CN113657667A - Data processing method, device, equipment and storage medium - Google Patents

Data processing method, device, equipment and storage medium Download PDF

Info

Publication number
CN113657667A
CN113657667A CN202110942369.4A CN202110942369A CN113657667A CN 113657667 A CN113657667 A CN 113657667A CN 202110942369 A CN202110942369 A CN 202110942369A CN 113657667 A CN113657667 A CN 113657667A
Authority
CN
China
Prior art keywords
time period
time
stock
sequence
proportion
Prior art date
Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
Pending
Application number
CN202110942369.4A
Other languages
Chinese (zh)
Inventor
詹昌飞
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
Beijing Wodong Tianjun Information Technology Co Ltd
Original Assignee
Beijing Wodong Tianjun Information Technology Co Ltd
Priority date (The priority date is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the date listed.)
Filing date
Publication date
Application filed by Beijing Wodong Tianjun Information Technology Co Ltd filed Critical Beijing Wodong Tianjun Information Technology Co Ltd
Priority to CN202110942369.4A priority Critical patent/CN113657667A/en
Publication of CN113657667A publication Critical patent/CN113657667A/en
Priority to PCT/CN2022/108897 priority patent/WO2023020255A1/en
Pending legal-status Critical Current

Links

Images

Classifications

    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
    • G06Q10/00—Administration; Management
    • G06Q10/04—Forecasting or optimisation specially adapted for administrative or management purposes, e.g. linear programming or "cutting stock problem"
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
    • G06Q10/00—Administration; Management
    • G06Q10/06—Resources, workflows, human or project management; Enterprise or organisation planning; Enterprise or organisation modelling
    • G06Q10/063—Operations research, analysis or management
    • G06Q10/0631—Resource planning, allocation, distributing or scheduling for enterprises or organisations
    • G06Q10/06311—Scheduling, planning or task assignment for a person or group
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
    • G06Q10/00—Administration; Management
    • G06Q10/08—Logistics, e.g. warehousing, loading or distribution; Inventory or stock management
    • G06Q10/087—Inventory or stock management, e.g. order filling, procurement or balancing against orders
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
    • G06Q30/00—Commerce
    • G06Q30/06—Buying, selling or leasing transactions
    • G06Q30/0601—Electronic shopping [e-shopping]
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
    • G06Q30/00—Commerce
    • G06Q30/06—Buying, selling or leasing transactions
    • G06Q30/0601—Electronic shopping [e-shopping]
    • G06Q30/0633—Lists, e.g. purchase orders, compilation or processing
    • G06Q30/0635—Processing of requisition or of purchase orders

Landscapes

  • Business, Economics & Management (AREA)
  • Engineering & Computer Science (AREA)
  • Human Resources & Organizations (AREA)
  • Economics (AREA)
  • Strategic Management (AREA)
  • Marketing (AREA)
  • Accounting & Taxation (AREA)
  • Physics & Mathematics (AREA)
  • General Business, Economics & Management (AREA)
  • General Physics & Mathematics (AREA)
  • Finance (AREA)
  • Theoretical Computer Science (AREA)
  • Development Economics (AREA)
  • Entrepreneurship & Innovation (AREA)
  • Operations Research (AREA)
  • Quality & Reliability (AREA)
  • Tourism & Hospitality (AREA)
  • Game Theory and Decision Science (AREA)
  • Educational Administration (AREA)
  • Management, Administration, Business Operations System, And Electronic Commerce (AREA)

Abstract

The application discloses a data processing method, which comprises the following steps: determining a target proportion sequence from at least one proportion sequence according to the total stock quantity of the first time period and the stock input quantity of the first time period; the first time period comprises 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 stock quantity of different time subsections in the at least one time subsection; predicting the stock quantity of a second time subsection in the first time section according to the stock total quantity and a target ratio in the target ratio sequence; the target proportion is the proportion of the spare capacity corresponding to the second time sub-segment in the target proportion sequence. In addition, the application also discloses a data processing device, equipment and a storage medium.

Description

Data processing method, device, equipment and storage medium
Technical Field
The present application relates to the field of data processing, and relates to, but is not limited to, a data processing method, apparatus, device, and storage medium.
Background
In the related art, the e-commerce platform estimates the stock quantity according to manual experience in 618 and 11 large-scale scenes, so that the estimated stock quantity is not high in accuracy.
Disclosure of Invention
Embodiments of the present application provide a data processing method, apparatus, device, and storage medium for solving at least one problem in the related art, which can improve the accuracy of the estimated stock quantity.
The technical scheme of the application is realized as follows:
in a first aspect, an embodiment of the present application provides a data processing method, where the method includes:
determining a target proportion sequence from at least one proportion sequence according to the total stock quantity of the first time period and the stock input quantity of the first time period; the first time period comprises 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 stock quantity of different time subsections in the at least one time subsection;
predicting the stock quantity of a second time subsection in the first time section according to the stock total quantity and a target ratio in the target ratio sequence; the target proportion is the proportion of the spare capacity corresponding to the second time sub-segment in the target proportion sequence.
In a second aspect, an embodiment of the present application provides a data processing apparatus, where the apparatus includes:
the determining unit is used for determining a target proportion sequence from at least one proportion sequence according to the total stock quantity in the first time period and the cargo input quantity in the first time period; the first time period comprises 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 stock quantity of different time subsections in the at least one time subsection;
and the predicting unit is used for predicting the stock quantity of a second time subsection in the first time period according to the stock total quantity and a target ratio in the target ratio sequence, wherein the target ratio is the ratio of the stock quantity corresponding to the second time subsection in the target ratio sequence.
In a third aspect, an embodiment of the present application provides an electronic device, a memory, a processor, and a computer program stored on the memory and executable on the processor, where the processor implements the data processing method when executing the computer program.
In a fourth aspect, embodiments of the present application provide a storage medium, on which a computer program is stored, and the computer program, when executed by a processor, implements the data processing method described above.
The application provides a data processing method, a data processing device, data processing equipment and a storage medium, wherein a target proportion sequence is determined from at least one proportion sequence according to the total stock quantity in a first time period and the cargo input and output quantity in the first time period; the first time period comprises 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 stock quantity of different time subsections in the at least one time subsection; and predicting the stock quantity of a second time subsection in the first time period according to the stock total quantity and a target ratio in the target ratio sequence, wherein the target ratio is the ratio of the stock quantity corresponding to the second time subsection in the target ratio sequence. In this way, in the process of predicting the stock quantity of the second time subsection in the first time period, the target proportion sequence can be determined according to the stock quantity of the first time period and the stock input quantity of the first time subsection which occurs, and then the stock quantity of the second time subsection which does not occur can be predicted according to the stock total quantity and the target proportion in the target proportion sequence. In this way, the accuracy of the estimated stock quantity of the second time sub-period can be improved.
Drawings
FIG. 1 is a schematic diagram of an alternative architecture of a data processing system according to an embodiment of the present application;
fig. 2 is an alternative flow chart of a data processing method provided in an embodiment of the present application;
fig. 3 is an alternative flow chart of a data processing method provided in an embodiment of the present application;
FIG. 4 is a schematic view of an alternative interface provided by embodiments of the present application;
fig. 5 is an alternative flow chart of a data processing method provided in an embodiment of the present application;
fig. 6 is an alternative schematic structural diagram of a data processing apparatus according to an embodiment of the present application;
fig. 7 is an alternative structural schematic diagram of an electronic device provided in an embodiment of the present application.
Detailed Description
In order to make the objects, technical solutions and advantages of the embodiments of the present application clearer, the following will describe the specific technical solutions of the present application in further detail with reference to the accompanying drawings in the embodiments of the present application. The following examples are intended to illustrate the present application but are not intended to limit the scope of the present application.
Unless defined otherwise, all technical and scientific terms used herein have the same meaning as commonly understood by one of ordinary skill in the art to which this application belongs. The terminology used herein in the description of the present application is for the purpose of describing particular embodiments only and is not intended to be limiting of the application. As used herein, the term "and/or" includes any and all combinations of one or more of the associated listed items.
Before the present application is explained in further detail, terms and expressions referred to in the embodiments of the present application are explained, and the terms and expressions referred to in the embodiments of the present application are applied to the following explanations.
1) Stock Keeping Unit (SKU) for characterizing the smallest available Unit in inventory management, for example, if a commodity has at least one color, each of the at least one color may be a SKU, for example, for a shirt, if the shirt has both black and white colors, a black shirt may be a SKU, and a white shirt may be a SKU.
2) And the stock total quantity is used for representing the total quantity of the stock required to be prepared in a time period. The time period is a continuous time period, for example, a time period with a set duration, such as one year, one month, etc., wherein one time period may be divided into a plurality of time sub-periods, such as: the time period is one year, the time sub-period is one month, and for example, the time period is one month and the time sub-period is one day.
3) The stock quantity is used for representing the quantity of the stock needed to be prepared in a time subsection.
In one example, the stock quantity may be the quantity of stock needed to be stocked in the first week of the month of May.
4) Inventory, for characterizing the quantity of goods remaining in the warehouse.
The data processing method of the embodiment of the present application may be applied to the data processing system 100 shown in fig. 1, where as shown in fig. 1, the data processing system 100 includes: a server 10 and a client 20. Wherein the server 10 and the client 20 communicate with each other via a network 30.
The data processing method provided by the embodiment of the application can be applied to data processing equipment, and the data processing equipment can be a server 10 and can also be a client 20.
The data processing equipment determines a target proportion sequence from at least one proportion sequence according to the total stock quantity in a first time period and the cargo input and output quantity in the first time subsection, and predicts the stock quantity in a second time subsection in the first time period according to the total stock quantity and the target proportion in the target proportion sequence, wherein the first time period comprises at least two time subsections; 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 stock quantity of different time subsections in the at least one time subsection; the target proportion is the proportion of the spare capacity corresponding to the second time sub-segment in the target proportion sequence.
In the case that the data processing device is the server 10, the server 10 sends the predicted stock amount of the second time sub-segment in the first time segment to the client 20 through the network 30, and the client 20 displays the stock amount of the second time sub-segment to the user after receiving the stock amount of the second time sub-segment.
In the case where the data processing apparatus is a client 20, the client 20 presents the stock amount of the second time sub-segment directly to the user.
Embodiments of a data processing method, an apparatus, a device, and a storage medium according to the embodiments of the present application are described below with reference to a schematic diagram of a data processing system 100 shown in fig. 1.
Fig. 2 is a schematic implementation flow diagram of a data processing method provided in an embodiment of the present application, where the method is applied to a data processing device, and as shown in fig. 2, the method may include the following steps:
s201, determining a target proportion sequence from at least one proportion sequence according to the total stock quantity in the first time period and the cargo input and output quantity in the first time period.
Here, the first time period is a continuous time period, and the continuous time period may be a day, a month, or a year, which is not limited in the embodiment of the present application.
The first time sub-section may comprise at least two time sub-sections, and the first time sub-section is any one of the at least two time sub-sections, wherein the historical time sub-section is a time sub-section that has already occurred.
In an example, the first time period is a month, and the at least two time sub-periods included in the month may include: a first week, a second week, a third week, and a fourth week; if the first week is a time sub-segment that has already occurred, then the first week is a first time sub-segment.
In another example, the first time period is a year, and the at least two time sub-periods included in the year may include: first, second, third, … …, eleventh, and twelfth months; if the first month is a time sub-segment that has already occurred, then the first month is a first time sub-segment.
In yet another example, the first time period is a year, and the at least two time sub-periods included in the year may include: a first quarter, a second quarter, a third quarter, and a fourth quarter; if the first quarter is a time sub-segment that has already occurred, then the first quarter is a first time sub-segment.
In this embodiment, after determining the first time period, the data processing apparatus may determine, according to the first time period, a first time sub-period included in the first time period, and after determining the first time sub-period, determine the cargo import/export amount of the first time sub-period.
Here, the cargo access amount includes: a shipment quantity, which is indicative of the quantity of the goods sold, and an inventory quantity, which is indicative of the quantity of the goods remaining in the warehouse.
In an embodiment of the present application, the method for determining the shipment volume may include: the data processing equipment acquires at least one order data; the data processing equipment determines the shipment volume by analyzing the at least one order data; wherein each order data of the at least one order data is used for representing the quantity of the goods purchased by the user.
Here, the acquiring of at least one order data includes: at least one order data is obtained from a Distributed File System (HDFS).
Determining the quantity of the goods by analyzing the at least one order data comprises: and determining the shipment volume by summarizing each order data in the at least one order data.
In an example, the data processing device obtains 3 order data from the HDFS, where in the first order data, 10 purchased goods a by the user a are recorded, in the second order data, 20 purchased goods a by the user B are recorded, in the third order data, 10 purchased goods a by the user C is recorded, and the data processing device determines that the sold goods a is 40 by summarizing the purchased goods a by the user recorded in the three order data.
In the embodiment of the present application, the goods may be SKUs, or may be all goods in one goods category, which is not limited in this embodiment of the present application.
In one example, where the goods are all goods under one goods category and the goods category is a sweater, the goods may include all sizes of sweaters and all colors of sweaters under the sweater category.
In this 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 a ratio of a stock quantity of a corresponding time sub-segment to a stock quantity of the first time period.
In an example, the first time period is 5 months, and the at least two time sub-periods comprised by 5 months may comprise: a first week, a second week, a third week, and a fourth week; the at least one proportion sequence of 5 months may include: [ 20%, 30%, 40%, 10% ], the proportion sequence includes 20%, 30%, 40%, 10% for the proportion sequence [ 20%, 30%, 40%, 10% ], wherein the proportion 20% is the ratio of the stock quantity of the first week to the total stock quantity of 5 months, the proportion 30% is the ratio of the stock quantity of the second week to the total stock quantity of 5 months, the proportion 40% is the ratio of the stock quantity of the third week to the total stock quantity of 5 months, and the proportion 40% is the ratio of the stock quantity of the fourth week to the total stock quantity of 5 months.
In the embodiment of the application, the data processing equipment can receive at least one proportion sequence; determining the at least one proportion sequence as the at least one proportion sequence.
Here, the receiving the input at least one proportion sequence includes: the data processing device receives at least one proportion sequence input by a user.
In one example, if the received at least one of the sequences of fractions comprises: [ 20%, 30%, 40%, 10% ] and [ 30%, 20%, 10%, 40% ], the determined at least one of the ratio sequences is [ 20%, 30%, 40%, 10% ] and [ 30%, 20%, 10%, 40% ].
In the embodiment of the application, the data processing equipment receives a historical proportion sequence; on the basis of the historical occupation ratio sequence, for the occupation ratio corresponding to each time sub-section, the adjustment ratio can be increased or decreased, and the at least one occupation ratio sequence is determined; the historical proportion sequence is a proportion sequence of a first historical time period corresponding to a first time period; the adjusting step length is used for representing the proportion which can be adjusted in each time within the adjustable range; the adjustable range is used for representing a maximum adjusting range when each ratio is adjusted; .
In an example, the first time period is 5 months, the first historical time period corresponding to the first time period of 5 months is 5 months in the last year, the duty ratio sequence of the last 5 months, that is, the historical duty ratio sequence is [ 30%, 20%, 10%, 40% ], the adjustable range is ± 5%, the adjustable ratio is 1%, and at least two time sub-segments included in the 5 months may include: first week, second week, third week, and fourth week. Determining the at least one proportion sequence for month 5 may include: for determining the ratio for the first week, the adjustment ratio may be increased by 1% to obtain a ratio of 31%, for determining the ratio for the second week, the adjustment ratio may be decreased by 1% to obtain a ratio of 19%, for determining the ratio for the third week, the adjustment ratio may be increased by 1% to obtain a ratio of 11%, for determining the ratio for the fourth week, the adjustment ratio may be decreased by 1% to obtain a ratio of 39%, so that a ratio sequence of [ 31%, 29%, 11%, 39%) may be determined.
The target proportion sequence is the proportion of the stock in different time subsections in at least one time subsection.
In one example, the at least one proportion sequence includes: the occupied sequence 1[ 20%, 30%, 40%, 10% ] and the occupied sequence 2[ 30%, 20%, 10%, 40% ], the target occupied sequence can be determined to be the occupied sequence 1 from the occupied sequences 1 and 2.
S202, predicting the stock quantity of a second time subsection in the first time section according to the stock total quantity and the target ratio in the target ratio sequence.
Here, the target proportion is the proportion of the spare capacity corresponding to the second time subsection in the target proportion sequence.
In an example, if the total stock quantity is 400 and the target proportion sequence is [ 20%, 30%, 40%, 10% ], wherein 30% is the proportion of the stock quantity corresponding to the second time sub-segment, the stock quantity of the second time sub-segment can be predicted to be 120 according to the total stock quantity 400 and the target proportion 30%.
The embodiment of the application provides a data processing method, which comprises the steps of determining a target proportion sequence from at least one proportion sequence according to the total stock quantity in a first time period and the stock input and output quantity in the first time period; the first time period comprises at least two time sub-segments; the first time subsegment is any historical time subsegment in the at least two time subsegments; the target proportion sequence is the proportion of the stock quantity of different time subsections in the at least one time subsection; and predicting the stock quantity of a second time subsection in the first time period according to the stock total quantity and a target ratio in the target ratio sequence, wherein the target ratio is the ratio of the stock quantity corresponding to the second time subsection in the target ratio sequence. In this way, in the process of predicting the stock quantity of the second time subsection in the first time period, the target proportion sequence can be determined according to the stock quantity of the first time period and the stock input quantity of the first time subsection which occurs, and then the stock quantity of the second time subsection which does not occur can be predicted according to the stock total quantity and the target proportion in the target proportion sequence. In this way, the accuracy of the estimated stock quantity of the second time sub-period can be improved.
In some embodiments, as shown in fig. 3, the S201 may include:
s301, determining at least one reference stock quantity according to the stock total quantity in the first time period and the reference ratio in the at least one ratio sequence.
Here, the total stock quantity of the first time period is 400, and the at least one proportion sequence includes: the sequence 1: [ 20%, 30%, 40%, 10% ] and the sequence 2: [ 25%, 35%, 25% ], for a first time subsection in a first time period, the reference proportion of the first time subsection may be 20%, or may be 25%, a reference stock quantity for the first time subsection may be determined to be 80 according to the total stock quantity 400 of the first time period and the reference proportion of the first time subsection being 20%, a reference stock quantity for the first time subsection may also be determined to be 100 according to the total stock quantity 400 of the first time period and the reference proportion of the first time subsection being 25%, and the reference stock quantities 80 and 100 of the two first time subsections constitute at least one reference stock quantity.
S302, determining at least one stock rate aiming at the first time sub-period according to the at least one reference stock quantity and the cargo input-output quantity of the first time sub-period.
Here, for the first time subsection, at least one spot rate for the first time subsection may be determined based on at least one reference stock quantity for the first time subsection and the stock in-put quantity for the first time subsection, wherein the spot rate is a ratio of the shipment quantity and the quantity to be sold.
And S303, taking the reference stock-reserve corresponding to the target stock-reserve meeting the condition in the at least one stock-reserve as a target reference stock-reserve.
Here, the target spot rate satisfying the condition may include: and taking the highest spot rate in the at least one spot rate as the target spot rate.
In an example, the 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, the reference stock quantity corresponding to 60% is 100, and if the target stock rate is 60%, the reference stock quantity corresponding to 60% of the target stock rate is 100 as the target reference stock quantity.
S304, determining the proportion sequence of the target reference stock quantity in at least one proportion sequence as the target proportion sequence.
In one example, the at least one proportion sequence includes: the sequence 1: [ 20%, 30%, 40%, 10% ] and the sequence 2: [ 25%, 35%, 25% ], if the proportion sequence which gives the target reference stock quantity is the proportion sequence 1, the proportion sequence 1 is the target proportion sequence.
In the embodiment of the application, the target proportion sequence may be determined from at least one proportion sequence according to the total stock quantity in the first time period, the cargo input quantity in the first time period, and the delivery time (VLT) of the supplier.
In some embodiments, the cargo in-out amount includes a cargo out amount and an inventory amount, and the S302 may include: determining at least one quantity to be sold according to the at least one reference stock quantity and the inventory quantity; determining the at least one spot rate based on the shipment volume and the at least one offered for sale volume.
Here, for the first time subsection, if the shipment volume of the first time subsection is 50 and the stock volume of the first time subsection is 100, the at least one reference stock volume includes: 80 and 100, determining a sales volume of 180 according to a reference stock quantity 80 and an inventory quantity 100, and determining an actual rate of 27% based on the shipment volume of 50 and the sales volume of 180; it is also possible to determine an amount to be sold as 200 based on a reference stock quantity of 100 and an inventory quantity of 100, and determine an actual rate of stock as 25% based on the shipment quantity of 50 and the amount to be sold as 200.
In the above explanation of determining at least one stock-out rate, the example of determining at least one stock-out rate of the first time sub-segment is taken as an example, in practical application, the stock-out rate of the first time period may be determined by first determining the stock-out rate of each time sub-segment of at least two time sub-segments included in the first time period, and then summing the stock-out rates of each time sub-segment to obtain the stock-out rate of the first time period.
In an embodiment of the present application, the determining, by the data processing device, at least one stock-in rate for the first time period includes: inputting each proportion sequence in at least one proportion sequence into a Mixed-Integer Programming (MIP) model to obtain a current rate corresponding to each proportion sequence.
The model objective of the MIP model is to minimize turnaround
Figure RE-GDA0003295556340000091
Wherein R is a sequence of ratios, i is at least one sequence of ratios, itoiThe turnover rate corresponding to the ith ratio sequence is shown, and min represents the minimum turnover rate.
The constraint condition of the MIP model is a maximum spot rate, wherein the maximum spot rate can be realized by the following formula (1):
s.t.cri≥crmax,i∈[1,T]formula (1);
wherein s.t. is an abbreviation for subjuct to, used to characterize the constraint, criIndicating the current rate, cr, corresponding to the ith proportion sequencemaxRepresents the maximum stock-keeping rate, s.t.cri≥crmaxThe spot rate corresponding to the ith ratio sequence is greater than or equal to the maximum spot rate.
After determining the 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).
In some embodiments, the method may further comprise: determining the total stock quantity according to the stock quantity of the first time period, the stock quantity of the second time of the first time period and the shipment quantity of the first time period; the first time is a start time of the first time period, and the second time is an end time of the first time period.
Here, determining the stock total amount according to the stock amount at the first time of the first period of time, the stock amount at the second time of the first period of time, and the shipment amount at the first period of time may include: and subtracting the stock at the first time from the stock at the second time, and adding the shipment quantity at the first time to determine the total stock quantity.
In one example, the first time period is 5 months at the starting time of 5 months, 5 months and 1 day, the second time period is 5 months at the ending time of 5 months, and 31 days, if the inventory of 5 months and 1 day is 100, the inventory of 5 months and 31 days is 200, and the shipment of 5 months is 200, the determined total stock amount is 200 + 100+200, which is 300.
In some embodiments, the method may further comprise: and determining the inventory at the second time according to the shipment quantity and the stocking-selling ratio coefficient in the second time period.
Here, the stock-sales ratio coefficient is used to characterize a ratio between the stock quantity and the shipment quantity; the second time period is a time period adjacent to and subsequent to the first time period.
The determining the inventory amount at the second time according to the shipment volume and the stock-sales ratio coefficient at the second time period may include: and multiplying the shipment quantity in the second time period by the stock-sales ratio coefficient to determine the stock quantity at the second time.
In an example, if the shipment volume of the second time period is 100 and the stock-sales ratio coefficient is 0.4, the stock quantity of the second time period may be determined to be 40 according to the shipment volume of the second time period of 100 multiplied by the stock-sales ratio coefficient of 0.4.
In some embodiments, the method may further comprise: determining a first increase rate of the shipment volume of the first historical time period relative to the shipment volume of the second historical time period according to the shipment volume of the first historical time period corresponding to the first time period and the shipment volume of the second historical time period corresponding to the third time period; and predicting the shipment volume of the first time period according to the first increase rate and the shipment volume of the third time period.
Here, when the first time period is one month, the first historical time period corresponding to the first time period is a time period in the same year as the previous year, for example, when the first time period is 5 months in this year, the first historical time period corresponding to the previous month 5 may be 5 months in the last year, or may be 5 months in the previous year, which is not limited in the embodiment of the present application.
For example, when the third time period is 4 months this year, the second historical time period corresponding to 4 months may be 4 months last year or 4 months previous year, which is not limited in this embodiment of the application.
In an example, if the first time period is today's 5 month, the first historical time period is last year's 5 month, the shipment volume of last year's 5 month is 200, the third time period is today's 4 month, the shipment volume of this year's 4 month is 100, the second historical time period is last year's 4 month, and the shipment volume of last year's 4 month is 100, the first increase rate of the shipment volume of last year's 5 month relative to the shipment volume of last year's 4 month is determined to be 100% according to the shipment volume of last year's 5 month and the shipment volume of last year's 4 month is 100, and then the shipment volume of this year's 5 month is predicted to be 200 according to the first increase rate of 100% and the shipment volume of this year's 4 month 100.
In some embodiments, the method may further comprise: the data processing equipment inputs the promotion data of the first time period into a fitting regression model and predicts the reference information of the goods in the first time period; and inputting the reference information of the first time period into a sales prediction model to predict the shipment volume of the first time period.
Here, the promotion data is used to characterize the promotion information and promotion plan of the goods, wherein the promotion information is used to characterize a specific preferential form, and the promotion plan is used to characterize the total amount of goods expected to be sold throughout the promotion process; the reference information is used for representing the exposure and the price of the goods; the sales forecasting model is used for forecasting the shipment volume.
Promotional data may be entered through a given template. Wherein the given template may include: goods, promotional information, and a duration of the promotional information.
The promotional information may include: the discount information, the bonus discount information and the second killing information. In one example, the full reduction offer information is: full 100 minus 50. In one example, the bonus offer information is: 100 gift full of 100. In one example, the killing-by-second information is: killing within a second time.
In one example, the promotion program may be: the total quantity of goods expected to be sold during a two month sales promotion is 1000.
In an embodiment of the present application, fitting the regression model may include: logistic Regression (LR) model, maximum Gradient Boosting (XGBoost) model, Light Gradient Boosting Machine (LightGBM) model, Convolutional Neural Network (CNN), and the like.
Determining the sales prediction model may include: the data processing equipment acquires the time sequence characteristics and the attribute characteristics of the goods; and inputting the time sequence characteristics, the attribute characteristics, the exposure of the goods and the price of the goods into a reference sales prediction model, and training the reference sales prediction model to obtain a sales prediction model.
Here, the sales prediction model may include: linear regression models, time series sequence models, deep learning models, and the like, wherein the time series sequence models may include: prophett (Prophet) model and Holt-warm (Holt Winter) model, etc.; the deep learning model may include: a Recurrent Neural Network (RNN) model, a Multi-Quantile Recurrent Neural Network (MQRNN) model, a Long Short-Term Memory (LSTM) Network model, and the like.
Here, the timing characteristics of the goods may include: a historical sales characteristic of the good, the historical sales characteristic being indicative of an average sales of the good over a historical period of time.
In an example, the historical sales features may include: average sales over 3 days of history, 5 days of history, 7 days of history, 14 days of history, or 30 days of history.
The attribute characteristics of the cargo may include: brand, body type and volume of goods.
Obtaining attribute characteristics of the good may include: the data processing equipment acquires the attribute information of the goods from the goods information system, stores the acquired attribute information of the goods into a relational database (MYSQL database) or HDFS (Hadoop distributed database), and processes the attribute information of the needed goods to obtain the attribute characteristics of the goods, wherein the attribute characteristics of the goods can be represented by attribute values.
In some embodiments, the method may further comprise: and fitting 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.
In an example, the first time period is 5 months, the first historical time period corresponding to the 5 months is 5 months in the last year, the promotion data of the 5 months in the last year comprises full and reduced benefits, and the promotion data of the full and reduced benefits of the 5 months in the last year is fitted with the exposure of the goods and the actual hand price in the 5 months in the last year to obtain a fitting regression model.
In some embodiments, the method may further comprise: determining a second increase rate of the shipment volume of the third history time period relative to the shipment volume of the second history time period according to the shipment volume of the second history time period corresponding to the third time period and the shipment volume of the third history time period corresponding to the second time period; and predicting the shipment volume of the second time period according to the second increase rate and the shipment volume of the third time period.
Here, the third history time period corresponding to the second time period is a time period in the same period as the previous year, for example, when the second time period is 6 months in this year, the third history time period corresponding to the 6 months may be 6 months in the last year or 6 months in the previous year, which is not limited in this embodiment of the application.
In an example, if the third time period is today's month 4, the second historical time period is last year 4, the shipment volume of last year 4 is 100, the second time period is today's month 6, the third historical time period is last year 6, and the shipment volume of last year 6 is 200, then the second increase rate of the shipment volume of last year 6 relative to the shipment volume of last year 4 can be determined to be 100% according to the shipment volume of last year 6 and the shipment volume of last year 4 100, and then the shipment volume of this year 6 can be predicted to be 200 according to the second increase rate of 100% and the shipment volume of this year 4.
In the embodiment of the application, after the second increase rate R1 of the SKU is determined, the second increase rate R2 of all the goods under the brand represented by the SKU is determined, the magnitude relationship between the second increase rate R1 of the SKU and the second increase rate R2 of all the goods under the brand is determined, and if the second increase rate R1 of the SKU is greater than three times the second increase rate R2 of the goods under the brand, the second increase rate R1 of the SKU is replaced by the second increase rate R2 of all the goods under the brand.
In some embodiments, the method may further comprise: inputting the promotion data of the second time period into a fitting regression model, and predicting reference information of the goods in the second time period; and inputting the reference information of the second time period into a sales prediction model to predict the shipment volume of the second time period.
Here, the promotion data is used to characterize promotional information and promotion plans for the goods; the reference information is used for representing the exposure and the price of the goods; the sales forecasting model is used for forecasting the shipment volume. For the explanation of the promotion data, the reference information and the sales prediction model, please refer to the above embodiments, which are not described herein again.
In the embodiment of the application, after the original data, the intermediate data and the result data of the goods are obtained, the three data can be stored in the MYSQL database and the HDFS, and the data stored in the MYSQL database and the HDFS can be stored in a platform, such as a big data market platform. The original data is used for representing data before processing the data, such as attribute information, commodity numbers, commodity names and the like of goods; the intermediate data is used to characterize all data utilized prior to obtaining the result data, e.g., cargo in-out data for a first time sub-period; the result data is used for characterizing data obtained after processing the intermediate data, such as the predicted stock quantity of the second time subsection in the first time section.
Here, after storing the raw data, the intermediate data, and the result data into the MYSQL database and the HDFS, the raw data, the intermediate data, and the result data may be stored in the form of data tables in the MYSQL database and the HDFS. Wherein a data table is a way to store data in a structured way.
After the data are stored in the big data market platform, the data can be pushed to a MYSQL database of the replenishment system by using a Plumber direct vehicle, original data, intermediate data and result data are displayed on a display interface, and meanwhile, a user can select the data to be displayed according to the self requirement. A schematic diagram of the raw data, the intermediate data and the result data displayed on the display interface may be as shown in fig. 4.
In fig. 4, in the column of the history BAND, letters a to F respectively represent the sales volume ranks of the histories, wherein the historical sales volume rank represented by letter a is the highest, and the historical sales volume rank represented by letter F is the lowest.
The computer visualization presentation presents the computed data, the computed process, and the computed results to the user.
A purchase in transit indicates that the supplier is purchasing goods, but has not yet been sent to the warehouse.
In the e-commerce retail scene, 618 and 11 are common national shopping festivals, and due to the fact that the e-commerce platform is rich in commodities and the demand of the commodities is greatly fluctuated in the scene of promotion, great challenges are brought to replenishment management. The goods replenishment needs to consider huge demand fluctuation of tens of millions of commodities, and simultaneously needs to solve warehousing capacity arrangement brought by large-batch goods replenishment, so that continuous goods replenishment in a large promotion period is ensured, and the e-commerce platform warehousing cost and cash flow occupation are reasonably controlled.
In order to achieve the sales goals of the merchant and the retail platform, the two parties communicate with each other to form a relevant sales plan, and plan and arrange the promotion activities and the corresponding replenishment schemes according to the sales plan. The replenishment scheme is mainly divided into two parts, wherein one part is the pre-estimation of sales, the arrangement of price preference, activity granularity and the like of mainly pushed exploded product and smooth sold product SKU is manually estimated according to historical experience to greatly promote sales in the future, and as the number of E-commerce SKUs is as high as ten million, the SKU can only be manually layered according to the original sales, the SKU at different levels is pre-estimated, the refinement is difficult, and finally the total replenishment quantity estimation is carried out according to the pre-estimated sales; and secondly, warehousing rhythm arrangement is performed, the whole warehousing quantity is steeply increased in the early stage, the warehousing arrangement is a huge challenge, too early warehousing brings increase of inventory turnover, the warehousing and cash flow cost of the e-commerce is increased, and too late warehousing may cause insufficient warehousing capacity, failure in warehousing and sales loss. And the human beings refer to the warehousing rhythm according to the history synchronization and communicate with the logistics to determine the approximate warehousing rhythm. The warehousing logics and the warehousing rhythms adopted by replenishment of different buyers are possibly different, and no planning and planning is carried out.
The data processing method is mainly realized based on a machine learning and operation planning optimization method, and mainly comprises five steps of data acquisition, sales forecast, warehousing rhythm optimization, large promotion replenishment scheme output, data storage and output, wherein the data acquisition comprises data analysis, commodity information acquisition and the like, the sales forecast outputs future sales forecast of commodities by using a statistical method and a machine learning model, the warehousing rhythm optimization solves an optimal warehousing rhythm proportion (namely a target proportion sequence in the embodiment) by using simulation and operation planning optimization, the large promotion replenishment scheme output, and sales forecast and the optimal warehousing rhythm are used for calculating replenishment suggestion quantity of a plurality of times of a single day in a large promotion period of the commodities.
The method and the device combine a sales volume estimation module and a warehousing rhythm optimization module to carry out automatic decision of the replenishment commodities. First, various types of information known to the article are acquired, including basic attribute information (brand, category, etc.) of the article, time series information (sales data that has occurred in history), and business input (sales plan, sales promotion information, etc.). Then, the input information is input into a sales forecast device and a warehousing rhythm optimization device, and the future sales forecast and the optimal warehousing rhythm are output respectively. And finally, according to the sales forecast and the optimal warehousing rhythm, giving out the proposed quantity of the future large stock-keeping of the SKU for multiple times. The specific flow is as follows:
the hardware conditions necessary in the process of establishing the model are a computer, a server and at least one database, the memory stores program instructions capable of being executed by the processor, and the processor calls the program instructions to be capable of executing any one of five steps of data acquisition, sales estimation time sequence model regression, warehousing rhythm optimization solution, promotion replenishment suggestion output and data storage and output.
Step one, data acquisition.
The application requires commodity attribute data, user order data, sales promotion data input by business, and the like. The commodity attribute data can be acquired from a commodity information system, mainly crawled through commodity master station information, stored in MYSQL and HDFS, and processed and stored through database operation and selection of needed commodity information. The user order data are read through a distributed file system (HDFS), the user order data are analyzed, daily sales data of the commodity are processed, for example, 10 users of the commodity A place an order in 1 month and 1 day of 2020, the total sales of the commodity A on the day is obtained as x pieces by summarizing the total sales of the 10 users, the analyzed data are stored in a database, and calling and processing of a subsequent model are facilitated. The sales promotion data input by the business is input through a given template, and the system processes the sales promotion data.
The data required by the application needs to be updated regularly, so that a data flow task from a data source to the database storage is established, and the data is acquired regularly and stored in the required database. An example of the acquired correlation data structure is as follows.
And step two, sales forecast.
Sales forecast for future sales via business input, because the time period of the forecast is different from daily sales, the fluctuation of the overall demand becomes much larger, and the main reason of the fluctuation of the demand comes from the change of the promotion price and the flow. Therefore, the overall estimation is classified into the following two types:
the first method is that no promotion plan and sales plan which have great influence on sales are input for the business, and the future sales are predicted by using a statistical method for SKU, and the method comprises the following specific steps: calculating SKU dimension historical contemporaneous sales volume ring ratio coefficients R1 and R2 and a brand dimension overall ring ratio coefficient; judging the rationality of the ring ratio coefficient by using a rule, and smoothing the ring ratio coefficient which exceeds the integral N (N is 3) times of the brand, wherein the smoothing is replaced by the integral ring ratio coefficient of the dimensionality of the product brand; sales projections of 5 and 6 months were obtained using the sales volume and ring ratio coefficients that have occurred in the near term.
The second method provides promotion information and a sales plan for business, and predicts future sales for SKU with rich information by using a machine learning model, and comprises the following specific steps: fitting the sales promotion data and sales volume data generated by the SKU dimension history with the actual flow and the hand price to obtain a factor fitting regression model, wherein the model is not limited to LR, Xgboost, LightGBM, CNN and the like, and then obtaining the future estimated flow and the hand price according to the sales promotion information and plan input by the service; carrying out sales prediction model training, model linear regression, a time sequence prediction algorithm (Prophet or Holt witter), a deep learning model (RNN, MQRNN, LSTM) and the like according to the time sequence characteristics and the attribute characteristics of the SKU, the flow generated historically and the hand price characteristics; and (4) obtaining a future time sequence prediction result and outputting the future time sequence prediction result by combining the future predicted flow, the hand price and the trained sales prediction model.
And step three, determining the warehousing proportion.
Here, the warehousing proportion is the proportion sequence described in the above embodiment, the warehousing proportion may be input by a service, or statistics may be performed by using historical contemporaneous procurement data, the warehousing proportion from the first week W1 to the nth week Wn is calculated, and meanwhile, the warehousing proportion adjustable space Range is given; and setting an adjusting step length according to the warehousing proportion and the adjustable space Range, and combining all possible warehousing proportions.
Simulating future stock sales of the SKU according to the large total stock quantity, all warehousing proportions and the initial stock I0+ VLT to obtain simulation results corresponding to different warehousing rhythms; and (3) solving the storage rhythm with the optimal SKU dimension by using the MIP model: the goal is to minimize turnaround, constrained to the optimal spot rate.
And finally, solving the optimal warehousing rhythm by using an optimization solver CPLEX solver to obtain the optimal target warehousing proportion in turnover under the condition of optimal current rate.
And finally, solving the optimal warehousing rhythm by using an optimization solver CPLEX solver to obtain the optimal warehousing rhythm proportion for turnover under the condition of the optimal current cargo rate.
Here, the target warehousing ratio is a warehousing ratio corresponding to a reference stock-in rate, and the reference stock-in rate is the highest stock-in rate of the at least one stock-in rate.
And step four, predicting the recommended quantity of the promotion replenishment.
And calculating the general stock plan of the whole SKU according to the general stock quantity and the optimal warehousing rhythm. And at each large stock promotion node, the recommended replenishment quantity is estimated as the total stock quantity and the warehousing rhythm proportion of the node.
And step five, storing and outputting data.
The result storage is mainly divided into 2 steps, wherein the first step is to store original data (attribute characteristics and promotion characteristics), intermediate data (intermediate variable data) and result data through a distributed file management system (HDFS), and store a data table to a big data mart platform. And the second step is that the Plumber straight-through vehicle is used for pushing the data to a MYSQL database of the replenishment system, the front end of the replenishment system is used for outputting original data, intermediate data and result data, and meanwhile, a user can select system display data according to the self requirement.
As shown in fig. 5, a data processing method provided in an embodiment of the present application may include:
s501, the data processing device receives target data.
Here, the target data may include: sales plans for goods, promotional information, or sales volume data.
S502, the data processing device judges whether the target data comprises the sales plan and the promotion information.
If the sales plan and the promotion information are included in the target data, the step S502a is executed: and carrying out sales forecast by utilizing a machine learning model.
If the sales plan and the promotion information are not included in the target data, then S502b is executed: and carrying out sales forecast by using historical sales data.
S503, the data processing device outputs monthly sales forecast.
And S504, calculating the historical synchronous warehousing proportion by the data processing equipment according to the sales data.
And S505, forming at least one warehousing proportion by the data processing equipment according to the adjusting proportion.
And S506, for different warehousing proportions, simulating the stock sales by the data processing equipment by using simulation to obtain the stock corresponding to the different warehousing proportions.
And S507, the data processing equipment solves the optimal warehousing proportion by utilizing the operational research model.
And S508, determining a promotion replenishment plan by the data processing equipment according to the monthly sales forecast and the optimal warehousing proportion.
Fig. 6 is a data processing apparatus according to an embodiment of the present application, and as shown in fig. 6, the data processing apparatus 600 includes:
a determining unit 601, configured to determine a target proportion sequence from at least one proportion sequence according to the total stock quantity in the first time period and the cargo input quantity in the first time period; the first time period comprises 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 stock quantity of different time subsections in the at least one time subsection;
a predicting unit 602, configured to predict a stock amount of a second time sub-segment in the first time segment according to the stock total amount and a target proportion in the target proportion sequence; the target proportion is the proportion of the spare capacity corresponding to the second time sub-segment in the target proportion sequence.
In some embodiments, the determining unit is further configured to:
determining at least one reference stock quantity according to the total stock quantity of the first time period and the reference ratio in the at least one ratio sequence;
determining at least one spot rate for the first time sub-period based on the at least one reference stock quantity and the cargo in-out quantity for the first time sub-period;
taking a reference stock-keeping quantity corresponding to a target stock-keeping rate meeting the condition in the at least one stock-keeping rate as a target reference stock-keeping quantity;
and determining a ratio sequence of the target reference stock quantity obtained from at least one ratio sequence as the target ratio sequence.
In some embodiments, the determining unit is further configured to:
determining at least one quantity to be sold according to the at least one reference stock quantity and the inventory quantity;
determining the at least one spot rate based on the shipment volume and the at least one offered for sale volume.
In some embodiments, the determining unit is further configured to:
determining the total stock quantity according to the stock quantity of the first time period, the stock quantity of the second time of the first time period and the shipment quantity of the first time period; the first time is a start time of the first time period, and the second time is an end time of the first time period.
In some embodiments, the determining unit is further configured to:
determining the inventory at the second time according to the shipment quantity and the stock-sales ratio coefficient at the second time period; the stock-sales ratio coefficient is used for representing the ratio between the stock quantity and the shipment quantity; the second time period is a time period adjacent to and subsequent to the first time period.
In some embodiments, the determining unit is further configured to:
determining a first increase rate of the shipment volume of the first historical time period relative to the shipment volume of the second historical time period according to the shipment volume of the first historical time period corresponding to the first time period and the shipment volume of the second historical time period corresponding to the third time period;
the prediction unit is further configured to:
and predicting the shipment volume of the first time period according to the first increase rate and the shipment volume of the third time period.
In some embodiments, the prediction unit 602 is further configured to:
inputting the promotion data of the first time period into a fitting regression model, and predicting reference information of the goods in the first time period; the promotion data is used to characterize promotional information and a promotion plan for the good; the reference information is used for representing the exposure and the price of the goods;
inputting the reference information of the first time period into a sales prediction model to predict the shipment volume of the first time period; the sales forecasting model is used for forecasting the shipment volume.
In some embodiments, the apparatus further includes a processing unit, and the processing unit is configured to fit the promotion data of the first historical time period corresponding to the first time period to the reference information of the first historical time period to obtain the fitted regression model.
In some embodiments, the determining unit is further configured to:
determining a second increase rate of the shipment volume of the third history time period relative to the shipment volume of the second history time period according to the shipment volume of the second history time period corresponding to the third time period and the shipment volume of the third history time period corresponding to the second time period;
and predicting the shipment volume of the second time period according to the second increase rate and the shipment volume of the third time period.
In some embodiments, the prediction unit is further configured to:
inputting the promotion data of the second time period into a fitting regression model, and predicting reference information of the goods in the second time period; the promotion data is used to characterize promotional information and a promotion plan for the good; the reference information is used for representing the exposure and the price of the goods;
inputting the reference information of the second time period into a sales prediction model to predict the shipment volume of the second time period; the sales forecasting model is used for forecasting the shipment volume.
An embodiment of the present application further provides an electronic device, which includes a memory and a processor, where the memory stores a computer program that can be run on the processor, and the processor executes the computer program to implement the data processing method provided in the foregoing embodiment.
The present application also provides a storage medium, that is, a computer-readable storage medium, on which a computer program is stored, and the computer program, when executed by a processor, implements the data processing method provided in the above embodiments.
Here, it should be noted that: the above description of the storage medium and device embodiments is similar to the description of the method embodiments above, with similar advantageous effects as the method embodiments. For technical details not disclosed in the embodiments of the storage medium and apparatus of the present application, reference is made to the description of the embodiments of the method of the present application for understanding.
Fig. 7 is a schematic diagram of a hardware entity of an electronic device according to an embodiment of the present application, and as shown in fig. 7, the electronic device 700 includes: a processor 701, at least one communication bus 702, at least one external communication interface 704 and memory 705. Wherein the communication bus 702 is configured to enable connective communication between these components. In an example, the electronic device 700 further comprises: a user interface 703, wherein the user interface 703 may comprise a display screen and the external communication interface 704 may comprise a standard wired interface and a wireless interface.
The Memory 705 is configured to store instructions and applications executable by the processor 701, and may also buffer data (e.g., image data, audio data, voice communication data, and video communication data) to be processed or already processed by the processor 701 and modules in the electronic device, and may be implemented by a FLASH Memory (FLASH) or a Random Access Memory (RAM).
It should be appreciated that reference throughout this specification to "one embodiment" or "an embodiment" means that a particular feature, structure or characteristic described in connection with the embodiment is included in at least one embodiment of the present application. Thus, the appearances of the phrases "in one embodiment" or "in some embodiments" in various places throughout this specification are not necessarily all referring to the same embodiment. Furthermore, the particular features, structures, or characteristics may be combined in any suitable manner in one or more embodiments. It should be understood that, in the various embodiments of the present application, the sequence numbers of the above-mentioned processes do not mean the execution sequence, and the execution sequence of each process should be determined by its function and inherent logic, and should not constitute any limitation to the implementation process of the embodiments of the present application. The above-mentioned serial numbers of the embodiments of the present application are merely for description and do not represent the merits of the embodiments.
It should be noted that, in this document, the terms "comprises," "comprising," or any other variation thereof, are intended to cover a non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements does not include only those elements but may include other elements not expressly listed or inherent to such process, method, article, or apparatus. Without further limitation, an element defined by the phrase "comprising an … …" does not exclude the presence of other like elements in a process, method, article, or apparatus that comprises the element.
In the several embodiments provided in the present application, it should be understood that the disclosed apparatus and method may be implemented in other ways. The above-described device embodiments are merely illustrative, for example, the division of the unit is only a logical functional division, and there may be other division ways in actual implementation, such as: multiple units or components may be combined, or may be integrated into another system, or some features may be omitted, or not implemented. In addition, the coupling, direct coupling or communication connection between the components shown or discussed may be through some interfaces, and the indirect coupling or communication connection between the devices or units may be electrical, mechanical or other forms.
The units described as separate parts may or may not be physically separate, and parts displayed as units may or may not be physical units; can be located in one place or distributed on a plurality of network units; some or all of the units can be selected according to actual needs to achieve the purpose of the solution of the embodiment.
In addition, all functional units in the embodiments of the present application may be integrated into one processing unit, or each unit may be separately regarded as one unit, or two or more units may be integrated into one unit; the integrated unit can be realized in a form of hardware, or in a form of hardware plus a software functional unit.
Those of ordinary skill in the art will understand that: all or part of the steps for realizing the method embodiments can be completed by hardware related to program instructions, the program can be stored in a computer readable storage medium, and the program executes the steps comprising the method embodiments when executed; and the aforementioned storage medium includes: various media that can store program codes, such as a removable Memory device, a Read Only Memory (ROM), a magnetic disk, or an optical disk.
Alternatively, the integrated units described above in the present application may be stored in a computer-readable storage medium if they are implemented in the form of software functional modules and sold or used as independent products. Based on such understanding, the technical solutions of the embodiments of the present application may be essentially implemented or portions thereof contributing to the related art may be embodied in the form of a software product stored in a storage medium, and including several instructions for enabling a computer device (which may be a personal computer, a server, or a network device) to execute all or part of the methods described in the embodiments of the present application. And the aforementioned storage medium includes: a removable storage device, a ROM, a magnetic or optical disk, or other various media that can store program code.
The above description is only for the embodiments of the present application, but the scope of the present application is not limited thereto, and any person skilled in the art can easily conceive of changes or substitutions within the technical scope of the present application, and shall be covered by the scope of the present application. Therefore, the protection scope of the present application shall be subject to the protection scope of the claims.

Claims (13)

1. A method of data processing, the method comprising:
determining a target proportion sequence from at least one proportion sequence according to the total stock quantity of the first time period and the stock input quantity of the first time period; the first time period comprises 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 stock quantity of different time subsections in the at least one time subsection;
predicting the stock quantity of a second time subsection in the first time section according to the stock total quantity and a target ratio in the target ratio sequence; the target proportion is the proportion of the spare capacity corresponding to the second time sub-segment in the target proportion sequence.
2. The method of claim 1, wherein determining a target proportion sequence from at least one proportion sequence based on the total inventory available for the first time period and the inventory in-put for the first time period comprises:
determining at least one reference stock quantity according to the total stock quantity of the first time period and the reference ratio in the at least one ratio sequence;
determining at least one spot rate for the first time sub-period based on the at least one reference stock quantity and the cargo in-out quantity for the first time sub-period;
taking a reference stock-keeping quantity corresponding to a target stock-keeping rate meeting the condition in the at least one stock-keeping rate as a target reference stock-keeping quantity;
and determining a ratio sequence of the target reference stock quantity obtained from at least one ratio sequence as the target ratio sequence.
3. The method of claim 2, wherein the cargo in-out amount includes a shipment amount and an inventory amount; the determining at least one spot rate for a first time sub-period according to the at least one reference stock quantity and the cargo in-out quantity of the first time sub-period comprises:
determining at least one quantity to be sold according to the at least one reference stock quantity and the inventory quantity;
determining the at least one spot rate based on the shipment volume and the at least one offered for sale volume.
4. The method of claim 1, further comprising:
determining the total stock quantity according to the stock quantity of the first time period, the stock quantity of the second time of the first time period and the shipment quantity of the first time period;
the first time is a start time of the first time period, and the second time is an end time of the first time period.
5. The method of claim 4, further comprising:
determining the inventory at the second time according to the shipment quantity and the stock-sales ratio coefficient at the second time period; the stock-sales ratio coefficient is used for representing the ratio between the stock quantity and the shipment quantity; the second time period is a time period adjacent to and subsequent to the first time period.
6. The method of claim 4, further comprising:
determining a first increase rate of the shipment volume of the first historical time period relative to the shipment volume of the second historical time period according to the shipment volume of the first historical time period corresponding to the first time period and the shipment volume of the second historical time period corresponding to the third time period;
and predicting the shipment volume of the first time period according to the first increase rate and the shipment volume of the third time period.
7. The method of claim 4, further comprising:
inputting the promotion data of the first time period into a fitting regression model, and predicting reference information of the goods in the first time period; the promotion data is used to characterize promotional information and a promotion plan for the good; the reference information is used for representing the exposure and the price of the goods;
inputting the reference information of the first time period into a sales prediction model to predict the shipment volume of the first time period; the sales forecasting model is used for forecasting the shipment volume.
8. The method of claim 7, further comprising:
and fitting 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.
9. The method of claim 5, further comprising:
determining a second increase rate of the shipment volume of the third history time period relative to the shipment volume of the second history time period according to the shipment volume of the second history time period corresponding to the third time period and the shipment volume of the third history time period corresponding to the second time period;
and predicting the shipment volume of the second time period according to the second increase rate and the shipment volume of the third time period.
10. The method of claim 5, further comprising:
inputting the promotion data of the second time period into a fitting regression model, and predicting reference information of the goods in the second time period; the promotion data is used to characterize promotional information and a promotion plan for the good; the reference information is used for representing the exposure and the price of the goods;
inputting the reference information of the second time period into a sales prediction model to predict the shipment volume of the second time period; the sales forecasting model is used for forecasting the shipment volume.
11. A data processing apparatus, characterized in that the apparatus comprises:
the determining unit is used for determining a target proportion sequence from at least one proportion sequence according to the total stock quantity in the first time period and the cargo input quantity in the first time period; the first time period comprises 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 stock quantity of different time subsections in the at least one time subsection;
and the predicting unit is used for predicting the stock quantity of a second time subsection in the first time period according to the stock total quantity and a target ratio in the target ratio sequence, wherein the target ratio is the ratio of the stock quantity corresponding to the second time subsection in the target ratio sequence.
12. An electronic device comprising a memory, a processor and a computer program stored on the memory and executable on the processor, characterized in that the processor implements the data processing method of any one of claims 1 to 10 when executing the computer program.
13. A storage medium storing a computer program which, when executed by a processor, implements the data processing method of any one of claims 1 to 10.
CN202110942369.4A 2021-08-17 2021-08-17 Data processing method, device, equipment and storage medium Pending CN113657667A (en)

Priority Applications (2)

Application Number Priority Date Filing Date Title
CN202110942369.4A CN113657667A (en) 2021-08-17 2021-08-17 Data processing method, device, equipment and storage medium
PCT/CN2022/108897 WO2023020255A1 (en) 2021-08-17 2022-07-29 Data processing method and apparatus, device, and storage medium

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN202110942369.4A CN113657667A (en) 2021-08-17 2021-08-17 Data processing method, device, equipment and storage medium

Publications (1)

Publication Number Publication Date
CN113657667A true CN113657667A (en) 2021-11-16

Family

ID=78479940

Family Applications (1)

Application Number Title Priority Date Filing Date
CN202110942369.4A Pending CN113657667A (en) 2021-08-17 2021-08-17 Data processing method, device, equipment and storage medium

Country Status (2)

Country Link
CN (1) CN113657667A (en)
WO (1) WO2023020255A1 (en)

Cited By (1)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
WO2023020255A1 (en) * 2021-08-17 2023-02-23 北京沃东天骏信息技术有限公司 Data processing method and apparatus, device, and storage medium

Families Citing this family (1)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN116342042B (en) * 2023-05-25 2024-04-19 北京京东乾石科技有限公司 Goods supplementing method and device and storage medium

Citations (12)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
JPH08241353A (en) * 1995-03-07 1996-09-17 Kobe Steel Ltd Stocking plan support device
US20080228604A1 (en) * 2005-09-07 2008-09-18 Von Helmolt Hans-Ulrich A Methods and Systems For Dynamic Calculation of Safety Stock Quantity
WO2017121285A1 (en) * 2016-01-14 2017-07-20 阿里巴巴集团控股有限公司 Time series-based data prediction method and device
CN107123017A (en) * 2017-03-22 2017-09-01 重庆允升科技有限公司 A kind of industrial goods source commodity recommends method
CN109272276A (en) * 2018-09-29 2019-01-25 石化盈科信息技术有限责任公司 A kind of inventory replenishes management method and device
CN110363454A (en) * 2018-04-09 2019-10-22 杉数科技(北京)有限公司 For determining the method and device of commodity replenishment quantity
CN111582788A (en) * 2020-04-29 2020-08-25 北京小米松果电子有限公司 Article scheduling method and device and computer readable storage medium
CN112085442A (en) * 2020-08-27 2020-12-15 北京每日优鲜电子商务有限公司 Device operation method, device, electronic device and computer readable medium
CN113095745A (en) * 2020-01-09 2021-07-09 北京沃东天骏信息技术有限公司 Replenishment decision model training and replenishment decision method, system, equipment and medium
CN113159355A (en) * 2020-01-07 2021-07-23 北京京邦达贸易有限公司 Data prediction method, data prediction device, logistics cargo quantity prediction method, medium and equipment
CN113159665A (en) * 2021-03-04 2021-07-23 深圳市腾辉信息技术有限公司 Warehouse stock method based on e-commerce platform, electronic equipment and storage medium
CN114742505A (en) * 2022-04-20 2022-07-12 农夫山泉股份有限公司 Inventory control method and device

Family Cites Families (3)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US20160092828A1 (en) * 2014-09-26 2016-03-31 Paul Sofsky System and Method for Taking Inventory and Ordering
CN109978428A (en) * 2017-12-28 2019-07-05 北京京东尚科信息技术有限公司 Data estimation method and apparatus and computer readable storage medium
CN113657667A (en) * 2021-08-17 2021-11-16 北京沃东天骏信息技术有限公司 Data processing method, device, equipment and storage medium

Patent Citations (12)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
JPH08241353A (en) * 1995-03-07 1996-09-17 Kobe Steel Ltd Stocking plan support device
US20080228604A1 (en) * 2005-09-07 2008-09-18 Von Helmolt Hans-Ulrich A Methods and Systems For Dynamic Calculation of Safety Stock Quantity
WO2017121285A1 (en) * 2016-01-14 2017-07-20 阿里巴巴集团控股有限公司 Time series-based data prediction method and device
CN107123017A (en) * 2017-03-22 2017-09-01 重庆允升科技有限公司 A kind of industrial goods source commodity recommends method
CN110363454A (en) * 2018-04-09 2019-10-22 杉数科技(北京)有限公司 For determining the method and device of commodity replenishment quantity
CN109272276A (en) * 2018-09-29 2019-01-25 石化盈科信息技术有限责任公司 A kind of inventory replenishes management method and device
CN113159355A (en) * 2020-01-07 2021-07-23 北京京邦达贸易有限公司 Data prediction method, data prediction device, logistics cargo quantity prediction method, medium and equipment
CN113095745A (en) * 2020-01-09 2021-07-09 北京沃东天骏信息技术有限公司 Replenishment decision model training and replenishment decision method, system, equipment and medium
CN111582788A (en) * 2020-04-29 2020-08-25 北京小米松果电子有限公司 Article scheduling method and device and computer readable storage medium
CN112085442A (en) * 2020-08-27 2020-12-15 北京每日优鲜电子商务有限公司 Device operation method, device, electronic device and computer readable medium
CN113159665A (en) * 2021-03-04 2021-07-23 深圳市腾辉信息技术有限公司 Warehouse stock method based on e-commerce platform, electronic equipment and storage medium
CN114742505A (en) * 2022-04-20 2022-07-12 农夫山泉股份有限公司 Inventory control method and device

Non-Patent Citations (2)

* Cited by examiner, † Cited by third party
Title
宋毅斐;鹿岩;孙世光;: "基于库存模型法的药品采购与库存控制策略", 中国药房, no. 01, 10 January 2016 (2016-01-10) *
智慧零售与餐饮: "智能补货***和库存预测的实现逻辑", Retrieved from the Internet <URL:https://www.toutiao.com/article/6876242790095782411/> *

Cited By (1)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
WO2023020255A1 (en) * 2021-08-17 2023-02-23 北京沃东天骏信息技术有限公司 Data processing method and apparatus, device, and storage medium

Also Published As

Publication number Publication date
WO2023020255A1 (en) 2023-02-23

Similar Documents

Publication Publication Date Title
JP7340456B2 (en) Dynamic feature selection for model generation
US20210334845A1 (en) Method and system for generation of at least one output analytic for a promotion
US11922440B2 (en) Demand forecasting using weighted mixed machine learning models
US20230018311A1 (en) Systems and methods for quantity determinations without predicting out of stock events
US11010798B2 (en) System and method for integrating retail price optimization for revenue and profit with business rules
US10181138B2 (en) System and method for determining retail-business-rule coefficients from current prices
Verstraete et al. A data-driven framework for predicting weather impact on high-volume low-margin retail products
WO2023020255A1 (en) Data processing method and apparatus, device, and storage medium
CN102282551A (en) Automated decision support for pricing entertainment tickets
US20160283954A1 (en) System and method for determining a combined effective price discount in tier pricing
CN115689451A (en) Method, device, terminal and medium for determining replenishment quantity of off-line retail store
US20200034859A1 (en) System and method for predicting stock on hand with predefined markdown plans
Wang et al. M-GAN-XGBOOST model for sales prediction and precision marketing strategy making of each product in online stores
EP2343683A1 (en) Data relationship preservation in a multidimension data hierarchy
CN111768243A (en) Sales prediction method, prediction model construction method, device, equipment and medium
Deng et al. Alibaba realizes millions in cost savings through integrated demand forecasting, inventory management, price optimization, and product recommendations
WO2002079901A2 (en) Customer preference system
US20200134649A1 (en) Forecasting demand for groups of items, such as mobile phones
US20210304279A1 (en) Information processing method, electronic device and computer-readable storage medium
US20210304231A1 (en) System and method for rule based forecasting in multichannel, multi-offer, and multi-customer-segment environments
US12039564B2 (en) Method and system for generation of at least one output analytic for a promotion
Liu et al. Intelligent modeling of abnormal demand forecasting for medical consumables in smart city
US20240185285A1 (en) Method and system for generation of at least one output analytics for a promotion
Stanelytė Inventory Optimization in Retail Network by Creating a Demand Prediction Model
Marcos Assessing the impact of operational performance improvement on business partners' profitability-the case of a luxury fashion e-commerce

Legal Events

Date Code Title Description
PB01 Publication
PB01 Publication
SE01 Entry into force of request for substantive examination
SE01 Entry into force of request for substantive examination