Material demand prediction and management method and device, computer device and storage medium

Abstract

The application relates to a material demand prediction and management method and device, computer equipment and a storage medium. The prediction method comprises the following steps: acquiring the express amount and the use amount of a target type material in a historical period corresponding to a to-be-predicted period; obtaining a first predicted demand amount of the target type material in the to-be-predicted period according to the time characteristics of the to-be-predicted period and the use amount of the target type material in the historical period; obtaining a second predicted demand amount of the target type material in the to-be-predicted period according to the time characteristics of the to-be-predicted period, the express amount in the historical period and the use amount proportion of the target type material in the to-be-predicted period; and determining the predicted demand amount of the target type material in the to-be-predicted period based on the first predicted demand amount and the second predicted demand amount. The method can improve the prediction accuracy.

Description

Technical Field

[0001] This application relates to the field of logistics technology, and in particular to a method, apparatus, computer equipment, and storage medium for material demand forecasting and management. Background Technology

[0002] With the development of the logistics industry, express delivery services are playing an increasingly important role in society. During the transit process, to prevent damage or loss of express items, protective measures are usually taken when packaging them, such as using folders, cardboard boxes, foam boxes, and fillers. As the number of express packages increases, the demand for materials also increases, making material management (including material requisition and issuance) more difficult and complex.

[0003] Currently, material requests at delivery points are typically made by couriers who subjectively assess the required quantity and submit a request to the material distribution department. Because couriers cannot accurately determine the necessary quantities, the requested quantities may not match the actual needs. For example, some delivery points may experience material shortages, while others may have material stockpiles, impacting packaging and shipping efficiency and easily leading to material waste. Summary of the Invention

[0004] Therefore, it is necessary to provide a method, apparatus, computer equipment, and storage medium for improving the accuracy of material demand forecasting and management in response to the above-mentioned technical problems.

[0005] A material demand forecasting method, the method comprising:

[0006] Obtain the volume of express parcels and the usage of target type materials within the historical time period corresponding to the time period to be predicted;

[0007] Based on the time characteristics of the period to be predicted and the usage of the target type of material in the historical period, the first predicted demand of the target type of material in the period to be predicted is obtained.

[0008] Based on the time characteristics of the period to be predicted, the volume of express parcels in the historical period, and the usage ratio of the target type of material in the period to be predicted, a second predicted demand for the target type of material in the period to be predicted is obtained.

[0009] Based on the first predicted demand and the second predicted demand, the predicted demand for the target type of material during the predicted period is determined.

[0010] A material demand forecasting device, the device comprising:

[0011] The acquisition module is used to acquire the volume of express parcels and the usage of target type materials in the historical period corresponding to the period to be predicted;

[0012] The first prediction module is used to obtain the first predicted demand of the target type material in the period to be predicted based on the time characteristics of the period to be predicted and the usage of the target type material in the historical period.

[0013] The second prediction module is used to obtain the second predicted demand for the target type of material in the period to be predicted based on the time characteristics of the period to be predicted, the volume of express parcels in the historical period, and the usage ratio of the target type of material in the period to be predicted.

[0014] The determination module is used to determine the predicted demand of the target type material during the predicted period based on the first predicted demand and the second predicted demand.

[0015] A computer device includes a memory and a processor, the memory storing a computer program, the processor executing the computer program to implement the steps of the material demand forecasting method.

[0016] A computer-readable storage medium having a computer program stored thereon, which, when executed by a processor, implements the steps of the material demand forecasting method.

[0017] A material management method, the method comprising:

[0018] When the material application conditions corresponding to the forecast period are met, the inventory of the target type of material and the forecast demand of the target type of material in the forecast period are obtained. The forecast demand is obtained according to the material demand forecasting method.

[0019] Based on the inventory and forecasted demand of the target type of material, the target demand for the target type of material during the forecast period is determined, whereby the target demand represents the demand that needs to be requested from the material issuer.

[0020] A material management device, the device comprising:

[0021] The acquisition module is used to acquire the inventory of the target type of material and the predicted demand of the target type of material during the predicted period when the material application conditions corresponding to the predicted period are met. The predicted demand is obtained through the material demand forecasting device.

[0022] The determination module is used to determine the target demand for the target type of material during the forecast period based on the inventory and forecast demand of the target type of material. The target demand represents the demand that needs to be requested from the material issuer.

[0023] A computer device includes a memory and a processor, the memory storing a computer program, the processor executing the computer program to implement the steps of the material management method.

[0024] A computer-readable storage medium having a computer program stored thereon, which, when executed by a processor, implements the steps of the material management method.

[0025] The aforementioned material demand forecasting and management methods, devices, computer equipment, and storage media obtain a first forecast result for the demand of target type materials based on the time characteristics of the period to be forecasted and the usage of target type materials in the corresponding historical period. Based on the time characteristics of the period to be forecasted, the volume of express shipments in the corresponding historical period, and the usage ratio of target type materials in the period to be forecasted, a second forecast result for the demand of target type materials is obtained. Combining the two forecast results to determine the final forecast demand can improve forecast accuracy, make the forecasted material demand more accurate and reasonable, help reduce waste caused by material stockpiling, and avoid material shortages affecting dispatch efficiency. Attached Figure Description

[0026] Figure 1 This is a flowchart illustrating a material demand forecasting method in one embodiment;

[0027] Figure 2 This is a flowchart illustrating the first predicted demand of a target type of material in a predicted period based on the time characteristics of the predicted period and the usage of the target type of material in historical periods, in one embodiment.

[0028] Figure 3 This is a flowchart illustrating the training process of the first prediction model in one embodiment;

[0029] Figure 4 This is a flowchart illustrating the steps of obtaining the predicted parcel volume for a given time period based on the time characteristics of that time period and the parcel volume in historical time periods, as shown in one embodiment.

[0030] Figure 5 This is a flowchart illustrating the training process of the second prediction model in one embodiment;

[0031] Figure 6 This is a flowchart illustrating a method for determining the percentage of usage of a target type of material within a given time period, as illustrated in one embodiment.

[0032] Figure 7 This is a flowchart illustrating a material management method in one embodiment;

[0033] Figure 8 This is a structural block diagram of a material demand forecasting device in one embodiment;

[0034] Figure 9 This is a structural block diagram of a material management device in one embodiment;

[0035] Figure 10 This is a structural block diagram of a material management device in one embodiment;

[0036] Figure 11 This is an internal structural diagram of a computer device in one embodiment;

[0037] Figure 12 This is an internal structural diagram of a computer device in one embodiment. Detailed Implementation

[0038] To make the objectives, technical solutions, and advantages of this application clearer, the following detailed description is provided in conjunction with the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are merely illustrative and not intended to limit the scope of this application.

[0039] In one embodiment, such as Figure 1 As shown, a material demand forecasting method is provided. This embodiment illustrates the method applied to a server as an example. It is understood that the method can also be applied to a terminal, or to a system including both a terminal and a server, and is implemented through the interaction between the terminal and the server. In this embodiment, the method includes the following steps S102 to S108.

[0040] S102, obtain the volume of express parcels and the usage of target type materials in the historical period corresponding to the period to be predicted.

[0041] The period to be predicted is a future period, and the corresponding historical period is the period preceding the period to be predicted. For example, using a week as the prediction period, the period to be predicted could be the next week, assuming T... i Let i represent the week number of the period to be predicted (the first week of each year is 1, and so on, counting backwards), i.e., T i Let T represent week i. The historical period corresponding to the period to be predicted is the weeks preceding week i. i-n (in) represents the week number of the historical period, i.e., T. i-n This indicates the (in)th week. n can take multiple values, such as positive integers like 1 and 2, meaning that the historical period includes multiple weeks.

[0042] The volume of parcels within a historical period refers to the number of parcels collected within that period, i.e., the number of parcels awaiting packing and shipment. The usage of target type materials within a historical period refers to the number of parcels packaged using target type materials. Target type indicates the type of material for which demand forecasting is required, which may include, but is not limited to, folders, foam boxes, and various types of cardboard boxes. Cardboard box types may include, but are not limited to, F1, F2, F2s, F3, and F4 models. Different parcel types use different types of materials. For example, parcels may be categorized as document parcels, fresh produce parcels, and other parcels. Document parcels may use folders, fresh produce parcels may use foam boxes, and other parcels may use various types of cardboard boxes. In some cases, logistics outlets may not need to provide corresponding packaging materials for parcels. For example, parcels where users bring their own packaging materials may not be counted in the number of parcels packaged using target type materials.

[0043] S104. Based on the time characteristics of the period to be predicted and the usage of the target type of material in historical periods, obtain the first predicted demand of the target type of material in the period to be predicted.

[0044] The time characteristics of the period to be predicted may include, but are not limited to, the following: the year, month, and week of the period, and whether the period falls at the beginning or end of the year. The periods defined as beginning and end of the year can be set according to actual needs; for example, January of each year can be set as the beginning of the year period, and December of each year as the end of the year period.

[0045] For any target material type, a corresponding material demand forecasting model can be pre-established to predict the demand for that target material type during the forecast period. Specifically, for any target material type, the input features to the corresponding material demand forecasting model can be determined based on the time characteristics of the forecast period and the usage of that target material type in historical periods. The model then maps these input features and outputs the first predicted demand for that target material type during the forecast period. This first predicted demand can be understood as a direct prediction of the demand for the target material type.

[0046] S106. Based on the time characteristics of the period to be predicted, the volume of express parcels in historical periods, and the usage ratio of target type materials in the period to be predicted, obtain the second predicted demand of target type materials in the period to be predicted.

[0047] For any target material type, the usage percentage of that target material type during the forecast period represents the proportion of parcels packaged using that target material type during the forecast period to the total number of parcels during the forecast period. Since the usage percentage of target material type is relatively stable, the usage percentage of that target material type during the forecast period can be determined by the usage percentage of that target material type in the corresponding historical period, or it can be taken as a preset empirical value.

[0048] In one embodiment, the step of obtaining the second predicted demand for target type materials in the predicted period based on the time characteristics of the predicted period, the volume of express shipments in historical periods, and the usage ratio of target type materials in the predicted period may specifically include: obtaining the predicted volume of express shipments in the predicted period based on the time characteristics of the predicted period and the volume of express shipments in historical periods; and obtaining the second predicted demand for target type materials in the predicted period based on the predicted volume of express shipments in the predicted period and the usage ratio of target type materials.

[0049] A pre-established express delivery volume prediction model can be used to predict the volume of express deliveries within a given time period. Specifically, the input features to the prediction model can be determined based on the time characteristics of the period to be predicted and the express delivery volume in historical periods. The model then maps these input features and outputs the predicted express delivery volume for the period to be predicted. Then, for any target material type, a second predicted demand for that target material type is obtained based on the predicted express delivery volume and the usage percentage of that target material type within the period to be predicted. In essence, the second predicted demand is obtained by first predicting the total number of express deliveries within the period to be predicted, and then using this prediction along with the usage percentage of the target material type.

[0050] S108, Based on the first and second predicted demand quantities, determine the predicted demand quantity of the target type material during the forecast period.

[0051] As mentioned earlier, the first and second forecasted demand quantities are demand forecasts obtained through different forecasting methods. The two forecasts can complement each other, making the forecasted demand quantity determined based on the two forecasts more accurate and reasonable.

[0052] In the above material demand forecasting method, a first forecast result of the demand for target type materials is obtained based on the time characteristics of the period to be forecasted and the usage of target type materials in the corresponding historical period. A second forecast result of the demand for target type materials is obtained based on the time characteristics of the period to be forecasted, the volume of express shipments in the corresponding historical period, and the usage ratio of target type materials in the period to be forecasted. Combining the two forecast results to determine the final forecast demand can improve forecast accuracy, make the forecast material demand more accurate and reasonable, help reduce waste caused by material stockpiling, and avoid material shortages affecting dispatch efficiency.

[0053] In one embodiment, such as Figure 2 As shown, the steps for obtaining the first predicted demand of the target type material in the predicted period based on the time characteristics of the predicted period and the usage of the target type material in historical periods may specifically include the following steps S202 to S204.

[0054] S202, based on the time characteristics of the period to be predicted and the usage of the target type of material in historical periods, the first input features are obtained.

[0055] The first input feature refers to the feature used to predict the demand for the target type of material during the forecast period. It may include the time characteristics of the forecast period and the features used to characterize the historical usage of the target type of material.

[0056] In one embodiment, the period to be predicted is the week following the current week, and the corresponding historical periods include: a first historical period and a second historical period. The first historical period includes a first preset number of historical weeks before the period to be predicted, and the second historical period includes a second preset number of historical weeks before the period to be predicted. The time features include: the year, month, and week number of the period to be predicted, and whether the period to be predicted is at the beginning or end of the year. The first input features include: time features, the usage of the target type material in each historical week of the first historical period, and the mean, sum, maximum, and minimum usage of the target type material in each historical week of the second historical period.

[0057] Here, the current time represents the forecast time, that is, the time when the demand for each target type of material is predicted within the forecast period. In implementation, a one-week forecast cycle can be used, and a fixed time can be set for forecasting each week. For example, 20:00 every Sunday can be selected as the forecast time to predict the demand for each target type of material in the following week (from Monday to Sunday).

[0058] The time characteristics can include the following five features: the year (represented by year), month (represented by month), week (represented by week), and whether it is at the beginning of the year (represented by is_year_start) and the end of the year (represented by is_year_end). Specifically, the year, month, week, and whether it is at the beginning or end of the year can be determined based on the year, month, week, and whether any date in the period to be predicted is at the beginning or end of the year. For example, if the period to be predicted is from next Monday to next Sunday, the year, month, week, and whether it is at the beginning or end of the year can be determined based on the year, month, week, and whether it is at the beginning or end of the year.

[0059] The first and second preset quantities can be set according to actual needs and are not limited here. The first and second preset quantities can be the same or different. In one embodiment, the second preset quantity is less than the first preset quantity. For example, the period to be predicted is week i (T). i The first historical period can be selected from the past 10 weeks, that is, the first historical period includes the following 10 historical weeks: T i-10 T i-9 T i-8 T i-7 T i-6 T i-5 T i-4 T i-3 T i-2 and T i-1 The corresponding second historical period can be selected from the past 4 weeks, that is, the second historical period includes the following 4 historical weeks: T i-10 T i-9 T i-8 T i-7 .

[0060] For target type a, the usage of type a materials in each historical week during the first historical period are as follows: B i-10,a B i-9,a B i-8,a B i-7,a B i-6,a B i-5,a B i-4,a B i-3,a B i-2,a and B i-1,a The usage of type a material in each historical week during the second historical period was as follows: B i-10,a B i-9,a B i-8,a and B i-7,a , for B i-10,a Bi-9,a B i-8,a and B i-7,a By averaging, we can obtain the average usage of type a material in each historical week of the second historical period (using B). mean,a (Indicates); for B i-10,a B i-9,a B i-8,a and B i-7,a Summing yields the total usage of type a material in each historical week of the second historical period (using B). sum,a (Indicates); Take B i-10,a B i-9,a B i-8,a and B i-7,a The maximum value in B is taken as the maximum usage of type a material in each historical week of the second historical period (using B). max,a (Indicates); Take B i-10,a B i-9,a B i-8,a and B i-7,a The minimum value in B is taken as the minimum usage of type a material in each historical week of the second historical period (using B). min,a express).

[0061] Based on the data from the above embodiments, the first input feature specifically includes the following 19 features: year, month, week, is_year_start, is_year_end, B i-10,a B i-9,a B i-8,a B i-7,a B i-6,a B i-5,a B i-4,a B i-3,a B i-2,a B i-1,a B mean,a B sum,a B max,a B min,a It should be noted that the first input feature is not limited to the features described above. In other embodiments, it may include more or fewer features than those described above, and there is no limitation on this.

[0062] S204. Using the first prediction model corresponding to the target type material, prediction is made based on the first input features to obtain the first predicted demand of the target type material in the period to be predicted.

[0063] The first prediction model is used to predict the demand for materials. Each target material type can correspond to one first prediction model. For example, for folder materials, the corresponding first prediction model is used to predict the demand for folder materials. Specifically, the first input features can be input into the first prediction model. The first prediction model maps based on the first input features and outputs the first predicted demand for the target material type within the predicted time period.

[0064] In one embodiment, using network outlets as the unit of measurement and a weekly statistical period, a first predictive model is trained based on the historical weekly material usage statistics of each network outlet to predict the demand for various target material types at that network outlet. For example... Figure 3 As shown, for any target type of material, the training process of its corresponding first prediction model may include the following steps S302 to S308.

[0065] S302, obtain the first sample time period and its corresponding first sample label. The first sample label represents the actual usage of the target type material within the first sample time period.

[0066] The first sample period is a historical period used to train the first prediction model. The actual usage of the target type material in the first sample period (i.e., the actual number of express parcels packaged with the target type material in the first sample period) is known, and the first sample label corresponding to the first sample period is the actual usage.

[0067] S304. Based on the time characteristics of the first sample period and the usage of the target type material in the first sample historical period corresponding to the first sample period, obtain the first sample input characteristics.

[0068] The first sample time period corresponds to the first sample historical time period, which is the time period preceding the first sample time period. For a detailed explanation of the first sample input features, please refer to the description of the first input features in the previous embodiment; it will not be repeated here.

[0069] S306, using the first model to be trained to make predictions based on the input features of the first sample, to obtain the predicted usage of the target type material within the first sample time period.

[0070] The first sample input features are input into the first training model. The first training model maps based on the first sample input features and outputs the predicted usage of the target type material within the first sample period. This predicted usage can be understood as the number of express parcels predicted to be packaged using the target type material within the first sample period based on historical data prior to the first sample period. In one embodiment, the first training model can be a time series prediction model built using the XGBoost algorithm.

[0071] S308. Based on the predicted usage and the first sample label, adjust the parameters of the first model to be trained until the training termination condition is met, and obtain the trained first prediction model.

[0072] In one embodiment, a loss function for a first prediction model can be established based on the mean squared error between the predicted usage and the corresponding actual usage. The training objective of this model is to make the predicted usage as close as possible to the corresponding actual usage. The training termination condition can be that the value of the loss function is less than a first threshold. This first threshold can be set according to actual needs and is not limited here.

[0073] Model training can obtain the mapping relationship between the first input feature and the output value (i.e. the predicted material demand). After the model training is completed, the first input feature, determined based on the time characteristics of the period to be predicted and the historical usage of the target type of material, is input into the trained first prediction model to obtain the first predicted demand of the target type of material in the period to be predicted.

[0074] In one embodiment, such as Figure 4 As shown, the steps for obtaining the predicted parcel volume for the predicted period based on the time characteristics of the predicted period and the parcel volume in historical periods can specifically include the following steps S402 to S404.

[0075] S402, based on the time characteristics of the period to be predicted and the volume of express parcels in historical periods, obtain the second input features.

[0076] The second input feature refers to the feature used to predict the volume of express shipments within the predicted period. It may include the temporal features of the predicted period and features used to characterize the historical volume of express shipments.

[0077] In one embodiment, the period to be predicted is the week following the current week, and the corresponding historical periods include: a third historical period and a fourth historical period. The third historical period includes a third preset number of historical weeks before the period to be predicted, and the fourth historical period includes a fourth preset number of historical weeks before the period to be predicted. The time features include: the year, month, and week number of the period to be predicted, and whether the period to be predicted is at the beginning or end of the year. The second input features include: the time features, the number of express shipments in each historical week of the third historical period, and the mean, sum, maximum, and minimum value of the number of express shipments in each historical week of the fourth historical period.

[0078] Specific details regarding the time characteristics can be found in the preceding embodiments and will not be repeated here. The third and fourth preset quantities can be set according to actual needs and are not limited here. The third and fourth preset quantities can be the same or different. In one embodiment, the fourth preset quantity is less than the third preset quantity. For example, the period to be predicted is week i (T... i The corresponding third historical period can be selected from the past 10 weeks, that is, the third historical period includes the following 10 historical weeks: T i-10 T i-9 T i-8 T i-7 T i-6 T i-5 T i-4 T i-3 T i-2 and T i-1 The corresponding fourth historical period can be selected from the past four weeks, that is, the fourth historical period includes the following four historical weeks: T i-10 T i-9 T i-8 T i-7 .

[0079] The parcel volumes for each historical week in the third historical period were as follows: L i-10 L i-9 L i-8 L i-7 L i-6 L i-5 L i-4 L i-3 L i-2 and L i-1 The parcel volumes for each historical week in the fourth historical period were as follows: L i-10 L i-9 L i-8 and L i-7 , for L i-10 L i-9 L i-8 and L i-7 Taking the average, we can obtain the mean value of the number of express parcels in each historical week within the fourth historical period (denoted by L). mean (Indicates); for L i-10 L i-9 L i-8 and L i-7 Summing yields the total number of parcels in each historical week within the fourth historical period (using L). sum (Indicates); Take L i-10 L i-9 L i-8 and L i-7The maximum value in L is used as the maximum value of the express shipment volume in each historical week within the fourth historical period (denoted by L). max (Indicates); Take L i-10 L i-9 L i-8 and L i-7 The minimum value in L is used as the minimum value of the express shipment volume in each historical week of the fourth historical period (denoted by L). min express).

[0080] Based on the data from the above embodiments, the second input features specifically include the following 19 features: year, month, week, is_year_start, is_year_end, L i-10 L i-9 L i-8 L i-7 L i-6 L i-5 L i-4 L i-3 L i-2 L i-1 L mean L sum L max L min It should be noted that the second input feature is not limited to the features described above. In other embodiments, it may include more or fewer features than those described above, and there is no limitation on this.

[0081] S404: Using the second prediction model, prediction is made based on the second input features to obtain the predicted number of express parcels within the predicted time period.

[0082] The second prediction model is used to predict the volume of express shipments. Specifically, the second input features can be input into the second prediction model, which then maps the second input features and outputs the predicted volume of express shipments within the predicted time period.

[0083] In one embodiment, using the network outlet as the unit of measurement and a weekly statistical period, a second prediction model is trained based on the historical weekly parcel collection statistics of the network outlet to predict the parcel volume for that outlet. For example... Figure 5 As shown, the training process of the second prediction model may include the following steps S502 to S508.

[0084] S502, obtain the second sample time period and its corresponding second sample label, where the second sample label represents the actual number of express parcels within the second sample time period.

[0085] The second sample period is a historical period used to train the second prediction model. The actual number of parcels in the second sample period (i.e., the actual number of parcels collected in the second sample period) is known, and the second sample label corresponding to the second sample period is the actual number of parcels.

[0086] S504. Based on the time characteristics of the second sample period and the number of express parcels in the second historical period corresponding to the second sample period, the second sample input characteristics are obtained.

[0087] The second sample time period corresponds to the second sample historical time period, which is the time period preceding the second sample time period. For a detailed explanation of the second sample input features, please refer to the description of the second input features in the previous embodiment; it will not be repeated here.

[0088] S506, using the second model to be trained to make predictions based on the input features of the second sample, to obtain the predicted number of express parcels within the second sample time period.

[0089] The second sample input features are fed into a second training model. The second training model maps these features to output the predicted parcel volume for the second sample period. This predicted parcel volume can be understood as the number of parcels predicted to be collected during the second sample period based on historical data prior to the second sample period. In one embodiment, the second training model can be a time series prediction model built using the XGBoost algorithm.

[0090] S508: Based on the predicted parcel volume and corresponding second sample labels within the second sample time period, adjust the parameters of the first model to be trained until the training termination condition is met, and obtain the trained second prediction model.

[0091] In one embodiment, a loss function for a second prediction model can be established based on the mean squared error between the predicted parcel volume and the corresponding actual parcel volume. The training objective of this model is to make the predicted parcel volume as close as possible to the corresponding actual parcel volume. The training termination condition can be that the value of the loss function is less than a second threshold. This second threshold can be set according to actual needs and is not limited here.

[0092] Model training can obtain the mapping relationship between the second input feature and the output value (i.e. the predicted number of parcels). After the model training is completed, the second input feature, which is determined based on the time feature of the period to be predicted and the historical parcel receipt situation, is input into the trained second prediction model to obtain the predicted number of parcels in the period to be predicted.

[0093] In one embodiment, such as Figure 6 As shown, the method for determining the usage percentage of the target type of material during the forecast period includes the following steps S602 to S608.

[0094] S602, obtain the number of express shipments in each target historical period corresponding to the period to be predicted, the first number of express shipments corresponding to the express shipment type associated with the target type material, and the second number of express shipments that used the target type material.

[0095] The parcel volume within the target historical period refers to the total number of parcels collected by the branch within the target historical period. The first parcel volume refers to the number of parcels of the type associated with the target type of material among the parcels collected, and the second parcel volume refers to the number of parcels of the type that were packaged using the target type of material.

[0096] In one embodiment, the number of parcels is counted using the network outlet as the unit, a week as the statistical period, and the waybill number, parcel type, and material type as dimensions, to obtain the weekly parcel volume, the first parcel volume, and the second parcel volume. The period to be predicted is the i-th week (T). i The corresponding target historical period can be selected from the past N weeks, where N represents a positive integer. The specific value can be set according to actual needs. Each target historical period is represented by T. i-y This indicates that y takes values ​​of 1, 2, ..., N.

[0097] S604: Based on the ratio of the first express shipment volume to the total express shipment volume in each target historical period, obtain the predicted proportion of the first express shipment volume in the period to be predicted.

[0098] Specifically, based on the ratio of the first parcel volume to the total parcel volume in each target historical period, the proportion of the first parcel volume in each target historical period is obtained. The average of the proportions of the first parcel volume in each target historical period is used as the predicted proportion of the first parcel volume in the period to be predicted. For target type 'a', assuming its associated parcel type is A, the predicted proportion of the first parcel volume in the period to be predicted (using γ) is... i,A The formula for calculating (represented) can be as follows:

[0099]

[0100] Where i represents the week number of the period to be predicted, (iy) represents the week number of each target historical period, and L i-y L represents the number of parcels collected in week (iy). i-y,A This indicates the number of parcels of type A among the parcels collected in week (iy), and N represents the number of the target historical period, which can be 20.

[0101] S606: Based on the ratio of the second express volume to the first express volume in each target historical period, obtain the predicted proportion of the second express volume in the period to be predicted.

[0102] Specifically, based on the ratio of the second express shipment volume to the first express shipment volume within each target historical period, the proportion of the second express shipment volume within each target historical period is obtained. The average of the proportions of the second express shipment volume within each target historical period is then used as the predicted proportion of the second express shipment volume within the period to be predicted. For target type a, the predicted proportion of the second express shipment volume within the period to be predicted (denoted by ε) is... i,a The formula for calculating (represented) can be as follows:

[0103]

[0104] Where i represents the week number of the period to be predicted, (iy) represents the week number of each target historical period, and L i-y,A This indicates the number of parcels of type A among the parcels collected in week (iy), and B. i-y,a This indicates the quantity of type A parcels collected in week (iy) that used type a materials. N represents the quantity of the target historical period, which can be 20.

[0105] S608. Based on the product of the predicted proportion of the first express shipment volume and the predicted proportion of the second express shipment volume, determine the usage proportion of the target type material during the forecast period.

[0106] For target type a, the usage percentage of type a materials during the forecast period (using...) The formula for calculating (represented) can be as follows:

[0107]

[0108] In one embodiment, the step of obtaining the second predicted demand for target type materials in the predicted period based on the predicted volume of express shipments and the usage ratio of target type materials in the predicted period can specifically be: determining the second predicted demand for target type materials in the predicted period based on the product of the predicted volume of express shipments and the usage ratio of target type materials in the predicted period.

[0109] For target type a, the second forecasted demand (C) for material type a during the forecast period. i,a The formula for calculating ) can be as follows:

[0110]

[0111] Among them, L i This represents the predicted volume of express parcels for the period to be predicted. This indicates the percentage of type A materials used during the forecast period.

[0112] In one embodiment, the step of determining the predicted demand of a target type of material within a forecast period based on a first predicted demand and a second predicted demand may specifically be: determining the predicted demand of the target type of material within a forecast period based on the average of the first predicted demand and the second predicted demand.

[0113] For target type a, the predicted demand (F) of material type a during the forecast period. i,a The formula for calculating ) can be as follows:

[0114] F i,a =k*(0.5*B) i,a +0.5*C i,a )

[0115] Among them, B i,a C represents the first forecasted demand for material type a during the forecast period. i,a This represents the second predicted demand for material type A during the forecast period. k is a fixed coefficient, and its value can be set according to actual demand; there is no limitation here. For example, k can be set to 1.1 to ensure that the final predicted demand can meet the actual demand as much as possible.

[0116] It should be noted that the method for forecasting the demand of other types of materials during the forecast period is similar to that for type A materials, and will not be repeated here. Through the above examples, the predicted demand for various target types of materials during the forecast period can be obtained.

[0117] In one embodiment, such as Figure 7 As shown, a material management method is provided, which is applied to the material management system of a branch office. The method includes the following steps S702 to S704.

[0118] S702, when the material application conditions corresponding to the forecast period are met, obtain the inventory of the target type material and the forecast demand of the target type material in the forecast period.

[0119] Meeting the material application conditions corresponding to the forecast period can specifically refer to meeting the material application time corresponding to the forecast period. For example, a branch can use Friday of each week as the material application date for the following week (the period included in the following week can be from this Saturday to next Friday). That is, at Friday of each week, the material demand for the following week is predicted, and the required materials are applied for from the material issuer.

[0120] The inventory levels of various material types can be obtained from the material inventory data of the network points. The predicted demand for the target material type during the forecast period can be obtained from the methods and examples described above, and will not be repeated here.

[0121] S704. Based on the inventory level and forecasted demand of the target type of material, determine the target demand for the target type of material during the forecast period. The target demand represents the demand that needs to be requested from the material issuer.

[0122] Specifically, the difference between the predicted demand and inventory of a target type of material can be used to determine the target demand for that material during the forecast period. For example, for target type 'a', assuming the predicted demand for 'a' material during the forecast period is 1000 and the current inventory is 100, then the target demand for 'a' material during the forecast period is 900, meaning the demand for 'a' material requested from the material issuer is 900.

[0123] In the above material management method, the predicted demand for target type materials during the forecast period is obtained based on the previous method implementation examples. That is, the final predicted demand is determined by combining the two forecast results, which can improve the forecast accuracy. The material demand that needs to be requested from the material issuer is determined based on the material inventory and the predicted demand, so that the requested materials are more in line with actual needs and help reduce waste caused by material hoarding. In addition, forecasting and requesting material demand in advance can avoid the lag problem that occurs when materials are insufficient, thereby avoiding the impact of insufficient materials on packaging and dispatch efficiency.

[0124] In one embodiment, when the requisition information of a target type material with a target demand quantity is detected, the inventory quantity of the target type material is updated according to the target demand quantity.

[0125] After determining the target demand for a specific type of material within the forecast period, the branch's material management system generates a material demand information code. This code contains information such as the branch, the target demand, and the personnel involved. The branch sends this code to the material issuer to request the necessary materials. The issuer then packages and transports the required materials to the branch based on the information in the code. Branch staff can then retrieve the materials by scanning the code. Upon detecting a material retrieval request, the material management system updates the inventory level to synchronize the data. The updated inventory level is the current inventory plus the target demand.

[0126] Therefore, intelligent material management makes the entire process from material application and distribution to receipt more transparent, reducing the difficulty of applying for and approving material needs. Compared to traditional experience-based management methods, it is more scientific, reasonable, and efficient. At the same time, it eliminates the need for staff to manually update material inventory after receiving materials, thus solving the problem of material management difficulties caused by staff forgetting to register receipts and reducing management complexity.

[0127] In one embodiment, the management method further includes: real-time monitoring of the inventory of target type materials, and generating an early warning message when the inventory of target type materials is less than the corresponding threshold.

[0128] For each type of material, a corresponding threshold can be set according to actual needs. This threshold can be understood as the minimum inventory level. The thresholds for different types of materials can be the same or different; there is no restriction on this. When the inventory level of any type of material is detected to be lower than the corresponding threshold, an early warning message is generated to indicate that the material needs to be replenished. For example, a phone call or SMS reminder may be sent to relevant staff at the branch. After receiving the reminder, the relevant staff can retrieve the necessary material from the branch's spare materials and update the material inventory level.

[0129] Therefore, by adding an early warning mechanism, it is possible to effectively prevent situations where insufficient materials at the outlets lead to the inability to pack express parcels in a timely manner, which helps to improve the efficiency of outlet packaging and dispatching.

[0130] It should be understood that although the steps in the flowcharts of the above embodiments are shown sequentially according to the arrows, these steps are not necessarily executed in the order indicated by the arrows. Unless explicitly stated herein, there is no strict order restriction on the execution of these steps, and they can be executed in other orders. Moreover, at least some steps in the flowcharts of the above embodiments may include multiple steps or multiple stages. These steps or stages are not necessarily completed at the same time, but can be executed at different times. The execution order of these steps or stages is not necessarily sequential, but can be performed alternately or in turn with other steps or at least some of the steps or stages in other steps.

[0131] In one embodiment, such as Figure 8 As shown, a material demand forecasting device 800 is provided, including: an acquisition module 810, a first forecasting module 820, a second forecasting module 830, and a determination module 840, wherein:

[0132] The acquisition module 810 is used to acquire the volume of express parcels and the usage of target type materials in the historical period corresponding to the period to be predicted.

[0133] The first forecasting module 820 is used to obtain the first forecasted demand of the target type material in the forecasting period based on the time characteristics of the forecasting period and the usage of the target type material in historical periods.

[0134] The second prediction module 830 is used to obtain the second predicted demand for target type materials in the predicted period based on the time characteristics of the predicted period, the volume of express shipments in historical periods, and the usage ratio of target type materials in the predicted period.

[0135] The determination module 840 is used to determine the predicted demand of the target type material within the forecast period based on the first predicted demand and the second predicted demand.

[0136] In one embodiment, the first prediction module 820 includes a first feature determination unit and a first prediction unit. The first feature determination unit is used to obtain first input features based on the time characteristics of the period to be predicted and the usage of the target type material in historical periods. The first prediction unit is used to use a first prediction model corresponding to the target type material to make a prediction based on the first input features, thereby obtaining a first predicted demand for the target type material in the period to be predicted.

[0137] In one embodiment, the training process of the first prediction model includes: obtaining a first sample time period and its corresponding first sample label, wherein the first sample label represents the actual usage of the target type material within the first sample time period; obtaining the first sample input features based on the time characteristics of the first sample time period and the usage of the target type material within the first sample historical time period corresponding to the first sample time period; using the first model to be trained to make predictions based on the first sample input features to obtain the predicted usage of the target type material within the first sample time period; and adjusting the parameters of the first model to be trained based on the predicted usage and the first sample label until the training termination condition is met to obtain the trained first prediction model.

[0138] In one embodiment, the period to be predicted is the week following the current week, and the corresponding historical periods include: a first historical period and a second historical period. The first historical period includes a first preset number of historical weeks before the period to be predicted, and the second historical period includes a second preset number of historical weeks before the period to be predicted. The time features include: the year, month, and week number of the period to be predicted, and whether the period to be predicted is at the beginning or end of the year. The first input features include: time features, the usage of the target type material in each historical week of the first historical period, and the mean, sum, maximum, and minimum usage of the target type material in each historical week of the second historical period.

[0139] In one embodiment, the second prediction module 830 includes a first prediction submodule and a second prediction submodule. The first prediction submodule is used to obtain the predicted volume of express shipments during the predicted period based on the time characteristics of the predicted period and the volume of express shipments during historical periods. The second prediction submodule is used to obtain a second predicted demand for the target type of material during the predicted period based on the predicted volume of express shipments during the predicted period and the usage ratio of the target type of material.

[0140] In one embodiment, the first prediction submodule includes a second feature determination unit and a second prediction unit. The second feature determination unit is used to obtain second input features based on the time characteristics of the period to be predicted and the volume of express shipments in historical periods. The second prediction unit is used to use a second prediction model to make a prediction based on the second input features to obtain the predicted volume of express shipments in the period to be predicted.

[0141] In one embodiment, the training process of the second prediction model includes: obtaining a second sample time period and its corresponding second sample label, wherein the second sample label represents the actual number of express parcels within the second sample time period; obtaining second sample input features based on the time characteristics of the second sample time period and the number of express parcels within the corresponding second historical time period; using the second model to be trained to make predictions based on the second sample input features to obtain the predicted number of express parcels within the second sample time period; and adjusting the model parameters based on the predicted number of express parcels within the second sample time period and the corresponding second sample label until the training termination condition is met to obtain the trained second prediction model.

[0142] In one embodiment, the period to be predicted is the week following the current week, and the corresponding historical periods include: a third historical period and a fourth historical period. The third historical period includes a third preset number of historical weeks before the period to be predicted, and the fourth historical period includes a fourth preset number of historical weeks before the period to be predicted. The time features include: the year, month, and week number of the period to be predicted, and whether the period to be predicted is at the beginning or end of the year. The second input features include: the time features, the number of express shipments in each historical week of the third historical period, and the mean, sum, maximum, and minimum value of the number of express shipments in each historical week of the fourth historical period.

[0143] In one embodiment, the method for determining the usage percentage of target type materials within the forecast period includes: obtaining the shipment volume of each target historical period corresponding to the forecast period, the first shipment volume corresponding to the shipment type associated with the target type material, and the second shipment volume that used the target type material; obtaining the predicted percentage of the first shipment volume within the forecast period based on the ratio of the first shipment volume to the total shipment volume within each target historical period; obtaining the predicted percentage of the second shipment volume within the forecast period based on the ratio of the second shipment volume to the first shipment volume within each target historical period; and determining the usage percentage of target type materials within the forecast period based on the product of the predicted percentage of the first shipment volume and the predicted percentage of the second shipment volume.

[0144] In one embodiment, when the second prediction submodule obtains the second predicted demand for target type materials in the predicted period based on the predicted volume of express shipments and the usage ratio of target type materials in the predicted period, it is specifically used to: determine the second predicted demand for target type materials in the predicted period based on the product of the predicted volume of express shipments and the usage ratio of target type materials in the predicted period.

[0145] In one embodiment, when determining the predicted demand of a target type of material within a forecast period based on a first predicted demand and a second predicted demand, the determining module 840 is specifically used to: determine the predicted demand of the target type of material within a forecast period based on the average of the first predicted demand and the second predicted demand.

[0146] Specific limitations regarding the material demand forecasting device can be found in the limitations of the material demand forecasting method described above, and will not be repeated here. Each module in the aforementioned material demand forecasting device can be implemented entirely or partially through software, hardware, or a combination thereof. These modules can be embedded in or independent of the processor in a computer device in hardware form, or stored in the memory of a computer device in software form, so that the processor can call and execute the corresponding operations of each module.

[0147] In one embodiment, such as Figure 9 As shown, a material management device 900 is provided, including: an acquisition module 910 and a determination module 920, wherein:

[0148] The acquisition module 910 is used to acquire the inventory of the target type of material and the predicted demand of the target type of material in the predicted period when the material application conditions corresponding to the predicted period are met. The predicted demand is obtained by the material demand prediction device 800 in the previous embodiment.

[0149] The determination module 920 is used to determine the target demand for the target type of material during the forecast period based on the inventory and forecast demand of the target type of material. The target demand represents the demand that needs to be requested from the material issuer.

[0150] In one embodiment, when determining the target demand of the target type material during the forecast period based on the inventory and forecast demand of the target type material, the determining module 920 is specifically used to: determine the difference between the forecast demand and the inventory of the target type material as the target demand of the target type material during the forecast period.

[0151] In one embodiment, such as Figure 10 As shown, the material management device 900 also includes an update module 930, which updates the inventory of the target type material according to the target demand when the requisition information of the target type material is detected.

[0152] In one embodiment, such as Figure 10 As shown, the material management device 900 also includes an early warning module 940, which is used to monitor the inventory of target type materials in real time and generate early warning information when the inventory of target type materials is less than the corresponding threshold.

[0153] Specific limitations regarding the material management device can be found in the limitations of the material management method described above, and will not be repeated here. Each module in the aforementioned material management device can be implemented entirely or partially through software, hardware, or a combination thereof. These modules can be embedded in or independent of the processor in a computer device in hardware form, or stored in the memory of a computer device in software form, so that the processor can call and execute the corresponding operations of each module.

[0154] In one embodiment, a computer device is provided, which may be a server, and its internal structure diagram may be as follows: Figure 11 As shown. The computer device includes a processor, memory, and a network interface connected via a system bus. The processor provides computing and control capabilities. The memory includes non-volatile storage media and internal memory. The non-volatile storage media stores an operating system, computer programs, and a database. The internal memory provides an environment for the operation of the operating system and computer programs stored in the non-volatile storage media. The network interface is used to communicate with external terminals via a network connection. When the computer program is executed by the processor, it implements a material requirements forecasting method and / or a material management method.

[0155] In one embodiment, a computer device is provided, which may be a terminal, and its internal structure diagram may be as follows: Figure 12 As shown, the computer device includes a processor, memory, communication interface, display screen, and input devices connected via a system bus. The processor provides computing and control capabilities. The memory includes non-volatile storage media and internal memory. The non-volatile storage media stores the operating system and computer programs. The internal memory provides an environment for the operation of the operating system and computer programs stored in the non-volatile storage media. The communication interface is used for wired or wireless communication with external terminals; wireless communication can be achieved through Wi-Fi, carrier networks, NFC (Near Field Communication), or other technologies. When executed by the processor, the computer program implements a material demand forecasting method and / or a material management method. The display screen can be an LCD screen or an e-ink display screen. The input devices can be a touch layer covering the display screen, buttons, a trackball, or a touchpad mounted on the computer device casing, or an external keyboard, touchpad, or mouse.

[0156] Those skilled in the art will understand that Figure 11 or Figure 12 The structure shown is merely a block diagram of a portion of the structure related to the present application and does not constitute a limitation on the computer device to which the present application is applied. Specific computer devices may include more or fewer components than those shown in the figure, or combine certain components, or have different component arrangements.

[0157] In one embodiment, a computer device is provided, including a memory and a processor, wherein the memory stores a computer program, and the processor executes the computer program to implement the steps in the above-described method embodiments.

[0158] In one embodiment, a computer-readable storage medium is provided having a computer program stored thereon, which, when executed by a processor, implements the steps in the above method embodiments.

[0159] In one embodiment, a computer program product or computer program is provided, the computer program product or computer program including computer instructions stored in a computer-readable storage medium. A processor of a computer device reads the computer instructions from the computer-readable storage medium, and executes the computer instructions, causing the computer device to perform the steps in the above method embodiments.

[0160] It should be understood that the terms "first," "second," etc., in the above embodiments are used for descriptive purposes only and should not be construed as indicating or implying relative importance or implicitly specifying the number of indicated technical features. Regarding the description of numerical ranges, the term "multiple" is understood to mean equal to or greater than two.

[0161] Those skilled in the art will understand that all or part of the processes in the methods of the above embodiments can be implemented by a computer program instructing related hardware. The computer program can be stored in a non-volatile computer-readable storage medium, and when executed, it can include the processes of the embodiments of the methods described above. Any references to memory, storage, databases, or other media used in the embodiments provided in this application can include at least one of non-volatile and volatile memory. Non-volatile memory can include read-only memory (ROM), magnetic tape, floppy disk, flash memory, or optical storage, etc. Volatile memory can include random access memory (RAM) or external cache memory. By way of illustration and not limitation, RAM can be in various forms, such as static random access memory (SRAM) or dynamic random access memory (DRAM), etc.

[0162] The technical features of the above embodiments can be combined in any way. For the sake of brevity, 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 specification.

[0163] The embodiments described above are merely illustrative of several implementation methods of this application, and while the descriptions are relatively specific and detailed, they should not be construed as limiting the scope of the invention patent. It should be noted that those skilled in the art can make various modifications and improvements without departing from the concept of this application, and these all fall within the protection scope of this application. Therefore, the protection scope of this patent application should be determined by the appended claims.

Claims

1. A method of material requirement prediction, characterized by, The method comprises: obtaining the express quantity and the use quantity of the target type material in the historical period corresponding to the to-be-predicted period; obtaining the first predicted demand quantity of the target type material in the to-be-predicted period according to the time feature of the to-be-predicted period and the use quantity of the target type material in the historical period; obtaining the second predicted demand quantity of the target type material in the to-be-predicted period according to the time feature of the to-be-predicted period, the express quantity in the historical period, and the use quantity proportion of the target type material in the to-be-predicted period; the determination method of the use quantity proportion of the target type material in the to-be-predicted period comprises: obtaining the express quantity in each target historical period corresponding to the to-be-predicted period, the first express quantity corresponding to the express type associated with the target type material, and the second express quantity using the target type material; obtaining the first express quantity prediction proportion in the to-be-predicted period according to the ratio of the first express quantity to the express quantity in each target historical period; obtaining the second express quantity prediction proportion in the to-be-predicted period according to the ratio of the second express quantity to the first express quantity in each target historical period; determining the use quantity proportion of the target type material in the to-be-predicted period according to the product of the first express quantity prediction proportion and the second express quantity prediction proportion; determining the predicted demand quantity of the target type material in the to-be-predicted period based on the first predicted demand quantity and the second predicted demand quantity.

2. The method of claim 1, wherein, obtaining the first predicted demand quantity of the target type material in the to-be-predicted period according to the time feature of the to-be-predicted period and the use quantity of the target type material in the historical period, comprises: obtaining first input features according to the time feature of the to-be-predicted period and the use quantity of the target type material in the historical period; obtaining the first predicted demand quantity of the target type material in the to-be-predicted period based on the first input features by using the first prediction model corresponding to the target type material.

3. The method of claim 2, wherein, The training process of the first prediction model comprises: obtaining a first sample period and a first sample label corresponding thereto, the first sample label representing the actual use quantity of the target type material in the first sample period; obtaining first sample input features according to the time feature of the first sample period and the use quantity of the target type material in the first sample historical period corresponding to the first sample period; obtaining the predicted use quantity of the target type material in the first sample period by using a first to-be-trained model based on the first sample input features; adjusting the parameters of the first to-be-trained model based on the predicted use quantity and the first sample label until a training end condition is met, and obtaining a trained first prediction model.

4. The method of claim 2, wherein, The to-be-predicted period is the next week of the week in which the current time is located, and the corresponding historical period comprises a first historical period and a second historical period; the first historical period comprises a first preset number of historical weeks before the to-be-predicted period, and the second historical period comprises a second preset number of historical weeks before the to-be-predicted period. The time feature comprises: a year, a month, a week number of the to-be-predicted period, and whether the to-be-predicted period is at the beginning of the year and whether the to-be-predicted period is at the end of the year; The first input feature comprises: the time feature, a usage amount of the target type material in each of the historical weeks in the first historical period, and a mean value, a sum, a maximum value and a minimum value of the usage amount of the target type material in each of the historical weeks in the second historical period.

5. The method of claim 1, wherein, According to the time feature of the to-be-predicted period, the express delivery amount in the historical period, and the usage amount proportion of the target type material in the to-be-predicted period, a second predicted demand amount of the target type material in the to-be-predicted period is obtained, comprising: According to the time feature of the to-be-predicted period and the express delivery amount in the historical period, a predicted express delivery amount in the to-be-predicted period is obtained. According to the predicted express delivery amount in the to-be-predicted period and the usage amount proportion of the target type material, a second predicted demand amount of the target type material in the to-be-predicted period is obtained.

6. The method of claim 5, wherein, According to the time feature of the to-be-predicted period and the express delivery amount in the historical period, a predicted express delivery amount in the to-be-predicted period is obtained, comprising: According to the time feature of the to-be-predicted period and the express delivery amount in the historical period, a second input feature is obtained. A second prediction model is used to make a prediction based on the second input feature, so as to obtain the predicted express delivery amount in the to-be-predicted period.

7. The method of claim 6, wherein, The training process of the second prediction model comprises: A second sample period and a corresponding second sample label are obtained, the second sample label representing an actual express delivery amount in the second sample period; According to the time feature of the second sample period and the express delivery amount in a second historical period corresponding to the second sample period, a second sample input feature is obtained; A second to-be-trained model is used to make a prediction based on the second sample input feature, so as to obtain a predicted express delivery amount in the second sample period; Based on the predicted express delivery amount in the second sample period and the corresponding second sample label, the model parameters are adjusted until a training end condition is met, so as to obtain a trained second prediction model.

8. The method of claim 6, wherein, The to-be-predicted period is a next week of a current week, and the corresponding historical period comprises a third historical period and a fourth historical period, the third historical period comprising a third preset number of historical weeks before the to-be-predicted period, and the fourth historical period comprising a fourth preset number of historical weeks before the to-be-predicted period; The time feature comprises: a year, a month, a week number of the to-be-predicted period, and whether the to-be-predicted period is at the beginning of the year and whether the to-be-predicted period is at the end of the year; The second input feature comprises: the time feature, the express delivery amount in each of the historical weeks in the third historical period, and a mean value, a sum, a maximum value and a minimum value of the express delivery amount in each of the historical weeks in the fourth historical period.

9. The method of claim 5, wherein, According to the predicted express delivery amount in the to-be-predicted period and the usage amount proportion of the target type material, a second predicted demand amount of the target type material in the to-be-predicted period is obtained, comprising: According to the product of the predicted express amount in the to-be-predicted period and the use amount proportion of the target type material, a second predicted demand amount of the target type material in the to-be-predicted period is determined.

10. The method according to any one of claims 1 to 9, characterized in that, Based on the first predicted demand amount and the second predicted demand amount, a predicted demand amount of the target type material in the to-be-predicted period is determined, including: According to the average of the first predicted demand amount and the second predicted demand amount, a predicted demand amount of the target type material in the to-be-predicted period is determined.

11. A material management method characterized by, The method comprises: When the material application condition corresponding to the to-be-predicted period is reached, an inventory amount of the target type material and a predicted demand amount of the target type material in the to-be-predicted period are obtained, and the predicted demand amount is obtained according to the method in any one of claims 1 to 10; According to the inventory amount and the predicted demand amount of the target type material, a target demand amount of the target type material in the to-be-predicted period is determined, and the target demand amount represents a demand amount that needs to be applied to a material issuing party.

12. The method of claim 11, wherein, According to the inventory amount and the predicted demand amount of the target type material, a target demand amount of the target type material in the to-be-predicted period is determined, including: A difference between the predicted demand amount and the inventory amount of the target type material is determined as the target demand amount of the target type material in the to-be-predicted period.

13. The method of claim 11, wherein, Further comprising: When the taking information of the target type material of the target demand amount is detected, the inventory amount of the target type material is updated according to the target demand amount.

14. The method according to any one of claims 11 to 13, characterized in that, Further comprising: The inventory amount of the target type material is monitored in real time, and when the inventory amount of the target type material is less than a corresponding threshold value, a warning information is generated.

15. A material requirement prediction device, characterized by, The device comprises: An acquisition module is configured to acquire an express amount and a use amount of a target type material in a historical period corresponding to a to-be-predicted period; A first prediction module is configured to obtain a first predicted demand amount of the target type material in the to-be-predicted period according to a time feature of the to-be-predicted period and the use amount of the target type material in the historical period; A second prediction module is configured to obtain a second predicted demand amount of the target type material in the to-be-predicted period according to the time feature of the to-be-predicted period, the express amount in the historical period, and a use amount proportion of the target type material in the to-be-predicted period; the determination method of the use amount proportion of the target type material in the to-be-predicted period comprises: acquiring an express amount in each target historical period corresponding to the to-be-predicted period, a first express amount corresponding to an express type associated with the target type material, and a second express amount using the target type material; obtaining a first express amount prediction proportion in the to-be-predicted period according to a ratio of the first express amount to the express amount in each target historical period; obtaining a second express amount prediction proportion in the to-be-predicted period according to a ratio of the second express amount to the first express amount in each target historical period; and determining the use amount proportion of the target type material in the to-be-predicted period according to a product of the first express amount prediction proportion and the second express amount prediction proportion. A determining module is configured to determine a predicted demand amount of the target type of material in the to-be-predicted period based on the first predicted demand amount and the second predicted demand amount.

16. A material management apparatus, characterized by, The device comprises: An obtaining module is configured to, when a material application condition corresponding to a to-be-predicted period is reached, obtain an inventory amount of a target type of material and a predicted demand amount of the target type of material in the to-be-predicted period, the predicted demand amount being obtained by the device of claim 15; A determining module is configured to determine a target demand amount of the target type of material in the to-be-predicted period according to the inventory amount and the predicted demand amount of the target type of material, the target demand amount representing a demand amount that needs to be applied for by a material issuing party. 17.A computer device, comprising a memory and a processor, wherein the memory stores a computer program, and the computer device is configured to perform the method according to any one of claims 1-16. The processor executes the computer program to implement the steps of the method in any one of claims 1 to 14.

18. A computer readable storage medium having stored thereon a computer program, characterized in that, The computer program is executed by the processor to implement the steps of the method in any one of claims 1 to 14.

Images