Store stockout compensation method and device

Abstract

The invention relates to the technical field of data processing, and discloses a store stockout compensation method and device, and the method comprises the steps: obtaining the daily sales information of a store in M historical days under the condition of stockout of the store, and the sales information is an influence factor on the sales quantity of the store; if the historical M days of the store include at least one day without stockout, determining K days with the highest similarity from the historical M days according to the similarity between the sales information of each day in the historical M days of the store and the sales information of the day when the store is stockout; according to the sales quantity and the sales volume trend index of each hour in at least one hour of each day in the K days, the compensation quantity of the store in the stockout period is obtained, and the sales volume trend index is obtained according to the sales quantity of the store in the non-stockout period and the sales quantity of the store in the same period in the historical M days. Therefore, dirty data generated by stockout can be restored, clean and effective data are provided for subsequent prediction, and the stability of a supply chain is improved.

Description

Technical Field

[0001] This application relates to the technical field of data processing, and in particular, to a method and device for compensating for out-of-stock in stores. Background Art

[0002] In the e-commerce scenario, products often have low actual sales due to out-of-stock, generating a large amount of dirty data. The actual sales volume when there is out-of-stock is the dirty data. Especially in the fresh food e-commerce industry, due to the characteristics of short shelf life, high inventory capital occupation, and high loss, each store cannot rely on high-level safety inventory to improve service levels. Therefore, out-of-stock situations are more likely to occur. In this case, if the actual sales volume of the store is directly used to predict future demand, it will lead to low downstream demand prediction and replenishment transfer volume, further resulting in out-of-stock, affecting the supply-demand balance of the entire supply chain, and entering a vicious cycle.

[0003] Therefore, how to correct the dirty data caused by out-of-stock in stores is a technical problem that urgently needs to be solved currently. Summary of the Invention

[0004] Embodiments of the present invention provide a method and device for compensating for out-of-stock in stores. In the case of out-of-stock in a store, the compensation amount for the out-of-stock period of the store is obtained based on historical data, providing clean and effective data for subsequent prediction, thereby improving the stability of the supply chain.

[0005] In a first aspect, an embodiment of the present invention provides a method for compensating for out-of-stock in stores, the method including: in the case of out-of-stock in a store, obtaining the daily sales information of the store in the past M days, where the sales information is a factor affecting the sales quantity of the store; if at least one day without out-of-stock exists in the past M days of the store, determining the K days with the highest similarity from the past M days according to the similarity between the daily sales information in the past M days of the store and the sales information of the day when the store is out-of-stock; obtaining the compensation amount for the out-of-stock period of the store according to the sales quantity per hour and the sales volume trend index in at least one hour of each day in the K days, where the sales volume trend index is obtained based on the sales quantity during the period when the store is not out-of-stock and the sales quantity in the same period in the past M days of the store, where M and N are both integers greater than or equal to 1, and M is greater than or equal to N.

[0006] Using the above method, in the case of out-of-stock in the store, according to the similarity between the daily sales information in the historical M days of the store and the sales information on the day when the store is out of stock, determine the K days with the highest similarity from the historical M days, and according to the sales quantity and sales trend index per hour in at least one hour of each day in the K days, obtain the compensation quantity for the out-of-stock period of the store. The sales trend index can reflect the relationship between the store's sales volume and time, repair the dirty data generated by the store due to out-of-stock in the time dimension, provide clean and effective data for subsequent prediction, and then improve the stability of the supply chain and the satisfaction of customers.

[0007] In an alternative embodiment, the sales trend index satisfies the following formula: where γ i is the sales trend index of the i-th day in the historical K days of the store, Q j is the sales quantity of the j-th hour of the store, and the j-th hour is the j-th hour in the non-out-of-stock period of the store, is the sales quantity of the j-th hour on the i-th day in the historical K days of the store.

[0008] In an alternative embodiment, the method further includes: if all the historical M days of the store are out of stock, obtain the sales quantities of N non-out-of-stock stores in the same city as the store; according to the historical average sales volume of the store, the average sales volume of the N non-out-of-stock stores when they are not out of stock in history, and the sales quantities of the N non-out-of-stock stores, obtain the compensation quantity for the out-of-stock period of the store, where N is an integer greater than or equal to 1.

[0009] Using the above method, when all the historical M days of the store are out of stock, that is, the actual sales volume in the historical M days cannot reflect the real needs of customers, repair the dirty data of out-of-stock from the spatial dimension, effectively solve the problem of consecutive days of out-of-stock, and avoid the vicious cycle caused by out-of-stock.

[0010] In an alternative embodiment, determining the compensation quantity for the out-of-stock period of the store according to the historical average sales volume of the store when it is not out of stock, the historical average sales volume of the N non-out-of-stock stores, and the sales quantities of the N non-out-of-stock stores includes: obtaining the compensation quantities of the N stores according to the historical average sales volume of the store, the average sales volume of the N non-out-of-stock stores when they are not out of stock in history, and the sales quantities of the N non-out-of-stock stores; determining the compensation quantity for the out-of-stock period of the store according to the median of the compensation quantities of the N stores.

[0011] In an alternative embodiment, the method further includes: determining a target compensation quantity according to the compensation quantity and at least one of the following: actual sales volume; sales volume in the out-of-stock state under the same historical period and the same activity; sales volume in the non-out-of-stock state under the same historical period and the same activity.

[0012] In an alternative embodiment, the sales information includes at least one of the daily activity discount information, holiday information, weekday information, and time information in the past M days of the store; the activity discount information is used to indicate the activity discount intensity of the store; the holiday information is used to indicate whether each day in the M days is a holiday; the weekday information is used to indicate whether each day in the M days is a weekday; the time information is used to indicate the time distance between each day in the M days and the day when the store is out of stock.

[0013] In a second aspect, an embodiment of the present invention provides a store out-of-stock compensation device, which includes: an acquisition module, configured to obtain the sales information of each day in the past M days of the store when the store is out of stock, and the sales information is a factor affecting the store's sales quantity; a processing module, configured to, if at least one day in the past M days of the store is not out of stock, determine the K days with the highest similarity from the past M days according to the similarity between the sales information of each day in the past M days of the store and the sales information of the day when the store is out of stock; a determination module, configured to obtain the compensation quantity for the out-of-stock period of the store according to the sales quantity and sales volume trend index of each hour in at least one hour of each day in the K days, and the sales volume trend index is obtained according to the sales quantity during the period when the store is not out of stock and the sales quantity in the same period in the past M days of the store.

[0014] In an alternative embodiment, the sales volume trend index satisfies the following formula: where γ i is the sales volume trend index of the i-th day in the past K days of the store, Q j is the sales quantity of the j-th hour of the store, and the j-th hour is the j-th hour during the period when the store is not out of stock, is the sales quantity of the j-th hour of the i-th day in the past K days of the store.

[0015] In an alternative embodiment, the acquisition module is configured to, if all the past M days of the store are out of stock, obtain the sales quantities of N non-out-of-stock stores in the same city as the store; the determination module is further configured to obtain the compensation quantity for the out-of-stock period of the store according to the historical average sales volume of the store, the average sales volume of the N non-out-of-stock stores when they are not out of stock in history, and the sales quantities of the N non-out-of-stock stores, where N is an integer greater than or equal to 1.

[0016] In an alternative embodiment, the determining module is specifically configured to obtain the compensation amounts for the N stores according to the historical average sales volume of the stores, the average sales volume when the N non-out-of-stock stores were not out of stock, and the sales quantities of the N non-out-of-stock stores; and determine the compensation amount for the out-of-stock period of the stores according to the median of the compensation amounts for the N stores.

[0017] In an alternative embodiment, the determining module is further configured to determine a target compensation amount according to the compensation amount and at least one of the following: actual sales volume; sales volume in the out-of-stock state during the same historical period and the same activity; sales volume in the non-out-of-stock state during the same historical period and the same activity.

[0018] In an alternative embodiment, the sales information includes at least one of the daily activity discount information, holiday information, weekday information, and time information in the historical M days of the store; the activity discount information is used to indicate the activity discount intensity of the store; the holiday information is used to indicate whether each day in the M days is a holiday; the weekday information is used to indicate whether each day in the M days is a weekday; the time information is used to indicate the time distance between each day in the M days and the day when the store is out of stock.

[0019] In a third aspect, the present application provides a store out-of-stock compensation device, including:

[0020] A memory for storing program instructions;

[0021] A processor for calling the program instructions stored in the memory and executing the steps included in the method according to any one of the first aspects according to the obtained program instructions.

[0022] In a fourth aspect, the present application provides a computer-readable storage medium, where the computer-readable storage medium stores a computer program, and the computer program includes program instructions, and when the program instructions are executed by a computer, the computer is caused to execute the method according to any one of the first aspects.

[0023] In a fifth aspect, the present application provides a computer program product, where the computer program product includes: computer program code, and when the computer program code runs on a computer, the computer is caused to execute the method according to any one of the first aspects. BRIEF DESCRIPTION OF THE DRAWINGS

[0024] In order to more clearly illustrate the technical solutions in the embodiments of the present invention, the following briefly introduces the drawings required for the description of the embodiments. Obviously, the following drawings are only some embodiments of the present invention, and those of ordinary skill in the art can also obtain other drawings based on these drawings without creative efforts.

[0025] Figure 1 A schematic diagram of the actual sales volume and out-of-stock rate of commodities provided by the embodiments of the present invention;

[0026] Figure 2 A flowchart corresponding to the store out-of-stock compensation method provided by the embodiments of the present invention;

[0027] Figure 3 A schematic diagram of the relationship between the similarity and the difference in activity discount strength provided by the embodiments of the present invention;

[0028] Figure 4 A schematic diagram of the out-of-stock compensation effect of commodities provided by the embodiments of the present invention;

[0029] Figure 5 A schematic diagram of the store out-of-stock compensation device provided by the embodiments of the present invention;

[0030] Figure 6 A schematic diagram of the store out-of-stock compensation equipment provided by the embodiments of the present invention. Detailed implementation manners

[0031] In order to make the objectives, technical solutions and advantages of the present invention clearer, the present invention will be further described in detail below with reference to the accompanying drawings. Obviously, the described embodiments are only a part of the embodiments of the present invention, rather than all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those of ordinary skill in the art without creative efforts shall fall within the scope of protection of the present invention. In the embodiments of the present invention, "a plurality of" means two or more. Terms such as "first" and "second" are only used for the purpose of distinguishing descriptions, and cannot be understood as indicating or implying relative importance, nor can they be understood as indicating or implying order.

[0032] As described in the above background, since the out-of-stock of commodities often leads to a low actual sales volume, if the sales volume after prediction is based on the actual sales volume of out-of-stock, and inventory replenishment is carried out according to the predicted sales volume, it will further lead to out-of-stock. As Figure 1 shown, the horizontal axis is the date, the left vertical axis is the out-of-stock rate, and the out-of-stock rate is the out-of-stock hours of the current date / business hours. The right vertical axis is the actual sales volume. It can be seen that the actual sales volume of the commodity when there is no out-of-stock is about 100. When out-of-stock occurs due to reasons such as insufficient production capacity and overdue transfer, the actual sales volume decreases significantly. Figure 1 On September 19th, the out-of-stock rate reached 80%, and the actual sales volume at this time was 30. On September 20th, the out-of-stock rate reached 100%. If the actual sales volume after prediction is based on the data at this time, the predicted actual sales volume will be lower than the true demand, and further lead to insufficient inventory reserves, and the out-of-stock situation will be further aggravated.

[0033] For the dirty data caused by out-of-stock (i.e., the actual sales volume corresponding to out-of-stock), there are currently two processing methods, including Method 1 and Method 2. Among them, Method 1: directly delete the dirty data caused by out-of-stock. However, direct deletion will lead to the loss of historical data. For example, during the initial launch of a new product, the amount of available data is already small. If directly deleted, it may cause the historical data to be unavailable for reference. Another example is when there are consecutive days of out-of-stock in the historical data. If the out-of-stock data is directly deleted, the prediction model can only refer to older data. At this time, for products with trends and seasons, the prediction model will not be able to capture the recent time series characteristics, resulting in a decrease in the accuracy of predicted sales volume and further leading to subsequent out-of-stock. Method 2: filling based on the moving average prediction model. However, this method does not consider the periodicity of the time series and the impact of activities on sales volume.

[0034] Based on this, the embodiments of the present application provide a method for compensating for store out-of-stock. Based on the historical sales data and sales volume trend indicators of the store, the compensation amount during the out-of-stock period of the store is determined, the dirty data caused by out-of-stock is repaired, clean and effective data is provided for subsequent prediction, and the stability of the supply chain is improved.

[0035] The method provided by the embodiments of the present application will be described in detail below with reference to specific embodiments.

[0036] Figure 2 It is a flowchart corresponding to the method for compensating for store out-of-stock provided by the embodiments of the present invention. This method can be executed by a store out-of-stock compensation device (abbreviated as the compensation device). As Figure 2 shown, this method includes the following steps:

[0037] Step 201, when there is out-of-stock in the store, the compensation device obtains the sales information of each day in the historical M days of the store.

[0038] Here, when there is out-of-stock in the store, the compensation device will obtain the sales information of each day in the M days before the date with out-of-stock according to the date with out-of-stock. Among them, the sales information is a factor affecting the store's sales volume, and the sales information includes at least one of the activity discount information, holiday information, working day information, and time information of each day in the historical M days of the store. The activity discount information is used to indicate the activity discount strength of the store. The holiday information is used to indicate whether each day in the M days is a holiday; the working day information is used to indicate whether each day in the M days is a working day; the time information is used to indicate the time distance between each day in the M days and the day when there is out-of-stock in the store.

[0039] Step 202, if there is at least one day without out-of-stock in the historical M days of the store, the compensation device determines the K days with the highest similarity from the historical M days according to the similarity between the sales information of each day in the historical M days of the store and the sales information of the day when there is out-of-stock in the store.

[0040] Exemplarily, after the compensation device obtains the sales information of the historical M days, it will determine whether there is a shortage of goods on each day in the historical M days of the store. For each day in the historical M days, if there is a shortage of goods for at least one hour during the business hours of that day, it is considered that there is a shortage of goods on that day. If there is at least one day in the historical M days of the store that does not have a shortage of goods (that is, not all of the historical M days have a shortage of goods), the compensation device selects the K days with the highest similarity from the historical M days according to the similarity between the sales information of each day in the historical M days of the store and the sales information of the day when there is a shortage of goods in the store. Among them, calculating the similarity between the sales information of each day in the historical M days of the store and the sales information of the day when there is a shortage of goods in the store can be evaluated by using a piecewise linear function. The piecewise linear function can effectively combine business knowledge and has strong interpretability and scalability. Taking the activity discount information in the sales information as an example, holiday information, weekday information, and time information can be referred to. Figure 3 shows the relationship between the similarity and the difference in activity discount strength, as Figure 3 shown. The horizontal axis is the difference in activity discount strength between two different values, and the vertical axis is the similarity. The piecewise linear function can conveniently specify the inflection point, and the inflection point usually represents known business knowledge. For example, when the difference in activity discount strength is 0.1, the similarity is defined as 0.3, and when the difference in activity discount strength exceeds 0.5, it is considered that the two activities have no similarity at all, and the similarity is defined as 0. The above is only an example, and the inflection point can be set according to the actual situation and is not limited here. The sales information includes at least one of the activity discount information, holiday information, weekday information, and time information of each day in the historical M days of the store. If the sales information has only one item, the corresponding similarity value is determined according to the piecewise linear function corresponding to the sales information. If the sales information includes multiple items, the similarities corresponding to each item in the sales information can be multiplied to obtain the final similarity. For example, if the sales information is the activity discount strength, the similarity between the date when there is a shortage of goods in the store and each day in the historical M days of the store is determined according to the difference between the activity discount strength on the date when there is a shortage of goods in the store and the activity discount strength of each day in the historical M days of the store. The M similarities are sorted from largest to smallest, and the K days with the highest similarity are selected.

[0041] Optionally, the historical M days can be divided into multiple scenarios according to the sales information, which can be scenarios such as activity - holiday, non - activity - holiday, activity - weekday, non - activity - weekday, etc. When determining the K days in the historical M days, only the samples in the same scenario are considered. For example, assume that the date when there is a shortage of goods in the store belongs to non - weekday - non - activity. At this time, K days without a shortage of goods in the M days are selected, that is, the dates in the historical M days that also belong to non - weekday - non - activity.

[0042] Step 203: The compensation device obtains the compensation quantity for the out-of-stock period of the store according to the sales quantity per hour and the sales volume trend index in at least one hour of each day in K days.

[0043] Exemplarily, the compensation device obtains the compensation quantity for the out-of-stock period of the store according to the sales quantity per hour and the sales volume trend index in at least one hour of each day in K days. Among them, the sales volume trend index is obtained according to the sales quantity during the non-out-of-stock period of the store and the sales quantity in the same period of the historical M days of the store. The calculation formula of the sales trend index is shown in formula (1):

[0044]

[0045] where γ i is the sales volume trend index of the i-th day in the historical K days of the store, Q j is the sales quantity of the j-th hour of the store. The j-th hour is the j-th hour during the non-out-of-stock period of the store, is the sales quantity of the j-th hour of the i-th day in the historical K days of the store.

[0046] The calculation formula of the compensation quantity for the out-of-stock period of the store is shown in formula (2):

[0047]

[0048] where H a is the out-of-stock compensation quantity of the a-th hour on the day when the store has out-of-stock, γ i is the sales volume trend index of the i-th day in the historical K days of the store, is the sales quantity of the a-th hour of the i-th day in the historical K days of the store.

[0049] For example, Table 1 is an example of K days determined from the historical M days of the same store. As shown in Table 1, the four days of 6.1, 6.2, 6.3, and 6.4 in Table 1 are the K days determined in step 202. The store was out of stock on June 5. At this time, it is necessary to determine the compensation quantity for the out-of-stock period on June 5.

[0050] Table 1: Example of K days determined from the historical M days of the same store

[0051]

[0052]

[0053] It can be seen that the store was out of stock during the two time periods of hour_11 and hour_12 on June 5. For the compensation quantity during the out-of-stock time period of hour_11, the dates without out-of-stock at the same time period in the corresponding K days are June 1, June 3, and June 4. At this time, the trend coefficient of June 5 to June 1 is (1 + 1 + 2 + 4) / (1 + 1 + 2 + 3) = 1.143; the trend coefficient of June 5 to June 3 is (1 + 1 + 2 + 4) / (1 + 1 + 3 + 2) = 1.143; the trend coefficient of June 5 to June 4 is (1 + 1 + 2 + 4) / (0 + 1 + 3 + 3) = 1.143; the compensation quantity during the out-of-stock time period of hour_11 is avg(3 * 1.143, 4 * 1.143, 2 * 1.143) = (3 * 1.143, 4 * 1.143, 2 * 1.143) / 3 = 3.429. For the compensation quantity during the out-of-stock time period of hour_12, the dates without out-of-stock at the same time period in the corresponding K days are June 1 and June 3. At this time, the trend coefficient of June 5 to June 1 is (1 + 1 + 2 + 4) / (1 + 1 + 2 + 3) = 1.143; the trend coefficient of June 5 to June 3 is (1 + 1 + 2 + 4) / (1 + 1 + 3 + 2) = 1.143; the compensation quantity during the out-of-stock time period of hour_12 is avg(1 * 1.143, 2 * 1.143) = (1 * 1.143, 2 * 1.143) / 3 = 1.7145.

[0054] In an alternative embodiment, since the store has spatial characteristics, such as in the same city, similar stores often have similar sales volumes. Therefore, when the store is out of stock for all M days in history, the compensation device obtains the sales quantities of N non-out-of-stock stores in the same city as the store, and obtains the compensation quantity during the out-of-stock time period of the store according to the historical average sales volume of the store, the average sales volume of the N non-out-of-stock stores when they are not out of stock in history, and the sales quantities of the N non-out-of-stock stores.

[0055] In an alternative embodiment, the compensation quantities of the N stores are obtained according to the historical average sales volume of the store, the average sales volume of the N non-out-of-stock stores when they are not out of stock in history, and the sales quantities of the N non-out-of-stock stores; the compensation quantity during the out-of-stock time period of the store is determined according to the median of the compensation quantities of the N stores. Among them, the historical average sales volume of the store is obtained by taking the average of the actual sales volumes every day under the state of being out of stock for all M days in history. The store is out of stock when at least one hour in the corresponding date is out of stock, and the sum of the sales volumes during the non-out-of-stock time periods is the actual sales volume. For example, assuming that store A is out of stock and stores B, C, and D in the city are not out of stock, then the compensation quantity of store A = Median(historical average sales volume of store A / historical non-out-of-stock average sales volume of store B * daily sales quantity of store B, historical average sales volume of store A / historical non-out-of-stock average sales volume of store C * daily sales quantity of store C, historical average sales volume of store A / historical non-out-of-stock average sales volume of store D * daily sales quantity of store D).

[0056] In an alternative embodiment, a target compensation quantity is determined based on the compensation quantity and at least one of the following: actual sales volume; sales volume in a stock-out state during the same historical period and the same activity; sales volume in a non-stock-out state during the same historical period and the same activity. For example, if the compensation quantity obtained in the above steps is less than the minimum of the actual sales volume and the sales volume in a stock-out state during the same historical period and the same activity, the target compensation quantity is the minimum of the actual sales volume and the sales volume in a stock-out state during the same historical period and the same activity; if the compensation quantity is greater than twice the sales volume in a non-stock-out state during the same historical period and the same activity, the target compensation quantity is twice the sales volume in a non-stock-out state during the same historical period and the same activity; if the compensation quantity is greater than or equal to the minimum of the actual sales volume and the sales volume in a stock-out state during the same historical period and the same activity and the compensation quantity is less than or equal to twice the sales volume in a non-stock-out state during the same historical period and the same activity, the target compensation quantity is the compensation quantity.

[0057] Using the above method, in the case of stock-out in the store, according to the similarity between the daily sales information in the historical M days of the store and the sales information on the day when the store is out of stock, the K days with the highest similarity are determined from the historical M days, and based on the sales quantity per hour and the sales trend index in at least one hour of each day in the K days, the compensation quantity for the stock-out period of the store is obtained. The sales trend index can reflect the relationship between the store's sales volume and time, repair the dirty data generated by the store due to stock-out in the time dimension, provide clean and effective data for subsequent prediction, and thus improve the stability of the supply chain and the satisfaction of customers.

[0058] To evaluate the effect of the above store stock-out compensation method, products that are greatly affected by stock-out are selected to observe the effect of stock-out compensation. Figure 4 For the stock-out compensation effect diagram of this product, as Figure 4 shown, the horizontal axis is the date, the left vertical axis is the stock-out rate, and the right vertical axis is the actual sales volume. Figure 4 The white bars in [[ ]] represent the stock-out rate on the corresponding date, the solid broken line represents the trend of the actual sales volume, and the dotted broken line represents the trend of the sales volume after compensation. It can be seen that the phenomenon of low sales volume caused by stock-out is alleviated and reaches the average sales volume in the normal state. Especially after September 19, the stock-out rate reached more than 80%, and the sales volume after compensation remained at a normal level.

[0059] To further evaluate the impact between the out-of-stock rate and the actual sales volume, the Pearson correlation coefficient of the sales volume and the out-of-stock rate before and after out-of-stock compensation is used to evaluate the overall effect. Table 2 shows an example of the correlation comparison of the sales volume and the out-of-stock rate before and after out-of-stock compensation. As shown in Table 2, since the increase in the out-of-stock rate will lead to the decrease of the actual sales volume, there is a strong negative correlation between the actual sales volume and the out-of-stock rate. It can be seen that the negative correlation between the sales volume and the out-of-stock rate after adopting the out-of-stock compensation method of the present application has been significantly reduced, and the phenomenon of the decrease in sales volume due to out-of-stock has been significantly improved.

[0060] Table 2: Example of the correlation comparison of the sales volume and the out-of-stock rate before and after out-of-stock compensation

[0061] Sales volume range Actual sales volume correlation Correlation of compensated sales volume (0,1] -0.53 -0.34 (1,2] -0.51 -0.24 (2,3] -0.49 -0.18 (3,4] -0.49 -0.15 (4,+] -0.49 -0.09

[0062] For the above-mentioned embodiments, it is not only applicable to the repair of out-of-stock data in stores, but also can be applied to the repair of abnormal data caused by external factors such as clearance sales and epidemics. Based on the method of the embodiments of the present invention, clean and effective data can be provided for subsequent prediction, thereby improving the stability of the supply chain and enhancing customer satisfaction.

[0063] Based on the same concept, the embodiments of the present invention further provide a store out-of-stock compensation device 5000, Figure 5 which is a schematic diagram of the store out-of-stock compensation device provided by the embodiments of the present invention. As Figure 5 shown, the device includes:

[0064] An acquisition module 501, configured to obtain the daily sales information of the store in the past M days when the store is out of stock, and the sales information is a factor affecting the store sales quantity.

[0065] A processing module 502, configured to, if at least one day without out-of-stock exists in the past M days of the store, determine the K days with the highest similarity from the past M days according to the similarity between the daily sales information in the past M days of the store and the sales information on the day when the store is out of stock.

[0066] A determination module 503, configured to obtain the compensation quantity for the out-of-stock period of the store according to the sales quantity per hour and the sales volume trend index in at least one hour of each day in the K days, where the sales volume trend index is obtained according to the sales quantity during the non-out-of-stock period of the store and the sales quantity in the same period in the past M days of the store.

[0067] In an optional implementation manner, the sales volume trend index satisfies the following formula: where γ i is the sales volume trend index of the i-th day in the past K days of the store, and Q jis the sales quantity of the store in the j-th hour, where the j-th hour is the j-th hour during the non-stockout period of the store. is the sales quantity of the store in the j-th hour of the i-th day in the past K days of the store.

[0068] In an alternative embodiment, the obtaining module 501 is configured to, if the store has been out of stock for all of the past M days, obtain the sales quantities of N non-stockout stores in the same city as the store. The determining module 503 is further configured to obtain the compensation quantity for the out-of-stock period of the store according to the historical average sales volume of the store, the average sales volume of the N non-stockout stores when they were not out of stock in the past, and the sales quantities of the N non-stockout stores, where N is an integer greater than or equal to 1.

[0069] In an alternative embodiment, the determining module 503 is specifically configured to obtain the compensation quantities for the N stores according to the historical average sales volume of the store, the average sales volume of the N non-stockout stores when they were not out of stock in the past, and the sales quantities of the N non-stockout stores; and determine the compensation quantity for the out-of-stock period of the store according to the median of the compensation quantities for the N stores.

[0070] In an alternative embodiment, the determining module 503 is further configured to determine the target compensation quantity according to the compensation quantity and at least one of the following: actual sales volume; sales volume in the out-of-stock state during the same historical period and under the same activity; sales volume in the non-stockout state during the same historical period and under the same activity.

[0071] In an alternative embodiment, the sales information includes at least one of the daily activity discount information, holiday information, weekday information, and time information in the past M days of the store; the activity discount information is used to indicate the activity discount strength of the store; the holiday information is used to indicate whether each day in the M days is a holiday; the weekday information is used to indicate whether each day in the M days is a weekday; the time information is used to indicate the time distance between each day in the M days and the day when the store was out of stock.

[0072] Based on the same concept, an embodiment of the present application further provides a structural schematic diagram of a store out-of-stock compensation device, as Figure 6 shown. The device 6000 includes at least one processor 601 and a memory 602 connected to at least one processor 601. In the embodiment of the present application, the specific connection medium between the processor 601 and the memory 602 is not limited. Figure 6Take the connection between the processor 601 and the memory 602 through a bus as an example. The bus can be divided into an address bus, a data bus, a control bus, etc. In the embodiment of the present application, the memory 602 stores instructions executable by at least one processor 601. By executing the instructions stored in the memory 602, the at least one processor 601 can implement the steps of the above-mentioned store out-of-stock compensation method.

[0073] Among them, the processor 601 is the control center of the computer device, which can connect various parts of the computer device through various interfaces and lines. By running or executing the instructions stored in the memory 602 and calling the data stored in the memory 602, resource settings can be performed. Optionally, the processor 601 may include one or more processing units. The processor 601 may integrate an application processor and a modem processor. Among them, the application processor mainly processes the operating system, user interface, application programs, etc., and the modem processor mainly processes wireless communication. It can be understood that the above-mentioned modem processor may not be integrated into the processor 601. In some embodiments, the processor 601 and the memory 602 can be implemented on the same chip. In some embodiments, they can also be separately implemented on independent chips.

[0074] The processor 601 can be a general-purpose processor, such as a central processing unit (CPU), a digital signal processor, an application specific integrated circuit (ASIC), a field programmable gate array, or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, which can implement or execute the various methods, steps and logic block diagrams disclosed in the embodiments of the present application. The general-purpose processor can be a microprocessor or any conventional processor, etc. The steps of the method disclosed in combination with the embodiments of the present application can be directly embodied as being completed by a hardware processor, or completed by a combination of hardware and software modules in the processor.

[0075] The memory 602 serves as a non-volatile computer-readable storage medium and can be used to store non-volatile software programs, non-volatile computer-executable programs, and modules. The memory 602 may include at least one type of storage medium. For example, it may include flash memory, hard disks, multimedia cards, card-type memories, random access memory (RAM), static random access memory (SRAM), programmable read-only memory (PROM), read-only memory (ROM), electrically erasable programmable read-only memory (EEPROM), magnetic memories, magnetic disks, optical disks, and so on. The memory 602 is any other medium that can be used to carry or store the desired program code in the form of instructions or data structures and can be accessed by a computer, but is not limited thereto. The memory 602 in the embodiments of the present application may also be a circuit or any other device capable of implementing a storage function, for storing program instructions and / or data.

[0076] Based on the same inventive concept, an embodiment of the present application provides a computer-readable storage medium. The computer program product includes: computer program code, which, when running on a computer, causes the computer to execute any one of the store out-of-stock compensation methods described above. Since the principle of solving problems by the above computer-readable storage medium is similar to that of the store out-of-stock compensation method, the implementation of the above computer-readable storage medium can refer to the implementation of the method, and the repeated parts will not be described again.

[0077] Based on the same inventive concept, an embodiment of the present application further provides a computer program product. The computer program product includes: computer program code, which, when running on a computer, causes the computer to execute any one of the store out-of-stock compensation methods described above. Since the principle of solving problems by the above computer program product is similar to that of the store out-of-stock compensation method, the implementation of the above computer program product can refer to the implementation of the method, and the repeated parts will not be described again.

[0078] Those skilled in the art should understand that the embodiments of the present application may be provided as a method, a system, or a computer program product. Therefore, the present application may take the form of a complete hardware embodiment, a complete software embodiment, or an embodiment combining software and hardware aspects. Moreover, the present application may take the form of a computer program product implemented on one or more computer-usable storage media (including but not limited to disk memories, CD-ROMs, optical memories, etc.) containing computer-usable program code.

[0079] This application is described with reference to the flowcharts and / or block diagrams of methods, apparatuses (systems), and computer program products according to this application. It should be understood that each flow and / or block in the flowchart and / or block diagram, as well as the combination of flows and / or blocks in the flowchart and / or block diagram, can be implemented by computer program instructions. These computer program instructions can be provided to the processor of a general-purpose computer, a special-purpose computer, an embedded processor, or other programmable data processing devices to generate a machine, such that the instructions executed by the processor of the computer or other programmable data processing devices produce means for implementing the functions specified in one Figure 1 flow or multiple flows and / or blocks Figure 1 block or multiple blocks.

[0080] These computer program instructions can also be stored in a computer-readable memory that can direct a computer or other programmable data processing device to work in a specific manner, such that the instructions stored in the computer-readable memory produce a manufactured article including instruction means that implement the functions specified in one Figure 1 flow or multiple flows and / or blocks Figure 1 block or multiple blocks.

[0081] These computer program instructions can also be loaded onto a computer or other programmable data processing device, such that a series of operation steps are executed on the computer or other programmable device to generate a computer-implemented process, and thus the instructions executed on the computer or other programmable device provide steps for implementing the functions specified in one Figure 1 flow or multiple flows and / or blocks Figure 1 block or multiple blocks.

[0082] Obviously, those skilled in the art can make various changes and modifications to this application without departing from the spirit and scope of this application. Thus, if these modifications and variations of this application fall within the scope of the claims of this application and their equivalent technologies, this application is also intended to include these changes and modifications.

Claims

1. A method for compensating for out-of-stock items in a store, characterized in that: The method comprises: When a store is out of stock, obtain the daily sales information of the store in the past M days, where the sales information is the factor affecting the sales volume of the store; If the store's M days of history include at least one day without out-of-stock, then based on the similarity between the sales information of each day in the store's M days of history and the sales information of the day when the store is out of stock, determine the K days with the highest similarity from the M days of history; The compensation amount for the out-of-stock period of the store is obtained based on the sales quantity and sales trend index in at least one hour of each day of the K days. The sales trend index is obtained based on the sales quantity during the period when the store is not out of stock and the sales quantity during the same period in the store's history of M days, wherein M and N are both integers greater than or equal to 1, and M is greater than or equal to N.

2. The method according to claim 1, characterized in that The sales trend indicator satisfies the following formula: Among them, γ i is the sales trend index of the store on the i-th day in the K-day history, Q j is the sales quantity of the store in the jth hour, where the jth hour is the jth hour in the period when the store is not out of stock, is the sales quantity of the store in the jth hour on the i-th day in the K-day history.

3. The method according to claim 1, characterized in that The method further comprises: If the store has been out of stock for all M days in history, obtain the sales volume of N stores in the same city where the store is not out of stock; The compensation amount for the out-of-stock period of the store is obtained based on the historical average sales volume of the store, the historical average sales volume of the N stores when they are not out of stock, and the sales quantity of the N stores when they are not out of stock, where N is an integer greater than or equal to 1.

4. The method according to claim 3, characterized in that The compensation amount for the store's out-of-stock period is determined according to the store's historical average sales volume when the store is not out of stock, the N historical average sales volume of the N stores that are not out of stock, and the sales quantity of the N stores that are not out of stock, including: Obtain compensation amounts for the N stores based on the store's historical average sales volume, the N stores' historical average sales volume when they are not out of stock, and the sales quantities of the N stores; The compensation amount for the store during the out-of-stock period is determined according to the median of the compensation amounts of the N stores.

5. The method according to any one of claims 1 to 4, characterized in that: The method further comprises: A target compensation amount is determined according to the compensation amount and at least one of the following: Actual sales volume; sales volume when the product is out of stock during the same historical period and under the same activity; sales volume when the product is not out of stock during the same historical period and under the same activity.

6. The method according to claim 1, characterized in that The sales information includes at least one of daily activity discount information, holiday information, working day information and time information in the store's history of M days; The activity discount information is used to indicate the activity discount strength of the store; The holiday information is used to indicate whether each day in the M days is a holiday; The working day information is used to indicate whether each day in the M days is a working day; The time information is used to indicate the time distance between each day of the M days and the day when the store is out of stock.

7. A store out-of-stock compensation device, characterized in that: The device comprises: An acquisition module, used to acquire the daily sales information of the store in the M days of history when there is a shortage of stock in the store, wherein the sales information is a factor affecting the sales quantity of the store; a processing module, configured to determine K days with the highest similarity from the M historical days, if the M historical days of the store include at least one day without out-of-stock conditions, based on the similarity between the sales information of each day in the M historical days of the store and the sales information of the day when the store was out of stock; A determination module is used to obtain the compensation amount for the out-of-stock period of the store based on the sales quantity per hour in at least one hour of each day of the K days and the sales trend index, wherein the sales trend index is obtained based on the sales quantity during the period when the store is not out of stock and the sales quantity during the same period in the store's history of M days.

8. A store out-of-stock compensation device, characterized in that: The device comprises: A memory for storing program instructions; A processor is used to call the program instructions stored in the memory, and execute the steps included in any one of claims 1-6 according to the obtained program instructions.

9. A computer-readable storage medium, characterized in that: The computer-readable storage medium stores a computer program, wherein the computer program includes program instructions. When the program instructions are executed by a computer, the method according to any one of claims 1 to 6 is executed.

10. A computer program product, characterized in that The computer program product comprises a computer program code, which causes any one of claims 1 to 6 to be performed when the computer program code is run on a computer.

Images