Inventory control method and device

Abstract

The present disclosure proposes an inventory control method and device, which relates to the technical field of inventory control. The method includes: obtaining the historical purchase quantity sequence of the target product of the target object before the observation time sequence, processing the historical purchase quantity sequence to obtain the initial inventory of the target product for each unit observation time in the observation time sequence; determining the inventory impact factor of the target product at the current observation time, and determining the inventory of the target product at the current observation time according to the inventory impact factor of the target product at the current observation time and the initial inventory of the target product in the observation time sequence. Through the above method, the inventory of the target product of the target object can be accurately determined, and the efficiency of inventory control can be improved.

Description

Technical Field

[0001] The present disclosure relates to the technical field of inventory control, and in particular to an inventory control method and device. Background Art

[0002] The control of product inventory and product age in retail terminal stores is an important task for traditional offline retail. If the product inventory is too high, the product age is likely to be stale, or even close to or expired, causing losses to the store; if the product inventory is too low, on the one hand, it is likely that the purchase demand will not be met, causing inconvenience to the purchaser, and on the other hand, the store needs to restock multiple times, wasting logistics resources and reducing logistics efficiency.

[0003] Inventory forecasting is an important part of inventory control. In the related art, due to the low accuracy of inventory forecasting, inventory control is inconvenient. Summary of the invention

[0004] A technical problem to be solved by the present disclosure is to provide a solution that can accurately determine the inventory of a target product and improve the efficiency of inventory control.

[0005] According to a first aspect of the present disclosure, an inventory control method is proposed, comprising: obtaining a historical purchase quantity sequence for a target product of a target object before an observation time sequence, wherein the observation time sequence includes at least one unit observation time; processing the historical purchase quantity sequence to obtain an initial inventory of the target product for each unit observation time in the observation time sequence; determining an inventory impact factor of the target product at a current observation time, wherein the current observation time is a unit observation time of the observation time sequence; determining the inventory of the target product at the current observation time based on the inventory impact factor of the target product at the current observation time and the initial inventory of the target product in the observation time sequence.

[0006] In some embodiments, it also includes: generating inventory control information based on the inventory of the target product at the current observation time; sending the inventory control information to the terminal corresponding to the target object, wherein the inventory control information is used to prompt the target object to perform inventory control on the target product.

[0007] In some embodiments, generating inventory control information based on the inventory of the target product at the current observation time includes at least one of the following: generating first inventory control information when the inventory of the target product at the current observation time is greater than a first inventory threshold, wherein the first inventory control information is used to instruct the target object to perform inventory clearing of the target product; generating second inventory control information when the inventory of the target product of the target object at the current observation time is less than a second inventory threshold, wherein the second inventory control information is used to instruct the target object to replenish the target product, wherein the second inventory threshold is less than the first inventory threshold.

[0008] In some embodiments, according to at least one of the identification of the target object and the identification of the target product, an inventory threshold storage table is queried to determine the first inventory threshold and the second inventory threshold.

[0009] In some embodiments, the inventory influencing factor of the target product at the current observation time includes at least one of the purchase volume increment index value, inventory turnover days, and the average inventory consumed per purchase interval of the target product at the current observation time.

[0010] In some embodiments, the inventory of the target product at the current observation time is positively correlated with the purchase volume increment index value; the inventory of the target product at the current observation time is negatively correlated with the inventory turnover days; the inventory of the target product at the current observation time is positively correlated with the average inventory consumed per purchase interval.

[0011] In some embodiments, the inventory of the target product at the current observation time is determined according to the following formula:

[0012]

[0013] in, is the inventory of the target product at the current observation time, α and β are adjustment coefficients, and K 0 is the initial inventory, ΔS is the incremental index value of purchase volume, is the average inventory consumed between each purchase, and D is the inventory turnover days.

[0014] In some embodiments, determining the inventory impact factor of the target product at the current observation time includes: determining the monthly month-on-month purchase volume difference of the target product based on the purchase volume of the target product at the current observation time and the purchase volume of the target product on the same day last month, and using the monthly month-on-month purchase volume difference as the purchase volume increment index value.

[0015] In some embodiments, determining the inventory impact factor of the target product at the current observation time includes: determining the inventory turnover days based on the initial inventory of the target product in the observation time series, the historical purchase volume of the target product within a preset time period before the current observation time, and the length of the preset time period.

[0016] In some embodiments, the inventory turnover days are positively correlated with the initial inventory and the length of the preset time period, and the inventory turnover days are negatively correlated with the historical purchase volume of the target product in the preset time period before the current observation time.

[0017] In some embodiments, determining the inventory impact factor of the target product at the current observation time includes: determining the average inventory consumed per purchase interval of the target product based on the historical purchase volume of the target product within a preset time period before the current observation time, and the historical number of purchases of the target product within the preset time period.

[0018] In some embodiments, the processing of the historical purchase quantity sequence to obtain the initial inventory of the target product for each unit observation time in the observation time series includes: decomposing the historical purchase quantity sequence according to an empirical mode decomposition algorithm to obtain an eigenmode function sequence; processing the eigenmode function sequence according to an inventory determination model to obtain the initial inventory of the target product in the observation time series.

[0019] According to a second aspect of the present disclosure, an inventory control device is proposed, comprising: an acquisition module, configured to acquire a historical purchase quantity sequence of a target product of a target object before an observation time sequence, wherein the observation time sequence includes at least one unit observation time; a first inventory determination module, configured to process the historical purchase quantity sequence to obtain an initial inventory of the target product for each unit observation time in the observation time sequence; an influence factor determination module, configured to determine an inventory influence factor of the target product at a current observation time, wherein the current observation time is a unit observation time in the observation time sequence; and a second inventory determination module, configured to determine the inventory of the target product at the current observation time based on the inventory influence factor of the target product at the current observation time and the initial inventory of the target product in the observation time sequence.

[0020] According to a third aspect of the present disclosure, an inventory control device is further provided, comprising: a memory; and a processor coupled to the memory, wherein the processor is configured to execute the above-mentioned inventory control method based on instructions stored in the memory.

[0021] According to a fourth aspect of the present disclosure, a computer-readable storage medium is further provided, on which computer program instructions are stored, and when the instructions are executed by a processor, the above-mentioned inventory control method is implemented.

[0022] Compared with the related art, in the embodiment of the present disclosure, by obtaining the historical purchase quantity sequence for the target product of the target object before the observation time sequence, the historical purchase quantity sequence is processed to obtain the initial inventory of the target product for each unit observation time in the observation time sequence, and the inventory of the target product at the current observation time is determined according to the inventory influence factor of the target product at the current observation time and the initial inventory, the inventory of the target product of the target object can be accurately determined, thereby improving the efficiency of inventory control for the target product.

[0023] Other features and advantages of the present disclosure will become apparent from the following detailed description of exemplary embodiments of the present disclosure with reference to the accompanying drawings. BRIEF DESCRIPTION OF THE DRAWINGS

[0024] The accompanying drawings, which constitute a part of the specification, illustrate embodiments of the present disclosure and, together with the description, serve to explain the principles of the present disclosure.

[0025] The present disclosure may be more clearly understood from the following detailed description with reference to the accompanying drawings, in which:

[0026] Figure 1 It is a flowchart of an inventory control method according to some embodiments of the present disclosure.

[0027] Figure 2 Schematic diagram of a flow chart of an inventory control method according to some other embodiments of the present disclosure.

[0028] Figure 3 It is a schematic diagram of the effect of the inventory control method according to some embodiments of the present disclosure.

[0029] Figure 4 It is a schematic diagram of the structure of an inventory control device according to some embodiments of the present disclosure.

[0030] Figure 5 It is a schematic diagram of the structure of an inventory control device according to some embodiments of the present disclosure.

[0031] Figure 6 Schematic diagram of the structure of an inventory control device according to some further embodiments of the present disclosure.

[0032] Figure 7 A schematic diagram of the structure of a computer system according to some embodiments of the present disclosure. DETAILED DESCRIPTION

[0033] Various exemplary embodiments of the present disclosure will now be described in detail with reference to the accompanying drawings. It should be noted that the relative arrangement of components and steps, numerical expressions and numerical values ​​set forth in these embodiments do not limit the scope of the present disclosure unless otherwise specifically stated.

[0034] At the same time, it should be understood that for the convenience of description, the sizes of the various parts shown in the drawings are not drawn according to the actual proportional relationship.

[0035] The following description of at least one exemplary embodiment is merely illustrative in nature and is in no way intended to limit the present disclosure, its application, or uses.

[0036] Technologies, methods, and apparatus known to ordinary technicians in the relevant field may not be discussed in detail, but where appropriate, such technologies, methods, and apparatus should be considered part of the authorization specification.

[0037] In all examples shown and discussed herein, any specific values ​​should be interpreted as merely exemplary and not as limiting. Therefore, other examples of the exemplary embodiments may have different values.

[0038] It should be noted that like reference numerals and letters refer to similar items in the following figures, and therefore, once an item is defined in one figure, it need not be further discussed in subsequent figures.

[0039] In order to make the objectives, technical solutions and advantages of the present disclosure more clearly understood, the present disclosure is further described in detail below in combination with specific embodiments and with reference to the accompanying drawings.

[0040] Figure 1 FIG. 1 is a flow chart of an inventory control method according to some embodiments of the present disclosure. Figure 1 As shown, the inventory control method of the embodiment of the present disclosure includes:

[0041] Step S110: Obtain the historical purchase quantity sequence of the target product of the target object before the observation time series.

[0042] Exemplarily, the target object is a terminal store directly facing consumers, such as a supermarket, a convenience store, a grocery store, or a hotel. The target object can be one terminal store or multiple terminal stores. For example, based on at least one factor of the type and geographical location of the terminal store, multiple terminal stores are selected from multiple terminal stores, and the selected multiple terminal stores are used as target objects, and product inventory control is performed for each target object.

[0043] Exemplarily, the target product is a collection of products of the same category or multiple categories. For example, the target product is a collection of products of the water category, wherein the product collection includes water products of various capacities such as 380ml, 550ml, 1.5L, 5L, and 12L water. For example, the target product is a collection of products of the water category and the beverage category.

[0044] The observation time series includes at least one unit observation time. For example, the observation time series is 7 days, two weeks, or one month, and the unit observation time is one day. For example, the observation time is 180 days, and the unit observation time is two days.

[0045] The historical purchase quantity sequence includes a plurality of historical purchase quantity data. For example, the historical purchase quantity data includes the purchase quantity data of the target object for water products for six consecutive months before the observation time series.

[0046] In some embodiments, a database is queried to obtain a historical purchase quantity sequence of the target product by the target object before the observation time series.

[0047] In other embodiments, an inventory determination request is received, and a historical purchase quantity sequence of the target product of the target object before the observation time series is obtained from the inventory determination request.

[0048] Step S120: Process the historical purchase quantity sequence to obtain the initial inventory of the target product for each unit observation time in the observation time sequence.

[0049] In some embodiments, the historical purchase quantity sequence is decomposed according to the Empirical Mode Decomposition (EMD) algorithm to obtain the intrinsic mode function sequence; the intrinsic mode function sequence is processed according to the inventory determination model to obtain the initial inventory of the target product in the observation time series.

[0050] The EMD algorithm decomposes signals based on the time scale characteristics of the data itself, without presetting any basis functions. It has the advantage of processing non-stationary and nonlinear data. The three assumptions of the EMD algorithm are as follows:

[0051] J1: The data has at least two extreme values, a maximum and a minimum;

[0052] J2: The local temporal characteristics of the data are uniquely determined by the time scale between extreme points;

[0053] J3: If the data has no extreme points but has inflection points, the extreme values ​​can be obtained by differentiating the data once or multiple times, and then the eigenmode function sequence can be obtained by integration.

[0054] In some embodiments, decomposing the historical purchase quantity sequence according to the empirical mode decomposition algorithm to obtain the eigenmode function sequence includes: steps 1.1 to 1.5.

[0055] Step 1.1: Use the cubic spline interpolation method to interpolate the historical purchase quantity series K 1 The extreme points of (t) are fitted to determine the maximum and minimum values, and the first average envelope is determined based on the maximum and minimum values.

[0056] Exemplarily, it is determined according to the following formula

[0057]

[0058] Among them, U(t) is the maximum value, L(t) is the minimum value, and M 1 (t) is the first average envelope.

[0059] Step 1.2: Set the historical purchase quantity sequence K 1 (t) and the first average envelope M 1 (t) is subtracted to obtain a new sequence H 1 (t).

[0060] In step 1.2, the calculation formula is as follows:

[0061] H 1 (t) = K 1 (t)-M 1 (t)

[0062] Step 1.3: Determine H 1 (t) Whether to reject the standard assumption of the intrinsic mode function (IMF) component. If so, use H 1 (t) replaces K 1 (t), and repeat steps 1.1 and 1.2 until the standard assumption of the intrinsic mode function (IMF) component is met.

[0063] The standard assumptions of the IMF components, namely the IMF criteria, include: the zero points and extreme points in the sequence are equal or at most 1; the means of the maximum and minimum values ​​are equal and are 0.

[0064] When the sequence in step 1.3 meets the IMF criteria for the first time, the sequence is recorded as IMF 1 (t), and go to step 1.4.

[0065] Step 1.4: Convert the sequence to IMF 1 (t) and K t Subtract and get the remaining sequence R 1(t).

[0066] In step 1.4, the calculation formula is as follows:

[0067] R 1 (t) = IMF 1 (t)-K t

[0068] Step 1.5: Use R 1 (t) replaces K t Repeat steps 1.1 to 1.4 until multiple IMF components and the last inseparable sequence are obtained, which is recorded as the trend term R n (t).

[0069] Finally, the historical purchase volume series is decomposed into multiple IMF components and a trend term, as shown below:

[0070]

[0071] in, is the sum of all IMF components.

[0072] After decomposing the historical purchase quantity sequence according to steps 1.1 to 1.5, the eigenmode function sequence is processed according to the inventory determination model to obtain the initial inventory of the target product per unit observation time in the observation time sequence. Exemplarily, the inventory determination model is a time series model, such as a back propagation (BP) neural network model, a support vector machine (SVM) model, etc.

[0073] In the embodiment of the present disclosure, by decomposing the historical purchase quantity sequence according to the empirical mode decomposition algorithm and then processing the decomposed intrinsic mode function sequence according to the inventory determination model, the non-stationary product inventory can be better predicted and the accuracy of the determined product inventory can be improved.

[0074] In some embodiments, before step S120, the process further includes: cleaning the data to obtain a historical purchase quantity sequence.

[0075] Exemplarily, data cleaning is performed according to one or more of the following rules:

[0076] 1. The historical purchase data of the selected customers and product categories must meet the three assumptions of EMD.

[0077] 2. The selected customers are those with normal cooperation and regular visit records of sales personnel. Fake customers or customers with no visit records of sales personnel for a long time will be excluded.

[0078] 3. In the purchase data of the selected customers, the purchase sources exclude order information directly supplied by non-superior dealers, such as cross-superior units, cross-provincial and municipal regions, etc.

[0079] 4. For customer order information with return records for corresponding categories, subtract the return quantity from the purchase quantity.

[0080] Through data cleaning, it is possible to eliminate the interference of noise data on the analysis results or unnecessary data omissions, which helps to improve the accuracy of the determined inventory.

[0081] Step S130: Determine the inventory impact factor of the target product at the current observation time.

[0082] Among them, the current observation time is the unit observation time in the observation time series.

[0083] In some embodiments, the inventory influencing factor of the target product at the current observation time includes at least one of the purchase volume increment index value, inventory turnover days, and the average inventory consumed per purchase interval of the target product at the current observation time.

[0084] For example, the inventory influencing factors of the target product at the current observation time include the purchase volume increment index value, inventory turnover days, and the average inventory consumed per purchase interval of the target product at the current observation time.

[0085] In some embodiments, the purchase volume increment index value of the target product at the current observation time is determined as follows: based on the purchase volume of the target product at the current observation time and the purchase volume of the target product on the same day last month, the monthly month-on-month purchase volume difference of the target product is determined, and the monthly month-on-month purchase volume difference is used as the purchase volume increment index value.

[0086] The calculation formula for the difference in monthly month-on-month purchase volume of the target product is as follows:

[0087] ΔS=S j1 -S j0

[0088] Among them, S j1 is the purchase quantity of the target product at the current observation time, S j0 is the purchase volume of the target product on the same day of the previous month, and j is the number in the observation time series, or the number of rolling date days of the observation.

[0089] In some embodiments, the inventory turnover days are determined as follows: the inventory turnover days are determined based on the initial inventory of the target product in the observation time series, the historical purchase volume of the target product in a preset time period before the current observation time, and the length of the preset time period.

[0090] In some embodiments, the inventory turnover days are positively correlated with the initial inventory and the length of a preset time period, and the inventory turnover days are negatively correlated with the historical purchase volume of the target product in the preset time period before the current observation time.

[0091] For example, the formula for calculating inventory cycle days is as follows:

[0092]

[0093] Among them, K 0 is the initial inventory, S 180 It is the historical purchase volume of the target product in the preset time period before the current observation time, specifically, the number of target product purchase boxes of the terminal store in the past 6 months, and 180 is the length of the preset time period.

[0094] In the above example, the preset time period is set to 180 days based on a comprehensive assessment of the company's category business system. The assessment includes the following options: the shelf life of the selected category; if the corresponding product terminal product has not been restocked for more than 6 months, it is considered that the terminal store has sold out. It should be pointed out that setting the preset time period to 180 days is only exemplary. In specific implementation, the preset time period can be determined based on a comprehensive assessment of multiple factors.

[0095] In some embodiments, the average inventory amount consumed per purchase interval for the target product is determined as follows: the average inventory amount consumed per purchase interval for the target product is determined based on the historical purchase amount of the target product within a preset time period before the current observation time, and the historical number of purchases of the target product within the preset time period.

[0096] For example, the formula for calculating the average inventory consumed per restocking interval for the target product is as follows:

[0097]

[0098] in, is the average inventory consumed per restocking interval for the target product, N t It is the total number of purchases by terminal customers’ stores during the current observation period.

[0099] Step S140: Determine the inventory of the target product at the current observation time according to the inventory influencing factor of the target product at the current observation time and the initial inventory of the target product in the observation time series.

[0100] In some embodiments, the inventory of the target product at the current observation time is positively correlated with the purchase volume increment index value; the inventory of the target product at the current observation time is negatively correlated with the inventory turnover days; the inventory of the target product at the current observation time is positively correlated with the average inventory consumed per purchase interval.

[0101] Exemplarily, the inventory of the target product at the current observation time is determined according to the following formula:

[0102]

[0103] in, is the inventory of the target product at the current observation time, α and β are adjustment coefficients, and K 0 is the initial inventory, ΔS is the incremental index value of purchase volume, is the average inventory consumed between each purchase, and D is the inventory turnover days.

[0104] Among them, the value range of α is between 0 and 1, specifically the value range of the terminal customer random error coefficient β is between 0 and 1, specifically the seasonal time cycle deviation coefficient, which is caused by statutory holidays, weekends, and days when the terminal stores are not open for business.

[0105] In some embodiments, the values ​​of α and β are determined in the above manner: through computer programming, multiple combinations of α and β are set by exhaustive method, inventory forecasting is performed under each combination of α and β, the root mean square error is calculated based on the inventory forecast result and the actual inventory, and the combination of α and β corresponding to the minimum root mean square error is selected as the optimal α and β.

[0106] In other embodiments, a genetic-neural network (GABP) model is trained based on the order data of the terminal stores in recent years, and the optimal α and β are obtained by continuously adjusting the parameter weights of the neural network model. It should be noted that other parameter optimization selection algorithms known to those skilled in the art can also be used to determine the optimal α and β, and the present invention does not limit the method for solving the parameters.

[0107] In the embodiment of the present disclosure, the above steps can accurately determine the inventory of the target product of the target object, thereby improving the effectiveness of inventory control for the target product. Moreover, compared with the related art, the embodiment of the present disclosure reduces the requirement for the scale of training samples through the above method, thereby improving the applicability of the method.

[0108] Figure 2 FIG. 1 is a flow chart of an inventory control method according to other embodiments of the present disclosure. Figure 2 As shown, the inventory control method of the embodiment of the present disclosure includes:

[0109] Step S110: Obtain the historical purchase quantity sequence of the target product of the target object before the observation time series.

[0110] The observation time series includes multiple unit observation times. For example, the observation time series includes 30 days, and the unit observation time is 1 day.

[0111] The historical purchase quantity sequence includes a plurality of historical purchase quantity data. For example, the historical purchase quantity data includes the purchase quantity data of the target object for water products for six consecutive months before the observation time series.

[0112] In some embodiments, a database is queried to obtain a historical purchase quantity sequence of the target product by the target object before the observation time series.

[0113] In other embodiments, an inventory determination request is received, and a historical purchase quantity sequence of the target product of the target object before the observation time series is obtained from the inventory determination request.

[0114] Step S120: Process the historical purchase quantity sequence to obtain the initial inventory of the target product for each unit observation time in the observation time sequence.

[0115] In some embodiments, the historical purchase quantity sequence is decomposed according to the Empirical Mode Decomposition (EMD) algorithm to obtain the intrinsic mode function sequence; the intrinsic mode function sequence is processed according to the inventory determination model to obtain the initial inventory of the target product for each unit observation time in the observation time series.

[0116] In the embodiment of the present disclosure, by decomposing the historical purchase quantity sequence according to the empirical mode decomposition algorithm and then processing the decomposed intrinsic mode function sequence according to the inventory determination model, the non-stationary product inventory can be better predicted and the accuracy of the determined product inventory can be improved.

[0117] In some embodiments, before step S120, the process further includes: cleaning the data to obtain a historical purchase quantity sequence.

[0118] Through data cleaning, it is possible to eliminate the interference of noise data on the analysis results or unnecessary data omissions, which helps to improve the accuracy of the determined inventory.

[0119] Step S130: Determine the inventory impact factor of the target product at the current observation time.

[0120] Among them, the current observation time is the unit observation time in the observation time series.

[0121] In some embodiments, the inventory influencing factor of the target product at the current observation time includes at least one of the purchase volume increment index value, inventory turnover days, and the average inventory consumed per purchase interval of the target product at the current observation time.

[0122] For example, the inventory influencing factors of the target product at the current observation time include the purchase volume increment index value, inventory turnover days, and the average inventory consumed per purchase interval of the target product at the current observation time.

[0123] Step S140: Determine the inventory of the target product at the current observation time according to the inventory influencing factor of the target product at the current observation time and the initial inventory of the target product in the observation time series.

[0124] In some embodiments, the inventory of the target product at the current observation time is positively correlated with the purchase volume increment index value; the inventory of the target product at the current observation time is negatively correlated with the inventory turnover days; the inventory of the target product at the current observation time is positively correlated with the average inventory consumed per purchase interval.

[0125] Exemplarily, the inventory of the target product at the current observation time is determined according to the following formula:

[0126]

[0127] in, is the inventory of the target product at the current observation time, α and β are adjustment coefficients, and K 0 is the initial inventory, ΔS is the incremental index value of purchase volume, is the average inventory consumed between each purchase, and D is the inventory turnover days.

[0128] Step S150: Generate inventory control information based on the inventory of the target product at the current observation time.

[0129] In some embodiments, the target object is a plurality of stores. After the inventory of each store is determined respectively, inventory control is performed on the inventory of each store respectively to generate inventory control information.

[0130] In other embodiments, the target object is multiple stores. After the inventory of each store is determined separately, the inventory of each store is aggregated, and unified inventory control is performed based on the aggregated overall inventory to generate inventory control information.

[0131] The inventory control information is used to prompt the target object to perform inventory control on the target product.

[0132] In some embodiments, when the inventory of the target product at the current observation time is greater than the first inventory threshold, first inventory control information is generated, wherein the first inventory control information is used to instruct the target object to perform inventory cleanup on the target product.

[0133] For example, when the target product is a water product in a supermarket, it is determined through steps S110 to S140 that the inventory of the water product at the current observation time is 120 boxes, and the first inventory threshold of the water product in the supermarket is 100 boxes. By comparison, it is found that the real-time inventory of the water product is greater than the first inventory threshold, and the first inventory control information is generated. Exemplarily, the first inventory control information generated is "the inventory of the water product is 120 boxes, the inventory is too high, please clear the inventory in time."

[0134] In some embodiments, when the inventory of the target product of the target object at the current observation time is less than a second inventory threshold, second inventory control information is generated, wherein the second inventory control information is used to instruct the target object to replenish the target product, wherein the second inventory threshold is less than the first inventory threshold.

[0135] For example, when the target product is a water product in a supermarket, it is determined through steps S110 to S140 that the inventory of the water product at the current observation time is 10 boxes, and the first inventory threshold of the water product in the supermarket is 20 boxes. By comparison, it is found that the real-time inventory of the water product is less than the second inventory threshold, and the second inventory control information is generated. Exemplarily, the second inventory control information generated is "the inventory of the water product is 10 boxes, the inventory is too low, please replenish in time."

[0136] In some embodiments, according to at least one of the identification of the target object and the identification of the target product, the inventory threshold storage table is queried to determine the first inventory threshold and the second inventory threshold.

[0137] For example, a stock threshold storage table is set in advance for multiple objects and multiple products, wherein the stock threshold storage table stores first stock thresholds and second stock thresholds set for multiple products of the multiple objects. When executing step S150, the stock threshold storage table is queried according to the identifier of the target object and the identifier of the target product to obtain the first stock threshold and the second stock threshold corresponding to the target product of the target object.

[0138] In the embodiments of the present disclosure, by setting corresponding first inventory thresholds and second inventory thresholds for different target objects and different target products, the flexibility of product inventory control and the effectiveness of inventory control can be improved.

[0139] Step S160: Send the inventory control information to the terminal corresponding to the target object.

[0140] In the embodiment of the present disclosure, the above steps can accurately determine the inventory of the target product of the target object, and perform efficient and accurate inventory control for different target objects. Moreover, compared with the related art, the embodiment of the present disclosure reduces the requirements for the scale of training samples and improves the applicability of the method by first roughly determining the initial inventory and then determining the inventory forecast value based on the inventory influencing factor at the current observation time.

[0141] Figure 3 It is a schematic diagram of the effect of the inventory control method according to some embodiments of the present disclosure. Figure 3 The error results between the inventory forecast value and the actual inventory value are shown. Figure 3 In the figure, actual category inventory values ​​of 10 selected terminal stores are displayed. By comparing with the inventory determined by the inventory control method in some embodiments of the present invention, it is found that the inventory accuracy determined by the inventory control method is very high, and the root mean square error (RMSE) value is about 80%.

[0142] Figure 4 FIG. 1 is a schematic diagram of the structure of an inventory control device according to some embodiments of the present disclosure. Figure 4 As shown, the inventory control device of the embodiment of the present disclosure includes: an acquisition module 410 , a first inventory determination module 420 , an impact factor determination module 430 , and a second inventory determination module 440 .

[0143] The acquisition module 410 is configured to acquire the historical purchase quantity sequence of the target product of the target object before the observation time sequence.

[0144] Exemplarily, the target object is a terminal store directly facing consumers, such as a supermarket, a convenience store, a grocery store, or a hotel. The target object can be one terminal store or multiple terminal stores. For example, based on at least one factor of the type and geographical location of the terminal store, multiple terminal stores are selected from multiple terminal stores, and the selected multiple terminal stores are used as target objects, and product inventory control is performed for each target object.

[0145] Exemplarily, the target product is a collection of products of the same category or multiple categories. For example, the target product is a collection of products of the water category, wherein the product collection includes water products of various capacities such as 380ml, 550ml, 1.5L, 5L, and 12L water. For example, the target product is a collection of products of the water category and the beverage category.

[0146] The observation time series includes at least one unit observation time. For example, the observation time series is 7 days, two weeks, or one month, and the unit observation time is one day.

[0147] The historical purchase quantity sequence includes a plurality of historical purchase quantity data. For example, the historical purchase quantity data includes the purchase quantity data of the target object for water products for six consecutive months before the observation time series.

[0148] In some embodiments, the acquisition module 410 queries a database to obtain a historical purchase quantity sequence of the target product of the target object before the observation time sequence.

[0149] In other embodiments, the acquisition module 410 receives an inventory determination request, and acquires from the inventory determination request a historical purchase quantity sequence of the target product of the target object before the observation time sequence.

[0150] The first inventory determination module 420 is configured to process the historical purchase quantity sequence to obtain the initial inventory of the target product for each unit observation time in the observation time sequence.

[0151] In some embodiments, the first inventory determination module 420 decomposes the historical purchase quantity sequence according to the Empirical Mode Decomposition (EMD) algorithm to obtain an eigenmode function sequence; and processes the eigenmode function sequence according to the inventory determination model to obtain the initial inventory of the target product in the observation time series.

[0152] The EMD algorithm decomposes signals based on the time scale characteristics of the data itself, without presetting any basis functions. It has the advantage of processing non-stationary and nonlinear data. The three assumptions of the EMD algorithm are as follows:

[0153] J1: The data has at least two extreme values, a maximum and a minimum;

[0154] J2: The local temporal characteristics of the data are uniquely determined by the time scale between extreme points;

[0155] J3: If the data has no extreme points but has inflection points, the extreme values ​​can be obtained by differentiating the data once or multiple times, and then the eigenmode function sequence can be obtained by integration.

[0156] The impact factor determination module 430 is configured to determine the inventory impact factor of the target product at the current observation time.

[0157] Among them, the current observation time is the unit observation time in the observation time series.

[0158] In some embodiments, the inventory influencing factor of the target product at the current observation time includes at least one of the purchase volume increment index value, inventory turnover days, and the average inventory consumed per purchase interval of the target product at the current observation time.

[0159] For example, the inventory influencing factors of the target product at the current observation time include the purchase volume increment index value, inventory turnover days, and the average inventory consumed per purchase interval of the target product at the current observation time.

[0160] In some embodiments, the influencing factor determination module 430 determines the purchase volume increment index value of the target product at the current observation time according to the following method: based on the purchase volume of the target product at the current observation time and the purchase volume of the target product on the same day last month, the monthly month-on-month purchase volume difference of the target product is determined, and the monthly month-on-month purchase volume difference is used as the purchase volume increment index value.

[0161] In some embodiments, the influencing factor determination module 430 determines the inventory turnover days in the following manner: the inventory turnover days are determined based on the initial inventory of the target product in the observation time series, the historical purchase volume of the target product in a preset time period before the current observation time, and the length of the preset time period.

[0162] In some embodiments, the influencing factor determination module 430 determines the average inventory amount consumed per purchase interval of the target product in the following manner: based on the historical purchase amount of the target product within a preset time period before the current observation time, and the historical number of purchases of the target product within the preset time period, determines the average inventory amount consumed per purchase interval of the target product.

[0163] The second inventory determination module 440 is configured to determine the inventory of the target product at the current observation time according to the inventory impact factor of the target product at the current observation time and the initial inventory of the target product in the observation time series.

[0164] In some embodiments, the inventory of the target product at the current observation time is positively correlated with the purchase volume increment index value; the inventory of the target product at the current observation time is negatively correlated with the inventory turnover days; the inventory of the target product at the current observation time is positively correlated with the average inventory consumed per purchase interval.

[0165] Exemplarily, the second inventory determination module 440 determines the inventory of the target product at the current observation time according to the following formula:

[0166]

[0167] in, is the inventory of the target product at the current observation time, α and β are adjustment coefficients, and K 0 is the initial inventory, ΔS is the incremental index value of purchase volume, is the average inventory consumed between each purchase, and D is the inventory turnover days.

[0168] In the embodiments of the present disclosure, the above device can accurately determine the inventory of the target product of the target object, thereby improving the effectiveness and efficiency of inventory control for the target product.

[0169] Figure 5 FIG. 1 is a schematic diagram of the structure of an inventory control device according to some embodiments of the present disclosure. Figure 5 As shown, the inventory control device of the embodiment of the present disclosure includes: an acquisition module 410 , a first inventory determination module 420 , an impact factor determination module 430 , a second inventory determination module 440 , a generation module 450 , and a sending module 460 .

[0170] The acquisition module 410 is configured to acquire the historical purchase quantity sequence of the target product of the target object before the observation time sequence.

[0171] The historical purchase quantity sequence includes a plurality of historical purchase quantity data. For example, the historical purchase quantity data includes the purchase quantity data of the target object for water products for six consecutive months before the observation time series.

[0172] In some embodiments, a database is queried to obtain a historical purchase quantity sequence of the target product by the target object before the observation time series.

[0173] In other embodiments, an inventory determination request is received, and a historical purchase quantity sequence of the target product of the target object before the observation time series is obtained from the inventory determination request.

[0174] The first inventory determination module 420 is configured to process the historical purchase quantity sequence to obtain the initial inventory of the target product for each unit observation time in the observation time sequence.

[0175] In some embodiments, the first inventory determination module 420 decomposes the historical purchase quantity sequence according to the Empirical Mode Decomposition (EMD) algorithm to obtain an eigenmode function sequence; and processes the eigenmode function sequence according to the inventory determination model to obtain the initial inventory of the target product in the observation time series.

[0176] The impact factor determination module 430 is configured to determine the inventory impact factor of the target product at the current observation time.

[0177] Among them, the current observation time is the unit observation time in the observation time series.

[0178] In some embodiments, the inventory influencing factor of the target product at the current observation time includes at least one of the purchase volume increment index value, inventory turnover days, and the average inventory consumed per purchase interval of the target product at the current observation time.

[0179] For example, the inventory influencing factors of the target product at the current observation time include the purchase volume increment index value, inventory turnover days, and the average inventory consumed per purchase interval of the target product at the current observation time.

[0180] The second inventory determination module 440 is configured to determine the inventory of the target product at the current observation time according to the inventory impact factor of the target product at the current observation time and the initial inventory of the target product in the observation time series.

[0181] In some embodiments, the inventory of the target product at the current observation time is positively correlated with the purchase volume increment index value; the inventory of the target product at the current observation time is negatively correlated with the inventory turnover days; the inventory of the target product at the current observation time is positively correlated with the average inventory consumed per purchase interval.

[0182] Exemplarily, the second inventory determination module 440 determines the inventory of the target product at the current observation time according to the following formula:

[0183]

[0184] in, is the inventory of the target product at the current observation time, α and β are adjustment coefficients, and K 0 is the initial inventory, ΔS is the incremental index value of purchase volume, is the average inventory consumed between each purchase, and D is the inventory turnover days.

[0185] The generating module 450 is configured to generate inventory control information according to the inventory of the target product at the current observation time.

[0186] In some embodiments, the target object is a plurality of stores. After the inventory of each store is determined respectively, inventory control is performed on the inventory of each store respectively to generate inventory control information.

[0187] In other embodiments, the target object is multiple stores. After the inventory of each store is determined separately, the inventory of each store is aggregated, and unified inventory control is performed based on the aggregated overall inventory to generate inventory control information.

[0188] The inventory control information is used to prompt the target object to perform inventory control on the target product.

[0189] In some embodiments, the generation module 450 generates first inventory control information when the inventory of the target product at the current observation time is greater than the first inventory threshold, wherein the first inventory control information is used to instruct the target object to perform inventory cleanup on the target product.

[0190] For example, when the target product is a water product in a supermarket, it is determined through steps S110 to S140 that the inventory of the water product at the current observation time is 120 boxes, and the first inventory threshold of the water product in the supermarket is 100 boxes. By comparison, it is found that the real-time inventory of the water product is greater than the first inventory threshold, and the first inventory control information is generated. Exemplarily, the first inventory control information generated is "the inventory of the water product is 120 boxes, the inventory is too high, please clear the inventory in time."

[0191] In some embodiments, the generation module 450 generates second inventory control information when the inventory of the target product of the target object at the current observation time is less than the second inventory threshold, wherein the second inventory control information is used to instruct the target object to replenish the target product, wherein the second inventory threshold is less than the first inventory threshold.

[0192] For example, when the target product is a water product in a supermarket, it is determined through steps S110 to S140 that the inventory of the water product at the current observation time is 10 boxes, and the first inventory threshold of the water product in the supermarket is 20 boxes. By comparison, it is found that the real-time inventory of the water product is less than the second inventory threshold, and the second inventory control information is generated. Exemplarily, the second inventory control information generated is "the inventory of the water product is 10 boxes, the inventory is too low, please replenish in time."

[0193] In some embodiments, the generation module 450 queries the inventory threshold storage table according to at least one of the identification of the target object and the identification of the target product to determine the first inventory threshold and the second inventory threshold.

[0194] For example, a stock threshold storage table is pre-set for multiple objects and multiple products, wherein the stock threshold storage table stores first stock thresholds and second stock thresholds set for multiple products of the multiple objects. The generation module 450 queries the stock threshold storage table according to the identifier of the target object and the identifier of the target product to obtain the first stock threshold and the second stock threshold corresponding to the target product of the target object.

[0195] In the embodiments of the present disclosure, by setting corresponding first inventory thresholds and second inventory thresholds for different target objects and different target products, the flexibility of product inventory control and the effectiveness of inventory control can be improved.

[0196] The sending module 460 is configured to send the inventory control information to the terminal corresponding to the target object.

[0197] In the embodiment of the present disclosure, the above device can accurately determine the inventory of the target product of the target object, and perform efficient and accurate inventory control for different target objects. Moreover, compared with the related art, the embodiment of the present disclosure reduces the requirements for the scale of training samples and improves the applicability of inventory control by first roughly determining the initial inventory and then determining the inventory forecast value based on the inventory impact factor at the current observation time through the above device.

[0198] Figure 6 is a block diagram showing an inventory control device according to other embodiments of the present disclosure.

[0199] like Figure 6 As shown, the inventory control device 600 includes a memory 610; and a processor 620 coupled to the memory 610. The memory 610 is used to store instructions for executing the corresponding embodiments of the inventory control method. The processor 620 is configured to execute the inventory control method in any of the embodiments of the present disclosure based on the instructions stored in the memory 610.

[0200] Figure 7 is a block diagram illustrating a computer system for implementing some embodiments of the present disclosure.

[0201] like Figure 7 As shown, computer system 700 may be embodied in the form of a general purpose computing device. Computer system 700 includes memory 710, processor 720, and bus 730 that connects various system components.

[0202] The memory 710 may include, for example, a system memory, a non-volatile storage medium, etc. The system memory may store, for example, an operating system, an application program, a boot loader, and other programs. The system memory may include a volatile storage medium, such as a random access memory (RAM) and / or a cache memory. The non-volatile storage medium may store, for example, instructions for executing at least one corresponding embodiment of the inventory control method. The non-volatile storage medium may include, but is not limited to, a disk memory, an optical memory, a flash memory, etc.

[0203] The processor 720 can be implemented by a general processor, a digital signal processor (DSP), an application-specific integrated circuit (ASIC), a field programmable gate array (FPGA) or other programmable logic devices, discrete gates or transistors, etc. Discrete hardware components. Accordingly, each module, such as the acquisition module and the first inventory determination module, can be implemented by a central processing unit (CPU) running instructions in a memory to execute corresponding steps, or can be implemented by a dedicated circuit to execute corresponding steps.

[0204] The bus 730 may use any of a variety of bus architectures, including, but not limited to, an Industry Standard Architecture (ISA) bus, a Micro Channel Architecture (MCA) bus, and a Peripheral Component Interconnect (PCI) bus.

[0205] The computer system 700 may also include an input / output interface 740, a network interface 750, a storage interface 760, etc. These interfaces 740, 750, 760, the memory 710, and the processor 720 may be connected via a bus 730. The input / output interface 740 may provide a connection interface for input / output devices such as a display, a mouse, and a keyboard. The network interface 750 may provide a connection interface for various networked devices. The storage interface 760 may provide a connection interface for external storage devices such as a floppy disk, a USB flash drive, and an SD card.

[0206] Here, various aspects of the present disclosure are described with reference to flowcharts and / or block diagrams of methods, devices, and computer program products according to embodiments of the present disclosure. It should be understood that each frame of the flowchart and / or block diagram and the combination of frames can be implemented by computer-readable program instructions.

[0207] These computer-readable program instructions may be provided to a processor of a general-purpose computer, a special-purpose computer or other programmable device to produce a machine, so that the processor executes the instructions to produce means for implementing the functions specified in one or more blocks in the flowchart and / or block diagram.

[0208] These computer-readable program instructions may also be stored in a computer-readable memory, which cause the computer to work in a specific manner to produce an article of manufacture, including instructions for implementing the functions specified in one or more blocks in the flowchart and / or block diagram.

[0209] The present disclosure can take the form of an entirely hardware embodiment, an entirely software embodiment, or an embodiment combining software and hardware aspects.

[0210] Through the inventory control method and device in the above embodiments, the inventory of the target product of the target object can be accurately determined, thereby improving the efficiency and effectiveness of inventory control.

[0211] So far, the inventory control method and device according to the present disclosure have been described in detail. In order to avoid obscuring the concept of the present disclosure, some details known in the art are not described. Based on the above description, those skilled in the art can fully understand how to implement the technical solution disclosed here.

Claims

1. A method for inventory control, comprising: Obtaining a historical purchase quantity sequence of a target product of a target object before an observation time sequence, wherein the observation time sequence includes at least one unit observation time; Processing the historical purchase quantity sequence to obtain the initial inventory of the target product for each unit observation time in the observation time sequence, including: decomposing the historical purchase quantity sequence according to an empirical mode decomposition algorithm to obtain an eigenmode function sequence; processing the eigenmode function sequence according to an inventory determination model to obtain the initial inventory of the target product in the observation time sequence; Determine the inventory impact factor of the target product at the current observation time, wherein the current observation time is a unit observation time in the observation time sequence, and the inventory impact factor of the target product at the current observation time includes the purchase quantity increment index value, inventory turnover days, and the average inventory consumed per purchase interval of the target product at the current observation time; The inventory of the target product at the current observation time is determined according to the inventory influencing factor of the target product at the current observation time and the initial inventory of the target product in the observation time series.

2. The inventory control method according to claim 1, further comprising: Generate inventory control information according to the inventory of the target product at the current observation time; The inventory control information is sent to a terminal corresponding to the target object, wherein the inventory control information is used to prompt the target object to perform inventory control on the target product.

3. The inventory control method according to claim 2, wherein: Generating inventory control information according to the inventory of the target product at the current observation time includes at least one of the following: When the inventory of the target product at the current observation time is greater than a first inventory threshold, generating first inventory control information, wherein the first inventory control information is used to instruct the target object to perform inventory cleanup on the target product; When the inventory of the target product of the target object at the current observation time is less than a second inventory threshold, second inventory control information is generated, wherein the second inventory control information is used to instruct the target object to replenish the target product, wherein the second inventory threshold is less than the first inventory threshold.

4. The inventory control method according to claim 3, wherein: According to at least one of the identifier of the target object and the identifier of the target product, an inventory threshold storage table is queried to determine the first inventory threshold and the second inventory threshold.

5. The inventory control method according to claim 1, wherein: The inventory of the target product at the current observation time is positively correlated with the purchase volume increment index value; The inventory of the target product at the current observation time is negatively correlated with the inventory turnover days; The inventory of the target product at the current observation time is positively correlated with the average inventory consumed per restocking interval.

6. The inventory control method according to claim 5, wherein: The inventory of the target product at the current observation time is determined according to the following formula: in, is the inventory of the target product at the current observation time, , is the adjustment factor, is the initial inventory, is the purchase volume increment indicator value, is the average inventory consumed per restocking interval, It is the inventory turnover days.

7. The inventory control method according to claim 1, wherein: The inventory influencing factors for determining the target product at the current observation time include: According to the purchase volume of the target product at the current observation time and the purchase volume of the target product on the same day of the previous month, the monthly month-on-month purchase volume difference of the target product is determined, and the monthly month-on-month purchase volume difference is used as the purchase volume increment index value.

8. The inventory control method according to claim 1, wherein: The inventory influencing factors for determining the target product at the current observation time include: The inventory turnover days are determined according to the initial inventory of the target product in the observation time series, the historical purchase volume of the target product in a preset time period before the current observation time, and the length of the preset time period.

9. The inventory control method according to claim 7, wherein: The inventory turnover days are positively correlated with the initial inventory and the length of a preset time period, and the inventory turnover days are negatively correlated with the historical purchase volume of the target product in the preset time period before the current observation time.

10. The inventory control method according to claim 1, wherein: The inventory influencing factors for determining the target product at the current observation time include: The average inventory consumed per purchase interval of the target product is determined based on the historical purchase quantity of the target product within a preset time period before the current observation time and the historical purchase times of the target product within the preset time period.

11. An inventory control device comprising: An acquisition module is configured to acquire a historical purchase quantity sequence of a target product of a target object before an observation time sequence, wherein the observation time sequence includes at least one unit observation time; The first inventory determination module is configured to process the historical purchase quantity sequence to obtain the initial inventory of the target product for each unit observation time in the observation time sequence, including: decomposing the historical purchase quantity sequence according to an empirical mode decomposition algorithm to obtain an eigenmode function sequence; processing the eigenmode function sequence according to an inventory determination model to obtain the initial inventory of the target product in the observation time sequence; An impact factor determination module is configured to determine the inventory impact factor of the target product at the current observation time, wherein the current observation time is a unit observation time in the observation time sequence, and the inventory impact factor of the target product at the current observation time includes the purchase quantity increment index value, inventory turnover days, and the average inventory consumed per purchase interval of the target product at the current observation time; The second inventory determination module is configured to determine the inventory of the target product at the current observation time according to the inventory influencing factor of the target product at the current observation time and the initial inventory of the target product in the observation time series.

12. An inventory control device comprising: Memory; as well as A processor coupled to the memory, wherein the processor is configured to execute the inventory control method according to any one of claims 1 to 10 based on instructions stored in the memory.

13. A computer-readable storage medium having computer program instructions stored thereon, wherein the instructions, when executed by a processor, implement the inventory control method according to any one of claims 1 to 10.

Images