable processor, which can be a special purpose or general purpose programmable processor that can receive data and instructions from a storage system, at least one input device, and at least one output device, and transmit data and instructions to the storage system, the at least one input device, and the at least one output device.

[0118] The computer program for implementing the inventory forecasting method of the present invention can be written in any combination of one or more programming languages. These computer programs can be provided to a processor of a general-purpose computer, a special-purpose computer or other programmable data processing device, so that when the computer program is executed by the processor, the functions / operations specified in the flow chart and / or block diagram are implemented. The computer program can be executed completely on the machine, partially on the machine, partially on the machine as a stand-alone software package and partially on a remote machine, or completely on a remote machine or server.

[0119] An embodiment of the present invention further provides a computer-readable storage medium, wherein the computer-readable storage medium stores computer instructions, and the computer instructions are used to enable a processor to execute an inventory forecasting method, the method comprising:

[0120] Acquire historical demand data of materials in a historical period; acquire a target forecasting strategy, and perform forecasting processing on the historical demand data of the materials based on the target forecasting strategy to obtain forecast demand data of the materials in the forecasting period; determine initial replenishment data based on the forecast demand data of the materials; determine correction parameters based on the historical forecast demand data and actual demand data of the historical period, and determine target replenishment data based on the correction parameters and the initial replenishment data.

[0121] In the context of the present invention, a computer-readable storage medium may be a tangible medium that may contain or store a computer program for use by or in combination with an instruction execution system, device or equipment. A computer-readable storage medium may include, but is not limited to, electronic, magnetic, optical, electromagnetic, infrared, or semiconductor systems, devices or equipment, or any suitable combination of the foregoing. Alternatively, a computer-readable storage medium may be a machine-readable signal medium. A more specific example of a machine-readable storage medium may include an electrical connection based on one or more lines, 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 foregoing.

[0122] To provide interaction with a user, the systems and techniques described herein may be implemented on an electronic device having: a display device (e.g., a CRT (cathode ray tube) or LCD (liquid crystal display) monitor) for displaying information to the user; and a keyboard and a pointing device (e.g., a mouse or trackball) through which the user can provide input to the electronic device. Other types of devices may also be used to provide interaction with the user; for example, the feedback provided to the user may be any form of sensory feedback (e.g., visual feedback, auditory feedback, or tactile feedback); and input from the user may be received in any form (including acoustic input, voice input, or tactile input).

[0123] The systems and techniques described herein may be implemented in a computing system that includes backend components (e.g., as a data server), or a computing system that includes middleware components (e.g., an application server), or a computing system that includes frontend components (e.g., a user computer with a graphical user interface or a web browser through which a user can interact with implementations of the systems and techniques described herein), or a computing system that includes any combination of such backend components, middleware components, or frontend components. The components of the system may be interconnected by any form or medium of digital data communication (e.g., a communication network). Examples of communication networks include: a local area network (LAN), a wide area network (WAN), a blockchain network, and the Internet.

[0124] A computing system may include a client and a server. The client and the server are generally remote from each other and usually interact through a communication network. The client and server relationship is generated by computer programs running on the respective computers and having a client-server relationship with each other. The server may be a cloud server, also known as a cloud computing server or cloud host, which is a host product in the cloud computing service system to solve the defects of difficult management and weak business scalability in traditional material hosts and VPS services.

[0125] It should be understood that the various forms of processes shown above can be used to reorder, add or delete steps. For example, the steps described in the present invention can be executed in parallel, sequentially or in different orders, as long as the desired results of the technical solution of the present invention can be achieved, and this document does not limit this.

[0126] The above specific implementations do not constitute a limitation on the protection scope of the present invention. It should be understood by those skilled in the art that various modifications, combinations, sub-combinations and substitutions can be made according to design requirements and other factors. Any modification, equivalent substitution and improvement made within the spirit and principle of the present invention should be included in the protection scope of the present invention.

Claims

1. A method for inventory forecasting, characterized in that: include: Obtain historical demand data for materials within the historical period; Acquire a target forecasting strategy, and perform forecasting processing on the historical demand data of the material based on the target forecasting strategy to obtain forecast demand data of the material in the forecasting period; Determining initial replenishment data based on the forecast demand data of the material; A correction parameter is determined based on the historical forecast demand data and the actual demand data of the historical period, and a target replenishment data is determined based on the correction parameter and the initial replenishment data.

2. The method according to claim 1, characterized in that The obtaining of historical demand data of materials in the historical period includes: Counting the original demand data of each material in each material library, and determining the original demand data of each material in the historical period based on the time information of the demand data; Based on the preset hit rate of the material library and the original demand data of each material in the historical period, the historical demand data of the material in the historical period is determined.

3. The method according to claim 1, characterized in that The target prediction strategy is obtained, including: Obtain historical forecast demand data for a historical period and actual demand data for the historical period by a candidate forecast strategy; Determining the prediction confidence of the candidate prediction strategy based on the historical prediction demand data and the actual demand data corresponding to the historical period; A target prediction strategy is determined based on the prediction confidence of the candidate prediction strategies.

4. The method according to claim 3, characterized in that The candidate prediction strategies include a first prediction strategy and a second prediction strategy; The first forecasting strategy is used to: determine the first forecast item of the historical period based on the historical demand data, weight data and seasonal parameters of each of the historical periods, and determine the forecast demand data of the forecast period based on the first forecast items of the historical periods of multiple historical periods and the seasonal parameters of the forecast period; The second forecasting strategy is used to determine the average forecast item of the historical period and the trend item of the forecasting period based on the historical demand data of multiple historical periods and seasonal parameters, and determine the forecast demand data of the forecasting period based on the average forecast item and the trend item.

5. The method according to claim 1, characterized in that Before determining the initial replenishment data based on the forecast demand data of the material, it also includes: Determining a supply material set based on a preset hit rate and the predicted demand data of each of the materials, wherein the material set includes the supply material; Accordingly, determining the initial replenishment data based on the forecast demand data of the material includes: In a case where the supply material meets the inventory replenishment condition, initial replenishment data is determined based on the forecast demand data of the supply material.

6. The method according to claim 5, characterized in that The step of determining the supply material set based on the preset hit rate and the predicted demand data of each material includes: Counting the total predicted demand data corresponding to the predicted demand data of each of the materials, and determining the stocking quantity based on the total predicted demand data and a preset hit rate; The materials are sorted based on the quantity and / or value of each of the materials, and a supply material set is determined based on the stock quantity and the sorting.

7. The method according to claim 5, characterized in that The inventory replenishment conditions include: the inventory of the supply material is less than or equal to the replenishment threshold data; The method for determining the replenishment threshold data includes: Determine a determination coefficient based on the preset hit rate, and determine safety stock data based on the determination coefficient and preset data parameters of the historical period; Demand data per unit time is determined based on the predicted demand data, and replenishment threshold data is determined based on the safety stock data and the demand data per unit time.

8. The method according to claim 5, characterized in that The determining of initial replenishment data based on the forecast demand data of the supply material includes: The current expected data is determined based on the predicted demand data, and the initial replenishment data is determined based on one or more items of currently available data, replenishable data and currently missing data and the expected data.

9. An inventory forecasting device, characterized in that: include: The historical data acquisition module is used to obtain the historical demand data of materials in the historical period; A demand forecasting module is used to obtain a target forecasting strategy, and to forecast the historical demand data of the material based on the target forecasting strategy to obtain forecast demand data of the material in the forecasting period; An initial replenishment data determination module, used to determine initial replenishment data based on the forecast demand data of the material; The target replenishment data determination module is used to determine correction parameters based on the historical forecast demand data and actual demand data of the historical period, and determine target replenishment data based on the correction parameters and the initial replenishment data.

10. An electronic device, characterized in that: The electronic device comprises: at least one processor; and a memory communicatively connected to the at least one processor; wherein, The memory stores a computer program executable by the at least one processor, and the computer program is executed by the at least one processor so that the at least one processor can perform the inventory forecasting method according to any one of claims 1 to 8.

11. A computer-readable storage medium, characterized in that: The computer-readable storage medium stores computer instructions, and the computer instructions are used to enable a processor to implement the inventory forecasting method according to any one of claims 1 to 8 when executed.

Images