A data processing method, device, equipment and storage medium

Abstract

The present application discloses a data processing method, the method comprising: determining a target proportion sequence from at least one proportion sequence according to the total inventory amount in a first time period and the cargo inflow and outflow amount in a first time sub-segment; the first time period includes at least two time sub-segments; the first time sub-segment is any historical time sub-segment in the at least two time sub-segments; the target proportion sequence is the proportion of the inventory amount in different time sub-segments in the at least one time sub-segment; predicting the inventory amount in a second time sub-segment in the first time period according to the total inventory amount and the target proportion in the target proportion sequence; the target proportion is the proportion of the inventory amount corresponding to the second time sub-segment in the target proportion sequence. In addition, the present application also discloses a data processing device, equipment and storage medium.

Description

Technical Field

[0001] The present application relates to the field of data processing, and relates to but is not limited to a data processing method, device, equipment and storage medium. Background Art

[0002] In the related art, in the promotional scenarios of 618 and Double 11, the e-commerce platform estimates the inventory quantity based on manual experience, which results in the problem of low accuracy of the estimated inventory quantity. Summary of the invention

[0003] The embodiments of the present application provide a data processing method, apparatus, device and storage medium to solve at least one problem existing in the related art, which can improve the accuracy of the estimated inventory quantity.

[0004] The technical solution of this application is implemented as follows:

[0005] In a first aspect, an embodiment of the present application provides a data processing method, the method comprising:

[0006] According to the total inventory volume of the first time period and the cargo inflow and outflow volume of the first time sub-segment, a target proportion sequence is determined from at least one proportion sequence; the first time period includes at least two time sub-segments; the first time sub-segment is any historical time sub-segment of the at least two time sub-segments; the target proportion sequence is the proportion of the inventory volume of different time sub-segments in the at least one time sub-segment;

[0007] The stock quantity of the second time sub-segment in the first time period is predicted according to the total stock quantity and the target proportion in the target proportion sequence; the target proportion is the proportion of the stock quantity corresponding to the second time sub-segment in the target proportion sequence.

[0008] In a second aspect, an embodiment of the present application provides a data processing device, the device comprising:

[0009] A determination unit, configured to determine a target proportion sequence from at least one proportion sequence according to the total inventory volume of a first time period and the cargo inflow and outflow volume of a first time sub-segment; the first time period includes at least two time sub-segments; the first time sub-segment is any historical time sub-segment of the at least two time sub-segments; the target proportion sequence is the proportion of the inventory volume of different time sub-segments in the at least one time sub-segment;

[0010] A prediction unit is used to predict the stock quantity of the second time sub-segment in the first time period according to the total stock quantity and the target proportion in the target proportion sequence, wherein the target proportion is the proportion of the stock quantity corresponding to the second time sub-segment in the target proportion sequence.

[0011] In a third aspect, an embodiment of the present application provides an electronic device, a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor implements the above-mentioned data processing method when executing the computer program.

[0012] In a fourth aspect, an embodiment of the present application provides a storage medium on which a computer program is stored, and the computer program implements the above-mentioned data processing method when executed by a processor.

[0013] The present application provides a data processing method, device, equipment and storage medium, which determines a target proportion sequence from at least one proportion sequence according to the total stocking amount in a first time period and the inflow and outflow of goods in the first time sub-segment; the first time period includes at least two time sub-segments; the first time sub-segment is any historical time sub-segment in the at least two time sub-segments; the target proportion sequence is the proportion of the stocking amount of different time sub-segments in the at least one time sub-segment; according to the total stocking amount and the target proportion in the target proportion sequence, the stocking amount of the second time sub-segment in the first time period is predicted, and the target proportion is the proportion of the stocking amount corresponding to the second time sub-segment in the target proportion sequence. In this way, in the process of predicting the stocking amount of the second time sub-segment in the first time period, the target proportion sequence can be determined first according to the stocking amount in the first time period and the inflow and outflow of goods in the first time sub-segment that has occurred, and then the stocking amount of the second time sub-segment that has not occurred is predicted according to the total stocking amount and the target proportion in the target proportion sequence. In this way, the accuracy of the estimated stocking amount of the second time sub-segment can be improved. BRIEF DESCRIPTION OF THE DRAWINGS

[0014] Figure 1 An optional structural diagram of a data processing system provided in an embodiment of the present application;

[0015] Figure 2 An optional flowchart of a data processing method provided in an embodiment of the present application;

[0016] Figure 3 An optional flowchart of a data processing method provided in an embodiment of the present application;

[0017] Figure 4 An optional interface diagram provided for an embodiment of the present application;

[0018] Figure 5 An optional flowchart of a data processing method provided in an embodiment of the present application;

[0019] Figure 6 An optional structural diagram of a data processing device provided in an embodiment of the present application;

[0020] Figure 7An optional structural diagram of an electronic device provided in an embodiment of the present application. DETAILED DESCRIPTION

[0021] In order to make the purpose, technical solution and advantages of the embodiments of the present application clearer, the specific technical solution of the application will be further described in detail below in conjunction with the drawings in the embodiments of the present application. The following embodiments are used to illustrate the present application, but are not used to limit the scope of the present application.

[0022] Unless otherwise defined, all technical and scientific terms used herein have the same meaning as those generally understood by those skilled in the art to which the present application belongs. The terms used herein in the specification of the present application are only for the purpose of describing specific embodiments and are not intended to limit the present application. The term "and / or" used herein includes any and all combinations of one or more of the related listed items.

[0023] Before further explaining the present application in detail, the nouns and terms involved in the embodiments of the present application are explained. The nouns and terms involved in the embodiments of the present application are subject to the following interpretations.

[0024] 1) Stock Keeping Unit (SKU), which is used to represent the smallest available unit in inventory management. For example, if a product has at least one color, then each of the at least one color can be a SKU. For example, for a sweatshirt, if the sweatshirt has two colors, black and white, then the black sweatshirt can be a SKU and the white sweatshirt can be a SKU.

[0025] 2) Total stock quantity is used to represent the total quantity of stock required in a time period. A time period is a continuous time period, such as a time period of a set length such as one year or one month. A time period can be divided into multiple time sub-segments, such as: if the time period is one year, the time sub-segment is one month, and if the time period is one month, the time sub-segment is one day.

[0026] 3) Inventory quantity, which is used to represent the quantity of goods needed in a time sub-segment.

[0027] In one example, the stock quantity may be the quantity of goods required to be stocked in the first week of May.

[0028] 4) Inventory: used to represent the quantity of goods remaining in the warehouse.

[0029] The data processing method of the embodiment of the present application can be applied to Figure 1 The data processing system 100 shown in FIG. Figure 1As shown, the data processing system 100 includes: a server 10 and a client 20. The server 10 and the client 20 communicate with each other via a network 30.

[0030] The data processing method provided in the embodiment of the present application can be applied to a data processing device, and the data processing device can be a server 10 or a client 20.

[0031] The data processing device determines a target proportion sequence from at least one proportion sequence based on the total inventory amount in the first time period and the cargo inflow and outflow amount in the first time sub-segment, and then predicts the inventory amount in the second time sub-segment in the first time period based on the total inventory amount and the target proportion in the target proportion sequence, wherein the first time period includes at least two time sub-segments; the first time sub-segment is any historical time sub-segment of the at least two time sub-segments; the target proportion sequence is the proportion of inventory amounts in different time sub-segments in the at least one time sub-segment; and the target proportion is the proportion of inventory amounts corresponding to the second time sub-segment in the target proportion sequence.

[0032] When the data processing device is a server 10, the server 10 sends the predicted inventory quantity of the second time sub-segment in the first time period to the client 20 through the network 30. After receiving the inventory quantity of the second time sub-segment, the client 20 displays the inventory quantity of the second time sub-segment to the user.

[0033] When the data processing device is the client 20, the client 20 directly displays the stock quantity of the second time sub-period to the user.

[0034] Next, combine Figure 1 The schematic diagram of the data processing system 100 shown illustrates various embodiments of the data processing method, apparatus, device and storage medium provided in the embodiments of the present application.

[0035] Figure 2 A schematic diagram of an implementation flow of a data processing method provided in an embodiment of the present application, wherein the method is applied to a data processing device, such as Figure 2 As shown, the method may include the following steps:

[0036] S201. Determine a target proportion sequence from at least one proportion sequence according to the total inventory volume in a first time period and the cargo inflow and outflow volume in a first time sub-segment.

[0037] Here, the first time period is a continuous time period, and the continuous time period can be one day, one month, or one year, which is not limited in the embodiment of the present application.

[0038] The first time period may include at least two time sub-segments, and the first time sub-segment is any historical time sub-segment of the at least two time sub-segments, wherein the historical time sub-segment is a time sub-segment that has already occurred.

[0039] In one example, the first time period is a month, and the at least two time sub-segments included in the month may include: the first week, the second week, the third week, and the fourth week; if the first week is a time sub-segment that has already occurred, the first week is the first time sub-segment.

[0040] In another example, the first time period is a year, and the at least two time sub-segments included in the year may include: the first month, the second month, the third month, ..., the eleventh month and the twelfth month; if the first month is a time sub-segment that has already occurred, the first month is the first time sub-segment.

[0041] In another example, the first time period is one year, and the at least two time sub-segments included in the year may include: the first quarter, the second quarter, the third quarter and the fourth quarter; if the first quarter is a time sub-segment that has already occurred, then the first quarter is the first time sub-segment.

[0042] In an embodiment of the present application, after determining the first time period, the data processing device may determine a first time subsegment included in the first time period according to the first time period, and after determining the first time subsegment, determine the cargo inflow and outflow volume of the first time subsegment.

[0043] Here, the goods inflow and outflow volume includes: shipment volume and inventory volume, wherein the shipment volume is used to represent the quantity of goods sold, and the inventory volume is used to represent the quantity of goods remaining in the warehouse.

[0044] In an embodiment of the present application, the method for determining the shipment volume may include: a data processing device obtains at least one order data; the data processing device determines the shipment volume by parsing the at least one order data; wherein each order data in the at least one order data is used to represent the quantity of goods purchased by the user.

[0045] Here, obtaining at least one order data includes: obtaining at least one order data from a distributed file system (Hadoop Distributed File System, HDFS).

[0046] Determining the shipment volume by parsing the at least one order data includes: determining the shipment volume by aggregating each order data in the at least one order data.

[0047] In one example, a data processing device obtains three order data from HDFS. In the first order data, it is recorded that user A purchased 10 goods A. In the second order data, it is recorded that user B purchased 20 goods A. In the third order data, it is recorded that user C purchased 10 goods A. The data processing device determines that the quantity of goods A sold is 40 by summarizing the quantities of goods A purchased by users recorded in the three order data.

[0048] In the embodiment of the present application, the goods may be a SKU or all goods under a commodity category, and the embodiment of the present application does not impose any limitation on this.

[0049] In one example, when the goods are all goods under a product category, and the product category is sweatshirts, the goods may include sweatshirts of all sizes and all colors under the sweatshirt category.

[0050] In an embodiment of the present application, the at least one proportion sequence is at least one proportion sequence corresponding to the first time period. For each of the at least one proportion sequence, the proportion sequence includes at least one proportion, and the proportion is the ratio of the inventory quantity of the corresponding time sub-segment to the total inventory quantity of the first time period.

[0051] In one example, the first time period is May, and May includes at least two time sub-segments: the first week, the second week, the third week and the fourth week; the at least one proportion sequence of May may include: [20%, 30%, 40%, 10%], and for the proportion sequence [20%, 30%, 40%, 10%], the proportion sequence includes proportion of 20%, proportion of 30%, proportion of 40% and proportion of 10%, wherein proportion of 20% is the ratio of the stocking quantity of the first week to the total stocking quantity of May, proportion of 30% is the ratio of the stocking quantity of the second week to the total stocking quantity of May, proportion of 40% is the ratio of the stocking quantity of the third week to the total stocking quantity of May, and proportion of 40% is the ratio of the stocking quantity of the fourth week to the total stocking quantity of May.

[0052] In an embodiment of the present application, a data processing device may receive at least one proportion sequence; and determine the at least one proportion sequence as the at least one proportion sequence.

[0053] Here, receiving at least one proportion sequence input includes: a data processing device receiving at least one proportion sequence input by a user.

[0054] In one example, if the at least one received proportion sequence includes: [20%, 30%, 40%, 10%] and [30%, 20%, 10%, 40%], the determined at least one proportion sequence is [20%, 30%, 40%, 10%] and [30%, 20%, 10%, 40%].

[0055] In an embodiment of the present application, a data processing device receives a historical proportion sequence; based on the historical proportion sequence, the adjustment ratio can be increased or decreased for the proportion corresponding to each time sub-segment to determine the at least one proportion sequence; wherein the historical proportion sequence is a proportion sequence of the first historical time period corresponding to the first time period; the adjustment step is used to characterize the proportion that can be adjusted each time within the adjustable range; the adjustable range is used to characterize a maximum adjustment range when adjusting each proportion;.

[0056] In one example, the first time period is May, and the first historical time period corresponding to the first time period May is May of last year. The proportion sequence of May of last year, that is, the historical proportion sequence is [30%, 20%, 10%, 40%], the adjustable range is ±5%, the adjustment ratio is 1%, and the at least two time sub-segments included in May may include: the first week, the second week, the third week, and the fourth week. Determining at least one proportion sequence of May may include: for determining the proportion corresponding to the first week, the adjustment ratio may be increased by 1% to obtain a proportion of 31%, for determining the proportion corresponding to the second week, the adjustment ratio may be reduced by 1% to obtain a proportion of 19%, for determining the proportion corresponding to the third week, the adjustment ratio may be increased by 1% to obtain a proportion of 11%, and for determining the proportion corresponding to the fourth week, the adjustment ratio may be reduced by 1% to obtain a proportion of 39%, so that a proportion sequence of [31%, 29%, 11%, 39%] can be determined.

[0057] The target proportion sequence is the proportion of the inventory in different time sub-segments in at least one time sub-segment.

[0058] In one example, at least one proportion sequence includes: proportion sequence 1 [20%, 30%, 40%, 10%] and proportion sequence 2 [30%, 20%, 10%, 40%], then the target proportion sequence can be determined as proportion sequence 1 from proportion sequence 1 and proportion sequence 2.

[0059] S202: predicting the inventory quantity of a second time sub-segment in the first time period according to the total inventory quantity and the target proportion in the target proportion sequence.

[0060] Here, the target proportion is the proportion of the inventory quantity corresponding to the second time sub-segment in the target proportion sequence.

[0061] In one example, if the total inventory quantity is 400, and the target proportion sequence is [20%, 30%, 40%, 10%], where 30% is the proportion of the inventory quantity corresponding to the second time sub-segment, then the inventory quantity for the second time sub-segment can be predicted to be 120 based on the total inventory quantity of 400 and the target proportion of 30%.

[0062] The embodiment of the present application provides a data processing method, according to the total stocking amount of the first time period and the cargo inflow and outflow of the first time sub-segment, a target proportion sequence is determined from at least one proportion sequence; the first time period includes at least two time sub-segments; the first time sub-segment is any historical time sub-segment of the at least two time sub-segments; the target proportion sequence is the proportion of the stocking amount of different time sub-segments in the at least one time sub-segment; according to the total stocking amount and the target proportion in the target proportion sequence, the stocking amount of the second time sub-segment in the first time period is predicted, and the target proportion is the proportion of the stocking amount corresponding to the second time sub-segment in the target proportion sequence. In this way, in the process of predicting the stocking amount of the second time sub-segment in the first time period, the target proportion sequence can be determined first according to the stocking amount of the first time period and the cargo inflow and outflow of the first time sub-segment that has occurred, and then the stocking amount of the second time sub-segment that has not occurred is predicted according to the total stocking amount and the target proportion in the target proportion sequence. In this way, the accuracy of the estimated stocking amount of the second time sub-segment can be improved.

[0063] In some embodiments, Figure 3 As shown, the above S201 may include:

[0064] S301. Determine at least one reference stock quantity according to the total stock quantity in the first time period and the reference proportion in the at least one proportion sequence.

[0065] Here, the total stock amount in the first time period is 400, and at least one proportion sequence includes: proportion sequence 1: [20%, 30%, 40%, 10%] and proportion sequence 2: [25%, 35%, 25%, 25%]. For the first time sub-segment in the first time period, the reference proportion of the first time sub-segment can be 20% or 25%. The reference stock amount of a first time sub-segment can be determined to be 80 based on the total stock amount of 400 in the first time period and the reference proportion of 20% of the first time sub-segment. The reference stock amount of a first time sub-segment can also be determined to be 100 based on the total stock amount of 400 in the first time period and the reference proportion of 25% of the first time sub-segment. The reference stock amounts of 80 and 100 of the two first time sub-segments constitute at least one reference stock amount.

[0066] S302: Determine at least one spot rate for the first time subsegment according to the at least one reference stock quantity and the goods inflow and outflow quantity of the first time subsegment.

[0067] Here, for the first time subsegment, at least one spot rate for the first time subsegment can be determined based on at least one reference stock quantity of the first time subsegment and the goods inflow and outflow quantity of the first time subsegment, wherein the spot rate is the ratio of the shipment quantity to the quantity to be sold.

[0068] S303: Use the reference stock quantity corresponding to the target spot rate that meets the conditions among the at least one spot rate as the target reference stock quantity.

[0069] Here, the target spot rate that satisfies the condition may include: taking the highest spot rate among the at least one spot rate as the target spot rate.

[0070] In one example, at least one spot rate includes: 30%, 50% and 60%, wherein the reference stock quantity corresponding to 30% is 50, the reference stock quantity corresponding to 50% is 80, and the reference stock quantity corresponding to 60% is 100. If the target spot rate is 60%, the reference stock quantity 100 corresponding to the target spot rate of 60% is used as the target reference stock quantity.

[0071] S304: Determine a proportion sequence of the target reference inventory quantity obtained in at least one proportion sequence as the target proportion sequence.

[0072] In one example, at least one proportion sequence includes: proportion sequence 1: [20%, 30%, 40%, 10%] and proportion sequence 2: [25%, 35%, 25%, 25%]. If the proportion sequence of the target reference inventory is proportion sequence 1, then proportion sequence 1 is the target proportion sequence.

[0073] In an embodiment of the present application, a target proportion sequence can be determined from at least one proportion sequence based on the total inventory in the first time period, the cargo inflow and outflow in the first time sub-segment, and the vendor lead time (VLT).

[0074] In some embodiments, the goods inflow and outflow volume includes the shipment volume and the inventory volume, and the above S302 may include: determining at least one quantity to be sold based on the at least one reference stock volume and the inventory volume; determining the at least one spot rate based on the shipment volume and the at least one quantity to be sold.

[0075] Here, for the first time sub-segment, if the shipment quantity of the first time sub-segment is 50, the inventory quantity of the first time sub-segment is 100, and at least one reference inventory quantity includes: 80 and 100, then a quantity to be sold can be determined to be 180 based on a reference inventory quantity of 80 and an inventory quantity of 100, and then a spot rate of 27% can be determined based on the shipment quantity of 50 and the quantity to be sold of 180; it is also possible to determine a quantity to be sold of 200 based on a reference inventory quantity of 100 and an inventory quantity of 100, and then a spot rate of 25% can be determined based on the shipment quantity of 50 and the quantity to be sold of 200.

[0076] In the above explanation of determining at least one spot rate, the explanation is based on the example of determining at least one spot rate of the first time sub-segment. In actual applications, the spot rate of the first time period can be determined by first determining the spot rate of each of the at least two time sub-segments included in the first time period, and then summing the spot rates of each time sub-segment to obtain the spot rate of the first time period.

[0077] In an embodiment of the present application, the data processing device determines at least one spot rate in the first time period, including: inputting each proportion sequence in at least one proportion sequence into a mixed integer programming (Mixed-Integer Programming, MIP) model to obtain a spot rate corresponding to each proportion sequence.

[0078] The model objective of the MIP model is to minimize turnover , where R is a proportion sequence, i is at least one proportion sequence, and ito i It represents the turnover rate corresponding to the i-th proportion sequence, and min represents the minimum turnover rate.

[0079] The constraint condition of the MIP model is the maximum spot rate, where the maximum spot rate can be achieved by the following formula (1):

[0080] stcr i ≥cr max ,i∈[1,T] Formula (1);

[0081] Among them, st is the abbreviation of subject to, which is used to represent the constraint condition, cr i represents the spot rate corresponding to the i-th proportion sequence, cr max Indicates the maximum spot rate, stcr i ≥cr max The spot rate corresponding to the i-th proportion sequence should be greater than or equal to the maximum spot rate.

[0082] After determining at least one spot rate, a maximum spot rate may be determined from the at least one spot rate using a mathematical optimization technique (CPLEX).

[0083] In some embodiments, the method may also include: determining the total inventory quantity based on the inventory quantity at the first time of the first time period, the inventory quantity at the second time of the first time period, and the shipment quantity of the first time period; the first time is the starting time of the first time period, and the second time is the end time of the first time period.

[0084] Here, determining the total stock amount based on the inventory at the first time of the first time period, the inventory at the second time of the first time period, and the shipment amount of the first time period may include: subtracting the inventory at the first time from the inventory at the second time, and adding the shipment amount of the first time period to determine the total stock amount.

[0085] In one example, the first time period is May, the starting time of the first time May is May 1st, and the end time of the second time May is May 31st. If the inventory on May 1st is 100, the inventory on May 31st is 200, and the shipment volume in May is 200, then the total inventory quantity determined is 200-100+200=300.

[0086] In some embodiments, the method may further include: determining the inventory quantity in the second time period based on the shipment quantity and the inventory-to-sales ratio coefficient in the second time period.

[0087] Here, the inventory-to-sales ratio coefficient is used to characterize the ratio between inventory and shipment; the second time period is a time period adjacent to the first time period and located after the first time period.

[0088] Determining the inventory level in the second time period based on the shipment volume and the inventory-to-sales ratio coefficient in the second time period may include: multiplying the shipment volume in the second time period by the inventory-to-sales ratio coefficient to determine the inventory level in the second time period.

[0089] In one example, if the shipment volume in the second time period is 100 and the inventory-to-sales ratio coefficient is 0.4, the inventory volume in the second time period can be determined to be 40 based on multiplying the shipment volume in the second time period 100 by the inventory-to-sales ratio coefficient 0.4.

[0090] In some embodiments, the method may also include: determining a first growth rate of shipments in the first historical time period relative to the shipments in the second historical time period based on the shipments in the first historical time period corresponding to the first time period and the shipments in the second historical time period corresponding to the third time period; and predicting the shipments in the first time period based on the first growth rate and the shipments in the third time period.

[0091] Here, when the first time period is one month, the first historical time period corresponding to the first time period is the time period of the same period in previous years. For example, when the first time period is May of this year, the first historical time period corresponding to May may be May of last year or May of the year before last. This embodiment of the present application does not limit this.

[0092] The second historical time period corresponding to the third time period is the time period of the same period in previous years. For example, when the third time period is April of this year, the second historical time period corresponding to April may be April of last year or April of the year before last. This embodiment of the present application does not limit this.

[0093] In one example, if the first time period is May of this year, the first historical time period is May of last year, and the shipment volume in May of last year was 200, the third time period is April of this year, and the shipment volume in April of this year was 100, and the second historical time period is April of last year, and the shipment volume in April of last year was 100, then based on the shipment volume of 200 in May of last year and the shipment volume of 100 in April of last year, it can be determined that the first growth rate of the shipment volume in May of last year relative to the shipment volume in April of last year is 100%, and then based on the first growth rate of 100% and the shipment volume of 100 in April of this year, it is predicted that the shipment volume in May will be 200.

[0094] In some embodiments, the method may also include: the data processing device inputs the promotional data of the first time period into a fitting regression model to predict the reference information of the goods in the first time period; inputs the reference information of the first time period into a sales forecasting model to predict the shipment volume in the first time period.

[0095] Here, the promotional data is used to characterize the promotional information and promotional plan of the goods, wherein the promotional information is used to characterize a specific form of discount, and the promotional plan is used to characterize the total amount of goods expected to be sold during the entire promotion process; the reference information is used to characterize the exposure and price of the goods; and the sales forecasting model is used to predict the shipment volume.

[0096] The promotion data can be input through a given template, wherein the given template may include: goods, promotion information and the duration of the promotion information.

[0097] Promotional information may include: full discount information, full gift information and flash sale information. In one example, full discount information is: 50 off for purchases over 100. In one example, full gift information is: 100 free for purchases over 100. In one example, flash sale information is: limited time flash sale.

[0098] In one example, the promotion plan may be: the total amount of goods expected to be sold during the two-month promotion is 1,000 pieces.

[0099] In an embodiment of the present application, the fitted regression model may include: a logistic regression (LR) model, an extreme gradient boosting (XGBoost) model, a lightweight gradient boosting machine (Light GBM) model, and a convolutional neural network (CNN).

[0100] Determining a sales forecast model may include: a data processing device obtains the timing characteristics and attribute characteristics of the goods; inputs the timing characteristics, the attribute characteristics, the exposure of the goods and the price of the goods into a reference sales forecast model, trains the reference sales forecast model, and obtains a sales forecast model.

[0101] Here, the sales forecasting model may include: linear regression model, time series model and deep learning model, among which the time series model may include: Prophet model and Holt Winter model, etc.; the deep learning model may include: Recurrent Neural Network (RNN) model, Multi-Quantile Recurrent Neural Network (MQRNN) model and Long Short-Term Memory (LSTM) network model, etc.

[0102] Here, the time series characteristics of the goods may include: historical sales characteristics of the goods, and the historical sales characteristics are used to represent the average sales volume of the goods in a historical time period.

[0103] In one example, the historical sales volume feature may include: average sales volume over the past 3 days, 5 days, 7 days, 14 days, or 30 days.

[0104] The attribute characteristics of the goods may include information such as the brand, shape and volume of the goods.

[0105] Obtaining the attribute characteristics of the goods may include: a data processing device obtains the attribute information of the goods from the commodity information system, stores the obtained attribute information of the goods in a relational database (MYSQL database) or HDFS, processes the required attribute information of the goods, and thus obtains the attribute characteristics of the goods, wherein the attribute characteristics of the goods can be represented by attribute values.

[0106] In some embodiments, the method may further include: fitting the promotion data of a first historical time period corresponding to the first time period with reference information of the first historical time period to obtain the fitting regression model.

[0107] In one example, the first time period is May, and the first historical time period corresponding to May is May of last year. The promotional data of May of last year includes discounts for purchases over a certain amount. The promotional data of discounts for purchases over a certain amount in May of last year are fit with the exposure volume and actual purchase price of the goods in May of last year to obtain a fitted regression model.

[0108] In some embodiments, the method may also include: determining a second growth rate of shipments in the third historical time period relative to the shipments in the second historical time period based on the shipments in the second historical time period corresponding to the third time period and the shipments in the third historical time period corresponding to the second time period; and predicting the shipments in the second time period based on the second growth rate and the shipments in the third time period.

[0109] Here, the third historical time period corresponding to the second time period is the time period of the same period in previous years. For example, when the second time period is June of this year, the third historical time period corresponding to June may be June of last year or June of the year before last. This embodiment of the present application does not limit this.

[0110] In one example, if the third time period is April of this year, the second historical time period is April of last year, the shipment volume in April of last year was 100, the second time period is June of this year, the third historical time period is June of last year, and the shipment volume in June of last year was 200, then based on the shipment volume of 200 in June of last year and the shipment volume of 100 in April of last year, it can be determined that the second growth rate of the shipment volume in June of last year relative to the shipment volume in April of last year is 100%, and then based on the second growth rate of 100% and the shipment volume of 100 in April of this year, it is predicted that the shipment volume in June of this year will be 200.

[0111] In an embodiment of the present application, after determining the second growth rate R1 of the SKU, the second growth rate R2 of all goods under the brand represented by the SKU is determined, and the relationship between the second growth rate R1 of the SKU and the second growth rate R2 of all goods under the brand is judged. If the second growth rate R1 of the SKU is greater than three times the second growth rate R2 of the goods under the brand, the second growth rate R1 of the SKU is replaced by the second growth rate R2 of all goods under the brand.

[0112] In some embodiments, the method may also include: inputting the promotional data of the second time period into a fitting regression model to predict the reference information of the goods in the second time period; inputting the reference information of the second time period into a sales forecasting model to predict the shipment volume in the second time period.

[0113] Here, the promotion data is used to characterize the promotion information and promotion plan of the goods; the reference information is used to characterize the exposure and price of the goods; and the sales forecast model is used to predict the shipment volume. For the explanation of the promotion data, reference information and sales forecast model, please refer to the above embodiment, which will not be repeated here.

[0114] In the embodiment of the present application, after obtaining the original data, intermediate data and result data of the goods, the three types of data can be stored in the MYSQL database and HDFS, and the data stored in the MYSQL database and HDFS can be stored in a platform, such as a big data mart platform. Among them, the original data is used to represent the data before processing the data, such as the attribute information, product number and product name of the goods; the intermediate data is used to represent all the data used before obtaining the result data, such as the data of the inflow and outflow of goods in the first time sub-segment; the result data is used to represent the data obtained after processing the intermediate data, such as the predicted inventory quantity of the second time sub-segment in the first time period.

[0115] Here, after the original data, intermediate data and result data are stored in the MYSQL database and HDFS, the original data, intermediate data and result data can be stored in the MYSQL database and HDFS in the form of data tables, where a data table is a way of storing data in a structured manner.

[0116] After storing the data in the big data mart platform, you can use Plumber Express to push the data to the MYSQL database of the replenishment system, and display the original data, intermediate data and result data on the display interface. At the same time, users can select the data to be displayed according to their own needs. The schematic diagram of the original data, intermediate data and result data displayed on the display interface can be as follows: Figure 4 shown.

[0117] exist Figure 4 In the historical BAND column, letters A to F represent the historical sales rankings, among which letter A represents the highest historical sales ranking, and letter F represents the lowest historical sales ranking.

[0118] Computer visualization displays the calculated data, calculation process and calculation results to users.

[0119] Purchase in transit means that the supplier is purchasing the goods, but they have not yet been delivered to the warehouse.

[0120] In the e-commerce retail scenario, 618 and Double 11 are common national shopping carnivals. Due to the richness of products on e-commerce platforms, the demand for products fluctuates greatly during promotional scenarios, which brings great challenges to replenishment management. Replenishment not only needs to consider the huge demand fluctuations of tens of millions of products, but also needs to solve the warehousing capacity arrangement caused by large-scale replenishment to ensure that products are not out of stock during the promotion period, and the storage costs and cash flow occupation of the e-commerce platform are reasonably controlled.

[0121] In order to achieve the sales target reached by merchants and retail platforms, the two parties will communicate the relevant sales plan before the promotion, plan and arrange the promotion activities according to the plan, and the corresponding replenishment plan. The replenishment plan is mainly divided into two parts. The first is the sales estimate. For the price discounts and activity granularity of the main popular and best-selling SKUs, the manual estimates of future promotion sales are made based on historical experience. Since there are tens of millions of e-commerce SKUs, the manual can only stratify the SKUs according to the original sales and estimate the SKUs at different levels, which is difficult to refine. Finally, the total replenishment amount is estimated based on the estimated sales; the second is the warehousing rhythm arrangement. Since the overall warehousing volume increased sharply in the early stage of the promotion, it is a huge challenge for the warehousing arrangement. Too early warehousing will increase inventory turnover and increase the warehousing and cash flow costs of e-commerce. Too late warehousing may lead to insufficient warehousing capacity, inability to warehousing, and sales losses. The manual will refer to the warehousing rhythm of the same period in history and communicate with the logistics to determine the approximate warehousing rhythm. The warehousing logic and rhythm adopted by different buyers for replenishment may be different, without coordination and planning.

[0122] The present application proposes a data processing method, which is mainly implemented based on machine learning and operations optimization methods. The main implementation steps are data acquisition, sales estimation, warehousing rhythm optimization, big promotion replenishment plan output and data storage and output, a total of five steps, wherein data acquisition includes data analysis and product information acquisition, etc., sales estimation uses statistical methods and machine learning models to output future sales estimates of products, warehousing rhythm optimization uses simulation and operations optimization to solve the optimal warehousing rhythm ratio (that is, the target proportion sequence described in the above embodiment), and the big promotion replenishment plan output uses sales estimation and optimal warehousing rhythm to calculate the recommended replenishment quantity for multiple order days during the big promotion period.

[0123] This application combines the sales forecast module and the warehousing rhythm optimization module to make automated decisions on big promotion replenishment products. First, obtain all kinds of known information about the product, including basic attribute information (product brand, category, etc.), timing information (historical sales data), and business input (sales plan, promotional information, etc.). Then, input the input information into the sales forecast device and the warehousing rhythm optimization device, which output future sales forecasts and the optimal warehousing rhythm, respectively. Finally, based on the sales forecast and the optimal warehousing rhythm, the recommended stocking quantity for multiple future big promotions for the SKU is given. The specific process is as follows:

[0124] The necessary hardware conditions for the model building process are a computer, a server, and at least one database. The memory stores program instructions that can be executed by the processor. The processor calls the program instructions to execute any one of the five steps of "data acquisition", "sales forecast timing model regression", "inventory rhythm optimization solution", "big sale replenishment suggestion output" and "data storage and output".

[0125] Step 1: Data acquisition.

[0126] This application requires product attribute data, user order data, promotional data input by the business, etc. Among them, the product attribute data can be obtained from the product information system, mainly through crawling the product main site information, and stored in MYSQL and HDFS. Through database operations, the required product information is selected for processing and storage. User order data is read through the distributed file system HDFS, and processed into daily sales data of the product by parsing the user order data. For example, a total of 10 users placed orders for product A on January 1, 2020. By summarizing the total sales of 10 users, the total sales of product A on that day is x pieces. The parsed data is stored in the database to facilitate subsequent model calls and processing. The promotional data input by the business is input through a given template and processed by the system.

[0127] The data required for this application needs to be updated regularly, so a data flow task from the data source to the database storage is established to regularly obtain data and store it in the required database. The following is an example of the relevant data structure obtained.

[0128] Step 2: Sales forecast.

[0129] Sales forecasts are used to forecast future sales through business input. Since the promotion period is different from daily sales, the overall demand volatility will be much greater, and the main reason for demand fluctuations comes from changes in promotional prices and traffic. Therefore, the overall forecast is divided into the following two types:

[0130] The first type is that the business has not input promotional plans and sales plans that have a significant impact on sales. For this type of SKU, statistical methods are used to estimate future sales. The specific steps include: calculating the month-on-month sales coefficients R1 and R2 of the historical same period in the SKU dimension, as well as the overall month-on-month coefficient of the brand dimension; using rules to determine the rationality of the month-on-month coefficients, and performing smoothing on the month-on-month coefficients that exceed N (N=3) times the overall brand coefficient. The smoothing is to replace them with the overall month-on-month coefficient of the brand dimension; using recent sales and month-on-month coefficients to obtain sales forecasts for May and June.

[0131] The second type provides the business with promotion information and sales plans. For SKUs with rich information, machine learning models are used to estimate future sales. The specific steps include: fitting the historical promotion data and sales data of the SKU dimension with the actual traffic and price to obtain a factor fitting regression model. The model is not limited to LR, Xgboost, LightGBM, CNN, etc., and then obtaining the future estimated traffic and price based on the promotion information and plan input by the business; training the sales forecast model based on the time series characteristics and attribute characteristics of the SKU, as well as the historical traffic and price characteristics, using models such as linear regression, time series forecasting algorithm (Prophet or Holt winter) and deep learning model (RNN, MQRNN, LSTM), etc.; combining the future estimated traffic, price and trained sales forecast model to obtain the future time series forecast result output.

[0132] Step 3: Determine the inventory ratio.

[0133] Here, the inventory ratio is the proportion sequence described in the above embodiment. The inventory ratio can be input by business, or it can be counted using historical procurement data for the same period to calculate the inventory ratio from the first week W1 to the nth week Wn, and at the same time give an adjustable space Range for the inventory ratio; according to the inventory ratio and the adjustable space Range, set the adjustment step size to combine all possible inventory ratios.

[0134] Based on the total inventory quantity for the promotion, all inventory ratios, and the initial inventory I0+VLT, the future inventory sales of SKU are simulated to obtain the simulation results corresponding to different inventory rhythms; the MIP model is used to solve the optimal inventory rhythm in the SKU dimension: the goal is to minimize turnover, and the constraint is the optimal spot rate.

[0135] Finally, the optimization solver CPLEX is used to solve the optimal warehousing rhythm and obtain the target warehousing ratio with the optimal turnover under the condition of optimal spot rate.

[0136] Finally, the optimization solver CPLEX is used to solve the optimal warehousing rhythm and obtain the warehousing rhythm ratio with the optimal turnover under the condition of optimal spot rate.

[0137] Here, the target inventory ratio is the inventory ratio corresponding to the reference spot rate, and the reference spot rate is the highest spot rate among the at least one spot rate.

[0138] Step 4: Forecast the recommended replenishment quantity for big sales.

[0139] Based on the total stocking quantity for the big promotion and the optimal warehousing rhythm, the overall SKU stocking plan for the big promotion can be calculated. At each big promotion stocking node, the recommended replenishment quantity = estimated total stocking quantity * the warehousing rhythm ratio of this node.

[0140] Step 5: Data storage and output.

[0141] The storage of results is mainly divided into two steps. The first step is to store the original data (attribute features and promotion features), intermediate data (intermediate variable data) and result data through the distributed file management system HDFS, and store the data table in the big data mart platform. The second step is to use Plumber Express to push the data to the MYSQL database of the replenishment system, and use the front end of the replenishment system to output the original data, intermediate data and result data. At the same time, users can select the system to display data according to their own needs.

[0142] like Figure 5 As shown, the data processing method provided in the embodiment of the present application may include:

[0143] S501: A data processing device receives target data.

[0144] Here, the target data may include: sales plan, promotion information or sales data of goods.

[0145] S502: The data processing device determines whether the target data includes sales plan and promotion information.

[0146] If the target data includes the sales plan and promotion information, execute S502a: use the machine learning model to make sales estimates.

[0147] If the target data does not include the sales plan and promotion information, execute S502b: use historical sales data to make sales estimates.

[0148] S503. The data processing device outputs the monthly sales forecast.

[0149] S504. The data processing device calculates the historical inventory ratio for the same period based on the sales data.

[0150] S505. The data processing device forms at least one warehousing ratio according to the adjustment ratio.

[0151] S506. For different warehousing ratios, the data processing device simulates the inventory sales volume using simulation to obtain the inventory quantities corresponding to the different warehousing ratios.

[0152] S507. The data processing device uses the operations research model to solve the optimal warehousing ratio.

[0153] S508. The data processing device determines a replenishment plan for the big promotion based on the monthly sales forecast and the optimal inventory ratio.

[0154] Figure 6 A data processing device provided in an embodiment of the present application, such as Figure 6 As shown, the data processing device 600 includes:

[0155] The determination unit 601 is used to determine a target proportion sequence from at least one proportion sequence according to the total inventory volume in a first time period and the cargo inflow and outflow volume in a first time sub-segment; the first time period includes at least two time sub-segments; the first time sub-segment is any historical time sub-segment in the at least two time sub-segments; the target proportion sequence is the proportion of the inventory volume in different time sub-segments in the at least one time sub-segment;

[0156] The prediction unit 602 is used to predict the inventory quantity of the second time sub-segment in the first time period according to the total inventory quantity and the target proportion in the target proportion sequence; the target proportion is the proportion of the inventory quantity corresponding to the second time sub-segment in the target proportion sequence.

[0157] In some embodiments, the determining unit is further configured to:

[0158] Determine at least one reference stock quantity according to the total stock quantity in the first time period and the reference proportion in the at least one proportion sequence;

[0159] Determining at least one spot rate for the first time subsegment according to the at least one reference stock quantity and the goods inflow and outflow quantity of the first time subsegment;

[0160] Using a reference stock quantity corresponding to a target spot rate that meets the condition among the at least one spot rate as a target reference stock quantity;

[0161] The target reference inventory quantity ratio sequence obtained from at least one ratio sequence is determined as the target ratio sequence.

[0162] In some embodiments, the determining unit is further configured to:

[0163] Determine at least one quantity to be sold according to the at least one reference stock quantity and the inventory quantity;

[0164] Based on the shipment quantity and the at least one pending quantity, the at least one spot rate is determined.

[0165] In some embodiments, the determining unit is further configured to:

[0166] The total inventory quantity is determined according to the inventory quantity at the first time of the first time period, the inventory quantity at the second time of the first time period and the shipment quantity of the first time period; the first time is the starting time of the first time period, and the second time is the end time of the first time period.

[0167] In some embodiments, the determining unit is further configured to:

[0168] The inventory level in the second time period is determined based on the shipment volume and the inventory-to-sales ratio coefficient in the second time period; the inventory-to-sales ratio coefficient is used to characterize the ratio between the inventory level and the shipment volume; the second time period is a time period adjacent to the first time period and located after the first time period.

[0169] In some embodiments, the determining unit is further configured to:

[0170] Determine a first growth rate of the shipment volume in the first historical time period relative to the shipment volume in the second historical time period according to the shipment volume in the first historical time period corresponding to the first time period and the shipment volume in the second historical time period corresponding to the third time period;

[0171] The prediction unit is further used for:

[0172] The shipment volume in the first time period is predicted according to the first growth rate and the shipment volume in the third time period.

[0173] In some embodiments, the prediction unit 602 is further configured to:

[0174] Inputting the promotion data of the first time period into the fitting regression model to predict the reference information of the goods in the first time period; the promotion data is used to characterize the promotion information and promotion plan of the goods; the reference information is used to characterize the exposure and price of the goods;

[0175] The reference information of the first time period is input into a sales forecasting model to predict the shipment volume of the first time period; the sales forecasting model is used to predict the shipment volume.

[0176] In some embodiments, the device further comprises a processing unit, and the processing unit is used to fit the promotion data of the first historical time period corresponding to the first time period with the reference information of the first historical time period to obtain the fitting regression model.

[0177] In some embodiments, the determining unit is further configured to:

[0178] Determine a second growth rate of the shipment volume in the third historical time period relative to the shipment volume in the second historical time period according to the shipment volume in the second historical time period corresponding to the third time period and the shipment volume in the third historical time period corresponding to the second time period;

[0179] The shipment volume in the second time period is predicted according to the second growth rate and the shipment volume in the third time period.

[0180] In some embodiments, the prediction unit is further configured to:

[0181] Inputting the promotion data of the second time period into the fitting regression model to predict the reference information of the goods in the second time period; the promotion data is used to characterize the promotion information and promotion plan of the goods; the reference information is used to characterize the exposure and price of the goods;

[0182] The reference information of the second time period is input into a sales volume forecasting model to forecast the shipment volume of the second time period; the sales volume forecasting model is used to forecast the shipment volume.

[0183] An embodiment of the present application also provides an electronic device, including a memory and a processor, wherein the memory stores a computer program that can be run on the processor, and when the processor executes the program, the data processing method provided in the above embodiment is implemented.

[0184] An embodiment of the present application also provides a storage medium, that is, a computer-readable storage medium, on which a computer program is stored. When the computer program is executed by a processor, the data processing method provided in the above embodiment is implemented.

[0185] It should be noted here that the description of the above storage medium and device embodiments is similar to the description of the above method embodiments, and has similar beneficial effects as the method embodiments. For technical details not disclosed in the storage medium and device embodiments of this application, please refer to the description of the method embodiments of this application for understanding.

[0186] It should be noted that Figure 7 A hardware entity diagram of an electronic device according to an embodiment of the present application is shown in FIG. Figure 7 As shown, the electronic device 700 includes: a processor 701, at least one communication bus 702, at least one external communication interface 704 and a memory 705. The communication bus 702 is configured to achieve connection and communication between these components. In an example, the electronic device 700 also includes: a user interface 703, wherein the user interface 703 may include a display screen, and the external communication interface 704 may include a standard wired interface and a wireless interface.

[0187] The memory 705 is configured to store instructions and applications executable by the processor 701, and can also cache data to be processed or processed by the processor 701 and various modules in the electronic device (for example, image data, audio data, voice communication data, and video communication data), which can be implemented through flash memory (FLASH) or random access memory (Random Access Memory, RAM).

[0188] It should be understood that "one embodiment" or "an embodiment" mentioned throughout the specification means that specific features, structures or characteristics related to the embodiment are included in at least one embodiment of the present application. Therefore, "in one embodiment" or "in some embodiments" appearing throughout the specification may not necessarily refer to the same embodiment. In addition, these specific features, structures or characteristics can be combined in one or more embodiments in any suitable manner. It should be understood that in various embodiments of the present application, the size of the sequence number of the above-mentioned processes does not mean the order of execution. The execution order of each process should be determined by its function and internal logic, and should not constitute any limitation on the implementation process of the embodiment of the present application. The above-mentioned sequence numbers of the embodiments of the present application are for description only and do not represent the advantages and disadvantages of the embodiments.

[0189] It should be noted that, in this article, the terms "include", "comprises" or any other variations thereof are intended to cover non-exclusive inclusion, so that a process, method, article or device including a series of elements includes not only those elements, but also other elements not explicitly listed, or also includes elements inherent to such process, method, article or device. In the absence of further restrictions, an element defined by the sentence "comprises a ..." does not exclude the existence of other identical elements in the process, method, article or device including the element.

[0190] In the several embodiments provided in the present application, it should be understood that the disclosed devices and methods can be implemented in other ways. The device embodiments described above are only schematic. For example, the division of the units is only a logical function division. There may be other division methods in actual implementation, such as: multiple units or components can be combined, or can be integrated into another system, or some features can be ignored or not executed. In addition, the coupling, direct coupling, or communication connection between the components shown or discussed can be through some interfaces, and the indirect coupling or communication connection of the devices or units can be electrical, mechanical or other forms.

[0191] The units described above as separate components may or may not be physically separated, and the components displayed as units may or may not be physical units; they may be located in one place or distributed on multiple network units; some or all of the units may be selected according to actual needs to achieve the purpose of the present embodiment.

[0192] In addition, all functional units in the embodiments of the present application may be integrated into one processing unit, or each unit may be a separate unit, or two or more units may be integrated into one unit; the above-mentioned integrated units may be implemented in the form of hardware or in the form of hardware plus software functional units.

[0193] A person skilled in the art can understand that all or part of the steps of implementing the above method embodiment can be completed by hardware related to program instructions, and the aforementioned program can be stored in a computer-readable storage medium. When the program is executed, it executes the steps of the above method embodiment; and the aforementioned storage medium includes: mobile storage devices, read-only memories (ROM), magnetic disks or optical disks, etc., various media that can store program codes.

[0194] Alternatively, if the above-mentioned integrated unit of the present application is implemented in the form of a software function module and sold or used as an independent product, it can also be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the embodiment of the present application can be essentially or partly embodied in the form of a software product that contributes to the relevant technology. The computer software product is stored in a storage medium, including several instructions to enable a computer device (which can be a personal computer, a server, or a network device, etc.) to execute all or part of the methods described in each embodiment of the present application. The aforementioned storage medium includes: various media that can store program codes, such as mobile storage devices, ROMs, magnetic disks, or optical disks.

[0195] The above is only an implementation method of the present application, but the protection scope of the present application is not limited thereto. Any person skilled in the art who is familiar with the present technical field can easily think of changes or substitutions within the technical scope disclosed in the present application, which should be included in the protection scope of the present application. Therefore, the protection scope of the present application should be based on the protection scope of the claims.

Claims

1. A data processing method, characterized in that: The method comprises: Receive a historical proportion sequence; based on the historical proportion sequence, increase or decrease the adjustment ratio for the proportion corresponding to each time sub-segment within a preset adjustment range, and determine at least one proportion sequence based on the proportion corresponding to each time sub-segment after the adjustment ratio; wherein the historical proportion sequence is a proportion sequence of a first historical time period corresponding to a first time period; and the first time period includes at least two time sub-segments; Determine at least one reference stock quantity according to the total stock quantity in the first time period and the reference proportion in the at least one proportion sequence; Determine at least one quantity to be sold according to the at least one reference stock quantity and the inventory quantity of the first time sub-segment; the first time sub-segment is any historical time sub-segment of the at least two time sub-segments; Determining at least one spot rate for the first time sub-period based on the shipment quantity of the first time sub-period and the at least one quantity to be sold; Using a reference stock quantity corresponding to a target spot rate that meets the condition among the at least one spot rate as a target reference stock quantity; Determine the target reference stocking quantity ratio sequence obtained in at least one ratio sequence as the target ratio sequence; the target ratio sequence is the ratio of the stocking quantity of different time sub-segments in at least one time sub-segment; The stock quantity of the second time sub-segment in the first time period is predicted according to the total stock quantity and the target proportion in the target proportion sequence; the target proportion is the proportion of the stock quantity corresponding to the second time sub-segment in the target proportion sequence; the second time sub-segment is a time sub-segment in the first time period.

2. The method according to claim 1, characterized in that The method further comprises: Determine the total stock amount according to the inventory amount at the first time of the first time period, the inventory amount at the second time of the first time period, and the shipment amount in the first time period; The first time is the start time of the first time period, and the second time is the end time of the first time period.

3. The method according to claim 2, characterized in that The method further comprises: The inventory level in the second time period is determined based on the shipment volume and the inventory-to-sales ratio coefficient in the second time period; the inventory-to-sales ratio coefficient is used to characterize the ratio between the inventory level and the shipment volume; the second time period is a time period adjacent to the first time period and located after the first time period.

4. The method according to claim 2, characterized in that: The method further comprises: Determine a first growth rate of the shipment volume in the first historical time period relative to the shipment volume in the second historical time period according to the shipment volume in the first historical time period corresponding to the first time period and the shipment volume in the second historical time period corresponding to the third time period; The shipment volume in the first time period is predicted according to the first growth rate and the shipment volume in the third time period.

5. The method according to claim 2, characterized in that: The method further comprises: Inputting the promotion data of the first time period into the fitting regression model to predict the reference information of the goods in the first time period; the promotion data is used to characterize the promotion information and promotion plan of the goods; the reference information is used to characterize the exposure and price of the goods; The reference information of the first time period is input into a sales forecasting model to predict the shipment volume of the first time period; the sales forecasting model is used to predict the shipment volume.

6. The method according to claim 5, characterized in that The method further comprises: The promotion data of the first historical time period corresponding to the first time period is fitted with the reference information of the first historical time period to obtain the fitted regression model.

7. The method according to claim 3, characterized in that The method further comprises: Determine a second growth rate of the shipment volume in the third historical time period relative to the shipment volume in the second historical time period according to the shipment volume in the second historical time period corresponding to the third time period and the shipment volume in the third historical time period corresponding to the second time period; The shipment volume in the second time period is predicted according to the second growth rate and the shipment volume in the third time period.

8. The method according to claim 3, characterized in that The method further comprises: Inputting the promotion data of the second time period into the fitting regression model to predict reference information of the goods in the second time period; the promotion data is used to characterize the promotion information and promotion plan of the goods; the reference information is used to characterize the exposure and price of the goods; The reference information of the second time period is input into a sales volume forecasting model to forecast the shipment volume of the second time period; the sales volume forecasting model is used to forecast the shipment volume.

9. A data processing device, characterized in that: The device comprises: A determination unit is configured to receive a historical proportion sequence; based on the historical proportion sequence, for the proportion corresponding to each time sub-segment, increase or decrease the adjustment ratio within a preset adjustment range, and determine at least one proportion sequence based on the proportion corresponding to each time sub-segment after the adjustment ratio; wherein the historical proportion sequence is a proportion sequence of a first historical time period corresponding to a first time period; the first time period includes at least two time sub-segments; at least one reference stock quantity is determined according to the total stock quantity of the first time period and the reference proportion in the at least one proportion sequence; at least one quantity to be sold is determined according to the at least one reference stock quantity and the inventory quantity of the first time sub-segment; the first time sub-segment is any historical time sub-segment of the at least two time sub-segments; at least one spot rate for the first time sub-segment is determined based on the shipment quantity of the first time sub-segment and the at least one quantity to be sold; the reference stock quantity corresponding to the target spot rate that meets the conditions in the at least one spot rate is used as the target reference stock quantity; the proportion sequence of the target reference stock quantity obtained in the at least one proportion sequence is determined as the target proportion sequence; the target proportion sequence is the proportion of the stock quantities of different time sub-segments in at least one time sub-segment; A prediction unit is used to predict the stock quantity of the second time sub-segment in the first time period according to the total stock quantity and the target proportion in the target proportion sequence, wherein the target proportion is the proportion of the stock quantity corresponding to the second time sub-segment in the target proportion sequence; and the second time sub-segment is a time sub-segment in the first time period.

10. An electronic device comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, characterized in that: When the processor executes the computer program, the data processing method according to any one of claims 1 to 8 is implemented.

11. A storage medium storing a computer program, characterized in that: When the computer program is executed by a processor, the data processing method according to any one of claims 1 to 8 is implemented.

Images