CN111325490B - Goods supplementing method and device - Google Patents
Goods supplementing method and device Download PDFInfo
- Publication number
- CN111325490B CN111325490B CN201811531470.5A CN201811531470A CN111325490B CN 111325490 B CN111325490 B CN 111325490B CN 201811531470 A CN201811531470 A CN 201811531470A CN 111325490 B CN111325490 B CN 111325490B
- Authority
- CN
- China
- Prior art keywords
- sku
- cost
- inventory
- sales
- stock
- 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 18
- 230000001502 supplementing effect Effects 0.000 title abstract description 8
- 230000001186 cumulative effect Effects 0.000 claims abstract description 31
- 238000012417 linear regression Methods 0.000 claims description 9
- 238000004364 calculation method Methods 0.000 claims description 8
- 238000009825 accumulation Methods 0.000 claims description 3
- 230000010354 integration Effects 0.000 claims description 3
- 230000006870 function Effects 0.000 description 21
- 230000006399 behavior Effects 0.000 description 5
- 238000005516 engineering process Methods 0.000 description 2
- 230000003068 static effect Effects 0.000 description 2
- 230000009286 beneficial effect Effects 0.000 description 1
- 238000004590 computer program Methods 0.000 description 1
- 238000005315 distribution function Methods 0.000 description 1
- 230000003203 everyday effect Effects 0.000 description 1
- 238000010801 machine learning Methods 0.000 description 1
- 230000007246 mechanism Effects 0.000 description 1
- 230000000737 periodic effect Effects 0.000 description 1
- 238000003672 processing method Methods 0.000 description 1
- 238000012216 screening Methods 0.000 description 1
- 230000001960 triggered effect 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
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 invention relates to a method and a device for replenishing goods, wherein the method for replenishing goods comprises the following steps: collecting stock data, historical sales and replenishment cycles of the SKUs; according to the time sequence, giving different weights to the historical sales volume, and calculating a sales volume cumulative density function of the SKU in the next replenishment period; calculating the inventory holding quantity of the corresponding SKU when the expected value of the inventory cost is minimum based on a preset constraint condition according to the sales quantity cumulative density function of the next replenishment period of the SKU; and comparing the inventory data of the SKU with the inventory holding quantity to obtain the inventory supplementing quantity, so that the inventory data of the SKU is not smaller than the inventory holding quantity, and comprehensively considering the inventory shortage cost and the inventory cost of the SKU, so that the inventory holding quantity calculated by the model is optimal in the overall cost of the warehouse, and the inventory management can be scientifically and systematically carried out for the warehouse.
Description
Technical Field
The present invention relates to the field of inventory management, and in particular, to a method and apparatus for supplementing goods.
Background
With the rise of online shopping, the perfected demands of corresponding logistics and supply chain mechanisms and technologies are also becoming urgent. The warehouse management is located in a position where the supply chain is critical, and inventory management of the warehouse management directly influences commodity order meeting rate, warehouse inventory management cost and the like.
For the determination of the restocking point R in the prior art solutions,
the static inventory (inventory R) specified according to the average value and variance of the sales of the SKU histories is simple, and because sales of each SKU fluctuate greatly, the proposal can not adapt to the variation trend of sales, and the inventory R is easy to obtain inaccurately;
secondly, a machine learning method is used to predict the sales of the sku so as to determine a lower replenishment limit (holding quantity R), and the prediction error is large because the sales of the sku is comprehensively influenced by various complex factors, and the lower replenishment limit of the proposal only considers the stock shortage cost (the temporary replenishment cost paid out due to the temporary replenishment behavior is generally greater than the conventional replenishment cost) and does not consider the stock cost.
Because the backorder cost of the Shunfeng warehouse cannot be directly measured by the market price of sku, which represents the labor cost of temporary replenishment after backorder, the backorder cost to be considered by the replenishment model is also difficult to estimate.
The human labor cost of work estimation has the following technical problems:
1. the lower limit of replenishment cannot capture the change of the sales volume of the sku in real time, so that the order satisfaction rate on certain days is low;
2. the lower limit of the restocking model fails to comprehensively consider inventory costs and backorder costs;
3. warehouse backorder costs to be considered by the backorder model are difficult to estimate, backorder costs cannot be directly measured by the market price or cost of the sku, and temporary backorder manual costs can be chosen to replace, however there are two difficulties in estimating the value: firstly, the number of the sku with temporary replenishment is small, the temporary replenishment manpower of all the sku of the warehouse cannot be directly calculated, and secondly, the temporary replenishment manpower is difficult to be converted into specific monetary cost.
Disclosure of Invention
In order to solve the above technical problems, the present invention aims to provide a method and a device for supplementing goods.
According to one aspect of the present invention, there is provided a method of restocking comprising:
collecting stock data, historical sales and replenishment cycles of the SKUs;
according to the time sequence, giving different weights to the historical sales volume, and calculating a sales volume cumulative density function of the SKU in the next replenishment period;
calculating the inventory holding quantity R of the corresponding SKU when the expected value of the inventory cost is minimum based on a preset constraint condition according to the sales quantity cumulative density function of the next replenishment period of the SKU;
and comparing the inventory data of the SKU with the holding quantity R to obtain the replenishment quantity, so that the inventory data of the SKU is not smaller than the holding quantity R.
Further, according to the time sequence, giving different weights to the historical sales, calculating a sales cumulative density function of the SKU in the next replenishment cycle, including:
giving a weight from small to large to the historical sales data of the SKU based on the chronological order;
accumulating and de-duplicating the historical sales, and integrating the historical sales into a sales distribution queue according to the sales sequence: r1, r2 … … rn;
calculating the probability of each sales occurrence to form a numerical distribution data set, and obtaining a cumulative density function of the historical sales by the weighted sum of each sales and the probability product thereof
Further, according to the sales volume cumulative density function of the next replenishment cycle of the SKU, calculating a holding volume R of the SKU corresponding to a minimum expected value of inventory cost based on a preset constraint condition, including:
calculating a unit stock out cost k of the SKU and collecting a unit stock out cost h of the SKU;
respectively calculating expected stock cost values of each historical sales of the SKU under the cumulative density function according to the unit backorder cost and the unit inventory cost: TC (r 1) and TC (r 2) … … TC (rn) meet preset constraint conditions TC (rn-1) which are not more than K/k+h which are not more than TC (rn);
the output rn is the holding quantity R of the SKU.
Further, calculating the unit backorder cost of the SKU includes:
randomly selecting the maximum temporary replenishment quantity in a SKU unit time from the inventory data and the historical sales volume data;
fitting a linear regression model according to the maximum temporary replenishment quantity, volume, weight and category of the SKU, and estimating the maximum temporary replenishment quantity in unit time of other SKUs;
and calculating the unit out-of-stock cost of the SKU based on the labor cost according to the maximum temporary replenishment quantity in the unit time of the SKU.
Further, the inventory cost expected value is an inventory cost or an out-of-stock cost of the SKU;
and/or
The restocking cycle includes at least one of: day, n days, week, month, year;
and/or
The inventory data includes at least one of: stock quantity, volume, weight, stock location volume, and temporary replenishment data for the SKU.
According to another aspect of the present invention, there is provided a restocking apparatus comprising:
the data acquisition module is configured for acquiring inventory data, historical sales and replenishment cycles of the SKU;
the sales predicting module is configured to give different weights to the historical sales according to the time sequence, and calculate a sales cumulative density function of the SKU in the next replenishment period;
the calculation module is configured to calculate the inventory holding quantity R of the corresponding SKU when the expected value of the inventory cost is minimum based on a preset constraint condition according to the sales volume cumulative density function of the next replenishment cycle of the SKU;
and comparing the inventory data of the SKU with the holding quantity R to obtain the replenishment quantity, so that the inventory data of the SKU is not smaller than the holding quantity R.
Further, the computing module includes:
a weight distribution unit configured to give a small to large weight to the historical sales data of SKUs based on the chronological order;
the integration unit is configured to integrate the historical sales volume according to the sales volume sequence to obtain a sales volume distribution queue based on accumulation and de-duplication of the historical sales volume: r1, r2 … … rn;
a first calculation unit: calculating the probability of each sales occurrence to form a numerical distribution data set, and calculating the weighted sum of each sales and the probability product thereof to obtain the cumulative density function of the historical sales
Further, the data acquisition module is further configured to acquire a unit inventory cost of the SKU;
the computing module further includes:
a second calculation unit configured to calculate a unit stock out cost k of the SKU and collect a unit stock out cost h of the SKU;
respectively calculating expected stock cost values of each historical sales of the SKU under the cumulative density function according to the unit backorder cost and the unit inventory cost: TC (r 1) and TC (r 2) … … TC (rn) meet preset constraint conditions TC (rn-1) which are not more than K/k+h which are not more than TC (rn);
the output rn is the holding quantity R of the SKU.
Further, calculating the unit backorder cost of the SKU includes:
randomly selecting the maximum temporary replenishment quantity in a SKU unit time from the inventory data and the historical sales quantity data;
fitting a linear regression model according to the maximum temporary replenishment quantity, volume, weight and category of the SKU, and estimating the maximum temporary replenishment quantity in unit time of other SKUs;
according to the maximum temporary replenishment quantity in the SKU unit time,
the unit out-of-stock cost for the SKU is calculated based on the labor cost.
Further, the inventory cost expected value is an inventory cost or an out-of-stock cost of the SKU;
and/or
The restocking cycle includes at least one of: day, n days, week, month, year;
and/or
The inventory data includes at least one of: stock quantity, volume, weight, stock location volume, and temporary replenishment data for the SKU.
According to another aspect of the present invention, there is provided an apparatus comprising
One or more processors;
a memory for storing one or more programs,
the one or more programs, when executed by the one or more processors, cause the one or more processors to perform the method of any of the preceding claims.
According to another aspect of the present invention, there is provided a computer readable storage medium storing a computer program which when executed by a processor implements a method as claimed in any one of the above.
Compared with the prior art, the invention has the following beneficial effects:
1. according to the goods supplementing method, the goods holding quantity R of the corresponding SKU when the expected value of the stock cost is minimum is calculated based on the preset constraint condition, and the stock cost comprehensively considers the stock shortage cost and the stock cost of the SKU, so that the goods holding quantity R calculated by the model is optimal in the overall cost of the warehouse, and the stock management can be scientifically and systematically carried out for the warehouse.
2. According to the replenishment device, the sales volume prediction module gives different weights to the data points according to the sales volume date, so that the sales volume R can capture the variation trend of sales volume, and inventory management can be performed for a warehouse scientifically and systematically.
Drawings
FIG. 1 is a flow chart of the present invention.
Detailed Description
For a better understanding of the technical solution of the present invention, the present invention will be further described with reference to the following specific examples and the accompanying drawings.
Example 1:
the utility model provides a replenishment device, includes:
the data acquisition module is configured for acquiring stock data, historical sales, replenishment cycles and unit inventory costs of the SKUs; the inventory data includes at least one of: stock quantity, volume, weight, stock location volume, and temporary replenishment data for the SKU.
The sales predicting module is configured to give different weights to the historical sales according to the time sequence, and calculate a sales cumulative density function of the SKU in the next replenishment period; the restocking cycle includes at least one of: day, n days, week, month, year. Specifically, the sales prediction module includes:
the frequency allocation unit is configured to give different weights to the historical sales data of the SKU based on time sequence;
a weight distribution unit configured to give a small to large weight to the historical sales data of SKUs based on the chronological order;
the integration unit is configured to integrate the historical sales volume according to the sales volume sequence to obtain a sales volume distribution queue based on accumulation and de-duplication of the historical sales volume: r1, r2 … … rn;
a first calculation unit: calculating the probability of each sales occurrence to form a numerical distribution data set, and calculating the weighted sum of each sales and the probability product thereof to obtain the cumulative density function of the historical sales
A second calculation unit configured to calculate a unit stock out cost k of the SKU and collect a unit stock out cost h of the SKU;
respectively calculating expected stock cost values of each historical sales of the SKU under the cumulative density function according to the unit backorder cost and the unit inventory cost: TC (r 1) and TC (r 2) … … TC (rn) meet preset constraint conditions TC (rn-1) which are not more than K/k+h which are not more than TC (rn);
the output rn is the holding quantity R of the SKU.
Further, calculating the unit backorder cost of the SKU includes: randomly selecting the maximum temporary replenishment quantity in a SKU unit time from the inventory data and the historical sales quantity data;
fitting a linear regression model according to the maximum temporary replenishment quantity, volume, weight and category of the SKU, and estimating the maximum temporary replenishment quantity in unit time of other SKUs;
according to the maximum temporary replenishment quantity in the SKU unit time,
the unit out-of-stock cost for the SKU is calculated based on the labor cost.
The replenishment method corresponding to the replenishment device of the embodiment comprises the following steps:
s1: collecting inventory data, historical sales, and replenishment cycles for a SKU, the inventory data comprising at least one of: stock quantity, volume, weight, stock location volume, and temporary replenishment data of the SKU; the replenishment cycle is as follows: the period from one replenishment to the next replenishment is the period of time of day, n days, week, month, year.
S2: according to different weights of historical sales given by time sequence, calculating a sales accumulated density function of the SKU in the next replenishment period, specifically comprising:
s2-1: the historical sales data of the SKU is given a weight from small to large based on time sequence, and in order to consider the instantaneity of sales change, the sales weight is larger when the sales change is more recent, and through discretization processing of a cumulative distribution function of the historical sales data, the error of inaccurate fitting of the historical data distribution is avoided, so that the solution of a newspaper-to-child model is more accurate;
s2-2: accumulating and de-duplicating the historical sales, and integrating the historical sales into a sales distribution queue according to the sales sequence: r1, r2 … … rn;
s2-3: calculating the probability of each sales occurrence to form a numerical distribution data set, and obtaining a cumulative density function of the historical sales by the weighted sum of each sales and the probability product thereof
S3: calculating the inventory holding quantity R of the corresponding SKU when the expected value of the inventory cost is minimum based on a preset constraint condition according to the sales quantity cumulative density function of the next replenishment period of the SKU, wherein the method comprises the following steps:
s3-1: calculating a unit stock out cost k of the SKU and collecting a unit stock out cost h of the SKU; calculating a unit backorder cost k for the SKU, comprising:
s3-1-1: randomly selecting the maximum temporary replenishment quantity in a SKU unit time from the inventory data and the historical sales quantity data;
s3-1-2: fitting a linear regression model according to the maximum temporary replenishment quantity, volume, weight and category of the SKU, estimating the maximum temporary replenishment quantity in unit time of other SKUs,
s3-1-3: calculating the unit stock-out cost of the SKU based on the labor cost according to the maximum temporary stock-out amount in the unit time of the SKU;
s3-2: respectively calculating expected stock cost values of each historical sales of the SKU under the cumulative density function according to the unit backorder cost and the unit inventory cost: TC (r 1) and TC (r 2) … … TC (rn) meet preset constraint conditions TC (rn-1) which are not more than K/k+h which are not more than TC (rn);
the output rn is the holding quantity R of the SKU.
And comparing the inventory data of the SKU with the holding quantity R to obtain the replenishment quantity, so that the inventory data of the SKU is not smaller than the holding quantity R.
And calculating the inventory holding quantity R for all SKUs in the warehouse in sequence, so that the overall inventory supplementing cost of the warehouse is minimum.
The method of replenishment is further described by way of example as follows:
step 1: and (3) data acquisition: collecting inventory data and historical sales data (sales data of a certain time, in this embodiment, sales data of nearly 60 days) of all SKUs in a warehouse, wherein the replenishment period is a day;
the unit inventory cost of the SKU is obtained from the tariff tables of the individual SKUs by storing information with the warehouse (which may also be obtained by communicating with warehouse personnel).
Step 2: sales data processing
Discretizing the probability density distribution of the historical sales volume, and integrating the probability density distribution into a sales volume distribution queue according to the real-time property of sales volume change and the sales volume sequence (from small to large): r1, r2 … … rn;
the discrete sales distribution is weighted, the sales weight is inversely proportional to the time sequence, the sales weight of the closer time is larger, the sales value weight count of the latest day is 60, the weight count of the sales value of the farthest day is 1, the replenishment period is day, and the probability P (rn) =rn of each sales occurrence is calculated to form a numerical distribution data set { r1: count1; r2: count2; … … rn: countn; }
Calculating the sales accumulated density function of the SKU in the next replenishment period
Step 3: calculating out-of-stock costs
When an order is out of stock for a certain sku, a temporary replenishment behavior is triggered, namely, warehouse staff can acquire the sku from a storage area and replenish the sku to a picking area after a certain time, and because the out-of-stock cost in the scene cannot be directly measured by the market price or cost of the sku, the manual cost of temporary replenishment is selected to replace, and the specific processing method is as follows:
(1) Screening out the SKU temporary replenishment behaviors from the inventory data, and selecting one temporary replenishment behavior with the largest replenishment quantity of SKU (recorded as SKU i).
(2) Fitting a linear regression model
Assume Q i = amount of temporary restocking for this SKU i
Fitting a linear regression model Q i =a 1*V i+a 2*W i+a 3*Type i
Where V i = the SKU i volume, W i = the SKU i weight, type i = the SKU i category.
(3) Using a linear regression model to estimate Q i of all SKUs in the warehouse (the a 1, a 2 and a 3 of each SKU are the same by default), calculating the unit stock-out cost of each SKU based on the labor cost according to Q i of each SKU in unit time, and obtaining the emergency stock-out cost of each SKU by analogy according to the estimated Q i of the model, if the stock-out amount of each SKU1 is 8 in one day and the stock-out amount of each SKU2 is 2, the stock-out cost of each SKU1 is 1/4 of the stock-out cost of each SKU2, and finally obtaining the emergency stock-out cost of each SKU, namely the final stock-out cost k of each SKU according to the wage of each SKU in one day. I.e., the higher Q i, the lower the temporary restocking cost per restock of 1 this sku, given the capacity of the restocking personnel. In a specific application, the labor cost can be analyzed from the wages of the restocking personnel in one day, the unit stock-out cost k of the sku1 and the sku2 can be obtained according to the stock-out capacity of the restocking personnel in one day, and the unit stock-out cost k of all skus can be obtained by analogy.
Step 3: calculating the holding capacity R of the SKU
Assuming r = expected sales on the same day, a sales distribution queue is taken from the SKU; r=today's hold R, the optimal restocking point.
R=today should prepare an inventory, the optimal restocking point
And r1< r2< … … < rn,
k=unit out-of-stock cost
h = unit inventory cost
If the SKU inventory exceeds the expected sales interval (R < R), the product occupancy warehouse generates inventory costs:
if the SKU inventory is less than the expected sales interval (R > R), a temporary restocking event occurs, yielding an inventory cost:
in summary, the expected value of stock cost TC (R) for one restocking cycle is:
the objective function is Min (TC (R)), and the expected value of the stock cost of each historical sales of the SKU under the cumulative density function is calculated according to the unit backorder cost and the unit stock cost respectively: TC (r 1), TC (r 2) … … TC (rn) satisfy the following three constraints: TC (rn-1) is more than or equal to K/k+h is more than or equal to TC (rn); the output rn is the holding quantity R of the SKU.
And comparing the inventory data of the SKU with the holding quantity R to obtain the replenishment quantity, so that the inventory data of the SKU is not smaller than the holding quantity R.
And calculating the inventory holding quantity R for all SKUs in the warehouse in sequence, so that the overall inventory supplementing cost of the warehouse is minimum.
The probability cumulative function of sales volume is changed, sales volume intervals are changed along with time change, and change information of the sales volume is captured through the weight of historical sales volume values, so that the optimal holding volume R of the SKU is changed every day instead of the traditional static holding volume R, the sum of the holding volumes R of the SKU is only required to be smaller than the upper stock limit of a warehouse, and the improved newspaper model is finally applied to periodic replenishment behaviors for many times.
The equipment in the embodiment can scientifically and systematically manage the inventory of the warehouse by executing the replenishment method through the processor.
The readable storage medium of this embodiment stores the replenishment method implemented when executed by the processor, so that the replenishment device is convenient to use and popularize.
The foregoing description is only of the preferred embodiments of the present application and is presented as a description of the principles of the technology being utilized. It will be appreciated by persons skilled in the art that the scope of the invention referred to in this application is not limited to the specific combinations of features described above, but it is intended to cover other embodiments in which any combination of features described above or equivalents thereof is possible without departing from the spirit of the invention. Such as the features described above, have similar functionality as disclosed (but not limited to) in this application.
Claims (6)
1. A method of restocking, comprising:
collecting stock data, historical sales and replenishment cycles of the SKUs;
according to the time sequence, giving different weights to the historical sales volume, and calculating a sales volume cumulative density function of the SKU in the next replenishment period;
calculating the inventory holding quantity R of the corresponding SKU when the expected value of the inventory cost is minimum based on a preset constraint condition according to the sales quantity cumulative density function of the next replenishment period of the SKU;
comparing the inventory data of the SKU with the holding quantity R to obtain a replenishment quantity, so that the inventory data of the SKU is not smaller than the holding quantity R;
wherein, the giving different weights to the historical sales according to the time sequence, calculating the sales cumulative density function of the SKU in the next replenishment cycle includes:
giving a weight from small to large to the historical sales data of the SKU based on the chronological order;
accumulating and de-duplicating the historical sales, and integrating the historical sales into a sales distribution queue according to the sales sequence: r1, r2 … … rn;
calculating the probability of each sales volume to form a numerical distribution data set, and calculating the weighted sum of each sales volume and the probability product thereof to obtain a cumulative density function of the historical sales volume
The calculating, according to the sales cumulative density function of the next replenishment cycle of the SKU, a holding amount R of the SKU corresponding to a minimum expected value of inventory cost based on a preset constraint condition, includes:
calculating a unit stock out cost k of the SKU and collecting a unit stock out cost h of the SKU;
calculating the cumulative density function for each historical sales of the SKU based on the unit stock cost and the unit stock costLower part (C)Inventory cost expectation: TC (r 1) and TC (r 2) … … TC (rn) meet preset constraint conditions TC (rn-1) which are not more than k/k+h not more than TC (rn);
the output rn is the holding quantity R of the SKU.
2. The restocking method of claim 1, wherein calculating the unit backorder cost of the SKU comprises:
randomly selecting the maximum temporary replenishment quantity in a SKU unit time from the inventory data and the historical sales volume data;
fitting a linear regression model according to the maximum temporary replenishment quantity, volume, weight and category of the SKU, and estimating the maximum temporary replenishment quantity in unit time of other SKUs;
and calculating the unit out-of-stock cost of the SKU based on the labor cost according to the maximum temporary replenishment quantity in the unit time of the SKU.
3. The restocking method as claimed in claim 1 or 2, wherein,
the inventory cost expected value is an inventory cost or a stock out cost of the SKU;
and/or
The restocking cycle includes at least one of: day, n days, week, month, year;
and/or
The inventory data includes at least one of: stock quantity, volume, weight, stock location volume, and temporary replenishment data for the SKU.
4. A restocking device, comprising:
the data acquisition module is configured for acquiring inventory data, historical sales and replenishment cycles of the SKU;
the sales predicting module is configured to give different weights to the historical sales according to the time sequence, and calculate a sales cumulative density function of the SKU in the next replenishment period;
the calculation module is configured to calculate the inventory holding quantity R of the corresponding SKU when the expected value of the inventory cost is minimum based on a preset constraint condition according to the sales volume cumulative density function of the next replenishment cycle of the SKU;
comparing the inventory data of the SKU with the holding quantity R to obtain a replenishment quantity, so that the inventory data of the SKU is not smaller than the holding quantity R;
wherein the computing module comprises:
a weight distribution unit configured to give a small to large weight to the historical sales data of SKUs based on the chronological order;
the integration unit is configured to integrate the historical sales volume according to the sales volume sequence to obtain a sales volume distribution queue based on accumulation and de-duplication of the historical sales volume: r1, r2 … … rn;
a first calculation unit: calculating the probability of each sales volume to form a numerical distribution data set, and calculating the weighted sum of each sales volume and the probability product thereof to obtain a cumulative density function of the historical sales volume
The data acquisition module is further configured to acquire a unit inventory cost of the SKU;
the computing module further includes:
a second calculation unit configured to calculate a unit stock out cost k of the SKU and collect a unit stock out cost h of the SKU;
calculating the cumulative density function for each historical sales of the SKU based on the unit stock cost and the unit stock costThe following inventory cost expectations: TC (r 1) and TC (r 2) … … TC (rn) meet preset constraint conditions TC (rn-1) which are not more than k/k+h not more than TC (rn);
the output rn is the holding quantity R of the SKU.
5. The restocking apparatus of claim 4, wherein calculating the unit backorder cost of the SKU comprises:
randomly selecting the maximum temporary replenishment quantity in a SKU unit time from the inventory data and the historical sales quantity data;
fitting a linear regression model according to the maximum temporary replenishment quantity, volume, weight and category of the SKU, and estimating the maximum temporary replenishment quantity in unit time of other SKUs;
according to the maximum temporary replenishment quantity in the SKU unit time,
the unit out-of-stock cost for the SKU is calculated based on the labor cost.
6. The restocking apparatus of claim 4 or 5, wherein the stock cost expected value is an inventory cost or a stock out cost of the SKU;
and/or
The restocking cycle includes at least one of: day, n days, week, month, year;
and/or
The inventory data includes at least one of: stock quantity, volume, weight, stock location volume, and temporary replenishment data for the SKU.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201811531470.5A CN111325490B (en) | 2018-12-14 | 2018-12-14 | Goods supplementing method and device |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201811531470.5A CN111325490B (en) | 2018-12-14 | 2018-12-14 | Goods supplementing method and device |
Publications (2)
Publication Number | Publication Date |
---|---|
CN111325490A CN111325490A (en) | 2020-06-23 |
CN111325490B true CN111325490B (en) | 2024-04-16 |
Family
ID=71167262
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201811531470.5A Active CN111325490B (en) | 2018-12-14 | 2018-12-14 | Goods supplementing method and device |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN111325490B (en) |
Families Citing this family (10)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN113887772A (en) * | 2020-07-02 | 2022-01-04 | 上海顺如丰来技术有限公司 | Order cycle optimization method, order cycle optimization device, computer equipment and storage medium |
CN113887771A (en) * | 2020-07-02 | 2022-01-04 | 上海顺如丰来技术有限公司 | Service level optimization method and device, computer equipment and storage medium |
CN113919764A (en) * | 2020-07-07 | 2022-01-11 | 上海顺如丰来技术有限公司 | Method and device for determining in-bin replenishment quantity, computer equipment and storage medium |
CN113935672A (en) * | 2020-07-13 | 2022-01-14 | 上海顺如丰来技术有限公司 | Automatic replenishment method and device, computer equipment and storage medium |
CN113947341A (en) * | 2020-07-17 | 2022-01-18 | 上海顺如丰来技术有限公司 | Supply chain replenishment method and device, computer equipment and storage medium |
CN113128932B (en) * | 2021-04-16 | 2024-04-16 | 北京京东振世信息技术有限公司 | Warehouse stock processing method and device, storage medium and electronic equipment |
CN113592153B (en) * | 2021-07-07 | 2022-06-17 | 杉数科技(北京)有限公司 | Goods distribution method, device, medium and computer equipment |
CN113743733B (en) * | 2021-08-06 | 2022-08-12 | 杉数科技(北京)有限公司 | Replenishment method and system |
CN114048931B (en) * | 2022-01-13 | 2022-06-07 | 北京京东振世信息技术有限公司 | Replenishment information generation method and device, electronic equipment and computer readable medium |
CN115630899B (en) * | 2022-11-01 | 2023-08-11 | 中国外运股份有限公司 | Multi-platform inventory optimization method and system |
Citations (4)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN104732287A (en) * | 2013-12-19 | 2015-06-24 | 广州市地下铁道总公司 | Stock control method based on optimum replenishment period of spare part |
CN106971249A (en) * | 2017-05-05 | 2017-07-21 | 北京挖玖电子商务有限公司 | A kind of Method for Sales Forecast and replenishing method |
CN107226311A (en) * | 2017-07-14 | 2017-10-03 | 李双玉 | The equipment that replenishes and transportation system |
CN108280538A (en) * | 2018-01-05 | 2018-07-13 | 广西师范学院 | Based on distributed logistics inventory's optimization method under cloud computing environment |
-
2018
- 2018-12-14 CN CN201811531470.5A patent/CN111325490B/en active Active
Patent Citations (4)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN104732287A (en) * | 2013-12-19 | 2015-06-24 | 广州市地下铁道总公司 | Stock control method based on optimum replenishment period of spare part |
CN106971249A (en) * | 2017-05-05 | 2017-07-21 | 北京挖玖电子商务有限公司 | A kind of Method for Sales Forecast and replenishing method |
CN107226311A (en) * | 2017-07-14 | 2017-10-03 | 李双玉 | The equipment that replenishes and transportation system |
CN108280538A (en) * | 2018-01-05 | 2018-07-13 | 广西师范学院 | Based on distributed logistics inventory's optimization method under cloud computing environment |
Non-Patent Citations (1)
Title |
---|
王东林."供应链环境下G公司成品空调的库存策略研究".《中国优秀硕士论文全文数据库》.2016,(第第1期期),第24-41页. * |
Also Published As
Publication number | Publication date |
---|---|
CN111325490A (en) | 2020-06-23 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN111325490B (en) | Goods supplementing method and device | |
Zhou et al. | Inventory management of platelets in hospitals: Optimal inventory policy for perishable products with regular and optional expedited replenishments | |
US8036925B2 (en) | System and method to manage assets of healthcare facility | |
US8538781B2 (en) | Workers compensation system for determining a cost of insurance | |
US8577712B2 (en) | Assessing risk | |
Kobbacy et al. | Forecasting for inventory management of service parts | |
CN111242524A (en) | Method, system, equipment and storage medium for determining replenishment quantity of single article | |
JP6603370B2 (en) | System and method for automatic ordering of products | |
CN108256898A (en) | A kind of product Method for Sales Forecast method, system and storage medium | |
US20120253876A1 (en) | Benefit-based earned value management system | |
CN111133460A (en) | Optimization of demand forecast parameters | |
CN109272276A (en) | A kind of inventory replenishes management method and device | |
Wagner | Demand planning | |
Alfieri et al. | Dynamic inventory rationing: How to allocate stock according to managerial priorities. An empirical study | |
US20150066570A1 (en) | System for self-managed inventory, supply chain dynamic sku performance and optimization | |
Cheng et al. | Intermittent demand forecasting in a tertiary pediatric intensive care unit | |
JP2016181039A (en) | Schedule determination method, schedule determination program and schedule determination system | |
CN114240473A (en) | Sku-based intelligent replenishment method and system | |
de Carvalho Guillén et al. | On the welfare costs of business-cycle fluctuations and economic-growth variation in the 20th century and beyond | |
Samii | Impact of nested inventory allocation policies in a newsvendor setting | |
Chen et al. | New sufficient conditions for (s, S) policies to be optimal in systems with multiple uncertainties | |
Argon et al. | Analysis of an inventory system under backorder correlated deterministic demand and geometric supply process | |
US20150324702A1 (en) | Predictive pattern profile process | |
Berk et al. | Inventory theory | |
CN117114761B (en) | Supply chain information management system based on integral data analysis |
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 |