Product supply and sales strategy determination method and system based on future refund condition

Abstract

The invention discloses a product supply and sales strategy determination method and system based on a future refund condition, and relates to the technical field of electronic commerce. According to the invention, when the accumulative refund amount of the product order of each month is calculated, the refund condition of the product order of the month in the whole refund period is considered, the calculation accuracy of the accumulative refund amount is improved, and the accurate refund rate of the quarter of the month can be calculated according to the accumulative refund amount. The refund conditions of the same quarter in different years are relatively similar, so that the refund condition of a certain quarter in the first year has a certain reference value for the refund condition of a certain month in the same quarter in the next year, and the method can be used for assisting in determining supply and sales strategies of products.

Description

Technical Field

[0001] The present invention relates to the technical field of e-commerce, and in particular to a method and system for determining product supply and sales strategies based on future refund situations. Background Art

[0002] E-commerce conducts various business activities through the Internet, enabling activities such as online shopping for consumers, online transactions between merchants, online electronic payments, and various other business transactions.

[0003] At present, e-commerce merchants usually adopt loose return conditions and give a longer return cycle. For example, for a product order in January, consumers can start the refund process in March. E-commerce merchants are not clear about the future refund status of product orders. It is difficult to accurately estimate the sales profit of the month based only on the sales and refund status of the month, which in turn affects the supply and sales decisions of products.

[0004] Therefore, the existing technology still needs to be improved and developed. Summary of the invention

[0005] The technical problem to be solved by the present invention is that, in view of the above-mentioned defects of the prior art, a method and system for determining product supply and sales strategies based on future refund situations are provided, aiming to solve the problem in the prior art that e-commerce merchants are not clear about the future refund situation of product orders, and it is difficult to accurately estimate the sales profit of the current month only by relying on the sales and refund situation of the current month, which in turn affects the supply and sales decisions of products.

[0006] The technical solution adopted by the present invention to solve the problem is as follows: In a first aspect, an embodiment of the present invention provides a method for determining a product supply and sales strategy based on future refund conditions, the method comprising: Obtain the actual monthly refund amount of orders in the target month of the first year within the returnable period, and calculate the cumulative refund amount of the target month of the first year based on the actual monthly refund amount of orders in the target month of the first year; The quarter in which the target month of the first year is located is taken as the target quarter, the total sales of orders in the target quarter are obtained, the total cumulative refund amount is determined according to the cumulative refund amount of each month in the target quarter, and the refund rate of the target quarter is calculated according to the total cumulative refund amount and the total sales; Obtaining the sales of orders for the target month of the next year, and calculating the predicted refund amount for the target month of the next year according to the refund rate of the target quarter and the sales of orders for the target month of the next year through a target prediction algorithm; The product supply and sales strategy is determined based on the sales volume and predicted refund amount of the target month of the following year.

[0007] In one implementation, obtaining actual monthly refund amounts for orders in the target month of the first year within the returnable period includes: For each month in the returnable period, select a number of target refund orders from orders in the target month of the first year from all refund orders received in that month; Calculate the refund amount for the orders in the target month of the first year based on all the target refund orders; According to the refund amount of each month for the orders in the target month of the first year, the actual monthly refund amount of the orders in the target month of the first year within the returnable time period is obtained.

[0008] In one embodiment, the method for selecting the target prediction algorithm includes: Presetting a number of prediction algorithms for predicting refund amounts and the usage priorities corresponding to the prediction algorithms; According to the usage priority of each prediction algorithm, determining the applicability of each prediction algorithm in turn; The first prediction algorithm whose applicability meets the preset requirements is taken as the target prediction algorithm.

[0009] In one embodiment, the predicted refund amount for the target month of the next year is calculated based on the refund rate of the target quarter and the sales volume of the orders for the target month of the next year, including: The refund rate of the target quarter is multiplied by the sales volume of orders of the target month of the following year to obtain the predicted refund amount of the target month of the following year.

[0010] In one implementation, the refund rate of the target quarter is multiplied by the sales of orders of the target month of the next year to obtain the predicted refund amount of the target month of the next year, including: Determine whether the sales gap between the first-year target month and the next-year target month is greater than a preset threshold; If the sales gap is greater than the preset threshold, a new month is selected within the preset time range before and after the first-year target month as the first-year reference month; The quarter in which the reference month of the first year is located is re-set as the target quarter, and the refund rate of the target quarter is multiplied by the sales volume of the orders of the target month of the following year to obtain the predicted refund amount of the target month of the following year.

[0011] In one embodiment, reselecting a month within a preset time range before and after the first-year target month as the first-year reference month includes: The months within a preset time range before and after the first year's target month are selected as candidate months; Obtaining sales volume influencing factors corresponding to the target month of the next year and each of the candidate months, wherein the sales volume influencing factors include sales strategy, product price, and proximity to the target month of the first year; Calculate the similarity of the sales volume influencing factors between the target month of the next year and each of the candidate months; According to the similarities of the candidate months, the candidate month with the highest similarity is selected as the reference month of the first year.

[0012] In one embodiment, the supply and sales strategy of the product is determined based on the sales volume and the predicted refund amount of the target month of the next year as reference data, including: The difference between the sales volume of the target month of the following year and the predicted refund amount is used as reference data. If the difference is less than the preset index value, it indicates that the return volume will be large and the product inventory will increase in the future. Then, the product supply and sales strategy is determined to be reducing product purchases and / or implementing product promotion strategies; If the difference is greater than or equal to the preset indicator value, it means that the return volume will be small and the product inventory will decrease in the future, so the product supply and sales strategy is determined to increase product purchases and / or implement a product pre-sale strategy.

[0013] In one embodiment, the method further comprises: Generate financial report data based on the forecast refund amount for the target month of the following year; When the actual refund amount of the target month of the following year is obtained, the deviation value between the predicted refund amount and the actual refund amount of the target month of the following year is calculated; wherein the actual refund amount of the target month of the following year includes: the refunds of orders in the target month of the following year and several previous historical months in the target month of the following year; the target month of the following year and each of the historical months correspond to a returnable time period; Correcting the gross profit value of the target month of the next year according to the sum of the deviation values ​​of the target month of the next year and each of the historical months; The financial report data is revised based on the adjusted gross profit value.

[0014] In a second aspect, an embodiment of the present invention further provides a product supply and sales strategy determination system based on future refund conditions, the system comprising: An analysis module, used to obtain actual monthly refund amounts for orders in the target month of the first year within the returnable period, and calculate the cumulative refund amount for the target month of the first year based on the actual monthly refund amounts for orders in the target month of the first year; a calculation module, configured to take the quarter in which the target month of the first year is located as the target quarter, obtain the total sales of orders in the target quarter, determine the total cumulative refund amount according to the cumulative refund amounts of each month in the target quarter, and calculate the refund rate of the target quarter according to the total cumulative refund amount and the total sales; A prediction module, used to obtain the sales of orders in the target month of the next year, and calculate the predicted refund amount of the target month of the next year according to the refund rate of the target quarter and the sales of orders in the target month of the next year through a target prediction algorithm; The determination module is used to determine the supply and sales strategy of the product based on the sales volume and predicted refund amount of the target month of the next year as reference data.

[0015] In a third aspect, an embodiment of the present invention further provides a computer-readable storage medium having a plurality of instructions stored thereon, wherein the instructions are suitable for being loaded and executed by a processor to implement the steps of any of the above-described methods for determining product supply and sales strategies based on future refund situations.

[0016] Beneficial effects of the present invention: When calculating the cumulative refund amount of monthly product orders, the embodiments of the present invention take into account the refund situation of the product orders of the month within the full return cycle, thereby improving the calculation accuracy of the cumulative refund amount, and then the accurate refund rate of the quarter in which the month is located can be calculated based on the cumulative refund amount. The refund situation of the same quarter in different years is relatively similar, so the refund situation of a certain quarter in the first year has a certain reference value for the refund situation of a certain month in the same quarter in the next year, and can be used to assist in determining the supply and sales strategy of the product. BRIEF DESCRIPTION OF THE DRAWINGS

[0017] In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, 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 recorded in the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying creative work.

[0018] Figure 1 It is a flowchart of a method for determining product supply and sales strategy based on future refund situations provided by an embodiment of the present invention.

[0019] Figure 2 It is a schematic diagram of functional modules of a system for determining product supply and sales strategy based on future refund situations provided by an embodiment of the present invention.

[0020] Figure 3 It is a principle block diagram of a terminal provided by an embodiment of the present invention. DETAILED DESCRIPTION

[0021] The present invention discloses a method and system for determining product supply and sales strategy based on future refund situations. In order to make the purpose, technical solution and effect of the present invention clearer and more specific, the present invention is further described in detail with reference to the accompanying drawings and examples. It should be understood that the specific embodiments described herein are only used to explain the present invention and are not used to limit the present invention.

[0022] It will be understood by those skilled in the art that, unless expressly stated, the singular forms "one", "said", and "the" used herein may also include plural forms. It should be further understood that the term "comprising" used in the specification of the present invention refers to the presence of the features, integers, steps, operations, elements and / or components, but does not exclude the presence or addition of one or more other features, integers, steps, operations, elements, components and / or groups thereof. It should be understood that when we refer to an element as being "connected" or "coupled" to another element, it may be directly connected or coupled to the other element, or there may be intermediate elements. In addition, the "connection" or "coupling" used herein may include wireless connection or wireless coupling. The term "and / or" used herein includes all or any unit and all combinations of one or more associated listed items.

[0023] It will be understood by those skilled in the art that, unless otherwise defined, all terms (including technical and scientific terms) used herein have the same meaning as generally understood by those skilled in the art in the art to which the present invention belongs. It should also be understood that terms such as those defined in general dictionaries should be understood to have meanings consistent with the meanings in the context of the prior art, and will not be interpreted with idealized or overly formal meanings unless specifically defined as herein.

[0024] In view of the above-mentioned defects of the prior art, the present invention provides a method for determining product supply and sales strategy based on future refund situation, the method obtains the actual monthly refund amount of the orders of the target month of the first year within the returnable period, and calculates the cumulative refund amount of the target month of the first year according to the actual monthly refund amount of the orders of the target month of the first year; takes the quarter of the target month of the first year as the target quarter, obtains the total sales of the orders of the target quarter, determines the total cumulative refund amount according to the cumulative refund amount of each month in the target quarter, and calculates the refund rate of the target quarter according to the total cumulative refund amount and the total sales; obtains the sales of the orders of the target month of the next year, and calculates the predicted refund amount of the target month of the next year according to the refund rate of the target quarter and the sales of the orders of the target month of the next year through the target prediction algorithm; determines the supply and sales strategy of the product with the sales and predicted refund amount of the target month of the next year as reference data. When calculating the cumulative refund amount of the monthly product orders, the present invention takes into account the refund situation of the product orders of the month within the full return cycle, improves the calculation accuracy of the cumulative refund amount, and then can calculate the accurate refund rate of the quarter of the month according to the cumulative refund amount. The refund situations in the same quarters of different years are relatively similar. Therefore, the refund situation in a certain quarter of the first year has a certain reference value for the refund situation in a certain month in the same quarter of the next year, and can be used to assist in determining product supply and sales strategies.

[0025] like Figure 1 As shown, the method specifically comprises the following steps: Step S100, obtaining the actual monthly refund amount of orders in the first-year target month within the returnable period, and calculating the cumulative refund amount of the first-year target month based on the actual monthly refund amount of orders in the first-year target month.

[0026] Specifically, the target month in this embodiment can be any month in a year, the first year refers to the year before the year to be predicted, and the year to be predicted is defined as the following year. Since e-commerce merchants usually adopt loose return conditions and give a longer return cycle, the refund of orders generated in the target month of the first year may be in the current month, or in other months after the current month and within the return cycle. In other words, there may be a difference of months between the consumer's order time and the refund time. In order to accurately calculate the cumulative refund amount of orders generated by a specified product in the target month of the first year, this embodiment defines the returnable time period for orders generated in the target month of the first year according to the return cycle of the product, and uses the returnable time period as the time range for tracing, and tracks the refunds of orders received in each month month by month, so as to obtain the actual refund amount per month. The cumulative refund amount for the target month of the first year is calculated by accumulating the actual refund amount per month within the returnable time period.

[0027] For example, let's predict the refund amount of product A in January 2024. The first year is 2023, the second year is 2024, and the target month is January. The return period of product A is 6 months, so the return period of the target month in the first year is from January to June 2023. Calculate the refund amount for January 2023 received each month from January to June 2023, and add them up to get the cumulative refund amount for January 2023.

[0028] In one implementation, the actual monthly refund amount of orders in the target month of the first year within the returnable period is obtained, including: For each month in the returnable period, select a number of target refund orders from orders in the target month of the first year from all refund orders received in that month; Calculate the refund amount for the orders in the target month of the first year based on all the target refund orders; According to the refund amount of each month for the orders in the target month of the first year, the actual monthly refund amount of the orders in the target month of the first year within the returnable time period is obtained.

[0029] After determining the returnable time period corresponding to the first-year target month, you need to filter refund orders by month within the returnable time period. Specifically, for each month in the returnable time period, filter out those refund orders with order placement time in the first-year target month from all refund orders received in that month, and define them as target refund orders. Count the target refund orders filtered out each month, and obtain the actual monthly refund amount of orders in the first-year target month based on the statistical results.

[0030] Step S200: take the quarter in which the target month of the first year is located as the target quarter, obtain the total sales of orders in the target quarter, determine the total cumulative refund amount based on the cumulative refund amount of each month in the target quarter, and calculate the refund rate of the target quarter based on the total cumulative refund amount and the total sales.

[0031] Specifically, the sales of the first-year target month can be extracted from the e-commerce management system, and the quarter in which the first-year target month is located is defined as the target quarter. The total sales are obtained by accumulating the sales of orders in all months of the target quarter. According to the calculation method of the cumulative refund amount of the first-year target month, the cumulative refund amount of other months in the target quarter is calculated. The total cumulative refund amount is obtained by accumulating the cumulative refund amount of all months in the target quarter. Finally, the ratio of the total cumulative refund amount to the total sales is calculated to obtain the refund rate of the target quarter. Product returns have seasonality and customer behavior inertia. For example, the refund amount in the clothing industry may increase when the season changes, and consumers' purchasing habits and return tendencies may maintain a certain continuity. Taking down jackets as an example, the refund rate is higher in summer and lower in winter. Therefore, the refund situation of each month in the same quarter is similar, and the refund situation of the same quarter in different years also has a certain reference value to each other. In addition, the calculation result of the refund rate calculated on a quarterly basis is more reliable than that calculated on a monthly basis.

[0032] Step S300, obtaining the sales of orders for the target month of the next year, and calculating the predicted refund amount for the target month of the next year according to the refund rate of the target quarter and the sales of orders for the target month of the next year through a target prediction algorithm.

[0033] In summary, this embodiment uses data analysis and artificial intelligence technology to objectively and quickly predict the refund amount in the same month of the following year. Specifically, a prediction algorithm suitable for the current product characteristics is pre-selected and defined as a target prediction algorithm. The sales of orders in the same month of the following year are obtained from the e-commerce management system and defined as the sales of orders in the target month of the following year. The sales of the target month of the following year and the refund rate of the target quarter are used as input data of the target prediction algorithm, and the input data is analyzed and evaluated by the target prediction algorithm, and finally the predicted refund amount of the target month of the following year is output.

[0034] In one implementation, the method for selecting the target prediction algorithm includes: Presetting a number of prediction algorithms for predicting refund amounts and the usage priorities corresponding to the prediction algorithms; According to the usage priority of each prediction algorithm, determining the applicability of each prediction algorithm in turn; The first prediction algorithm whose applicability meets the preset requirements is taken as the target prediction algorithm.

[0035] Specifically, the present embodiment will reserve a variety of prediction algorithms that can be used to predict the refund amount in advance. Common prediction algorithms include linear regression, time series analysis, machine learning algorithms, etc. And combined with factors such as user preferences, algorithm complexity, and algorithm accuracy, the use priority of each prediction algorithm is comprehensively determined. In actual application, for the product that currently needs to predict the refund amount, the applicability of each prediction algorithm is evaluated in turn according to the usage priority. If the applicability of the currently evaluated prediction algorithm does not meet the preset requirements, the prediction algorithm is eliminated, and the next prediction algorithm with the highest usage priority is queried, and the applicability of the queried prediction algorithm is continued to be evaluated. If the applicability of the currently evaluated prediction algorithm meets the preset requirements, the prediction algorithm is used as the target prediction algorithm, and the predicted refund amount for the target month of the next year is subsequently calculated by the target prediction algorithm.

[0036] Furthermore, the adaptability evaluation method includes: obtaining the amount of historical data of the product, and determining the algorithm data volume requirements based on the amount of historical data. For example, some prediction algorithms rely only on a small amount of historical data for prediction, but some prediction algorithms require a large amount of historical data for prediction, and the two prediction algorithms have different corresponding algorithm data volume requirements. Obtain the historical refund amount change trend of the product, determine the correlation between the prediction accuracy and the number of calculation periods based on the historical refund amount change trend, and determine the algorithm prediction range requirements based on the correlation. For example, some prediction algorithms can perform long-term predictions, and some prediction algorithms can only perform short-term predictions, and the two prediction algorithms have different corresponding algorithm prediction ranges. For the prediction algorithm to be evaluated, based on the aforementioned determined algorithm data volume requirements and algorithm prediction range requirements, combined with the algorithm characteristics of the prediction algorithm itself, comprehensively evaluate the applicability of the prediction algorithm for predicting the future refund amount of the product.

[0037] In one implementation, calculating the predicted refund amount for the target month of the next year according to the refund rate of the target quarter and the sales of orders for the target month of the next year includes: The refund rate of the target quarter is multiplied by the sales volume of orders of the target month of the following year to obtain the predicted refund amount of the target month of the following year.

[0038] Specifically, the refund situation of each month in the same quarter is similar, and the refund situation of the same month in different years also has a certain reference value to each other. For example, when the product is a down jacket, the refund rate is higher in summer and lower in winter. In this embodiment, it is assumed that the refund situation of the quarter in which the same month is located in the first year and the next year is similar. The sales volume of the target month of the next year is known, and the refund rate of the quarter in which the target month of the first year is located is combined with the refund rate of the quarter in which the target month of the first year is located. The predicted refund amount of the target month of the next year is calculated by multiplication. In actual application, the refund amount can refer to the refund amount caused by objective factors such as product quality problems. When the product supply chain remains unchanged, the production environment of the products in the same season and month is similar, and the refund situation caused by product quality problems has a mutual reference value. For example, the defective rate of products such as agricultural products or fired porcelain products is easily affected by seasonal factors. There are differences in the quality of the same agricultural product in different seasons, such as different tastes and flavors. The quality of porcelain products is easily affected by the weather during firing. Porcelain products fired in humid weather are prone to soften and lose their shape, and porcelain products fired in windless and rainy weather will affect coloring.

[0039] In one implementation, the refund rate of the target quarter is multiplied by the sales of orders of the target month of the next year to obtain the predicted refund amount of the target month of the next year, including: Determine whether the sales gap between the first-year target month and the next-year target month is greater than a preset threshold; If the sales gap is greater than the preset threshold, a new month is selected within the preset time range before and after the first-year target month as the first-year reference month; The quarter in which the reference month of the first year is located is re-set as the target quarter, and the refund rate of the target quarter is multiplied by the sales volume of the orders of the target month of the following year to obtain the predicted refund amount of the target month of the following year.

[0040] Specifically, changes in product sales will also affect refunds. If the sales of a specified product in the first year's target month differs too much from the sales in the same month of the following year, the refund rate in the quarter of the first year's target month will have a lower reference value for predicting the refund amount in the same month of the following year. In order to more accurately calculate the predicted refund amount for the next year's target month, you can select a month around the first year's target month that is close to the target month and has similar sales to the next year's target month as the first year's reference month, such as the previous quarter or the next quarter of the first year's target month. According to the aforementioned method for calculating the refund rate for the target quarter, the quarter of the first year's reference month is used as the new target quarter, and the refund rate for the target quarter is recalculated. Finally, the sales of the orders in the next year's target month are combined with the recalculated refund rate, and the predicted refund amount for the next year's target month is calculated by multiplication.

[0041] In one implementation, a month is reselected within a preset time range before and after the first-year target month as the first-year reference month, including: The months within a preset time range before and after the first year's target month are selected as candidate months; Obtaining sales volume influencing factors corresponding to the target month of the next year and each of the candidate months, wherein the sales volume influencing factors include sales strategy, product price, and proximity to the target month of the first year; Calculate the similarity of the sales volume influencing factors between the target month of the next year and each of the candidate months; According to the similarities of the candidate months, the candidate month with the highest similarity is selected as the reference month of the first year.

[0042] In general, changes in product sales will also affect the refund of the product. In this embodiment, a new reference month is selected from the adjacent months of the first-year target month by comparing the sales impact factors. Specifically, multiple months adjacent to the first-year target month are used as candidate months according to the preset time range, and the first-year reference month is located among these candidate months. Taking a month as an example, the sales strategy (such as promotion strategy, price adjustment strategy) of the specified product in that month, the product price, and the proximity of the month to the first-year target month are obtained through the e-commerce management system (the closer the market conditions and seasonal factors of the month are, the higher the reference value). The sales impact factor of the month is obtained based on these data. The sales impact factor of the target month of the next year is compared with the sales impact factor of each candidate month one by one, and the similarity is calculated. The candidate months are sorted from high to low according to the similarity, and the candidate month ranked first can be used as the reference month of the first year.

[0043] Step S400: Determine the supply and sales strategy of the product based on the sales volume and predicted refund amount of the target month of the next year as reference data.

[0044] Specifically, by analyzing the sales volume and predicted refund amount in the target month of the following year, we can estimate the actual sales popularity of the product, understand the future inventory changes of the product, and then make correct decisions on the supply and sales plan of the product to avoid product surplus or shortage.

[0045] In one implementation, the supply and sales strategy of the product is determined based on the sales volume and the predicted refund amount of the target month of the next year as reference data, including: The difference between the sales volume of the target month of the following year and the predicted refund amount is used as reference data. If the difference is less than the preset index value, it indicates that the return volume will be large and the product inventory will increase in the future. Then, the product supply and sales strategy is determined to be reducing product purchases and / or implementing product promotion strategies; If the difference is greater than or equal to the preset indicator value, it means that the return volume will be small and the product inventory will decrease in the future, so the product supply and sales strategy is determined to increase product purchases and / or implement a product pre-sale strategy.

[0046] Specifically, the sales in the target month of the next year minus the predicted refund amount is used to obtain a difference. The size of the difference can be used as a reference for the actual profit of that month. The smaller the difference, the closer the sales are to the predicted refund amount, which means that there are more refunds and returns in that month, which will lead to an increase in product inventory. Therefore, the purchase of products can be reduced, and product promotion strategies can be implemented to clear inventory. The smaller the difference, the further the sales are from the predicted refund amount, which means that there are fewer refunds and returns in that month, which will lead to a decrease or even insufficient product inventory. Therefore, the purchase of products can be increased, and a product pre-sale strategy can be implemented to deal with insufficient product inventory. In order to objectively measure the size of the difference, this embodiment presets an indicator value, and the difference is compared with the preset indicator value to determine the size of the difference.

[0047] In one implementation, the method further includes: Generate financial report data based on the forecast refund amount for the target month of the following year; When the actual refund amount of the target month of the following year is obtained, the deviation value between the predicted refund amount and the actual refund amount of the target month of the following year is calculated; wherein the actual refund amount of the target month of the following year includes: the refunds of orders in the target month of the following year and several previous historical months in the target month of the following year; the target month of the following year and each of the historical months correspond to a returnable time period; Correcting the gross profit value of the target month of the next year according to the sum of the deviation values ​​of the target month of the next year and each of the historical months; The financial report data is revised based on the adjusted gross profit value.

[0048] Specifically, the actual refund amount of the target month of the next year is obtained through the e-commerce management system, and the predicted refund amount of the target month of the next year is subtracted from the actual refund amount to obtain the deviation value of the target month of the next year. Taking the return period of half a year as an example, and the target month of the next year is November 2004, the actual refund amount in November 2004 refers to the refund of orders from June to November 2004 in November 2004. Subtract the predicted refund amount of November 2024 from the actual refund amount to obtain the deviation value of November 2024, which can reflect the prediction error.

[0049] According to the method of calculating the deviation value of the target month of the next year, the deviation value of each historical month before the target month of the next year is calculated to obtain the deviation value of all months in the returnable period. These deviation values ​​are added together to obtain the total deviation value, and the gross profit value of the target month of the next year is corrected based on the total deviation value, so as to obtain a more realistic gross profit value.

[0050] Predicting refund amounts can assist sales decisions, estimate actual gross profit, and generate initial financial report data in advance. However, after the gross profit value is corrected, the financial report data for the relevant month needs to be revised based on the corrected gross profit value to obtain the correct financial report data.

[0051] In one implementation, the method further includes: A number of analysis dimensions and the priority of each analysis dimension are preset; wherein the analysis dimensions are in descending order of priority: sub-SKU dimension, main SKU dimension, three-level classification dimension, main SKU global dimension, three-level classification global dimension and global dimension; SKU stands for stock keeping unit, which is a unique number for each product; When it is necessary to estimate the future refund situation of a product, the analysis dimension with the highest priority is selected to execute the method for determining product supply and sales strategy based on the future refund situation; If the total sales of orders in the target quarter obtained under this analysis dimension is less than the preset value, the analysis dimension is considered invalid; After eliminating the analysis dimension, continue to execute the step of selecting the analysis dimension with the highest priority to execute the method for determining product supply and sales strategy based on future refund situation, until it is determined that the selected analysis dimension is valid, and execute the method for determining product supply and sales strategy based on future refund situation on the analysis dimension to obtain the future refund situation of the product.

[0052] Based on the above embodiments, the present invention also provides a product supply and sales strategy determination system based on future refund conditions, such as Figure 2 As shown, the system comprises: Analysis module 01, used to obtain actual monthly refund amounts of orders in the target month of the first year within the returnable period, and calculate the cumulative refund amount of the target month of the first year according to the actual monthly refund amounts of orders in the target month of the first year; Calculation module 02, used to take the quarter in which the target month of the first year is located as the target quarter, obtain the total sales of orders in the target quarter, determine the total cumulative refund amount according to the cumulative refund amount of each month in the target quarter, and calculate the refund rate of the target quarter according to the total cumulative refund amount and the total sales; Prediction module 03, used to obtain the sales of orders in the target month of the next year, and calculate the predicted refund amount of the target month of the next year according to the refund rate of the target quarter and the sales of orders in the target month of the next year through a target prediction algorithm; The determination module 04 is used to determine the supply and sales strategy of the product based on the sales volume and the predicted refund amount of the target month of the next year as reference data.

[0053] Based on the above embodiment, the present invention further provides a terminal, whose principle block diagram can be shown as follows: Figure 3 As shown. The terminal includes a processor, a memory, a network interface, and a display screen connected via a system bus. Among them, the processor of the terminal is used to provide computing and control capabilities. The memory of the terminal includes a non-volatile storage medium and an internal memory. The non-volatile storage medium stores an operating system and a computer program. The internal memory provides an environment for the operation of the operating system and the computer program in the non-volatile storage medium. The network interface of the terminal is used to communicate with an external terminal via a network connection. When the computer program is executed by the processor, a method for determining product supply and sales strategy based on future refund conditions is implemented. The display screen of the terminal can be a liquid crystal display screen or an electronic ink display screen.

[0054] Those skilled in the art will understand that Figure 3 The principle block diagram shown in the figure is only a block diagram of a partial structure related to the scheme of the present invention, and does not constitute a limitation on the terminal to which the scheme of the present invention is applied. The specific terminal may include more or fewer components than those shown in the figure, or combine certain components, or have a different arrangement of components.

[0055] In one implementation, the terminal has one or more programs stored in its memory and is configured to be executed by one or more processors. The one or more programs include instructions for performing a method for determining product supply and sales strategies based on future refund situations.

[0056] A person of ordinary skill in the art can understand that all or part of the processes in the above-mentioned embodiment method can be completed by instructing the relevant hardware through a computer program, and the computer program can be stored in a non-volatile computer-readable storage medium. When the computer program is executed, it can include the processes of the embodiments of the above-mentioned methods. Among them, any reference to memory, storage, database or other media used in the embodiments provided by the present invention can include non-volatile and / or volatile memory. Non-volatile memory may include read-only memory (ROM), programmable ROM (PROM), electrically programmable ROM (EPROM), electrically erasable programmable ROM (EEPROM) or flash memory. Volatile memory may include random access memory (RAM) or external cache memory. As an illustration and not limitation, RAM is available in many forms, such as static RAM (SRAM), dynamic RAM (DRAM), synchronous DRAM (SDRAM), double data rate SDRAM (DDRSDRAM), enhanced SDRAM (ESDRAM), synchronous link (Synchlink) DRAM (SLDRAM), memory bus (Rambus) direct RAM (RDRAM), direct memory bus dynamic RAM (DRDRAM), and memory bus dynamic RAM (RDRAM).

[0057] In summary, the present invention discloses a method and system for determining product supply and sales strategies based on future refund situations, which relates to the field of e-commerce technology. The method obtains the actual monthly refund amount of orders in the first-year target month within the returnable period, and calculates the cumulative refund amount of the first-year target month based on the actual monthly refund amount of orders in the first-year target month; takes the quarter in which the first-year target month is located as the target quarter, obtains the total sales of orders in the target quarter, determines the total cumulative refund amount based on the cumulative refund amount of each month in the target quarter, and calculates the refund rate of the target quarter based on the total cumulative refund amount and the total sales; obtains the sales of orders in the target month of the next year, and calculates the predicted refund amount of the target month of the next year based on the refund rate of the target quarter and the sales of orders in the target month of the next year through a target prediction algorithm; uses the sales and predicted refund amount of the target month of the next year as reference data to determine the supply and sales strategy of the product. When calculating the cumulative refund amount of monthly product orders, the present invention takes into account the refund situation of product orders in that month within the full return cycle, thereby improving the calculation accuracy of the cumulative refund amount, and then the accurate refund rate of the quarter in which the month is located can be calculated based on the cumulative refund amount. The refund situation of the same quarter in different years is relatively similar, so the refund situation of a certain quarter in the first year has a certain reference value for the refund situation of a certain month in the same quarter in the next year, and can be used to assist in determining the supply and sales strategy of the product.

[0058] It should be understood that the application of the present invention is not limited to the above examples. For ordinary technicians in this field, improvements or changes can be made based on the above description. All these improvements and changes should fall within the scope of protection of the claims attached to the present invention.

Claims

1. A method for determining product supply and sales strategy based on future refund conditions, characterized in that: The method comprises: Obtain the actual monthly refund amount of orders in the target month of the first year within the returnable period, and calculate the cumulative refund amount of the target month of the first year based on the actual monthly refund amount of orders in the target month of the first year; The quarter in which the target month of the first year is located is taken as the target quarter, the total sales of orders in the target quarter are obtained, the total cumulative refund amount is determined according to the cumulative refund amount of each month in the target quarter, and the refund rate of the target quarter is calculated according to the total cumulative refund amount and the total sales; Obtaining the sales of orders for the target month of the next year, and calculating the predicted refund amount for the target month of the next year according to the refund rate of the target quarter and the sales of orders for the target month of the next year through a target prediction algorithm; The product supply and sales strategy is determined based on the sales volume and predicted refund amount of the target month of the following year.

2. The method for determining product supply and sales strategy based on future refund situations according to claim 1, characterized in that: Get the actual monthly refund amount of orders in the target month of the first year within the returnable period, including: For each month in the returnable period, select a number of target refund orders from orders in the target month of the first year from all refund orders received in that month; Calculate the refund amount for the orders in the target month of the first year based on all the target refund orders; According to the refund amount of each month for the orders in the target month of the first year, the actual monthly refund amount of the orders in the target month of the first year within the returnable time period is obtained.

3. The method for determining product supply and sales strategy based on future refund situations according to claim 1, characterized in that: The method for selecting the target prediction algorithm includes: Presetting a number of prediction algorithms for predicting refund amounts and the usage priorities corresponding to the prediction algorithms; According to the usage priority of each prediction algorithm, determining the applicability of each prediction algorithm in turn; The first prediction algorithm whose applicability meets the preset requirements is taken as the target prediction algorithm.

4. The method for determining product supply and sales strategy based on future refund situations according to claim 1, characterized in that: According to the refund rate of the target quarter and the sales of orders in the target month of the following year, the predicted refund amount of the target month of the following year is calculated, including: The refund rate of the target quarter is multiplied by the sales volume of orders of the target month of the following year to obtain the predicted refund amount of the target month of the following year.

5. The method for determining product supply and sales strategy based on future refund conditions according to claim 4, characterized in that: The refund rate of the target quarter is multiplied by the sales of orders in the target month of the following year to obtain the predicted refund amount for the target month of the following year, including: Determine whether the sales gap between the first-year target month and the next-year target month is greater than a preset threshold; If the sales gap is greater than the preset threshold, a new month is selected within the preset time range before and after the first-year target month as the first-year reference month; The quarter in which the reference month of the first year is located is re-set as the target quarter, and the refund rate of the target quarter is multiplied by the sales volume of the orders of the target month of the following year to obtain the predicted refund amount of the target month of the following year.

6. The method for determining product supply and sales strategy based on future refund conditions according to claim 5, characterized in that: Reselect a month within the preset time range before and after the first-year target month as the first-year reference month, including: The months within a preset time range before and after the first year's target month are selected as candidate months; Obtaining sales volume influencing factors corresponding to the target month of the next year and each of the candidate months, wherein the sales volume influencing factors include sales strategy, product price, and proximity to the target month of the first year; Calculate the similarity of the sales volume influencing factors between the target month of the next year and each of the candidate months; According to the similarities of the candidate months, the candidate month with the highest similarity is selected as the reference month of the first year.

7. The method for determining product supply and sales strategy based on future refund situations according to claim 1, characterized in that: Based on the sales and forecast refund amount of the target month of the following year, determine the product supply and sales strategy, including: The difference between the sales volume of the target month of the following year and the predicted refund amount is used as reference data. If the difference is less than the preset index value, it indicates that the return volume will be large and the product inventory will increase in the future. Then, the product supply and sales strategy is determined to be reducing product purchases and / or implementing product promotion strategies; If the difference is greater than or equal to the preset indicator value, it means that the return volume will be small and the product inventory will decrease in the future, so the product supply and sales strategy is determined to increase product purchases and / or implement a product pre-sale strategy.

8. The method for determining product supply and sales strategy based on future refund situations according to claim 1, characterized in that: The method further comprises: Generate financial report data based on the forecast refund amount for the target month of the following year; When the actual refund amount of the target month of the following year is obtained, the deviation value between the predicted refund amount and the actual refund amount of the target month of the following year is calculated; wherein the actual refund amount of the target month of the following year includes: the refunds of orders in the target month of the following year and several previous historical months in the target month of the following year; the target month of the following year and each of the historical months correspond to a returnable time period; Correcting the gross profit value of the target month of the next year according to the sum of the deviation values ​​of the target month of the next year and each of the historical months; The financial report data is revised based on the adjusted gross profit value.

9. A product supply and sales strategy determination system based on future refund conditions, characterized in that: The system comprises: An analysis module, used to obtain actual monthly refund amounts for orders in the target month of the first year within the returnable period, and calculate the cumulative refund amount for the target month of the first year based on the actual monthly refund amounts for orders in the target month of the first year; a calculation module, configured to take the quarter in which the target month of the first year is located as the target quarter, obtain the total sales of orders in the target quarter, determine the total cumulative refund amount according to the cumulative refund amounts of each month in the target quarter, and calculate the refund rate of the target quarter according to the total cumulative refund amount and the total sales; A prediction module, used to obtain the sales of orders in the target month of the next year, and calculate the predicted refund amount of the target month of the next year according to the refund rate of the target quarter and the sales of orders in the target month of the next year through a target prediction algorithm; The determination module is used to determine the supply and sales strategy of the product based on the sales volume and predicted refund amount of the target month of the next year as reference data.

10. A computer-readable storage medium having a plurality of instructions stored thereon, characterized in that: The instructions are suitable for being loaded and executed by a processor to implement the steps of the method for determining product supply and sales strategy based on future refund situations as described in any one of claims 1-8.

Images