Product sales forecasting method and related equipment

By detecting sales errors and calculating corrections within a preset time period, the accuracy of existing sales forecasting models in the face of data changes is solved, enabling more accurate sales forecasting and inventory management.

CN113723989BActive Publication Date: 2024-11-08SHANSHU TECH (BEIJING) CO LTD +4
View PDF 0 Cites 0 Cited by

Patent Information

Application Number
CN202110911699.7
Authority / Receiving Office
CN · China
Patent Type
Patents(China)
Current Assignee / Owner
Filing Date
2021-08-10
Publication Date
2024-11-08
Estimated Expiration
2041-08-10

AI Technical Summary

Technical Problem

Existing sales forecasting models are not accurate enough for certain product categories when faced with changes in data patterns. Furthermore, the models have long training times and are difficult to adapt to short-term sales fluctuations, leading to the accumulation of errors.

Method used

By detecting whether there are errors in multiple prediction cycles of the target product within a preset time period, the correction amount is calculated and corrected. The correction amount is determined by using the median or weighted average absolute error percentage, and the threshold and correction cycle are set to adapt to changes in sales volume.

Benefits of technology

This avoids the impact of short-term sales fluctuations on forecast results, improves the accuracy and flexibility of sales forecasts, adapts to the sales characteristics of different products, and ensures reasonable inventory levels.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure CN113723989B_ABST
    Figure CN113723989B_ABST
Patent Text Reader

Abstract

The present invention discloses a product sales forecasting method and related equipment. The method comprises: detecting whether there are errors in multiple forecasting cycles of a target product in a preset time period, wherein the errors are used to characterize the deviation between the actual sales and the predicted sales in multiple forecasting cycles; if so, calculating the correction amount of the target product in the preset time period, and correcting the sales forecast result of the target product based on the correction amount. The above method can avoid the impact of short-term sales fluctuations on the sales forecast result, and can comprehensively consider the forecast errors within a period of time to make more accurate corrections to the sales forecast result.
Need to check novelty before this filing date? Find Prior Art

Description

Technical Field

[0001] The present invention relates to the field of product sales, and more specifically, to a product sales forecasting method and related equipment. Background Art

[0002] The current sales industry attaches great importance to sales forecasting, and the use of big data technologies such as machine learning and deep learning is becoming increasingly common. The so-called big data refers to data scenarios with high data sample size and big data dimensions. All data samples are modeled together during prediction. Since the model takes into account the commonalities of the prediction objects, it can improve the overall prediction accuracy. However, the prediction accuracy for individual categories of goods may be insufficient, and the training time of such complex models is long. They also predict the original historical data. Once the data patterns change and the model is not retrained, the existing model is very likely to have persistently high or low predictions for individual prediction objects.

[0003] In view of this, in order to accurately predict sales volume, the traditional correction method is to add a fixed value or multiply an adjustment coefficient based on the current error. However, when faced with comprehensive changes over a period of time, such as volatility changes, relying solely on fixed values ​​or adjustment coefficients will obviously cause the error to continue to be large. Summary of the invention

[0004] A series of simplified concepts are introduced in the Summary of the Invention, which will be further described in detail in the Detailed Description of the Invention. The Summary of the Invention does not mean to attempt to define the key features and essential technical features of the claimed technical solution, nor does it mean to attempt to determine the scope of protection of the claimed technical solution.

[0005] In order to at least partially solve the above problems, in a first aspect, the present invention provides a product sales forecasting method, the method comprising:

[0006] Detect whether there is an error in multiple forecast cycles of the target product in a preset time period, the above error is used to indicate that there is a deviation value between the actual sales volume and the forecast sales volume in the above multiple forecast cycles;

[0007] If so, calculate the correction amount of the target product in the preset time period, and correct the sales forecast result of the target product based on the correction amount.

[0008] Optionally, the above-mentioned detecting whether there is an error in a plurality of prediction cycles of a preset time period for a target product includes:

[0009] Detect whether the error of multiple prediction cycles of the target product in a preset time period exceeds a set threshold, wherein the above-mentioned set threshold is set by the user.

[0010] Optionally, the calculating of the correction amount of the target product in the preset time period includes:

[0011] The median of the errors of multiple prediction cycles in the above preset time period is selected as the correction amount.

[0012] Optionally, the above method further includes:

[0013] Calculate the weighted average absolute error percentage of multiple preset time periods in the preset time period;

[0014] The preset time period corresponding to the minimum weighted mean absolute error percentage is selected as the preset time period.

[0015] Optionally, the target product is a product corresponding to at least one dimension, and the dimension is determined based on the product category.

[0016] Optionally, the target products include non-long-tail products, which are products whose actual sales volume exceeds a preset threshold.

[0017] Optionally, the above method further includes:

[0018] After the sales forecast result of the target product is corrected for a correction period, the target product is again tested for the errors in the multiple forecast periods in the preset time period, wherein the correction period is set by the user;

[0019] If so, the correction amount of the target product in the preset time period is calculated again, and the sales forecast result of the target product is corrected based on the correction amount.

[0020] In a second aspect, the present invention further provides a product sales forecasting device, comprising:

[0021] A detection unit, used to detect whether there is an error in multiple prediction cycles of a target product in a preset time period;

[0022] The correction unit is used to calculate the correction amount of the above-mentioned target product in the above-mentioned preset time period, and to correct the sales forecast result of the target product based on the above-mentioned correction amount.

[0023] In a third aspect, an electronic device comprises: a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor is configured to implement the steps of the product sales forecasting method of any one of the first aspects described above when executing the computer program stored in the memory.

[0024] In a fourth aspect, the present invention further proposes a computer-readable storage medium having a computer program stored thereon, and when the computer program is executed by a processor, the product sales forecasting method according to any one of the above items in the first aspect is implemented.

[0025] In summary, it is possible to detect whether there are errors in multiple forecast cycles of the target product in a preset time period, rather than making adjustments based on errors within one cycle. This avoids the impact of short-term sales fluctuations on the accuracy of sales forecast results. When it is determined that the sales forecast results need to be modified, the errors of multiple cycles in the preset time period are comprehensively considered for correction, which can better reflect the trend of errors in the sales forecast results during this period, so as to make more accurate modifications to the product sales forecast. The above method can avoid the impact of short-term sales fluctuations on sales forecast results, and can comprehensively consider errors within a period of time to make more accurate corrections to sales forecast results.

[0026] The product sales forecasting method of the present invention, and other advantages, objectives and features of the present invention will be reflected in part through the following description, and in part will be understood by technicians in this field through research and practice of the present invention. BRIEF DESCRIPTION OF THE DRAWINGS

[0027] Various other advantages and benefits will become apparent to those of ordinary skill in the art by reading the detailed description of the preferred embodiments below. The accompanying drawings are only for the purpose of illustrating the preferred embodiments and are not to be considered as limiting the present specification. Also, the same reference symbols are used throughout the accompanying drawings to represent the same components. In the accompanying drawings:

[0028] Figure 1 A possible product sales forecasting method flow chart provided in an embodiment of the present application;

[0029] Figure 2 A schematic diagram of a possible product sales forecasting device structure provided in an embodiment of the present application;

[0030] Figure 3 A schematic diagram of a possible product sales forecasting electronic device structure provided in an embodiment of the present application. DETAILED DESCRIPTION

[0031] The embodiments of the present application provide a product sales forecasting method and related equipment, which comprehensively considers the errors within a period of time to make more accurate corrections to the sales forecast results.

[0032] The terms "first", "second", "third", "fourth", etc. (if any) in the specification and claims of the present application and the above-mentioned drawings are used to distinguish similar objects, and are not necessarily used to describe a specific order or sequence. It should be understood that the data used in this way can be interchangeable where appropriate, so that the embodiments described herein can be implemented in an order other than that illustrated or described herein. In addition, the terms "including" and "having" and any of their variations are intended to cover non-exclusive inclusions, for example, a process, method, system, product or device that includes a series of steps or units is not necessarily limited to those steps or units that are clearly listed, but may include other steps or units that are not clearly listed or inherent to these processes, methods, products or devices. The technical solutions in the embodiments of the present application will be clearly and completely described below in conjunction with the drawings in the embodiments of the present application. Obviously, the described embodiments are only part of the embodiments of the present application, rather than all of the embodiments.

[0033] See also Figure 1 , which is a possible product sales forecasting method flow chart provided in an embodiment of the present application, and may specifically include:

[0034] S110, detecting whether there is an error in multiple forecasting cycles of a target product in a preset time period, wherein the error is used to indicate a deviation between the actual sales volume and the forecasted sales volume in the multiple forecasting cycles;

[0035] Specifically, the predicted sales volume of multiple prediction cycles of a preset time period of the target product is obtained, and the actual sales volume of the target product within the preset period is obtained. The difference between the predicted sales volume and the actual sales volume is the prediction error of the target product within the preset period. For example, in actual applications, when it is found that the deviation of a certain product within a certain time period is always positive or negative, that is, it is found that the predicted sales volume of a certain product is always higher than the actual sales volume, or is always lower than the actual sales volume within a period of time, then it can be determined that the original sales volume prediction method has an inaccurate prediction phenomenon and needs to be corrected;

[0036] S120: If yes, calculate the correction amount of the target product in the preset time period, and correct the sales forecast result of the target product based on the correction amount.

[0037] Specifically, if there is an error, a correction amount is calculated based on the deviation between the actual sales volume and the predicted sales volume in multiple forecast cycles in a preset time period, and the sales volume forecast result of the target product is corrected based on the correction amount;

[0038] In summary, the deviation between the predicted sales volume and the actual sales volume in multiple cycles within the preset time period can be detected to avoid the impact of short-term sales fluctuations on the sales forecast results, and the errors of multiple forecast cycles within the preset time period can be comprehensively considered to make more accurate corrections to the sales forecast results.

[0039] In some examples, it is detected whether the errors of multiple prediction cycles of the target product in a preset time period exceed a set threshold, where the set threshold is set by a user.

[0040] Specifically, the target product is mineral water, the preset time period is one month, the prediction cycle is one week, the prediction error in the first week is 10 bottles, the prediction error in the second week is 8 bottles, the prediction error in the third week is 7 bottles, and the error in the fourth week is 9 bottles. The threshold set by the user is 100 bottles. At this time, although the error continues to be positive, the sales forecast result is not corrected. Setting thresholds can give users more choices. Different thresholds can be set for different types of goods. A smaller threshold can be set for goods with high prices that avoid large inventories, and a larger threshold can be set for products with low prices and large sales fluctuations.

[0041] In summary, by using the threshold setting method, users can set different thresholds for different categories of products, enriching the flexibility of prediction.

[0042] In some examples, calculating the correction amount of the target product in the preset time period includes:

[0043] The median of the errors of multiple prediction cycles in the above preset time period is selected as the correction amount.

[0044] Specifically, the target product is mineral water. The predicted sales volume in the past week was 5 boxes, 5 boxes, 5 boxes, 5 boxes, 5 boxes, 5 boxes, and 5 boxes. However, since the weather this year is hotter than the same period last year, customers' demand for mineral water is higher than the same period last year. The actual sales volume was 10 boxes, 12 boxes, 13 boxes, 10 boxes, 14 boxes, 16 boxes, and 15 boxes respectively. If the original result is still used for estimation, insufficient inventory may affect sales. The forecast errors are calculated according to the above method as 5 boxes, 7 boxes, 8 boxes, 5 boxes, 9 boxes, 11 boxes, and 10 boxes. The median of the forecast error is 8 boxes. Then, 8 boxes are used as the correction amount for the target product mineral water to correct the original forecast result. The corrected forecast result can take into account the recent weather factor of rising temperature and make an accurate forecast of the demand for mineral water. Moreover, the median can well reflect the sales trend of the product within a week. Using the median error as the correction amount will not be too large, causing the forecast result to have a reverse deviation due to excessive correction, nor will it be too small to achieve the correction effect.

[0045] In summary, the median error can well characterize the prediction error within the preset period, and the median error can be used as a correction amount to correct the prediction results.

[0046] In some examples, the method further includes:

[0047] Calculate the weighted average absolute error percentage of multiple preset time periods in the preset time period;

[0048] The preset time period corresponding to the minimum weighted mean absolute error percentage is selected as the preset time period.

[0049] Specifically, Weighted Mean Absolute Percentage Error (WMAPE)

[0050]

[0051] In the above formula, WMAPE represents the weighted mean absolute error percentage, y' represents the predicted value, y represents the true value, and n represents the preset time period. For example, the preset time period can be 7 days, 10 days, and 15 days. The prediction cycle is 1 day, then the n values ​​of the three time periods correspond to 7, 10, and 15 respectively. According to the above formula, WMAPE is calculated. If the WMAPE value is the smallest when n is 10, then 10 days is selected as the preset time period. Determining the preset time period in this way can make the prediction result more accurate.

[0052] In summary, the preset time period is determined by calculating the WMAPE value, so that the optimal preset time period is determined, and the prediction result can be more accurate.

[0053] In some examples, the target product is a product corresponding to at least one dimension, and the dimension is determined based on the product category.

[0054] Optionally, the target product is a product corresponding to at least one dimension, and the dimension is determined based on the product category.

[0055] Specifically, the target product can be set as beverages, and beverages include cola, juice, tea and other categories. The target product can also be specific to cola, or even to a specific brand of cola. The selection of the target product can be free.

[0056] In summary, this production and sales volume forecasting method can freely select product types according to user needs. This method is flexible and convenient and can be used in different forecasting scenarios.

[0057] Optionally, the target products include non-long-tail products, which are products whose actual sales volume exceeds a preset threshold.

[0058] Specifically, long-tail products refer to products with low sales but a wide variety, while non-long-tail products are the opposite, referring to products with large sales. When sales are too small, they cannot be accurately predicted due to their large sales volatility, and if they are added to the target products, the total volume may be greatly deviated. Users can set preset thresholds to prevent long-tail products from being included in the forecast results and affecting the results.

[0059] In summary, thresholds are set based on actual sales to prevent products with low sales but a wide variety from affecting the authenticity of product prediction results.

[0060] In some examples, the method further includes:

[0061] After the sales forecast result of the target product is corrected for a correction period, the target product is again tested for the errors in the multiple forecast periods in the preset time period, wherein the correction period is set by the user;

[0062] If so, the correction amount of the target product in the preset time period is calculated again, and the sales forecast result of the target product is corrected based on the correction amount.

[0063] Specifically, the user can set the correction cycle to one month. One month after the current forecast result is corrected, the sales forecast result will be corrected again using the above correction method. The cycle setting can be formulated according to the sales characteristics of the product. For example, moon cakes and rice dumplings, which are festive products, can be set to a quarter or even half a year because they are sold more during the festival months of each year. For products such as umbrellas that are related to recent weather and seasons, the correction cycle can be shortened to allow for timely modification of the forecast result to ensure sufficient supply and avoid excessive inventory.

[0064] In summary, users can set the correction cycle according to the characteristics of the products to ensure that the product forecast results are updated in a timely manner in combination with their own product characteristics, and to ensure that the supply of products in each category is sufficient and the inventory is appropriate.

[0065] See also Figure 2 , an embodiment of the product sales prediction device in the embodiment of the present application may include:

[0066] A detection unit 21, used to detect whether there is an error in multiple prediction cycles of the target product in a preset time period;

[0067] The correction unit 22 is used to calculate the correction amount of the above-mentioned target product in the above-mentioned preset time period, and correct the sales forecast result of the target product based on the above-mentioned correction amount.

[0068] See also Figure 3 , Figure 3A schematic diagram of an embodiment of an electronic device provided in an embodiment of the present application.

[0069] like Figure 3 As shown, an embodiment of the present application also provides an electronic device 300, including a memory 310, a processor 320, and a computer program 311 stored in the memory 320 and executable on the processor, and when the processor 320 executes the computer program 311, the steps of any of the above-mentioned product sales forecasting methods are implemented.

[0070] Since the electronic device introduced in this embodiment is a device used to implement a product sales forecasting device in the embodiment of the present application, based on the method introduced in the embodiment of the present application, technical personnel in this field can understand the specific implementation mode of the electronic device of this embodiment and its various variations. Therefore, how the electronic device implements the method in the embodiment of the present application is not introduced in detail here. As long as the equipment used by technical personnel in this field to implement the method in the embodiment of the present application is within the scope of protection of this application.

[0071] In the specific implementation process, when the computer program 311 is executed by the processor, it can achieve Figure 1 Any implementation manner in the corresponding embodiments.

[0072] It should be noted that in the above embodiments, the description of each embodiment has its own emphasis, and for parts that are not described in detail in a certain embodiment, reference can be made to the relevant descriptions of other embodiments.

[0073] Those skilled in the art will appreciate that the embodiments of the present application may be provided as methods, systems, or computer program products. Therefore, the present application may adopt the form of a complete hardware embodiment, a complete software embodiment, or an embodiment in combination with software and hardware. Moreover, the present application may adopt the form of a computer program product implemented in one or more computer-usable storage media (including but not limited to disk storage, CD-ROM, optical storage, etc.) that include computer-usable program code.

[0074] The present application is described with reference to the flowcharts and / or block diagrams of the methods, devices (systems), and computer program products according to the embodiments of the present application. It should be understood that each process and / or box in the flowchart and / or block diagram, as well as the combination of the processes and / or boxes in the flowchart and / or block diagram, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, a special-purpose computer, an embedded computer, or other programmable data processing device to generate a machine, so that the instructions executed by the processor of the computer or other programmable data processing device generate instructions for implementing the processes in the flowchart and / or block diagram. Figure 1 A process or multiple processes and / or boxes Figure 1A device that provides the functions specified in a block or multiple blocks.

[0075] These computer program instructions may also be stored in a computer readable memory capable of directing a computer or other programmable data processing device to operate in a specific manner, so that the instructions stored in the computer readable memory produce an article of manufacture including an instruction device, which implements the process Figure 1 A process or multiple processes and / or boxes Figure 1 A function specified in one or more boxes.

[0076] These computer program instructions can also be loaded onto a computer or other programmable data processing device so that a series of operating steps are executed on the computer or other programmable device to produce a computer-implemented process, thereby providing instructions for implementing the process in the computer or other programmable device. Figure 1 A process or multiple processes and / or boxes Figure 1 The steps for the functions specified in one or more boxes.

[0077] The present application also provides a computer program product, which includes computer software instructions. When the computer software instructions are executed on a processing device, the processing device is caused to execute the following Figure 1 This corresponds to the process of sales volume correction in the embodiment.

[0078] The computer program product includes one or more computer instructions. When the computer program instructions are loaded and executed on the computer, the process or function according to the embodiment of the present application is generated in whole or in part. The computer can be a general-purpose computer, a special-purpose computer, a computer network, or other programmable devices. The computer instructions can be stored in a computer-readable storage medium, or transmitted from one computer-readable storage medium to another computer-readable storage medium. For example, the computer instructions can be transmitted from a website site, a computer, a server or a data center by wired (e.g., coaxial cable, optical fiber, digital subscriber line (digital subscriber line, DSL)) or wireless (e.g., infrared, wireless, microwave, etc.) mode to another website site, computer, server or data center. The computer-readable storage medium can be any available medium that a computer can store or a data storage device such as a server or a data center that includes one or more available media integration. The available medium can be a magnetic medium, (e.g., a floppy disk, a hard disk, a tape), an optical medium (e.g., a DVD), or a semiconductor medium (e.g., a solid state drive (SSD)), etc.

[0079] Those skilled in the art can clearly understand that, for the convenience and brevity of description, the specific working processes of the systems, devices and units described above can refer to the corresponding processes in the aforementioned method embodiments and will not be repeated here.

[0080] In the several embodiments provided in the present application, it should be understood that the disclosed systems, devices and methods can be implemented in other ways. For example, the device embodiments described above are only schematic. For example, the division of units is only a logical function division. There may be other division methods in actual implementation. For example, multiple units or components can be combined or integrated into another system, or some features can be ignored or not executed. Another point is that the mutual coupling or direct coupling or communication connection shown or discussed can be an indirect coupling or communication connection through some interfaces, devices or units, which can be electrical, mechanical or other forms.

[0081] The units described as separate components may or may not be physically separated, and the components shown as units may or may not be physical units, that is, they may be located in one place or distributed on multiple network units. Some or all of the units may be selected according to actual needs to achieve the purpose of the solution of this embodiment.

[0082] In addition, each functional unit in each embodiment of the present application may be integrated into one processing unit, or each unit may exist physically separately, or two or more units may be integrated into one unit. The above-mentioned integrated unit may be implemented in the form of hardware or in the form of software functional units.

[0083] If the integrated unit is implemented in the form of a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the present application is essentially or the part that contributes to the prior art or all or part of the technical solution can be embodied in the form of a software product, and the computer software product is stored in a storage medium, including a number of instructions to enable a computer device (which can be a personal computer, a server, or a network device, etc.) to perform all or part of the steps of the various embodiments of the present application. The aforementioned storage medium includes: U disk, mobile hard disk, read-only memory (Read-Only Memory, ROM), random access memory (Random Access Memory, RAM), disk or optical disk and other media that can store program codes.

[0084] The above embodiments are only used to illustrate the technical solutions of the present application, rather than to limit them. Although the present application has been described in detail with reference to the aforementioned embodiments, a person skilled in the art should understand that the technical solutions described in the aforementioned embodiments may still be modified, or some of the technical features may be replaced by equivalents. However, these modifications or replacements do not deviate the essence of the corresponding technical solutions from the spirit and scope of the technical solutions of the embodiments of the present application.

Claims

1. A product sales forecasting method, characterized in that: include: Detecting whether there is an error in multiple forecasting cycles of a target product in a preset time period, wherein the error is used to characterize the deviation between the actual sales volume and the forecasted sales volume in the multiple forecasting cycles; If so, calculating the correction amount of the target product in the preset time period, and correcting the sales forecast result of the target product based on the correction amount; The calculating the correction amount of the target product in the preset time period includes: Selecting the median of the errors of multiple prediction cycles in the preset time period as the correction amount; Also includes: Calculating the weighted average absolute error percentage of multiple preset time periods in the preset time period; Selecting the preset time period corresponding to the minimum weighted mean absolute error percentage as the preset time period; The detecting whether there is an error in a plurality of prediction cycles of a preset time period for a target product comprises: Detecting whether the error of multiple forecast cycles of the target product in a preset time period exceeds a set threshold, wherein the set threshold is set by the user; The target product is a product corresponding to at least one dimension, and the dimension is determined based on the product category; The target products include non-long-tail products, which are products whose actual sales volume exceeds a preset threshold; After the sales forecast result of the target product is corrected for a correction period, the target product is again detected to see whether the error exists in the multiple forecast periods of the preset time period, wherein the correction period is set by the user; If so, the correction amount of the target product in the preset time period is calculated again, and the sales forecast result of the target product is corrected based on the correction amount.

2. A product sales forecasting device, characterized in that: include: A detection unit, used to detect whether there is an error in multiple prediction cycles of a target product in a preset time period; A correction unit, configured to calculate a correction amount of the target product in the preset time period, and to correct the sales forecast result of the target product based on the correction amount; The calculating the correction amount of the target product in the preset time period includes: Selecting the median of the errors of multiple prediction cycles in the preset time period as the correction amount; Also includes: Calculating the weighted average absolute error percentage of multiple preset time periods in the preset time period; Selecting the preset time period corresponding to the minimum weighted mean absolute error percentage as the preset time period; The detecting whether there is an error in a plurality of prediction cycles of a preset time period for a target product comprises: Detecting whether the error of multiple forecast cycles of the target product in a preset time period exceeds a set threshold, wherein the set threshold is set by the user; The target product is a product corresponding to at least one dimension, and the dimension is determined based on the product category; The target products include non-long-tail products, which are products whose actual sales volume exceeds a preset threshold; After the sales forecast result of the target product is corrected for a correction period, the target product is again detected to see whether the error exists in the multiple forecast periods of the preset time period, wherein the correction period is set by the user; If so, the correction amount of the target product in the preset time period is calculated again, and the sales forecast result of the target product is corrected based on the correction amount.

3. An electronic device, comprising a memory and a processor, characterized in that: The processor is used to implement the steps of the product sales forecasting method as claimed in claim 1 when executing the computer program stored in the memory.

4. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, the steps of the product sales forecasting method according to claim 1 are implemented.