CN116342042B - Goods supplementing method and device and storage medium - Google Patents
Goods supplementing method and device and storage medium Download PDFInfo
- Publication number
- CN116342042B CN116342042B CN202310599591.8A CN202310599591A CN116342042B CN 116342042 B CN116342042 B CN 116342042B CN 202310599591 A CN202310599591 A CN 202310599591A CN 116342042 B CN116342042 B CN 116342042B
- Authority
- CN
- China
- Prior art keywords
- replenishment
- inventory
- stock
- restocking
- sample
- 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.)
- Active
Links
- 238000000034 method Methods 0.000 title claims abstract description 58
- 230000001502 supplementing effect Effects 0.000 title claims abstract description 23
- 238000012549 training Methods 0.000 claims description 24
- 238000012545 processing Methods 0.000 claims description 17
- 238000004590 computer program Methods 0.000 claims description 4
- 244000309464 bull Species 0.000 abstract description 4
- 230000000694 effects Effects 0.000 abstract description 4
- 210000003899 penis Anatomy 0.000 abstract description 3
- 238000004891 communication Methods 0.000 description 3
- 238000004364 calculation method Methods 0.000 description 2
- 238000010586 diagram Methods 0.000 description 2
- KLDZYURQCUYZBL-UHFFFAOYSA-N 2-[3-[(2-hydroxyphenyl)methylideneamino]propyliminomethyl]phenol Chemical compound OC1=CC=CC=C1C=NCCCN=CC1=CC=CC=C1O KLDZYURQCUYZBL-UHFFFAOYSA-N 0.000 description 1
- 238000009825 accumulation Methods 0.000 description 1
- 201000001098 delayed sleep phase syndrome Diseases 0.000 description 1
- 208000033921 delayed sleep phase type circadian rhythm sleep disease Diseases 0.000 description 1
- 238000012217 deletion Methods 0.000 description 1
- 230000037430 deletion Effects 0.000 description 1
- 230000006870 function Effects 0.000 description 1
- 230000003287 optical effect Effects 0.000 description 1
- 230000000737 periodic effect Effects 0.000 description 1
- 230000007306 turnover Effects 0.000 description 1
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
- G06Q10/08—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
-
- Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
- Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
- Y02P—CLIMATE CHANGE MITIGATION TECHNOLOGIES IN THE PRODUCTION OR PROCESSING OF GOODS
- Y02P90/00—Enabling technologies with a potential contribution to greenhouse gas [GHG] emissions mitigation
- Y02P90/30—Computing systems specially adapted for manufacturing
Landscapes
- Business, Economics & Management (AREA)
- Economics (AREA)
- Engineering & Computer Science (AREA)
- Marketing (AREA)
- Quality & Reliability (AREA)
- Finance (AREA)
- Entrepreneurship & Innovation (AREA)
- Human Resources & Organizations (AREA)
- Accounting & Taxation (AREA)
- Operations Research (AREA)
- Development Economics (AREA)
- Strategic Management (AREA)
- Tourism & Hospitality (AREA)
- Physics & Mathematics (AREA)
- General Business, Economics & Management (AREA)
- General Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
The application relates to the technical field of electronic application. The application provides a method and a device for supplementing goods, and a storage medium, wherein the method comprises the following steps: acquiring historical sales data before the replenishment time of the product; generating time sequence characteristic data corresponding to the historical sales data; acquiring attribute information and replenishment parameters of a product; inputting the time sequence characteristic data, the attribute information and the replenishment parameters into a preset inventory model, and outputting the target inventory quantity and the replenishment point inventory quantity of the product; acquiring stock in stock and in transit stock of the product; and generating a restocking strategy according to the target stock quantity, the restocking point stock quantity, the spot stock quantity and the in-transit stock quantity so as to execute corresponding restocking operation based on the restocking strategy. The application solves the problem of large error of the goods supplementing quantity caused by the bull penis effect in the related technology, so that the goods supplementing quantity is more accurate, and the error of the goods supplementing quantity is reduced.
Description
Technical Field
The present application relates to the field of electronic applications, and in particular, to a method and apparatus for supplementing goods, and a storage medium.
Background
In the supply chain, an important link is replenishment of stock keeping units (Stock Keeping Unit, skus), and how to rapidly and accurately complete replenishment of skus is a primary problem due to the large number of skus currently operated. Since the amount typically purchased is to account for sales of one restocking cycle after arrival, one restocking cycle is typically multiple days. At present, the daily sales of the SKU is firstly predicted, the sales of each day in the future are output, and then the target inventory output purchasing suggestion is output by utilizing the formula of the periodic inventory checking model.
In this process, the output of the target stock quantity and the output of the stock quantity of the replenishment point are summed by using the predicted sales quantity of each day, and the predicted sales quantity of each day has a prediction error, and there is a bull penis effect with accumulated errors, so that the output target stock quantity and the stock quantity of the replenishment point deviate from the actual data greatly, and the error of the replenishment quantity is large.
Disclosure of Invention
The embodiment of the application provides a method and a device for supplementing goods and a storage medium, which can reduce large errors of the supplementing goods.
The technical scheme of the application is realized as follows:
In a first aspect, an embodiment of the present application provides a method for restocking, where the method includes:
Acquiring the replenishment time of a product and historical sales volume data before the replenishment time; generating time sequence characteristic data corresponding to the historical sales data;
Acquiring attribute information and replenishment parameters of the product; inputting the time sequence characteristic data, the attribute information and the replenishment parameters into a preset inventory model, and outputting the target inventory quantity and the replenishment point inventory quantity of the product;
acquiring stock in stock and in transit stock of the product; and generating a restocking strategy according to the target stock quantity, the restocking point stock quantity, the spot stock quantity and the in-transit stock quantity so as to execute corresponding restocking operation based on the restocking strategy.
In the method, the preset stock model comprises a target stock model and a restocking point stock model; the time sequence characteristic data, the attribute information and the replenishment parameters are input into a preset inventory model, and before the target inventory quantity and the replenishment point inventory quantity of the product are output, the method further comprises:
Generating a sample time for the product; acquiring attribute information of the product; the attribute information includes: replenishment cycle and time-in-transit;
According to the sample time, acquiring historical sales sample data in a plurality of historical sales times before the sample time; generating sample time sequence characteristic data corresponding to the historical sales sample data;
According to the sample time, acquiring a first sample sales volume in one replenishment cycle after the sample time as a target sample inventory volume, and acquiring a second sample sales volume in one time-in-transit after the sample time and as a replenishment sample inventory volume;
training an initial target inventory model by utilizing the attribute information of the product, the sample time sequence characteristic data and the target sample inventory quantity to obtain the target inventory model;
and training an initial replenishment point inventory model by utilizing the attribute information of the product, the sample time sequence characteristic data and the replenishment sample point inventory quantity to obtain the replenishment point inventory model.
In the above method, the generating a restocking strategy according to the target stock quantity, the restocking point stock quantity, the spot stock quantity and the in-transit stock quantity to perform a corresponding restocking operation based on the restocking strategy includes:
determining a sum of the stock quantity of the stock-in-transit quantity and the stock quantity of the in-transit quantity;
If the sum of the stock quantity is larger than the stock quantity of the replenishment points, judging that replenishment is not needed;
If the sum of the stock quantity is not greater than the stock quantity of the stock supplementing point, judging that the stock supplementing is needed, and determining the product stock supplementing quantity according to the target stock quantity, the stock quantity and the in-transit stock quantity.
In the method, the preset stock model comprises a target stock model and a restocking point stock model; the replenishment parameters comprise time-in-transit and replenishment period; inputting the time sequence characteristic data, the attribute information and the replenishment parameters into a preset inventory model, and outputting a target inventory quantity and a replenishment point inventory quantity of a product, wherein the method comprises the following steps:
Inputting the time sequence characteristic data, the attribute information and the time-in-transit into the replenishment point inventory model to obtain the replenishment point inventory;
And inputting the time sequence characteristic data, the attribute information and the replenishment period into the target inventory model to obtain the target inventory.
In the method, the historical sales volume data before the replenishment time is acquired; and generating time sequence characteristic data corresponding to the historical sales data, comprising:
acquiring a plurality of historical sales data corresponding to a plurality of time periods before the replenishment time;
performing multiple types of data processing on the multiple historical sales volume data to obtain multiple processed data;
and forming the plurality of processed data into the time sequence characteristic data.
In the above method, the product is a SKU, the method further comprising:
acquiring attribute information of the SKU, replenishment parameters and historical sales volume data before replenishment time of the SKU;
Generating time sequence feature data corresponding to the historical sales data, inputting the time sequence feature data, the attribute information and the replenishment parameters into a preset inventory model, and outputting the target inventory quantity and the replenishment point inventory quantity of the SKU;
Acquiring stock in stock and in transit stock of the SKU; and generating a SKU restocking strategy based on the target inventory, the restocking point inventory, the spot inventory and the on-the-fly inventory.
In a second aspect, an embodiment of the present application proposes a restocking device, the device comprising:
the system comprises an acquisition unit, a storage unit and a storage unit, wherein the acquisition unit is used for acquiring the replenishment time of a product and historical sales data before the replenishment time; acquiring attribute information and replenishment parameters of the product;
The generation unit is used for generating time sequence characteristic data corresponding to the historical sales data;
The data processing unit is used for inputting the time sequence characteristic data, the attribute information and the replenishment parameters into a preset inventory model and outputting the target inventory quantity and the replenishment point inventory quantity of the product; acquiring stock in stock and in transit stock of the product;
And the replenishment unit is used for generating a replenishment strategy according to the target stock quantity, the replenishment point stock quantity, the spot stock quantity and the on-the-way stock quantity so as to execute corresponding replenishment operation based on the replenishment strategy.
In the device, the preset stock model comprises a target stock model and a restocking point stock model; the apparatus further comprises: a training unit;
the generating unit is also used for generating sample time of the product; generating sample time sequence characteristic data corresponding to the historical sales sample data;
The acquisition unit is also used for acquiring attribute information of the product; the attribute information includes: replenishment cycle and time-in-transit; according to the sample time, acquiring historical sales sample data in a plurality of historical sales times before the sample time; according to the sample time, acquiring a first sample sales volume in one replenishment cycle after the sample time as a target sample inventory volume, and acquiring a second sample sales volume in one time-in-transit after the sample time and as a replenishment sample inventory volume;
The training unit is used for training an initial target inventory model by utilizing the attribute information of the product, the sample time sequence characteristic data and the target sample inventory quantity to obtain the target inventory model; and training an initial replenishment point inventory model by utilizing the attribute information of the product, the sample time sequence characteristic data and the replenishment sample point inventory quantity to obtain the replenishment point inventory model.
In a third aspect, an embodiment of the present application proposes a restocking device, the device comprising: the system comprises a processor and a memory, wherein the processor executes an operating program stored in the memory to realize the replenishment method.
In a fourth aspect, an embodiment of the present application proposes a storage medium having stored thereon a computer program which, when executed by a processor, implements a restocking method as described in any of the preceding claims.
The embodiment of the application provides a method and a device for supplementing goods and a storage medium, wherein the method comprises the following steps: acquiring historical sales data before the replenishment time of the product; generating time sequence characteristic data corresponding to the historical sales data; acquiring attribute information and replenishment parameters of a product; inputting the time sequence characteristic data, the attribute information and the replenishment parameters into a preset inventory model, and outputting the target inventory quantity and the replenishment point inventory quantity of the product; acquiring stock in stock and in transit stock of the product; and generating a restocking strategy according to the target stock quantity, the restocking point stock quantity, the spot stock quantity and the in-transit stock quantity so as to execute corresponding restocking operation based on the restocking strategy. By adopting the implementation scheme of the method, the preset inventory model is pre-trained, the time sequence characteristic data, the product attribute information and the replenishment parameters corresponding to the historical sales data are directly input into the preset inventory model, the target inventory quantity and the replenishment point inventory quantity of the product are output, the operations of forecasting and accumulating daily sales quantity are not existed, the bull whip effect is reduced, the replenishment quantity is more accurate, and the error of the replenishment quantity is reduced.
Drawings
FIG. 1 is a flow chart of a method for restocking according to an embodiment of the present application;
FIG. 2 is a flowchart of a method for restocking based on a pre-trained target inventory model and a restocking point inventory model according to an embodiment of the present application;
FIG. 3 is a schematic flow chart of training a preset inventory model according to an embodiment of the present application;
Fig. 4 is a schematic structural diagram of a replenishment device according to an embodiment of the present application;
fig. 5 is a schematic diagram of a replenishment device according to a second embodiment of the present application.
Detailed Description
For a more complete understanding of the nature and the technical content of the embodiments of the present application, reference should be made to the following detailed description of embodiments of the application, taken in conjunction with the accompanying drawings, which are meant to be illustrative only and not limiting of the embodiments of the 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 is for the purpose of describing embodiments of the application only and is not intended to be limiting of the application.
In the following description, reference is made to "some embodiments" which describe a subset of all possible embodiments, but it is to be understood that "some embodiments" can be the same subset or different subsets of all possible embodiments and can be combined with one another without conflict. It should also be noted that the term "first\second\third" in relation to embodiments of the present application is used merely to distinguish similar objects and does not represent a particular ordering for the objects, it being understood that the "first\second\third" may be interchanged in a particular order or sequence, where allowed, to enable embodiments of the present application described herein to be practiced in an order other than that illustrated or described herein.
An embodiment of the present application provides a method for restocking, as shown in fig. 1, the method includes:
S101, acquiring historical sales data before the replenishment time of the product; and generating time sequence characteristic data corresponding to the historical sales data.
The goods supplementing method provided by the embodiment of the application is suitable for a scene of periodically checking the inventory of the products in the warehouse.
In the embodiment of the application, the replenishment time of the product is firstly obtained, and then a plurality of historical sales data corresponding to a plurality of time periods before the replenishment time are obtained; performing various types of data processing on the historical sales volume data to obtain processed data; and forming the plurality of processed data into time sequence characteristic data.
It should be noted that, the time periods before the replenishment time may be days before the replenishment time, or time periods divided in a finer time unit, such as hours, minutes, etc.; and the selection of the time periods can also be selected according to actual conditions, and the embodiment of the application is not particularly limited.
Illustratively, the plurality of time periods prior to the restocking time may be day 3, day 7, day 14, day 30, day 60, and day 140 prior to the restocking time.
In an embodiment of the present application, the plurality of types of data processing may include at least one of: determining a mean value of the plurality of historical sales data, determining a standard deviation of the plurality of historical sales data, determining a median of the plurality of historical sales data, determining a maximum of the plurality of historical sales data, determining a value corresponding to 90% of the fractional numbers of the plurality of historical sales data, determining a mean value of the sales differences of the plurality of historical sales data, determining a 0.985 fractional number corresponding to a gaussian distribution of a full-scale historical sales fit corresponding to the plurality of historical sales data, determining a 0.985 fractional number corresponding to a gamma distribution of the full-scale historical sales fit corresponding to the plurality of historical sales data, determining an autoregressive coefficient obtained from the full-scale historical sales corresponding to the plurality of historical sales data, determining a square (equal to the square of the variance divided by the mean) of a full-scale historical sales variation coefficient corresponding to the plurality of historical sales data the method comprises the steps of determining a total historical sales variation coefficient (equal to standard deviation divided by mean value) corresponding to a plurality of historical sales data, determining a mean value of total historical sales demand intervals corresponding to a plurality of historical sales data, determining a total historical sales non-zero sales mean value corresponding to a plurality of historical sales data, determining a total historical sales non-zero sales standard deviation corresponding to a plurality of historical sales data, determining a square of the total historical sales non-zero sales variation coefficient corresponding to a plurality of historical sales data, determining a total historical sales time length corresponding to a plurality of historical sales data, determining a total historical sales non-zero sales length corresponding to a plurality of historical sales data, determining a week of one year corresponding to a replenishment time and determining a week corresponding to a replenishment time. The addition and deletion can be specifically performed according to actual conditions, and the embodiment of the application does not limit specific data processing types.
S102, acquiring attribute information and replenishment parameters of a product; and inputting the time sequence characteristic data, the attribute information and the replenishment parameters into a preset inventory model, and outputting the target inventory quantity and the replenishment point inventory quantity of the product.
In an embodiment of the present application, the attribute information of the product includes at least one of the following: the length of the product, the width of the product, the height of the product, the weight of the product, the tertiary product class name of the product, etc.
In an embodiment of the application, the replenishment parameters include time-in-transit and replenishment cycle.
In an embodiment of the present application, the preset inventory model may include a target inventory model and a restocking point inventory model; inputting the time sequence characteristic data, the attribute information and the time-in-transit into a replenishment point inventory model to obtain replenishment point inventory; and inputting the time sequence characteristic data, the attribute information and the replenishment period into a target inventory model to obtain a target inventory.
It should be noted that, the target inventory model and the restocking point inventory model are pre-trained, and specific training process is described in the following description of fig. 3, which is not repeated here.
S103, acquiring stock in stock and in-transit stock of the product; and generating a restocking strategy according to the target stock quantity, the restocking point stock quantity, the spot stock quantity and the in-transit stock quantity so as to execute corresponding restocking operation based on the restocking strategy.
In the embodiment of the application, the replenishment judgment is carried out according to the replenishment point stock quantity, the spot stock quantity and the on-the-way stock quantity, and the product replenishment quantity is determined according to the target stock quantity, the spot stock quantity and the on-the-way stock quantity under the condition that the replenishment is judged to be needed.
In an embodiment of the application, a sum of stock amounts of stock-in-transit amounts and stock-in-transit amounts is determined; comparing the sum of the stock quantity with the stock quantity of the replenishment point, and judging that replenishment is not needed if the sum of the stock quantity is larger than the stock quantity of the replenishment point; if the sum of the stock quantity is not greater than the stock quantity of the stock-supplementing point, judging that the stock is needed to be supplemented, and determining the product stock-supplementing quantity according to the target stock quantity, the stock-in-stock quantity and the in-transit stock quantity.
In the embodiment of the application, the sum of the stock in stock and the in-transit stock is subtracted from the target stock to obtain the product stock.
It can be understood that the preset inventory model is pre-trained, the time sequence characteristic data, the product attribute information and the replenishment parameters corresponding to the historical sales data are directly input into the preset inventory model, the target inventory quantity and the replenishment point inventory quantity of the product are output, the operations of daily sales quantity prediction and accumulation do not exist, the bull penis effect is reduced, the replenishment quantity is more accurate, and the error of the replenishment quantity is reduced.
Based on the above embodiment, if the product is SKU, the restocking method for SKU may be: acquiring attribute information, replenishment parameters and historical sales volume data of the SKU before replenishment time; generating time sequence feature data corresponding to the historical sales data, inputting the time sequence feature data, attribute information and replenishment parameters into a preset inventory model, and outputting target inventory quantity and replenishment point inventory quantity of the SKU; acquiring stock in stock and in transit stock of the SKU; and generating a SKU restocking strategy according to the target stock quantity, the restocking point stock quantity, the spot stock quantity and the in-transit stock quantity.
It should be noted that, the SKU is a minimum delivery unit of a product, and is a division of update granularity of the product, and a specific replenishment method for the SKU is consistent with an execution process of the replenishment method for the product, and specific reference may be made to a description of the replenishment method for the product, which is not repeated herein.
Based on the above embodiments, a method for restocking based on a pre-trained target inventory model and a restocking point inventory model is provided, as shown in fig. 2, the method includes:
1. And generating corresponding time sequence characteristic data according to the historical sales volume data before the replenishment time of the product.
2. And inputting the time sequence characteristic data, the product attribute information and the replenishment period into a target inventory model to obtain a target inventory.
3. And inputting the time sequence characteristic data, the product attribute information and the time-in-transit into a restocking point inventory model to obtain the restocking point inventory.
4. And determining the sum of stock quantity of the stock quantity and the in-transit stock quantity.
5. The sum of the stock amounts is compared with the stock amounts of the restocking points.
6. If the sum of the stock amounts is greater than the stock amount of the stock points, the stock amount of the product is 0.
7. If the sum of the stock amounts is not greater than the stock amount of the stock points, the product stock amount is a value obtained by subtracting the sum of the stock amounts from the target stock amount.
It should be noted that, before inputting the time sequence feature data, the attribute information and the replenishment parameters into the preset inventory model and outputting the target inventory amount and the replenishment point inventory amount of the product, the preset inventory model needs to be trained, and the specific implementation process is shown in fig. 3, S201, the sample time of the product is generated; acquiring attribute information of the product; the attribute information includes: replenishment cycle and time-in-transit.
S202, acquiring historical sales sample data in a plurality of historical sales times before sample time according to the sample time; and generating sample time sequence characteristic data corresponding to the historical sales sample data.
S203, according to the sample time, acquiring a first sample sales volume in a replenishment period after the sample time as a target sample inventory volume, and acquiring a second sample sales volume in a time-in-transit period after the sample time and as a replenishment sample inventory volume.
S204, training an initial target inventory model by using the attribute information of the product, the sample time sequence characteristic data and the target sample inventory quantity to obtain a target inventory model.
S205, training an initial replenishment point inventory model by utilizing the attribute information of the product, the sample time sequence characteristic data and the replenishment sample point inventory quantity to obtain a replenishment point inventory model.
It should be noted that, S204 and S205 are two parallel steps after S203, and specifically, the steps may be selectively performed with reference to actual situations, and the embodiment of the present application is not limited to the execution sequence between S204 and S205.
In an embodiment of the application, the target sample inventory isThe calculation formula of (1) is shown in the formula (1), and the stock quantity of the replenishment sample is calculatedThe calculation formula of (2) is shown in the formula,
（1）；
（2）；
Wherein,For sample time, t is the time point,/>For time-in-transit,/>For replenishment period,/>Is the sample sales.
In the embodiment of the application, the independent variables in the sample points of a certain day are sample time sequence characteristic data, attribute information of products and replenishment parameter information corresponding to historical sales sample data before the certain day, and the independent variables are target sample stock quantity and replenishment sample stock quantity. And training a target inventory model by taking the attribute information of the product, the sample time sequence characteristic data and the target sample inventory amount as a sample set, and training a replenishment point inventory model by taking the attribute information of the product, the sample time sequence characteristic data and the replenishment point inventory amount as a sample set.
In the embodiment of the application, a supervised learning integrated model (LIGHT GRADIENT Boosting Machine, LGBM) is adopted to train two regression models, namely a target stock model and a replenishment point stock model, which can be specifically selected according to actual conditions, and the embodiment of the application is not specifically limited.
Based on the above embodiment, compared with the existing method for predicting daily sales, the method for suggesting product replenishment by adopting the target inventory model and the replenishment point inventory model provided by the embodiment of the application can greatly reduce the turnover days and the month end inventory under the condition of keeping the spot rate of the platform unchanged, thereby reducing the holding cost of the inventory.
Based on the above embodiments, an embodiment of the present application proposes a restocking device 1, as shown in fig. 4, which includes:
An acquiring unit 10, configured to acquire a replenishment time of a product and historical sales volume data before the replenishment time; acquiring attribute information and replenishment parameters of the product;
a generating unit 20, configured to generate time sequence feature data corresponding to the historical sales data;
A data processing unit 30, configured to input the time sequence feature data, the attribute information, and the replenishment parameter into a preset inventory model, and output a target inventory amount and a replenishment point inventory amount of a product; acquiring stock in stock and in transit stock of the product;
And a restocking unit 40 for generating restocking strategies according to the target stock quantity, the restocking point stock quantity, the stock-in-transit stock quantity and the in-transit stock quantity so as to execute corresponding restocking operations based on the restocking strategies.
Optionally, the preset inventory model includes a target inventory model and a restocking point inventory model; the apparatus further comprises: a training unit;
the generating unit 20 is further configured to generate a sample time of the product; generating sample time sequence characteristic data corresponding to the historical sales sample data;
The acquiring unit 10 is further configured to acquire attribute information of the product; the attribute information includes: replenishment cycle and time-in-transit; according to the sample time, acquiring historical sales sample data in a plurality of historical sales times before the sample time; according to the sample time, acquiring a first sample sales volume in one replenishment cycle after the sample time as a target sample inventory volume, and acquiring a second sample sales volume in one time-in-transit after the sample time and as a replenishment sample inventory volume;
The training unit is used for training an initial target inventory model by utilizing the attribute information of the product, the sample time sequence characteristic data and the target sample inventory quantity to obtain the target inventory model; and training an initial replenishment point inventory model by utilizing the attribute information of the product, the sample time sequence characteristic data and the replenishment sample point inventory quantity to obtain the replenishment point inventory model.
Optionally, the apparatus further includes: a determination unit;
The determining unit is used for determining the sum of the stock quantity of the stock quantity and the in-transit stock quantity; if the sum of the stock quantity is larger than the stock quantity of the replenishment points, judging that replenishment is not needed; if the sum of the stock quantity is not greater than the stock quantity of the stock supplementing point, judging that the stock supplementing is needed, and determining the product stock supplementing quantity according to the target stock quantity, the stock quantity and the in-transit stock quantity.
Optionally, the preset inventory model includes a target inventory model and a restocking point inventory model; the replenishment parameters comprise time-in-transit and replenishment period;
The data processing unit 30 is further configured to input the time sequence feature data, the attribute information, and the time-in-transit time into the restocking point inventory model to obtain the restocking point inventory; and inputting the time sequence characteristic data, the attribute information and the replenishment period into the target inventory model to obtain the target inventory.
Optionally, the acquiring unit 10 is further configured to acquire a plurality of historical sales data corresponding to a plurality of time periods before the restocking time;
The generating unit 20 is further configured to perform multiple types of data processing on the multiple historical sales volume data to obtain multiple processed data; and forming the plurality of processed data into the time sequence characteristic data.
Optionally, the product is a SKU, and the obtaining unit 10 is further configured to obtain attribute information of the SKU, a replenishment parameter, and historical sales volume data before a replenishment time of the SKU; acquiring stock in stock and in transit stock of the SKU;
The generating unit 20 is further configured to generate time sequence feature data corresponding to the historical sales data;
the data processing unit is further used for inputting the time sequence characteristic data, the attribute information and the replenishment parameters into a preset inventory model and outputting the target inventory quantity and the replenishment point inventory quantity of the SKU;
The restocking unit 40 is further configured to generate a SKU restocking strategy based on and in accordance with the target inventory, the restocking point inventory, the spot inventory, and the on-transit inventory.
Based on the above embodiments, an embodiment of the present application proposes a restocking device 1, in practical application, based on the same disclosure concept as the above embodiments, as shown in fig. 5, the restocking device 1 of the present embodiment includes: processor 100, memory 101, and communication bus 102.
In a specific embodiment, the processor 100 may be at least one of an Application Specific Integrated Circuit (ASIC), a digital signal processor (DSP, digital Signal processor), a digital signal processing image processing device (DSPD, digital Signal Processing Device), a programmable logic image processing device (PLD, programmable Logic Device), a field programmable gate array (FPGA, field Programmable GATE ARRAY), a CPU, a controller, a microcontroller, and a microprocessor. It will be appreciated that the electronics for implementing the above-described processor functions may be other for different devices, and the present embodiment is not particularly limited.
In the embodiment of the present application, the communication bus 102 is used to implement connection communication between the processor 100 and the memory 101; the processor 100 implements the following method when executing the running program stored in the memory 101:
Acquiring the replenishment time of a product and historical sales volume data before the replenishment time; generating time sequence characteristic data corresponding to the historical sales data; acquiring attribute information and replenishment parameters of the product; inputting the time sequence characteristic data, the attribute information and the replenishment parameters into a preset inventory model, and outputting the target inventory quantity and the replenishment point inventory quantity of the product; acquiring stock in stock and in transit stock of the product; and generating a restocking strategy according to the target stock quantity, the restocking point stock quantity, the spot stock quantity and the in-transit stock quantity so as to execute corresponding restocking operation based on the restocking strategy.
Optionally, the preset inventory model includes a target inventory model and a restocking point inventory model;
The processor 100 is further configured to generate a sample time of the product; acquiring attribute information of the product; the attribute information includes: replenishment cycle and time-in-transit; according to the sample time, acquiring historical sales sample data in a plurality of historical sales times before the sample time; generating sample time sequence characteristic data corresponding to the historical sales sample data; according to the sample time, acquiring a first sample sales volume in one replenishment cycle after the sample time as a target sample inventory volume, and acquiring a second sample sales volume in one time-in-transit after the sample time and as a replenishment sample inventory volume; training an initial target inventory model by utilizing the attribute information of the product, the sample time sequence characteristic data and the target sample inventory quantity to obtain the target inventory model; and training an initial replenishment point inventory model by utilizing the attribute information of the product, the sample time sequence characteristic data and the replenishment sample point inventory quantity to obtain the replenishment point inventory model.
Optionally, the processor 100 is further configured to determine a sum of the stock quantity of the stock in stock and the in transit stock quantity; if the sum of the stock quantity is larger than the stock quantity of the replenishment points, judging that replenishment is not needed; if the sum of the stock quantity is not greater than the stock quantity of the stock supplementing point, judging that the stock supplementing is needed, and determining the product stock supplementing quantity according to the target stock quantity, the stock quantity and the in-transit stock quantity.
Optionally, the preset inventory model includes a target inventory model and a restocking point inventory model; the replenishment parameters comprise time-in-transit and replenishment period;
The processor 100 is further configured to input the time sequence feature data, the attribute information, and the time-in-transit time into the restocking point inventory model to obtain the restocking point inventory; and inputting the time sequence characteristic data, the attribute information and the replenishment period into the target inventory model to obtain the target inventory.
Optionally, the processor 100 is further configured to obtain a plurality of historical sales data corresponding to a plurality of time periods before the restocking time; performing multiple types of data processing on the multiple historical sales volume data to obtain multiple processed data; and forming the plurality of processed data into the time sequence characteristic data.
Optionally, the product is a SKU, and the processor 100 is further configured to obtain attribute information of the SKU, a replenishment parameter, and historical sales data before a replenishment time of the SKU; generating time sequence feature data corresponding to the historical sales data, inputting the time sequence feature data, the attribute information and the replenishment parameters into a preset inventory model, and outputting the target inventory quantity and the replenishment point inventory quantity of the SKU; acquiring stock in stock and in transit stock of the SKU; and generating a SKU restocking strategy based on the target inventory, the restocking point inventory, the spot inventory and the on-the-fly inventory.
An embodiment of the present application provides a storage medium, on which a computer program is stored, where the computer readable storage medium stores one or more programs, where the one or more programs are executable by one or more processors and applied to a restocking device, where the computer program implements a restocking method as described above.
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 one … …" does not exclude the presence of other like elements in a process, method, article, or apparatus that comprises the element.
From the above description of the embodiments, it will be clear to those skilled in the art that the above-described embodiment method may be implemented by means of software plus a necessary general hardware platform, but of course may also be implemented by means of hardware, but in many cases the former is a preferred embodiment. Based on such understanding, the technical solution of the present disclosure may be embodied essentially or in a part contributing to the related art in the form of a software product stored in a storage medium (such as ROM/RAM, magnetic disk, optical disk), including several instructions for causing an image display device (which may be a mobile phone, a computer, a server, an air conditioner, or a network device, etc.) to perform the method described in the embodiments of the present disclosure.
The foregoing description is only of the preferred embodiments of the present application, and is not intended to limit the scope of the present application.
Claims (7)
1. A method of restocking, the method comprising:
acquiring the replenishment time of a product and historical sales volume data before the replenishment time; generating time sequence characteristic data corresponding to the historical sales volume data;
Acquiring attribute information and replenishment parameters of the product; inputting the time sequence characteristic data, the attribute information and the replenishment parameters into a preset inventory model, and outputting the target inventory quantity and the replenishment point inventory quantity of the product;
Acquiring stock in stock and in transit stock of the product; generating a restocking strategy according to the target stock quantity, the restocking point stock quantity, the spot stock quantity and the in-transit stock quantity so as to execute corresponding restocking operation based on the restocking strategy;
The preset inventory model comprises a target inventory model and a restocking point inventory model; the replenishment parameters comprise time-in-transit and replenishment period; inputting the time sequence characteristic data, the attribute information and the replenishment parameters into a preset inventory model, and outputting a target inventory quantity and a replenishment point inventory quantity of a product, wherein the method comprises the following steps:
Generating a sample time for the product; acquiring attribute information of the product; the attribute information includes: the length, width, height, weight and tertiary class name of the product;
according to the sample time, acquiring historical sales sample data in a plurality of historical sales times before the sample time, and generating the sample time sequence characteristic data;
According to the sample time, acquiring a first sample sales volume in one replenishment cycle after the sample time as a target sample inventory volume, and acquiring a second sample sales volume in one time-in-transit after the sample time and as a replenishment sample inventory volume;
Inputting the time sequence characteristic data, the attribute information and the time-in-transit into the replenishment point inventory model to obtain the replenishment point inventory; the replenishment point inventory model is obtained by training an initial replenishment point inventory model by utilizing attribute information of the product, sample time sequence characteristic data corresponding to the historical sales sample data and the replenishment point inventory quantity;
Inputting the time sequence characteristic data, the attribute information and the replenishment period into the target inventory model to obtain the target inventory quantity; the target inventory model is obtained by training an initial target inventory model by utilizing the attribute information of the product, the sample time sequence characteristic data and the target sample inventory quantity; the restocking point inventory model and the target inventory model are regression models.
2. The method of claim 1, wherein the generating a restocking strategy from the target inventory level, the restocking point inventory level, the spot inventory level, and the in-transit inventory level to perform a corresponding restocking operation based on the restocking strategy comprises:
determining a sum of the stock quantity of the stock-in-transit quantity and the stock quantity of the in-transit quantity;
If the sum of the stock quantity is larger than the stock quantity of the replenishment points, judging that replenishment is not needed;
If the sum of the stock quantity is not greater than the stock quantity of the stock supplementing point, judging that the stock supplementing is needed, and determining the product stock supplementing quantity according to the target stock quantity, the stock quantity and the in-transit stock quantity.
3. The method of claim 1, wherein the acquiring the restocking time of the product and the historical sales data prior to the restocking time; and generating time sequence characteristic data corresponding to the historical sales volume data, comprising:
acquiring a plurality of historical sales data corresponding to a plurality of time periods before the replenishment time of the product;
performing multiple types of data processing on the multiple historical sales volume data to obtain multiple processed data;
and forming the plurality of processed data into the time sequence characteristic data.
4. The method of claim 1, wherein the product is a SKU, the method further comprising:
acquiring attribute information of the SKU, replenishment parameters and historical sales volume data before replenishment time of the SKU;
Generating time sequence feature data corresponding to the historical sales volume data, inputting the time sequence feature data, the attribute information and the replenishment parameters into a preset inventory model, and outputting the target inventory quantity and the replenishment point inventory quantity of the SKU;
Acquiring stock in stock and in transit stock of the SKU; and generating a SKU restocking strategy based on the target inventory, the restocking point inventory, the spot inventory and the on-the-fly inventory.
5. A restocking apparatus, the apparatus comprising:
the system comprises an acquisition unit, a storage unit and a storage unit, wherein the acquisition unit is used for acquiring the replenishment time of a product and historical sales data before the replenishment time; acquiring attribute information and replenishment parameters of the product;
the generation unit is used for generating time sequence characteristic data corresponding to the historical sales volume data;
The data processing unit is used for inputting the time sequence characteristic data, the attribute information and the replenishment parameters into a preset inventory model and outputting the target inventory quantity and the replenishment point inventory quantity of the product; acquiring stock in stock and in transit stock of the product;
A restocking unit for generating restocking strategies according to the target stock quantity, the restocking point stock quantity, the spot stock quantity and the in-transit stock quantity so as to execute corresponding restocking operations based on the restocking strategies;
The preset inventory model comprises a target inventory model and a restocking point inventory model; the replenishment parameters comprise time-in-transit and replenishment period;
The data processing unit 30 is further configured to input the time sequence feature data, the attribute information, and the time-in-transit time into the restocking point inventory model to obtain the restocking point inventory; inputting the time sequence characteristic data, the attribute information and the replenishment period into the target inventory model to obtain the target inventory quantity;
Wherein the device further comprises a training unit:
The training unit is used for training an initial target inventory model by utilizing the attribute information of the product, sample time sequence characteristic data corresponding to the historical sales sample data and the target sample inventory quantity to obtain the target inventory model; training an initial replenishment point inventory model by utilizing the attribute information of the product, the sample time sequence characteristic data and the replenishment sample point inventory quantity to obtain the replenishment point inventory model; the restocking point inventory model and the target inventory model are regression models;
Wherein the apparatus further comprises:
The generating unit is also used for generating sample time of the product; generating the sample timing characteristic data;
The acquisition unit is also used for acquiring attribute information of the product; the attribute information includes: the length, width, height, weight and tertiary class name of the product; according to the sample time, acquiring historical sales sample data in a plurality of historical sales times before the sample time; and according to the sample time, acquiring a first sample sales volume in the replenishment period after the sample time as the target sample inventory volume, and acquiring a second sample sales volume in the time-in-transit period after the sample time and as the replenishment sample inventory volume.
6. A restocking apparatus, the apparatus comprising: a processor and a memory, which processor, when executing a running program stored in the memory, implements the method according to any one of claims 1-4.
7. A storage medium having stored thereon a computer program which, when executed by a processor, implements the method of any of claims 1-4.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202310599591.8A CN116342042B (en) | 2023-05-25 | 2023-05-25 | Goods supplementing method and device and storage medium |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202310599591.8A CN116342042B (en) | 2023-05-25 | 2023-05-25 | Goods supplementing method and device and storage medium |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN116342042A CN116342042A (en) | 2023-06-27 |
| CN116342042B true CN116342042B (en) | 2024-04-19 |
Family
ID=86886132
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202310599591.8A Active CN116342042B (en) | 2023-05-25 | 2023-05-25 | Goods supplementing method and device and storage medium |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN116342042B (en) |
Citations (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| 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 |
| CN111429048A (en) * | 2019-01-09 | 2020-07-17 | 北京沃东天骏信息技术有限公司 | Method, device and equipment for determining replenishment information |
| CN114663015A (en) * | 2022-03-18 | 2022-06-24 | 北京京东振世信息技术有限公司 | Replenishment method and device |
| WO2023273696A1 (en) * | 2021-06-30 | 2023-01-05 | 北京京东振世信息技术有限公司 | Replenishment quantity determination method and apparatus, device, storage medium, and program product |
| CN115689451A (en) * | 2022-11-14 | 2023-02-03 | 创优数字科技(广东)有限公司 | Method, device, terminal and medium for determining replenishment quantity of off-line retail store |
| 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 |
| CN115936582A (en) * | 2022-12-27 | 2023-04-07 | 华润数字科技有限公司 | Commodity replenishment method, system, electronic device and readable storage medium |
Family Cites Families (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN115358651A (en) * | 2021-05-17 | 2022-11-18 | 星巴克公司 | Method, system and computer readable storage medium for automatic replenishment of retail store |
-
2023
- 2023-05-25 CN CN202310599591.8A patent/CN116342042B/en active Active
Patent Citations (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| 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 |
| CN111429048A (en) * | 2019-01-09 | 2020-07-17 | 北京沃东天骏信息技术有限公司 | Method, device and equipment for determining replenishment information |
| WO2023273696A1 (en) * | 2021-06-30 | 2023-01-05 | 北京京东振世信息技术有限公司 | Replenishment quantity determination method and apparatus, device, storage medium, and program product |
| 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 |
| CN114663015A (en) * | 2022-03-18 | 2022-06-24 | 北京京东振世信息技术有限公司 | Replenishment method and device |
| CN115689451A (en) * | 2022-11-14 | 2023-02-03 | 创优数字科技(广东)有限公司 | Method, device, terminal and medium for determining replenishment quantity of off-line retail store |
| CN115936582A (en) * | 2022-12-27 | 2023-04-07 | 华润数字科技有限公司 | Commodity replenishment method, system, electronic device and readable storage medium |
Also Published As
| Publication number | Publication date |
|---|---|
| CN116342042A (en) | 2023-06-27 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN110276571B (en) | Cargo scheduling method and apparatus and computer readable storage medium | |
| CN104217355A (en) | Method and device for predicting sales volume of promotion items | |
| WO2019001120A1 (en) | Method and system for processing dynamic pricing data of commodity | |
| WO2019125612A1 (en) | Dynamic feature selection for model generation | |
| US20140039979A1 (en) | System and Method for Demand Forecasting | |
| CN110633820B (en) | Warehouse address recommendation method and device and computer readable storage medium | |
| CN107862413A (en) | Based on markovian Forecasting Methodology and device | |
| CN114240304B (en) | Warehouse inventory control method and device, storage medium and ERP system | |
| JP2009187151A (en) | Inventory management system and order quantity calculation program | |
| CN109978421B (en) | Information output method and device | |
| Lahrichi et al. | A first MILP model for the parameterization of Demand-Driven MRP | |
| US20160034928A1 (en) | Systems and methods for promotional forecasting | |
| WO2023020255A1 (en) | Data processing method and apparatus, device, and storage medium | |
| CN113449939A (en) | Inventory data prediction method, device, computing equipment and medium | |
| US20120226585A1 (en) | Method and Apparatus for Dynamic Online Pricing | |
| CN113191806B (en) | Method and device for determining flow regulation target | |
| JP2009043291A (en) | System for predicting demand of merchandise and system for adjusting number of sales of merchandise | |
| CN114358874A (en) | Replenishment method and device and electronic equipment | |
| CN111222668A (en) | Warehouse list prediction method and device, electronic equipment and readable storage medium | |
| CN116342042B (en) | Goods supplementing method and device and storage medium | |
| JP6193817B2 (en) | Demand prediction apparatus and program | |
| CN113159281A (en) | Data processing method and data processing device | |
| JP2015032267A (en) | Demand prediction apparatus and program | |
| Albrecht | Determining near optimal base-stock levels in two-stage general inventory systems | |
| JP6276655B2 (en) | Demand prediction apparatus and program |
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 | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |