CN115689451A - Method, device, terminal and medium for determining replenishment quantity of off-line retail store - Google Patents
Method, device, terminal and medium for determining replenishment quantity of off-line retail store Download PDFInfo
- Publication number
- CN115689451A CN115689451A CN202211422846.5A CN202211422846A CN115689451A CN 115689451 A CN115689451 A CN 115689451A CN 202211422846 A CN202211422846 A CN 202211422846A CN 115689451 A CN115689451 A CN 115689451A
- Authority
- CN
- China
- Prior art keywords
- sales data
- replenishment
- historical
- data
- store
- 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
Links
Images
Landscapes
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
The method comprises the steps of predicting predicted sales data of a target commodity in a future preset period through a preset machine learning model based on historical data of a store commodity sales process, then calculating a fluctuation coefficient of sales prediction and a fluctuation coefficient of a replenishment period according to the historical sales data and the predicted sales data, and calculating the demand of the target commodity in the future preset period according to the predicted sales data and the fluctuation coefficient and by combining safety stock of the target commodity; and finally, calculating the replenishment quantity of the target commodity according to the demand quantity and the store inventory of the target commodity, so that replenishment is carried out according to the calculated replenishment quantity, and the technical problem that the single replenishment quantity of the existing off-line retail store depends too much on manual experience is solved.
Description
Technical Field
The application relates to the technical field of big data, in particular to a method, a device, a terminal and a medium for determining the replenishment quantity of an offline retail store.
Background
With the development of internet technology, the digital fine operation is extremely urgent for the traditional industry. For an offline store, the core problem is that a certain commodity needs no supplement and a small amount of supplement, and the condition of inventory turnover needs to be balanced under the condition of ensuring the service level. The method can accurately predict the single products according to the historical sales conditions of the single products, and reasonably determine the replenishment quantity of the single products in stores by combining the conditions of the stocks of the single products in stores and the like.
At present, most off-line retail store single item replenishment quantity calculation methods generally determine the initial replenishment quantity of a single item through the recent sale of the single item of the store, and then process the initial replenishment quantity according to manual historical experience or rules to obtain the replenishment quantity of the single item of the store.
Disclosure of Invention
The application provides a method, a device, a terminal and a medium for determining the replenishment quantity of an offline retail store, which are used for solving the technical problem that the replenishment quantity of a single item of the offline retail store depends too much on manual experience.
In order to solve the above technical problem, a first aspect of the present application provides a method for determining a replenishment quantity of an offline retail store, including:
acquiring historical sales data and historical replenishment data of a target store;
predicting sales prediction data of the target commodity in a future preset period through a preset machine learning model according to the historical sales data;
calculating a first fluctuation coefficient according to the historical sales data and the predicted sales data, wherein the first fluctuation coefficient is used for quantifying the fluctuation of sales data prediction;
calculating a second fluctuation coefficient according to historical replenishment data, wherein the second fluctuation coefficient is used for quantifying the fluctuation of a replenishment period of a target commodity;
and calculating the demand of the target commodity in the future preset period by combining the safety stock of the target commodity according to the predicted sales data, the first fluctuation coefficient and the second fluctuation coefficient, and calculating the replenishment quantity of the target commodity by combining the store stock of the target commodity according to the demand.
Preferably, the machine learning model is specifically: the composite model comprises a time sequence algorithm model and a tree algorithm model.
Preferably, the predicting, according to the historical sales data and through a preset machine learning model, the predicted sales data of the commodity in a future preset period specifically includes:
according to the historical sales data, the historical sales data are used as input of a time sequence algorithm model, and store commodity predicted sales data of the target store in a future preset period are obtained through operation of the time sequence algorithm model;
and taking the predicted sales volume of the store commodities as the input of a tree algorithm model, and obtaining the predicted sales data of the target commodities in a future preset period through the operation of the tree algorithm model.
Preferably, the time sequence algorithm model specifically includes: the fbprophet algorithm model specifically comprises the following steps: a multi-output lightgbm model.
Preferably, calculating a first fluctuation coefficient according to the historical sales data and the predicted sales data specifically includes:
and fitting the historical sales data and the predicted sales data according to the time dimension characteristics of the historical sales data and the predicted sales data, and calculating a first fluctuation coefficient according to the fitted historical sales data and the predicted sales data.
Preferably, the calculating the second fluctuation coefficient according to the historical replenishment data specifically includes:
and fitting the historical replenishment data according to the time dimension characteristics of the historical replenishment data, and calculating a second fluctuation coefficient according to the fitted historical replenishment data.
Preferably, the calculating of the replenishment quantity of the target product according to the demand in combination with store inventory of the target product further includes:
and comparing the replenishment quantity with a preset minimum order quantity according to the replenishment quantity, and if the replenishment quantity is less than the minimum order quantity, adjusting the replenishment quantity according to the minimum order quantity.
A second aspect of the present application provides an offline retail store replenishment quantity determination device, including:
the historical data acquisition unit is used for acquiring historical sales data and historical replenishment data of a target store;
the sales data prediction unit is used for predicting the predicted sales data of the target commodity in a future preset period through a preset machine learning model according to the historical sales data;
a first fluctuation coefficient calculation unit configured to calculate a first fluctuation coefficient for quantifying fluctuation of sales data prediction, based on the historical sales data and the predicted sales data;
a second fluctuation coefficient calculation unit for calculating a second fluctuation coefficient for quantifying fluctuation of a replenishment period of the target commodity, based on the historical replenishment data;
and the replenishment quantity calculation unit is used for calculating the demand quantity of the target commodity in the future preset period by combining the safety stock of the target commodity according to the predicted sales data, the first fluctuation coefficient and the second fluctuation coefficient, and then calculating the replenishment quantity of the target commodity by combining the store stock of the target commodity according to the demand quantity.
A third aspect of the present application provides an offline retail store replenishment quantity determination terminal, including: a memory and a processor;
the memory is configured to store program code corresponding to the off-line retail store replenishment quantity determination method as provided by the first aspect of the present application;
the processor is configured to execute the program code.
A fourth aspect of the present application provides a computer-readable storage medium having stored therein program code corresponding to the method for determining the replenishment quantity of an off-line retail store as provided in the first aspect of the present application.
According to the technical scheme, the embodiment of the application has the following advantages:
the method includes the steps that predicted sales data of a target commodity in a future preset period are predicted through a preset machine learning model based on historical data of a shop commodity sales process, then according to the historical sales data and the predicted sales data, a fluctuation coefficient of sales prediction and a fluctuation coefficient of a replenishment period are calculated, and according to the predicted sales data and the fluctuation coefficient, the demand of the target commodity in the future preset period is calculated by combining safety stock of the target commodity; and finally, calculating the replenishment quantity of the target commodity according to the demand quantity and the store inventory of the target commodity, so that replenishment is carried out according to the calculated replenishment quantity, and the technical problem that the single replenishment quantity of the existing off-line retail store depends too much on manual experience is solved.
Drawings
In order to more clearly illustrate the embodiments of the present application or the technical solutions in the prior art, the drawings used in the description of the embodiments or the prior art will be briefly described below, it is obvious that the drawings in the description below are only some embodiments of the present application, and for those skilled in the art, other drawings can be obtained according to the drawings without inventive labor.
Fig. 1 is a schematic flowchart of an embodiment of a method for determining an amount of replenishment of an offline retail store according to the present application.
Fig. 2 is a schematic flowchart of another embodiment of the method for determining the replenishment quantity of the offline retail store according to the present application.
Fig. 3 is a schematic flow chart of the sales data prediction in the offline retail store replenishment quantity determination method provided by the present application.
Fig. 4 is a schematic structural diagram of an embodiment of the offline retail store replenishment quantity determination device provided in the present application.
Detailed Description
The embodiment of the application provides a method, a device, a terminal and a medium for determining the replenishment quantity of an offline retail store, and is used for solving the technical problem that the replenishment quantity of a single item of the offline retail store is too dependent on manual experience and cannot be applied to all single items and scenes.
According to the method, a new supply chain theory DDMRP is introduced, the DDMRP part is improved and applied according to the specific scene of the off-line retail store, the replenishment quantity of the store commodities is dynamically determined on the basis of store commodity inventory, and the commodity shortage rate and commodity turnover are reduced.
In order to make the objects, features and advantages of the present invention more apparent and understandable, the technical solutions in the embodiments of the present application will be clearly and completely described below with reference to the accompanying drawings in the embodiments of the present application, and it is apparent that the embodiments described below are only a part of the embodiments of the present application, and not all of the embodiments. All other embodiments, which can be derived by a person skilled in the art from the embodiments given herein without making any creative effort, shall fall within the protection scope of the present application.
Referring to fig. 1, a first embodiment of the present application provides a method for determining an amount of replenishment of an offline retail store, including:
First, historical sales data and historical replenishment data of a store are obtained, where the historical sales data records commodity basic features, commodity sales records, and store commodity sales activities of various types of commodities in the store, and the historical replenishment data records a historical replenishment record of the commodities in the store, and generally includes: the delivery period and the order placing period of each replenishment event.
And 102, predicting sales data of the target commodity in a future preset period through a preset machine learning model according to historical sales data.
Next, based on the historical sales data obtained in step 101, the sales data is predicted by using a machine learning algorithm to predict sales in a future preset period through a preset machine learning model.
And 103, calculating a first fluctuation coefficient according to the historical sales data and the predicted sales data, wherein the first fluctuation coefficient is used for quantifying the fluctuation of the sales data prediction.
And calculating the sales forecast fluctuation degree of the target commodity of the store, namely a first fluctuation coefficient according to the forecast sales obtained by the machine learning model in the step 102 and the real sales recorded in the historical sales data, and considering the sales fluctuation caused by the forecast inaccuracy, so that the sales forecast fluctuation can be dynamically quantified.
And 104, calculating a second fluctuation coefficient according to the historical replenishment data, wherein the second fluctuation coefficient is used for quantifying the fluctuation of the replenishment period of the target commodity.
And calculating the fluctuation degree of the replenishment period of the target commodity of the store, namely a second fluctuation coefficient according to the replenishment events recorded in the historical replenishment data, and considering the sales fluctuation caused by the untimely replenishment, so that the replenishment period fluctuation can be dynamically quantified.
And 105, calculating the demand of the target commodity in a future preset period according to the predicted sales data, the first fluctuation coefficient and the second fluctuation coefficient by combining the safety stock of the target commodity, and calculating the replenishment quantity of the target commodity by combining the store stock of the target commodity according to the demand.
And then, obtaining predicted sales data, a first fluctuation coefficient and a second fluctuation coefficient based on the preorder steps, calculating the demand of the target commodity in a future preset period by combining the safety stock requirement of an upper store for the target commodity, and finally calculating the replenishment quantity of the target commodity according to the demand and the store stock condition of the target commodity, thereby performing ordering replenishment according to the calculated replenishment quantity.
The method includes the steps that predicted sales data of a target commodity in a future preset period are predicted through a preset machine learning model based on historical data of a shop commodity sales process, then according to the historical sales data and the predicted sales data, a fluctuation coefficient of sales prediction and a fluctuation coefficient of a replenishment period are calculated, and according to the predicted sales data and the fluctuation coefficient, the demand of the target commodity in the future preset period is calculated by combining safety stock of the target commodity; and finally, calculating the replenishment quantity of the target commodity by combining store inventory of the target commodity according to the demand quantity, thereby replenishing according to the replenishment quantity obtained by calculation, and solving the technical problem that the single replenishment quantity of the existing off-line retail store excessively depends on manual experience.
The above content is a detailed description of an embodiment of the method for determining the replenishment quantity of the offline retail store provided by the present application, and the following is a detailed description of another embodiment of the method for determining the replenishment quantity of the offline retail store provided by the present application.
Referring to fig. 2, based on the content of the previous embodiment, the method for determining the replenishment quantity of the offline retail store provided by this embodiment specifically includes the following steps:
further, the machine learning model mentioned in step 102 is specifically: and the composite model comprises a time sequence algorithm model and a tree algorithm model, such as arima + lightgbm, arima + catboost, sarima + lightgbm and the like.
Meanwhile, in order to improve the effect of sales prediction, the present embodiment preferably uses a composite model of fbprophet + multi-output lightgbm.
The Fbprophet is a time series algorithm, can predict single-dimensional data (historical sales) and only capture trends and periodicity, but cannot learn other characteristics well (such as holiday characteristics and weather characteristics). The lightgbm can learn the multidimensional characteristics, and the combination of the multidimensional characteristics and the lightgbm can learn the trend, periodicity and the influence of other external characteristics (such as holiday characteristics, weather characteristics and the like) on sales volume, so that the accuracy is more accurate than the future sales volume predicted by a conventional rule.
More specifically, the step 102 of predicting, according to the historical sales data and by using a preset machine learning model, the predicted sales data of the commodity in a future preset period specifically includes:
and 1022, taking the predicted sales volume of the store commodities as the input of the tree algorithm model, and obtaining the predicted sales data of the target commodities in a future preset period through the operation of the tree algorithm model.
It should be noted that the sales prediction process of the present embodiment mainly uses a composite model of fbprophet and a multiple output lightgbm model. That is, the fbprophet model is used to predict the sales of stores at n time points in the future, then the predicted sales of stores at n time points are used as the input of the multi-output lightgbm model, and finally the sales of stores at n time points in the future are predicted, as shown in fig. 3. In the figure, qty s,g,t Actual sales volume of the g commodities of the s stores at the time point t;
the predicted sales volume of the fbprophet model at the time point t for the g commodities of the s-store at the nth time point in the future (namely the time point t + n); pqty s,g,t+n The combined model eventually predicts the sales of the product of the s-shop g at the nth future time point (i.e., t + n time point) at the t time point.
Further, the step 103 of calculating the first fluctuation coefficient according to the historical sales data and the predicted sales data specifically includes:
and fitting the historical sales data and the predicted sales data according to the time dimension characteristics of the historical sales data and the predicted sales data, and calculating a first fluctuation coefficient according to the fitted historical sales data and the predicted sales data.
It should be noted that, according to the time dimension characteristics of the historical replenishment data, the time dimension characteristics here include: the same month, festival, activity days, etc., for example: fitting historical sales data of past double 11 activity periods with predicted sales data of future double 11 activity periods, fitting the historical sales data with the predicted sales data, and calculating a first fluctuation coefficient according to the fitted historical sales data and the predicted sales data, wherein the specific calculation formula is as follows:
in the formula, p s,g, t is a predicted fluctuation coefficient of sales of the g commodities of the s store for m days at the time point of t, namely a first fluctuation coefficient, pqty s,g,t-i Sales forecast, qty, for time point t-i for g merchandise in s stores s,g,t-i The actual sales volume of the g commodities at the time point of t-i of the s-store is m, and the m is the number of days of a recent period of time at the time point of t.
Further, the step 104 of calculating the second fluctuation coefficient according to the historical replenishment data specifically includes:
and fitting the historical replenishment data according to the time dimension characteristics of the historical replenishment data, and calculating a second fluctuation coefficient according to the fitted historical replenishment data.
The fluctuation coefficient of the individual product distribution cycle of the store is fitted by using historical individual product distribution cycle data of the store, and the specific calculation formula is as follows:
in the formula, rl _ dlv s,g,t-i Is the mean value of the real distribution cycle of the g commodities t-i time points of the s stores, dlv s,g,t-i Planned delivery cycle for time point t-i of commodity of store g of s, d s,g,t And the distribution cycle fluctuation coefficient is a second fluctuation coefficient which is the distribution cycle fluctuation coefficient of the g commodities of the s stores for m days at the time point of t, and m is the number of days in a recent period at the time point of t.
Further, the step 105 of calculating the demand of the target product in the future preset period according to the predicted sales data, the first fluctuation coefficient and the second fluctuation coefficient in combination with the safety stock of the target product specifically includes the following steps:
the replenishment quantity calculation in the step introduces a formula of a DDMRP theory, and the DDMRP is improved on the basis of the DDMRP according to the characteristics of off-line retail stores, and the method specifically comprises the following steps:
RZ s,g,t ＝RB s,g,t +RS s,g,t
TOG s,g,t ＝RZ s,g,t +YZ s,g,t +GZ s,g,t
wherein, YZ s,g,t For the size of the yellow area of the g commodities of the s-store at the time point t, the consumption of the commodities in the distribution period, ypred, is calculated s,g,t+j Predicting sales volume of the commodities of the s-store g at the jth time point of the distribution cycle; GZ s,g,t The term "green region size at time t" for the product of store g means the product consumption in the next cycle, but if the product consumption in the next cycle is smaller than the product consumption due to the fluctuation of the delivery cycle in the delivery cycle, the product consumption is the fluctuation sales in the delivery cycle, ypred s,g,t+d+i Forecast sales of g-stores in the s-store for the i-th time point of the next single period, d s,g,t Distribution cycle fluctuation coefficient, RB, for g-shop goods at time t s,g,t The size of a red basic area of the g commodities of the s-store at the time point t is the fluctuation of the consumption of the commodities in a distribution period; RS s,g,t The calculated mean is the fluctuating sales volume, p, generated by the fluctuation of sales forecast in the distribution cycle and the ordering cycle for the size of red safety zone of the g-shop goods at the time point t s,g, t is a predicted fluctuation coefficient of the g commodities of the s stores at the time point t; RZ s,g,t For the red area of the s-shop g goods at the time point t, the sum of the red safety area and the red base area, the safety stock is calculated, and the safety stock is the goods sales amount covering the distribution fluctuation and the forecast fluctuation. TOG s,g,t The top line of the green zone of the g commodities of the s-shop at the time point t is a red zoneThe sum of the domain, the yellow area and the green area covers the future ordering period, the distribution period and the fluctuating commodity sales demand, the parameter can be used as the basis for confirming the replenishment quantity, and the replenishment quantity of the commodity can be calculated by combining the commodity inventory condition of a store according to the demand quantity, and the specific calculation formula is as follows:
in the formula, rpl _ qty s,g,t Replenishment of g goods in s stores at time point t, dis s,g,t The display demand for the g store goods at time t, which is negligible in some scenarios,
the goods are available at time t for store g,
and (5) warehousing the commodities of the s-storehouses g in transit at the time point t.
Further, according to the demand, in combination with store inventory of the target product, after calculating the replenishment quantity of the target product, the method further comprises:
and 106, comparing the replenishment quantity with a preset minimum order quantity according to the replenishment quantity, and if the replenishment quantity is less than the minimum order quantity, adjusting the replenishment quantity according to the minimum order quantity.
It should be noted that, the plan for determining the replenishment quantity of the store also introduces the minimum order quantity, so that the replenishment is more realistic, and when the minimum order quantity is added, the above-mentioned calculation formula of the replenishment quantity can be rewritten into the following form:
wherein, moq s,g, And t is the minimum ordering amount of the g commodities of the s stores at the time point t.
The above is a detailed description of another embodiment of the method for determining the replenishment quantity of the offline retail store provided by the present application, and the following is a detailed description of an embodiment of the apparatus for determining the replenishment quantity of the offline retail store provided by the present application,
referring to fig. 4, an embodiment of the present application provides an offline retail store replenishment quantity determination apparatus, including:
a historical data acquisition unit 201 for acquiring historical sales data and historical replenishment data of a target store;
the sales data prediction unit 202 is configured to predict, according to historical sales data, predicted sales data of the target commodity in a future preset period through a preset machine learning model;
a first fluctuation coefficient calculation unit 203 for calculating a first fluctuation coefficient for quantifying fluctuation of sales data prediction, based on the historical sales data and the predicted sales data;
a second fluctuation coefficient calculation unit 204 for calculating a second fluctuation coefficient for quantifying fluctuation of the replenishment cycle of the target commodity, based on the historical replenishment data;
the replenishment quantity calculation unit 205 is configured to calculate a demand quantity of the target commodity in a future preset period according to the predicted sales data, the first fluctuation coefficient and the second fluctuation coefficient in combination with the safety stock of the target commodity, and then calculate the replenishment quantity of the target commodity in combination with the store stock of the target commodity according to the demand quantity.
In addition, the present application further provides a description of the terminal embodiment and the storage medium embodiment related to the content of the above embodiments on the basis of the above embodiments.
A fourth embodiment of the present application provides an offline retail store replenishment quantity determination terminal, including: a memory and a processor;
the memory is used for storing program codes, and the program codes correspond to the method for determining the replenishment quantity of the off-line retail store according to the first embodiment or the second embodiment of the application;
the processor is used for executing the program codes, so that the terminal can realize the method for determining the replenishment quantity of the off-line retail store provided by the first embodiment or the second embodiment of the application.
A fifth embodiment of the present application provides a computer-readable storage medium having stored therein program code corresponding to the method for determining the replenishment quantity of an offline retail store as provided in the first or second embodiment of the present application.
It can be clearly understood by those skilled in the art that, for convenience and simplicity of description, the specific working processes of the terminal, the device and the unit described above may refer to the corresponding processes in the foregoing method embodiments, and are not described herein again.
In the several embodiments provided in the present application, it should be understood that the disclosed terminal, apparatus and method may be implemented in other manners. For example, the above-described apparatus embodiments are merely illustrative, and for example, a division of a unit is merely a logical division, and an actual implementation may have another division, for example, a plurality of units or components may be combined or integrated into another system, or some features may be omitted, or not executed. In addition, the shown or discussed mutual coupling or direct coupling or communication connection may be an indirect coupling or communication connection through some interfaces, devices or units, and may be in an electrical, mechanical or other form.
The terms "first," "second," "third," "fourth," and the like in the description of the application and the above-described figures, if any, are used for distinguishing between similar elements and not necessarily for describing a particular sequential or chronological order. It is to be understood that the data so used is interchangeable under appropriate circumstances such that the embodiments of the application described herein are, for example, capable of operation in sequences other than those illustrated or otherwise described herein. Furthermore, the terms "comprises," "comprising," and "having," and any variations thereof, are intended to cover a non-exclusive inclusion, such that a process, method, system, article, or apparatus that comprises a list of steps or elements is not necessarily limited to those steps or elements expressly listed, but may include other steps or elements not expressly listed or inherent to such process, method, article, or apparatus.
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, may be located in one position, or may be distributed on multiple 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, functional units in the embodiments of the present invention may be integrated into one processing unit, or each unit may exist alone physically, or two or more units are integrated into one unit. The integrated unit can be realized in a form of hardware, and can also be realized in a form of a software functional unit.
The integrated unit, if implemented in the form of a software functional unit and sold or used as a stand-alone product, may be stored in a computer readable storage medium. Based on such understanding, the technical solution of the present invention may be embodied in the form of a software product, which is stored in a storage medium and includes instructions for causing a computer device (which may be a personal computer, a server, or a network device) to execute all or part of the steps of the method according to the embodiments of the present invention. And the aforementioned storage medium includes: a U-disk, a removable hard disk, a Read-Only Memory (ROM), a Random Access Memory (RAM), a magnetic disk or an optical disk, and other various media capable of storing program codes.
The above embodiments are only used to illustrate the technical solutions of the present application, and not to limit the same; although the present application has been described in detail with reference to the foregoing embodiments, it should be understood by those of ordinary skill in the art that: the technical solutions described in the foregoing embodiments may still be modified, or some technical features may be equivalently replaced; and such modifications or substitutions do not depart from the spirit and scope of the corresponding technical solutions of the embodiments of the present application.
Claims (10)
1. An offline retail store replenishment quantity determination method is characterized by comprising the following steps:
acquiring historical sales data and historical replenishment data of a target store;
predicting the predicted sales data of the target commodity in a future preset period through a preset machine learning model according to the historical sales data;
calculating a first fluctuation coefficient according to the historical sales data and the predicted sales data, wherein the first fluctuation coefficient is used for quantifying the fluctuation of sales data prediction;
calculating a second fluctuation coefficient according to historical replenishment data, wherein the second fluctuation coefficient is used for quantifying the fluctuation of a replenishment period of a target commodity;
and calculating the demand of the target commodity in the future preset period by combining the safety stock of the target commodity according to the predicted sales data, the first fluctuation coefficient and the second fluctuation coefficient, and calculating the replenishment quantity of the target commodity by combining the store stock of the target commodity according to the demand.
2. The method for determining the replenishment quantity of the offline retail store according to claim 1, wherein the machine learning model is specifically: the composite model comprises a time sequence algorithm model and a tree algorithm model.
3. The method for determining the replenishment quantity of the offline retail store according to claim 2, wherein predicting the predicted sales data of the commodity in a future preset period through a preset machine learning model according to the historical sales data specifically comprises:
according to the historical sales data, the historical sales data are used as input of a time sequence algorithm model, and store commodity predicted sales data of the target store in a future preset period are obtained through operation of the time sequence algorithm model;
and taking the predicted sales volume of the store commodities as the input of a tree algorithm model, and obtaining the predicted sales data of the target commodities in a future preset period through the operation of the tree algorithm model.
4. The method for determining the replenishment quantity of the offline retail store according to claim 2, wherein the time-series algorithm model is specifically: the fbprophet algorithm model specifically comprises the following steps: a multi-output lightgbm model.
5. The method for determining the replenishment quantity of the offline retail store according to claim 1, wherein calculating the first fluctuation coefficient based on the historical sales data and the predicted sales data specifically comprises:
and fitting the historical sales data and the predicted sales data according to the time dimension characteristics of the historical sales data and the predicted sales data, and calculating a first fluctuation coefficient according to the fitted historical sales data and the predicted sales data.
6. The method for determining the replenishment quantity of the offline retail store according to claim 1, wherein the calculating the second fluctuation coefficient according to the historical replenishment data specifically comprises:
and fitting the historical replenishment data according to the time dimension characteristics of the historical replenishment data, and calculating a second fluctuation coefficient according to the fitted historical replenishment data.
7. The method as claimed in claim 1, wherein the calculating the replenishment quantity of the target product according to the demand and the store inventory of the target product further comprises:
and comparing the replenishment quantity with a preset minimum order quantity according to the replenishment quantity, and if the replenishment quantity is less than the minimum order quantity, adjusting the replenishment quantity according to the minimum order quantity.
8. An offline retail store replenishment quantity determination device, comprising:
the historical data acquisition unit is used for acquiring historical sales data and historical replenishment data of the target store;
the sales data prediction unit is used for predicting the predicted sales data of the target commodity in a future preset period through a preset machine learning model according to the historical sales data;
a first fluctuation coefficient calculation unit configured to calculate a first fluctuation coefficient for quantifying fluctuation of sales data prediction, based on the historical sales data and the predicted sales data;
the second fluctuation coefficient calculation unit is used for calculating a second fluctuation coefficient according to historical replenishment data, wherein the second fluctuation coefficient is used for quantifying the fluctuation of the replenishment period of the target commodity;
and the replenishment quantity calculation unit is used for calculating the demand quantity of the target commodity in the future preset period by combining the safety stock of the target commodity according to the predicted sales data, the first fluctuation coefficient and the second fluctuation coefficient, and then calculating the replenishment quantity of the target commodity by combining the store stock of the target commodity according to the demand quantity.
9. An offline retail store replenishment quantity determination terminal, comprising: a memory and a processor;
the memory is configured to store a program code corresponding to the off-line retail store replenishment quantity determination method according to any one of claims 1 to 7;
the processor is configured to execute the program code.
10. A computer-readable storage medium having stored therein a program code corresponding to the method for determining the replenishment quantity of an off-line retail store according to any one of claims 1 to 7.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202211422846.5A CN115689451A (en) | 2022-11-14 | 2022-11-14 | Method, device, terminal and medium for determining replenishment quantity of off-line retail store |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202211422846.5A CN115689451A (en) | 2022-11-14 | 2022-11-14 | Method, device, terminal and medium for determining replenishment quantity of off-line retail store |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN115689451A true CN115689451A (en) | 2023-02-03 |
Family
ID=85051987
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202211422846.5A Pending CN115689451A (en) | 2022-11-14 | 2022-11-14 | Method, device, terminal and medium for determining replenishment quantity of off-line retail store |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN115689451A (en) |
Cited By (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN116051000A (en) * | 2023-02-16 | 2023-05-02 | 深圳一资源网络平台有限公司 | Data sales analysis method, system and readable storage medium |
| CN116342042A (en) * | 2023-05-25 | 2023-06-27 | 北京京东乾石科技有限公司 | Goods supplementing method and device and storage medium |
| CN116664052A (en) * | 2023-07-21 | 2023-08-29 | 厦门易驰软件有限公司 | Global digitalized operation management method and system based on artificial intelligence |
| CN116739655A (en) * | 2023-07-14 | 2023-09-12 | 上海朗晖慧科技术有限公司 | Intelligent supply chain management method and system based on big data |
| CN116911742A (en) * | 2023-08-04 | 2023-10-20 | 杭州聚水潭网络科技有限公司 | E-commerce goods supplementing method, system and equipment |
| CN117575683A (en) * | 2023-12-29 | 2024-02-20 | 深圳市觅客科技有限公司 | Commodity sales management method and platform |
-
2022
- 2022-11-14 CN CN202211422846.5A patent/CN115689451A/en active Pending
Cited By (10)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN116051000A (en) * | 2023-02-16 | 2023-05-02 | 深圳一资源网络平台有限公司 | Data sales analysis method, system and readable storage medium |
| CN116051000B (en) * | 2023-02-16 | 2023-10-20 | 深圳一资源网络平台有限公司 | Data sales analysis method, system and readable storage medium |
| CN116342042A (en) * | 2023-05-25 | 2023-06-27 | 北京京东乾石科技有限公司 | Goods supplementing method and device and storage medium |
| 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 |
| CN116739655A (en) * | 2023-07-14 | 2023-09-12 | 上海朗晖慧科技术有限公司 | Intelligent supply chain management method and system based on big data |
| CN116739655B (en) * | 2023-07-14 | 2024-04-02 | 上海朗晖慧科技术有限公司 | Intelligent supply chain management method and system based on big data |
| CN116664052A (en) * | 2023-07-21 | 2023-08-29 | 厦门易驰软件有限公司 | Global digitalized operation management method and system based on artificial intelligence |
| CN116664052B (en) * | 2023-07-21 | 2023-10-20 | 厦门易驰软件有限公司 | Global digitalized operation management method and system based on artificial intelligence |
| CN116911742A (en) * | 2023-08-04 | 2023-10-20 | 杭州聚水潭网络科技有限公司 | E-commerce goods supplementing method, system and equipment |
| CN117575683A (en) * | 2023-12-29 | 2024-02-20 | 深圳市觅客科技有限公司 | Commodity sales management method and platform |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN115689451A (en) | Method, device, terminal and medium for determining replenishment quantity of off-line retail store | |
| Yang et al. | Integrated multi-period dynamic inventory classification and control | |
| De Kok et al. | A break-even analysis of RFID technology for inventory sensitive to shrinkage | |
| CN109740793B (en) | Inventory optimization method based on probability demand distribution | |
| van der Vorst et al. | Modelling and simulating multi-echelon food systems | |
| US5459656A (en) | Business demand projection system and method | |
| CN103971170B (en) | The method and apparatus that a kind of change being used for characteristic information is predicted | |
| Panda et al. | Optimal pricing and lot-sizing for perishable inventory with price and time dependent ramp-type demand | |
| US20100138281A1 (en) | System and method for retail store shelf stock monitoring, predicting, and reporting | |
| US9990597B2 (en) | System and method for forecast driven replenishment of merchandise | |
| Janssen et al. | A stochastic micro-periodic age-based inventory replenishment policy for perishable goods | |
| US20160232461A1 (en) | System and method for determining forecast errors for merchandise in retail | |
| CN110348635A (en) | Intelligent replenishing method, storage medium, system and device based on end-to-end study | |
| JP2003162619A (en) | Sales prediction apparatus and method | |
| CN116109252A (en) | Warehouse replenishment management method and device, warehouse management system and storage medium | |
| WO2023020255A1 (en) | Data processing method and apparatus, device, and storage medium | |
| Lahrichi et al. | A first MILP model for the parameterization of Demand-Driven MRP | |
| CN111768243A (en) | Sales prediction method, prediction model construction method, device, equipment and medium | |
| CN115860800A (en) | Festival and holiday commodity sales volume prediction method and device and computer storage medium | |
| Hung et al. | Capacity rationing decision procedures with order profit as a continuous random variable | |
| JP2013131259A (en) | Integrated demand prediction device, integrated demand prediction method, and integrated demand prediction program | |
| CN116308494A (en) | Supply chain demand prediction method | |
| CN116050987A (en) | Prediction method and device for material replenishment, storage medium and processor | |
| JPH11259564A (en) | Sales prediction supporting system | |
| CN114626660A (en) | Method and apparatus for surge regulation forecasting |
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 |