Stock order quantity prediction method based on clothing life cycle

Abstract

The invention belongs to the technical field of clothing life prediction, and particularly relates to a clothing life cycle-based inventory order quantity prediction method, which comprises the following steps of A, obtaining all commodity selling information of each year in the history, and generating weekly selling data of corresponding commodities according to the selling natural weekly of each commodity; and B, classifying, calculating and analyzing the data obtained in the step A. And step C, summarizing inventory, sales and production information of a certain kind of currently sold commodities to generate a corresponding chart. And D, performing proportional conversion according to the curve of the currently sold commodities obtained in the step C and the classification life cycle curve. According to the inventory order quantity prediction method based on the clothing life cycle, the product sales rules of different categories are mined from the historical data, the accuracy of the reorder quantity of the clothing industry can be improved in combination with the data rules, the efficiency is improved through a system algorithm and the like, the business accuracy is finally improved, and inventory overstock and sales loss are reduced.

Description

Technical Field

[0001] The invention belongs to the technical field of clothing life cycle prediction, and in particular relates to a method for predicting inventory order quantity based on clothing life cycle. Background Art

[0002] The forecasting method of inventory order quantity is widely used in supply chain management. There are two main methods for determining and implementing it in IT systems: fixed quantity ordering method and periodic ordering method. The specific methods are as follows:

[0003] The fixed quantity ordering method is to set an order point and order quantity in advance. When the inventory drops to the order point, an order is issued for replenishment. The key to this method is to determine the order point and order quantity. The order point (s) is the point at which ordering begins when the inventory drops to a certain preset level, and the order quantity (Q) is the quantity of each order, usually the economic order quantity (EOQ). The main advantages of this method are simple operation and effective control of inventory costs, but the disadvantages are lack of flexibility and the need to constantly check the inventory.

[0004] The periodic ordering method is a method of replenishing inventory at a predetermined ordering interval. The order quantity may vary each time, and the order quantity = maximum inventory - existing inventory + customer delayed purchase quantity. This method is suitable for commodities with a large number of varieties and low average capital occupation. The advantage of the periodic ordering method is that it is highly planned and conducive to the overall arrangement of warehousing, but the disadvantage is that the safety inventory cannot be set too small, the demand deviation is large, and the economy is poor. Summary of the invention

[0005] The purpose of the present invention is to provide a method for predicting inventory order quantity based on the clothing life cycle, aiming to solve the technical problems in the prior art such as lack of flexibility, need to constantly check inventory, safety inventory cannot be set too small, large demand deviation and poor economy.

[0006] To achieve the above purpose, the embodiment of the present invention provides a method for predicting inventory order quantity based on clothing life cycle, comprising the following steps:

[0007] Step A: Obtain all product sales information for each year in history, and generate weekly sales data for each product based on the natural week of sales of each product;

[0008] Step B: Align all the starting sales weeks of the data obtained in step A as the first week, and perform classification calculation and analysis to generate multiple weekly sales curves of different categories, referred to as classified life cycle curves;

[0009] Step C: Summarize the inventory, sales, and production information of a certain type of goods currently on sale, generate corresponding charts, compare the data obtained in step B with the goods currently on sale, and place the corresponding curve that best fits the classification life cycle curve on the currently generated chart;

[0010] Step D: Proportionally convert the current sales product curve obtained in step C with the classification life cycle curve, and then generate the predicted sales volume of the current sales product in the subsequent weeks based on the current inventory and production information;

[0011] Step E: Based on the predicted sales volume obtained in step D and the current inventory, regional warehouse inventory, weekly turnover, two-week turnover, planned weekly inventory quantity, cumulative sales ratio, sales-to-sales ratio, single-store inventory depth, single-store average sales-to-sales, single-store average sales-to-sales, number of inventory stores, number of sales stores, and number of levels, determine whether it is necessary to reduce or increase the order quantity, and make a decision until the predicted data is met;

[0012] Step F: After the forecast is completed, the forecast data is written into the archive for archiving; after the forecast is completed, the business department prepares materials and places orders for finished products based on the production cycle, weekly sales ratio, cumulative sales ratio, and single store inventory depth.

[0013] As an optional solution of the present invention, the weekly sales data in step A is summed up according to the sales quantity of the corresponding commodities in the natural week to obtain the sales quantity of each week.

[0014] As an optional solution of the present invention, the steps for generating weekly sales data of the corresponding goods in step A are as follows: the goods personnel create a task, input the annual sales information to be analyzed, configure the weekly information, classification category, and classification calculation accuracy.

[0015] As an optional solution of the present invention, according to the set parameters of step A, the parameters are transmitted to the server, and the server performs decomposition calculations on the task.

[0016] As an optional solution of the present invention, the data obtained according to the calculation in step A is presented to the merchandise personnel for verification and confirmation.

[0017] As an optional solution of the present invention, the calculation and analysis process in step B is as follows: randomly select one of the products as the centroid, use the Euclidean distance method to make a judgment, repeat the steps, and for each subsequent classification, take the product farthest from the centroid of the previous classification as the new centroid; the Euclidean distance method is the product sales volume.

[0018] As an optional solution of the present invention, the steps of generating the classification life cycle curve in step B are as follows:

[0019] Step 1: Align the confirmed sales data to the first week, obtain the number of classification categories set in the parameters, randomly obtain a piece of product sales data from the sales data as the centroid, and calculate the fit of other products to the current centroid; the Euclidean distance judgment method is used to calculate the fit;

[0020] Step 2: Take the data obtained in step 1 and obtain the product sales data farthest from the centroid as the new centroid, and calculate the fit of other products to the current centroid. Finally, classify all product sales data and classify the products with different centroid fits within the input parameter accuracy to obtain a new classification.

[0021] Step 3: Repeat the process of step 2 until all product sales data are classified into centroid classifications with a fit within the accuracy of the input parameters;

[0022] Step 4: Filter the categories obtained in step 3, sort them from high to low according to the degree of fit, and input the parameter classification data according to the product personnel. For each category, take the top 4 items according to the sales volume, and set the labels as S, A, B, C according to the sales volume, and archive them in the database.

[0023] As an optional solution of the present invention, in step C, the steps of generating a corresponding chart by summarizing the inventory, sales, and production information of a certain type of goods currently being sold are as follows:

[0024] Step 1: The merchandise personnel select a certain merchandise being sold, import the corresponding sales, inventory, and production information into the system, and generate the sales data for the corresponding natural week, which is checked and confirmed; the sales data is queried in the database for the merchandise range selected by the merchandise personnel on the interface through the program provided by the DBA, and synchronized to the system through DBLINK;

[0025] Step 2: The system archives the confirmed data and performs fitting analysis with the multiple sales life cycle curves obtained in step B to obtain a historical sales life cycle curve with the highest fitting degree;

[0026] Step 3: Place the historical sales life cycle curve obtained in step 2 on the current sales product analysis interface.

[0027] As an optional solution of the present invention, the ratio conversion method in step D is as follows: a ratio is obtained by dividing the sales volume in the corresponding week of the life cycle curve by the weekly sales volume of the current product, and the ratios of multiple weeks are summarized and weighted averaged, and the final value obtained is the corresponding conversion ratio.

[0028] As an optional solution of the present invention, in step D, the steps of generating the predicted sales volume of the current selling commodity in the subsequent unseen weeks are as follows:

[0029] Step 1: Perform proportional conversion on the historical sales life cycle curve of step C to obtain the ratio of the weekly sales proportion of the historical sales life cycle curve to the total sales. The proportional conversion method is as follows: the sales volume of the corresponding week of the life cycle curve / the weekly sales volume of the current sales product is obtained as the ratio xi, which is subsequently referred to the weighted average formula;

[0030] Step 2: Convert the obtained ratio with the sales weeks of the current product to obtain the predicted sales volume for the weeks that have not occurred.

[0031] The above one or more technical solutions in the method for predicting inventory order quantity based on clothing life cycle provided by the embodiment of the present invention have at least one of the following technical effects:

[0032] The method for predicting inventory order quantity based on the clothing life cycle provided in this application mines the sales patterns of products of different categories from historical data. Combined with the data patterns, it can improve the accuracy of reorder quantity in the clothing industry, and improve efficiency through system algorithms, etc., ultimately improving the accuracy of the business and reducing inventory backlogs and sales losses. BRIEF DESCRIPTION OF THE DRAWINGS

[0033] In order to more clearly illustrate the technical solutions in the embodiments of the present invention, the drawings required for use in the embodiments or the description of the prior art will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying creative labor.

[0034] Figure 1 A flowchart of obtaining commodity sales information and generating corresponding weekly sales data in a method for predicting inventory order quantity based on clothing life cycle provided in an embodiment of the present invention.

[0035] Figure 2 A flowchart summarizing the inventory, sales, and production information of a certain type of merchandise currently on sale is provided for generating a method for predicting inventory order quantity based on the clothing life cycle provided by an embodiment of the present invention.

[0036] Figure 3 A flowchart of a method for predicting inventory order quantity based on clothing life cycle provided in an embodiment of the present invention, in which the obtained prediction data is written into an archive for archiving. DETAILED DESCRIPTION

[0037] Embodiments of the present invention are described in detail below, examples of which are shown in the accompanying drawings, wherein the same or similar reference numerals throughout represent the same or similar elements or elements having the same or similar functions. The embodiments described below with reference to the accompanying drawings are exemplary and are intended to be used to explain the embodiments of the present invention, and should not be construed as limiting the present invention.

[0038] In the description of the embodiments of the present invention, it should be understood that the terms "length", "width", "up", "down", "front", "back", "left", "right", "vertical", "horizontal", "top", "bottom", "inside" and "outside" etc., indicating orientations or positional relationships, are based on the orientations or positional relationships shown in the accompanying drawings, and are only for the convenience of describing the embodiments of the present invention and simplifying the description, and do not indicate or imply that the referred device or element must have a specific orientation, be constructed and operated in a specific orientation, and therefore should not be understood as a limitation on the present invention.

[0039] In addition, the terms "first" and "second" are used for descriptive purposes only and should not be understood as indicating or implying relative importance or implicitly indicating the number of the indicated technical features. Thus, a feature defined as "first" or "second" may explicitly or implicitly include one or more of the features. In the description of the embodiments of the present invention, the meaning of "plurality" is two or more, unless otherwise clearly and specifically defined.

[0040] In the embodiments of the present invention, unless otherwise clearly specified and limited, the terms "installed", "connected", "connected", "fixed" and the like should be understood in a broad sense, for example, it can be a fixed connection, a detachable connection, or an integral connection; it can be a mechanical connection or an electrical connection; it can be a direct connection or an indirect connection through an intermediate medium, it can be the internal connection of two elements or the interaction relationship between two elements. For ordinary technicians in this field, the specific meanings of the above terms in the embodiments of the present invention can be understood according to specific circumstances.

[0041] In one embodiment of the present invention, Figures 1 to 3 As shown, a method for predicting inventory order quantity based on clothing life cycle is provided, including the following steps:

[0042] Step A: Obtain all the commodity sales information of each year in history, and generate the weekly sales data of the corresponding commodity according to the natural week of sales of each commodity; the weekly sales data in step A is summed up according to the number of sales of the corresponding commodity in the natural week to obtain the sales volume of each week; the steps of generating the weekly sales data of the corresponding commodity in step A are as follows (the specific process is as shown in the attached Figure 1 As shown): The merchandise personnel creates a task, inputs the annual sales information to be analyzed, configures weekly information, classification categories, and classification calculation accuracy; transmits the parameters to the server according to the set parameters of step A, and the server decomposes and calculates the task; and presents the data obtained according to the calculation of step A to the merchandise personnel for verification and confirmation.

[0043] Step B: Align all the starting sales weeks of the data obtained in step A as the first week, and perform classification calculation and analysis to generate multiple weekly sales curves of different categories, referred to as classified life cycle curves; the calculation and analysis process in step B is as follows: randomly select one of the products as the centroid, use the Euclidean distance method to make a judgment, repeat the steps, and for each subsequent classification, take the product farthest from the last classification centroid as the new centroid; the Euclidean distance method is the product sales volume; the steps for generating the classified life cycle curve in step B are as follows:

[0044] Step 1: Align the confirmed sales data to the first week, obtain the number of classification categories set in the parameters, randomly obtain a product sales data from the sales data as the centroid, and calculate the fit of other products to the current centroid. The fit is the sum of the squares of (multiple corresponding weekly sales of the centroid - the corresponding weekly sales of the current product) and the root; the Euclidean distance judgment method is used to calculate the fit; the fit calculation formula is as follows: In the formula, d represents the difference in fit. The larger the value, the lower the fit (similarity). p and q represent the sales of two products in the same week.

[0045] Step 2: Take the data obtained in step 1 and obtain the product sales data farthest from the centroid as the new centroid, and calculate the fit of other products to the current centroid. Finally, classify all product sales data and classify the products with different centroid fits within the input parameter accuracy to obtain a new classification.

[0046] Step 3: Repeat the process of step 2 until all product sales data are classified into centroid classifications with a fit within the accuracy of the input parameters;

[0047] Step 4: Filter the categories obtained in step 3, sort them from high to low according to the degree of fit, and input the parameter classification data according to the product personnel. For each category, take the top 4 items according to the sales volume, and set the labels as S, A, B, C according to the sales volume, and archive them in the database.

[0048] Step C: Summarize the inventory, sales, and production information of a certain type of goods currently on sale, generate a corresponding chart, compare the data obtained in step B with the goods currently on sale, and place the corresponding curve that best fits the classification life cycle curve on the currently generated chart; In step C, the steps of summarizing the inventory, sales, and production information of a certain type of goods currently on sale and generating a corresponding chart are as follows (see the attached figure for details). Figure 2 shown):

[0049] Step 1: The merchandise personnel select a certain merchandise being sold, import the corresponding sales, inventory, and production information into the system, and generate the sales data for the corresponding natural week, which is checked and confirmed; the sales data is queried in the database for the merchandise range selected by the merchandise personnel on the interface through the program provided by the DBA, and synchronized to the system through DBLINK;

[0050] Step 2: The system archives the confirmed data and performs fitting analysis with the multiple sales life cycle curves obtained in step B to obtain a historical sales life cycle curve with the highest fitting degree;

[0051] Step 3: Place the historical sales life cycle curve obtained in step 2 on the current sales product analysis interface.

[0052] Step D: perform a proportional conversion based on the current sales commodity curve obtained in step C and the classification life cycle curve, and then generate the predicted sales volume of the current sales commodity in the subsequent weeks that have not occurred based on the current inventory and production information; the proportional conversion method in step D is as follows: obtain a ratio by the sales volume of the corresponding week of the life cycle curve / the weekly sales volume of the current sales commodity, and calculate the weighted average of the ratios of multiple weeks, and the final value obtained is the corresponding conversion ratio;

[0053] In step D, the steps for generating the predicted sales volume of the current product in the subsequent unsold weeks are as follows:

[0054] Step 1: Perform proportional conversion on the historical sales life cycle curve in step C to obtain the ratio of the weekly sales proportion of the historical sales life cycle curve to the total sales. The proportional conversion method is as follows: the sales volume of the corresponding week of the life cycle curve / the weekly sales volume of the current sales product is obtained as the ratio xi, and then refer to the weighted average formula; the weighted average formula is as follows: Where xi is the ith value, wi is the weight of the ith value, and n is the total number of values.

[0055] Step 2: Convert the obtained ratio with the sales weeks of the current product to obtain the predicted sales volume for the weeks that have not occurred.

[0056] Step E: Based on the predicted sales volume obtained in step D and the current inventory, regional warehouse inventory, weekly turnover, two-week turnover, planned weekly inventory quantity, cumulative sales ratio, sales-to-sales ratio, single-store inventory depth, single-store average sales-to-sales, single-store average sales-to-sales, number of inventory stores, number of sales stores, and number of levels, determine whether it is necessary to reduce or increase the order quantity, and make a decision until the predicted data is met;

[0057] In step E, it is determined whether the order quantity needs to be reduced / increased, and a decision is made until the forecast data is met. The steps are as follows:

[0058] Step 1: The program (product life cycle) obtains the inventory quantity of the current product for the corresponding sales week and presents it in a chart;

[0059] Step 2: The program obtains the inventory quantity of the regional warehouse corresponding to the sales week of the current product and presents it in a chart;

[0060] Step 3: The program obtains the sales quantity of the current product corresponding to the sales week and presents it in a chart;

[0061] Step 4: The program obtains the weekly turnover of the current product, the formula is the inventory quantity corresponding to the sales week / the sales quantity corresponding to the sales week, and presents it in a chart;

[0062] Step 5: The program obtains the two-week turnover of the current product, the formula is (the inventory quantity corresponding to the sales week / (the sales quantity corresponding to the sales week + the sales quantity of the previous week corresponding to the sales week))X2, and presents it in the chart;

[0063] Step 6: The merchandise personnel enter the inventory quantity in the specified week. The program calculates (refer to the proportion weighted average method in step 1) the predicted inventory quantity for the week that did not occur based on the entered quantity and the ratio of the historical sales life cycle curve for the subsequent week that did not occur.

[0064] Step 7: The program obtains the number of stores that have sold the current product;

[0065] Step 8: The program obtains the number of stores that have shipped the current product;

[0066] Step 9: The program obtains the number of stores with inventory for the current product in the week;

[0067] Step 10: The program obtains the number of stores that sell the current product in the corresponding week;

[0068] Step 11: The program obtains the number of stores selling goods in the corresponding week;

[0069] Step 12: The program obtains the total number of stores that plan to ship the current product;

[0070] Step 13: The program obtains the weekly sales quantity corresponding to the current product;

[0071] Step 14: The program obtains the total inventory quantity of the weekly area corresponding to the current product;

[0072] Step 15: The program obtains the cumulative sales ratio of the current product, the formula is the number of stores that have sold the current product / the number of stores that have shipped the current product;

[0073] Step 16: The program obtains the sales ratio (week) of the current product. The formula is the number of stores selling the current product in the corresponding week / the number of stores with inventory in the corresponding week;

[0074] Step 17: The program obtains the single-store inventory depth of the current product. The formula is the total weekly regional inventory quantity of the current product / the total number of stores planned to ship the current product.

[0075] Step 18: The program obtains the average sales volume (shipping) of the current product in a single store. The formula is the weekly sales volume of the current product / the number of stores with inventory of the current product in the corresponding week.

[0076] Step 19: The program obtains the average sales per store of the current product. The formula is the weekly sales quantity of the current product / the number of stores that sell the current product in the corresponding week.

[0077] Step 20: The program obtains the total sales quantity of the SABC4 curves of the historical fitting curve of the current commodity;

[0078] Step 21: The program presents the data obtained in the above steps into the corresponding chart and provides it to the product personnel for review;

[0079] Step 22: Based on the information provided, the merchandise personnel increase the order quantity or reduce the supply quantity of the current merchandise, so that the current merchandise sales curve and the historical sales curve of the corresponding level are optimally fitted.

[0080] Step F: After the forecast is completed, the forecast data is written into the archive for archiving; after the forecast is completed, the business department prepares materials and places orders for finished products based on the production cycle, weekly sales ratio, cumulative sales ratio, and single store inventory depth;

[0081] The specific steps of writing the obtained prediction data into the archive for archiving in step F are as follows (see Appendix for the specific process). Figure 3 shown):

[0082] Step 1: The product staff initiates the archiving operation;

[0083] Step 2: The program receives the save instruction, and jumps to step 6 if an exception occurs;

[0084] Step 3: The program determines whether the instruction is legal, if not, jumps to step 6;

[0085] Step 4: The program determines whether the data is correct. If not, it jumps to step 6.

[0086] Step 5: The program writes the data into the archive database;

[0087] Step 6: The program returns the processing results to the product personnel.

[0088] The method for predicting inventory order quantity based on the clothing life cycle provided in this application mines the sales patterns of products of different categories from historical data. Combined with the data patterns, it can improve the accuracy of reorder quantity in the clothing industry, and improve efficiency through system algorithms, etc., ultimately improving the accuracy of the business and reducing inventory backlogs and sales losses.

[0089] The above description is only a preferred embodiment of the present invention and is not intended to limit the present invention. Any modifications, equivalent substitutions and improvements made within the spirit and principles of the present invention should be included in the protection scope of the present invention.

Claims

1. A method for predicting inventory order quantity based on clothing life cycle, characterized in that: The following steps are involved: Step A: Obtain all product sales information for each historical year, and generate weekly sales data for each product based on the natural week of sales of each product; Step B: Align all the starting sales weeks of the data obtained in step A as the first week, and perform classification calculation and analysis to generate multiple weekly sales curves of different categories, referred to as classified life cycle curves; Step C: Summarize the inventory, sales, and production information of a certain type of goods currently on sale, generate corresponding charts, compare the data obtained in step B with the goods currently on sale, and place the corresponding curve that best fits the classification life cycle curve on the currently generated chart; Step D: Proportionally convert the current sales product curve obtained in step C with the classification life cycle curve, and then generate the predicted sales volume of the current sales product in the subsequent weeks based on the current inventory and production information; Step E: Based on the predicted sales volume obtained in step D and the current inventory, regional warehouse inventory, weekly turnover, two-week turnover, planned weekly inventory quantity, cumulative sales ratio, sales-to-sales ratio, single-store inventory depth, single-store average sales-to-sales, single-store average sales-to-sales, number of inventory stores, number of sales stores, and number of levels, determine whether it is necessary to reduce or increase the order quantity, and make a decision until the predicted data is met; Step F: After the forecast is completed, the forecast data is written into the archive for archiving; after the forecast is completed, the business department prepares materials and places orders for finished products based on the production cycle, weekly sales ratio, cumulative sales ratio, and single store inventory depth.

2. The method for predicting inventory order quantity based on clothing life cycle according to claim 1 is characterized in that: The weekly sales data in step A is obtained by summing the sales quantity of the corresponding commodities in the natural week to obtain the sales quantity of each week.

3. The method for predicting inventory order quantity based on clothing life cycle according to claim 1 is characterized in that: The steps for generating the weekly sales data of the corresponding product in step A are as follows: the product personnel create a task, input the annual sales information to be analyzed, configure the weekly information, classification category, and classification calculation accuracy.

4. The method for predicting inventory order quantity based on clothing life cycle according to claim 3 is characterized in that: According to the set parameters of step A, the parameters are transmitted to the server, and the server performs decomposition calculations on the task.

5. The method for predicting inventory order quantity based on clothing life cycle according to claim 4 is characterized in that: The data obtained according to the operation in step A is presented to the merchandise personnel for verification and confirmation.

6. The method for predicting inventory order quantity based on clothing life cycle according to claim 1 is characterized in that: The calculation and analysis process in step B is as follows: randomly select one of the products as the centroid, use the Euclidean distance method to make a judgment, repeat the steps, and for each subsequent classification, select the product farthest from the centroid of the previous classification as the new centroid; the Euclidean distance method is the product sales volume.

7. The method for predicting inventory order quantity based on clothing life cycle according to claim 1 is characterized in that: The steps of generating the classification life cycle curve in step B are as follows: Step 1: Align the confirmed sales data to the first week, obtain the number of classification categories set in the parameters, randomly obtain a piece of product sales data from the sales data as the centroid, and calculate the fit of other products to the current centroid; the Euclidean distance judgment method is used to calculate the fit; Step 2: Take the data obtained in step 1 and obtain the product sales data farthest from the centroid as the new centroid, and calculate the fit of other products to the current centroid. Finally, classify all product sales data and classify the products with different centroid fits within the input parameter accuracy to obtain a new classification. Step 3: Repeat the process of step 2 until all product sales data are classified into centroid classifications with a fit within the accuracy of the input parameters; Step 4: Filter the categories obtained in step 3, sort them from high to low according to the degree of fit, and input the parameter classification data according to the product personnel. For each category, take the top 4 items according to the sales volume, and set the labels as S, A, B, C according to the sales volume, and archive them in the database.

8. The method for predicting inventory order quantity based on clothing life cycle according to claim 1 is characterized in that: In step C, the steps of generating a corresponding chart by summarizing the inventory, sales, and production information of a certain type of goods currently being sold are as follows: Step 1: The merchandise personnel select a certain merchandise being sold, import the corresponding sales, inventory, and production information into the system, and generate the sales data for the corresponding natural week, which is checked and confirmed; the sales data is queried in the database for the merchandise range selected by the merchandise personnel on the interface through the program provided by the DBA, and synchronized to the system through DBLINK; Step 2: The system archives the confirmed data and performs fitting analysis with the multiple sales life cycle curves obtained in step B to obtain a historical sales life cycle curve with the highest fitting degree; Step 3: Place the historical sales life cycle curve obtained in step 2 on the current sales product analysis interface.

9. The method for predicting inventory order quantity based on clothing life cycle according to claim 1, characterized in that: The ratio conversion method in step D is as follows: obtain a ratio by dividing the sales volume of the corresponding week of the life cycle curve by the weekly sales volume of the current product, and calculate the weighted average of the ratios of multiple weeks. The final value obtained is the corresponding conversion ratio.

10. The method for predicting inventory order quantity based on clothing life cycle according to claim 1, characterized in that: In step D, the steps for generating the predicted sales volume of the current product in the subsequent unsold weeks are as follows: Step 1: Perform proportional conversion on the historical sales life cycle curve of step C to obtain the ratio of the weekly sales proportion of the historical sales life cycle curve to the total sales. The proportional conversion method is as follows: the sales volume of the corresponding week of the life cycle curve / the weekly sales volume of the current sales product is obtained as the ratio xi, which is subsequently referred to the weighted average formula; Step 2: Convert the obtained ratio with the sales weeks of the current product to obtain the predicted sales volume for the weeks that have not occurred.

Images