Sales volume dynamic factor intelligent prediction and analysis system and method

Abstract

The invention relates to the technical field of sales volume prediction, in particular to a sales volume dynamic factor intelligent prediction and analysis system and method, and the method comprises the steps: obtaining a to-be-marketed product and marketing budget information; matching a historical day-by-day sales data curve of the to-be-marketed product in a database according to the to-be-marketed product; intercepting significant sales sub-curves in the historical day-by-day sales data curve of the to-be-marketed product as a significant sales sub-curve set of the to-be-marketed product; calculating the similarity between the historical day-by-day sales data curve of each other product and the significant sales sub-curve set of the to-be-marketed product; screening out products of which the similarity of the historical day-by-day sales data curves reaches a preset similarity to generate a standard curve set; taking the historical day-by-day sales data curve with the maximum final reference degree in the standard curve set as a reference sales curve; and generating a recommendation strategy. The method and the device have the effects of improving the accuracy of predicting the sales volume change of product marketing with insufficient data accumulation and recommending a more appropriate marketing scheme.

Description

Technical Field

[0001] The present invention relates to the technical field of sales forecasting, and in particular to a system and method for intelligent forecasting and analyzing sales dynamic factors. Background Art

[0002] In the current business environment, accurately predicting the future sales of products is crucial to developing effective marketing strategies. However, for some new products or products with insufficient data accumulation, their historical sales data may not be sufficient to support detailed analysis and prediction.

[0003] Specifically, product marketing analysis mainly relies on the historical sales data of the product to be marketed. This data usually includes key information such as daily sales records, seasonal changes, and holiday impacts. By analyzing this data, companies can understand product sales trends, seasonal fluctuations, and the impact of holidays on sales, and thus formulate corresponding marketing strategies. However, when the historical sales data of the product to be marketed is insufficient, the prediction results of this analysis method may be greatly biased. Summary of the invention

[0004] In order to improve the accuracy of the prediction of sales volume changes for products with insufficient data accumulation and recommend more appropriate marketing plans, the present application provides a sales volume dynamic factor intelligent prediction and analysis system and method.

[0005] The above-mentioned invention objective of the present application is achieved through the following technical solutions: A sales dynamic factor intelligent prediction and analysis method, comprising: Obtain information on products to be marketed and marketing budget; Matching the historical daily sales data curve of the product to be marketed in the database according to the product to be marketed; If the time span of the historical daily sales data curve of the product to be marketed meets the preset condition, the historical daily sales data curves of other products in the database whose time span reaches the preset length are screened out; intercepting a significant sales volume sub-curve from the historical daily sales data curve of the product to be marketed as a significant sales volume sub-curve set of the product to be marketed; Calculate the similarity between the historical daily sales data curve of each other product and the significant sales sub-curve set of the product to be marketed; Filter out products whose historical daily sales data curves have similarities reaching a preset similarity to generate a qualified curve set; A reference marketing holiday weight value is obtained based on the ratio of the sales volume during marketing holidays to the average daily sales volume during non-marketing holidays in the historical daily sales data curve of the product to be marketed; a reference quarterly weight value is obtained based on the ratio of the sales volume of each quarter to the sales volume of the quarter with the lowest sales volume in the historical daily sales data curve of the product to be marketed; Calculate the reference degree of each curve in the target curve set based on the marketing holiday weight value and the reference quarter weight value of each quarter; Calculate the marketing holiday weight value of each curve in the target curve set and the quarterly weight value of each quarter; Adjusting the reference degree of each curve based on the reference marketing holiday weight value, the reference quarterly weight value, the marketing holiday weight value of each curve, and the quarterly weight value of each quarter to obtain the final reference degree of each curve; The historical daily sales data curve with the largest final reference degree in the target curve set is used as the reference sales curve; A recommendation strategy is generated based on the marketing budget information and the reference sales curve.

[0006] In a preferred example, the present application can be further configured to: calculate the similarity between the historical daily sales data curve of each other product and the significant sales volume sub-curve set of the product to be marketed, including: Count the curve segments in the historical daily sales data curve whose similarity with any element in the significant sales sub-curve set of the product to be marketed reaches a preset curve similarity, traverse all elements in the significant sales sub-curve set of the product to be marketed, and take the ratio of the counting result to the time span of the historical daily sales data curve as the similarity of the historical daily sales data curve.

[0007] In a preferred example, the present application can be further configured as follows: based on the marketing holiday weight value and the reference quarter weight value of each quarter, the reference degree of each curve in the target curve set is calculated, including: Determine the season to which the date of the curve segment in the historical daily sales data curve that reaches the preset curve similarity belongs, and determine whether the date of the curve segment in the historical daily sales data curve that reaches the preset curve similarity belongs is a marketing holiday; If the date of the curve segment is a marketing holiday, the sub-reference degree of the curve segment is calculated according to the marketing holiday weight value and the similarity of the curve segment; If the date of the curve segment is not a marketing holiday, the sub-reference degree of the curve segment is calculated according to the reference quarter weight value corresponding to the season to which the date of the curve segment belongs and the similarity of the curve segment; The sum of the sub-reference degrees of all curve segments of the historical daily sales data curve is calculated as the reference degree of the historical daily sales data curve.

[0008] In a preferred example, the present application can be further configured as follows: adjusting the reference degree of each curve based on the reference marketing holiday weight value, the reference quarterly weight value, the marketing holiday weight value of each curve, and the quarterly weight value of each quarter to obtain the final reference degree of each curve, including: The final reference degree of each curve is calculated using the following formula: , Among them, P is the final reference degree, is the reference degree, H is the reference marketing holiday weight value, is the maximum value of the reference quarter weight, h is the reference quarter weight, It is the maximum value of the quarterly weight value of each quarter.

[0009] The second object of the invention is achieved by the following technical solutions: A sales dynamic factor intelligent prediction and analysis system, comprising: The acquisition module is used to obtain the information of the products to be marketed and the marketing budget; A matching module, used for matching the historical daily sales data curve of the product to be marketed in the database according to the product to be marketed; A first screening module is used to screen out historical daily sales data curves of other products in the database whose time span reaches a preset length if the time span of the historical daily sales data curve of the product to be marketed meets a preset condition; An interception module, used for intercepting a significant sales volume sub-curve in the historical daily sales data curve of the product to be marketed as a significant sales volume sub-curve set of the product to be marketed; A similarity calculation module, used to calculate the similarity between the historical daily sales data curves of each other product and the significant sales sub-curve set of the product to be marketed; The second screening module is used to screen out products whose historical daily sales data curves have similarities reaching a preset similarity to generate a qualified curve set; The first weight value calculation module is used to obtain a reference marketing holiday weight value based on the ratio of the sales volume during marketing holidays to the average daily sales volume during non-marketing holidays in the historical daily sales data curve of the product to be marketed; and obtain a reference quarterly weight value for each quarter based on the ratio of the sales volume of each quarter to the sales volume of the quarter with the lowest sales volume in the historical daily sales data curve of the product to be marketed; A reference degree calculation module is used to calculate the reference degree of each curve in the target curve set based on the marketing holiday weight value and the reference quarter weight value of each quarter; The second weight value calculation module is used to calculate the marketing holiday weight value of each curve in the target curve set and the quarterly weight value of each quarter; A reference adjustment module, used to adjust the reference of each curve based on the reference marketing holiday weight value, the reference quarterly weight value, the marketing holiday weight value of each curve, and the quarterly weight value of each quarter to obtain a final reference of each curve; A module is selected to use the historical daily sales data curve with the largest final reference degree in the target curve set as a reference sales curve; A recommendation strategy generation module is used to generate a recommendation strategy based on the marketing budget information and the reference sales curve.

[0010] In a preferred example, the present application can be further configured as: a similarity calculation module, including: The sub-similarity calculation summary unit is used to count the curve segments in the historical daily sales data curve whose similarity with any element in the significant sales sub-curve set of the product to be marketed reaches a preset curve similarity, traverse all elements in the significant sales sub-curve set of the product to be marketed, and take the ratio of the counting result to the time span of the historical daily sales data curve as the similarity of the historical daily sales data curve.

[0011] In a preferred example, the present application can be further configured as: a reference degree calculation module, including: A judgment unit, used to judge the season to which the date of the curve segment in the historical daily sales data curve that reaches the preset curve similarity belongs, and to judge whether the date of the curve segment in the historical daily sales data curve that reaches the preset curve similarity belongs is a marketing holiday; A first sub-reference degree calculation unit, configured to calculate the sub-reference degree of the curve segment according to the marketing holiday weight value and the similarity of the curve segment if the date of the curve segment is a marketing holiday; A second sub-reference degree calculation unit is used to calculate the sub-reference degree of the curve segment according to the reference quarter weight value corresponding to the season to which the date of the curve segment belongs and the similarity of the curve segment if the date of the curve segment is not a marketing holiday; The summary calculation unit is used to calculate the sum of the sub-reference degrees of all curve segments of the historical daily sales data curve as the reference degree of the historical daily sales data curve.

[0012] In a preferred example, the present application can be further configured as: a reference adjustment module, including: The final reference degree of each curve is calculated using the following formula: , Among them, P is the final reference degree, is the reference degree, H is the reference marketing holiday weight value, is the maximum value of the reference quarter weight, h is the reference quarter weight, It is the maximum value of the quarterly weight value of each quarter.

[0013] In summary, the present application includes at least one of the following beneficial technical effects: 1. By obtaining detailed information and historical sales data of the products to be marketed, and matching and calculating similarity with the historical sales data of other products in the database, it is possible to accurately find products with similar sales trends to the products to be marketed; improve the accuracy of predicting changes in marketing sales of products with insufficient data accumulation, and recommend more appropriate marketing plans. In addition, by using significant sales sub-curves and similarity analysis, it is possible to predict the possible sales trends of the products to be marketed in the future, provide data support for the formulation of marketing strategies, improve the accuracy of predicting changes in marketing sales of products with insufficient data accumulation, and recommend more appropriate marketing plans; through in-depth analysis of historical sales data, it is possible to identify the best sales period and potential market opportunities for the products to be marketed, so as to formulate more targeted marketing strategies. The recommended marketing strategy can accurately locate the sales peak period and potential growth area based on the significant sales sub-curve and marketing budget information, and improve the accuracy and effectiveness of marketing activities.

[0014] 2. Based on the marketing budget information provided by the user and the cost of each promotion, determine the number of promotions that can be supported. In the reference sales curve, divide it into multiple reference sales sub-curves with a span of years. Superimpose multiple reference sales sub-curves to obtain an integrated annual sales curve. According to significant sales, extract multiple time intervals and sort them based on sales volume. Based on the number of promotions, select several top time intervals to obtain a recommended plan. BRIEF DESCRIPTION OF THE DRAWINGS

[0015] Figure 1 It is a flowchart for realizing the method for intelligent prediction and analysis of sales dynamic factors in one embodiment of the present application;

[0016] Figure 2 This is a schematic diagram of the module connections of the sales dynamic factor intelligent prediction and analysis system in one embodiment of the present application. DETAILED DESCRIPTION

[0017] The following is a description of exemplary embodiments of the present application in conjunction with the accompanying drawings, including various details of the embodiments of the present application to facilitate understanding, which should be considered as merely exemplary. Therefore, it should be recognized by those of ordinary skill in the art that various changes and modifications can be made to the embodiments described herein without departing from the scope and spirit of the present application. Similarly, for the sake of clarity and conciseness, the description of well-known functions and structures is omitted in the following description.

[0018] It should be noted that the terms "first", "second", etc. in the present invention 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 interchanged where appropriate, so that the embodiments of the present disclosure described herein can be implemented in an order other than those illustrated or described herein. The embodiments described in the following exemplary embodiments do not represent all embodiments consistent with the present disclosure.

[0019] In addition, the term "and / or" in this article is only a description of the association relationship of associated objects, indicating that there can be three relationships. For example, A and / or B can represent: A exists alone, A and B exist at the same time, and B exists alone. In addition, the character " / " in this article, unless otherwise specified, generally means that the associated objects before and after are in an "or" relationship.

[0020] Figure 1 is a flowchart of the implementation of the sales dynamic factor intelligent prediction and analysis method in one embodiment of the present application, such as Figure 1 As shown, the sales dynamic factor intelligent prediction and analysis method includes: S1. Obtain information on products to be marketed and marketing budget.

[0021] Specifically, the products to be marketed and the marketing budget information are provided by the customer. The information on the products to be marketed mainly includes basic attributes, including the product name, type (such as physical goods, digital content, software services, etc.), functional features, etc. The marketing budget information involves the optimal amount of budget required to implement various marketing strategies, as well as the budget allocation between various marketing links and various marketing methods, sales promotion expenses, and promotion expenses. In this application, the marketing budget information mainly refers to the platform promotion expenses.

[0022] S2. Matching the historical daily sales data curve of the product to be marketed in the database according to the product to be marketed.

[0023] Specifically, the database obtains detailed sales data from official or third-party authorized databases on e-commerce platforms (such as Amazon, Alibaba, etc.), and obtains historical daily sales data through the backend management system or API interface to construct a historical daily sales data curve for each product in the database.

[0024] S3. If the time span of the historical daily sales data curve of the product to be marketed meets the preset condition, the historical daily sales data curves of other products in the database whose time span reaches the preset length are screened out; Among them, satisfying the preset conditions means that the time span of the historical daily sales data curve of the product to be marketed is within a preset interval, such as an interval less than one year and more than half a year, or an interval less than two years and more than half a year. The specific setting can be based on the data time length that cannot meet the actual forecasting and analysis needs in actual applications; the preset length is set in advance, for example, 3 years.

[0025] S4. Extracting a significant sales volume sub-curve from the historical daily sales data curve of the product to be marketed as a significant sales volume sub-curve set of the product to be marketed.

[0026] A significant sales sub-curve means that the sales details in a certain time interval of the curve exceed those in other time intervals. This can be done manually or by marking the intervals of the historical daily sales data curve with a rectangular marking box, marking the time intervals with non-significant sales, and taking the curve portion of the interval between two non-significant sales intervals as the significant sales sub-curve.

[0027] S5. Calculate the similarity between the historical daily sales data curves of each other product and the significant sales sub-curve set of the product to be marketed.

[0028] Count the curve segments in the historical daily sales data curve whose similarity with any element in the significant sales sub-curve set of the product to be marketed reaches the preset curve similarity, traverse all elements in the significant sales sub-curve set of the product to be marketed, and take the ratio of the counting result to the time span of the historical daily sales data curve as the similarity of the historical daily sales data curve.

[0029] Specifically, after selecting a sub-curve of the significant sales sub-curve set, based on the time span of the sub-curve, the historical daily sales data curve is sequentially intercepted from the starting date with curve segments of the same time span, and the starting date of each intercepted curve segment is increased by one; then similarity calculation is performed with the selected sub-curve, specifically, the mean square error algorithm, Pearson correlation coefficient algorithm, Euclidean distance, Fréchet distance, edit distance algorithm, cosine similarity, etc. can be used. In one embodiment, the mean square error algorithm is used for calculation. The preset curve similarity can be set to 80%. If there is a curve segment in the historical daily sales data curve whose similarity with the sub-curve reaches 80%, the count is 1, and the number of curve segments in the historical daily sales data curve whose similarity with the sub-curve in the significant sales sub-curve set reaches 80% is counted in turn, and the ratio of the counting result to the time span of the historical daily sales data curve is used as the similarity. It is understandable that by calculating the ratio of the counting result to the time span of the historical daily sales data curve, rather than directly using the counting result as the similarity, the historical daily sales data curves of products with different time spans can be smoothed to avoid data distortion that cannot accurately reflect the similarity of real sales changes. For the time span as the denominator, the specific value is the value of the date difference, that is, the difference between the start date and the end date of the time span.

[0030] S6. Filter out products whose historical daily sales data curves have similarities reaching a preset similarity to generate a qualified curve set.

[0031] Among them, the preset similarity can be set to 0.004.

[0032] S7. A reference marketing holiday weight value is obtained based on the ratio of the sales volume during marketing holidays to the average daily sales volume during non-marketing holidays in the historical daily sales data curve of the product to be marketed; a reference quarterly weight value is obtained based on the ratio of the sales volume of each quarter to the sales volume of the quarter with the lowest sales volume in the historical daily sales data curve of the product to be marketed.

[0033] It is worth mentioning that marketing holidays are not the same as normal holidays. They refer to dates that are usually good for sales, such as Double 11, Double 12, Christmas, National Day, Children's Day, etc., which can be marked in advance by personnel. The ratio of the average daily sales during marketing holidays to the average daily sales during non-marketing holidays can reflect the weight of the product during marketing holidays.

[0034] S8. Calculate the reference degree of each curve in the target curve set based on the marketing holiday weight value and the reference quarter weight value of each quarter.

[0035] S8 specifically includes: S81, determining the season to which the date of the curve segment in the historical daily sales data curve that reaches the preset curve similarity belongs, and determining whether the date of the curve segment in the historical daily sales data curve that reaches the preset curve similarity belongs is a marketing holiday.

[0036] If some dates in the curve segment are marketing holidays, it is determined that the dates of the curve segment are marketing holidays.

[0037] S82. If the date of the curve segment is a marketing holiday, the sub-reference degree of the curve segment is calculated according to the marketing holiday weight value and the similarity of the curve segment.

[0038] Specifically, the product of the marketing holiday weight value and the similarity of the curve segment is used as the sub-reference degree of the curve segment.

[0039] S83. If the date of the curve segment is not a marketing holiday, the sub-reference degree of the curve segment is calculated according to the reference quarter weight value corresponding to the season to which the date of the curve segment belongs and the similarity of the curve segment.

[0040] Specifically, if a curve segment spans two seasons, the sum of the partial values ​​of the reference quarterly weight values ​​of the two seasons is taken as the new reference quarterly weight value of the curve segment according to the proportion of dates, and the size of the partial value is proportional to the number of dates.

[0041] S84. Calculate the sum of the sub-reference degrees of all curve segments of the historical daily sales data curve as the reference degree of the historical daily sales data curve.

[0042] It is understandable that the marketing holiday weight value is usually greater than the reference quarter weight value, indicating that the weight of the holiday is higher than the quarter to distinguish them.

[0043] S9. Calculate the marketing holiday weight value of each curve in the target curve set and the quarterly weight value of each quarter.

[0044] Specifically, the calculation method of the aforementioned reference marketing holiday weight value and reference quarter weight value is also referred to, that is, the marketing holiday weight value of the target curve is obtained based on the ratio of the sales volume during marketing holidays in the historical daily sales data curve to the average daily sales during non-marketing holidays; the reference quarterly weight value of each quarter of the target curve is obtained based on the ratio of the sales volume of each quarter in the historical daily sales data curve to the sales volume of the quarter with the lowest sales volume.

[0045] S10. Adjust the reference degree of each curve based on the reference marketing holiday weight value, the reference quarterly weight value, the marketing holiday weight value of each curve, and the quarterly weight value of each quarter to obtain the final reference degree of each curve.

[0046] Including: using the following formula to calculate the final reference degree of each curve: , Among them, P is the final reference degree, is the reference degree, H is the reference marketing holiday weight value, is the maximum value of the reference quarter weight, h is the reference quarter weight, It is the maximum value of the quarterly weight value of each quarter.

[0047] Through this formula, the curves in the target curve set are finally adjusted. Specifically, based on the difference in sales between marketing holidays and non-marketing holidays, as well as the difference between the peak sales quarter and the lowest peak sales quarter, the similarity between the target curve and the historical daily sales data curve of the product to be marketed is further corrected to obtain the final reference degree, making the curve reference representation more accurate and convenient for subsequent selection.

[0048] S11. The historical daily sales data curve with the largest final reference degree in the target curve set is used as the reference sales curve.

[0049] S12. Generate a recommendation strategy based on marketing budget information and reference sales curve.

[0050] Specifically, based on the marketing budget information provided by the user and the cost of each promotion, the number of promotions that can be supported is determined. The reference sales curve is divided into multiple reference sales sub-curves with a span of years. The multiple reference sales sub-curves are superimposed to obtain an integrated annual sales curve. Multiple time intervals are extracted according to significant sales and sorted based on sales volume. Based on the number of promotions, several top time intervals are selected to obtain a recommended plan.

[0051] This application also provides a sales dynamic factor intelligent prediction and analysis system, referring to Figure 2 ,include: The acquisition module is used to obtain the products to be marketed and the marketing budget information.

[0052] The matching module is used to match the historical daily sales data curve of the product to be marketed in the database according to the product to be marketed.

[0053] The first screening module is used to screen out the historical daily sales data curves of other products in the database whose time span reaches a preset length if the time span of the historical daily sales data curve of the product to be marketed meets a preset condition.

[0054] The interception module is used to intercept the significant sales volume sub-curve in the historical daily sales data curve of the product to be marketed as the significant sales volume sub-curve set of the product to be marketed.

[0055] The similarity calculation module is used to calculate the similarity between the historical daily sales data curves of each other product and the significant sales sub-curve set of the product to be marketed.

[0056] The second screening module is used to screen out products whose historical daily sales data curves have similarities reaching a preset similarity to generate a qualified curve set.

[0057] The first weight value calculation module is used to obtain a reference marketing holiday weight value based on the ratio of sales volume during marketing holidays to the average daily sales during non-marketing holidays in the historical daily sales data curve of the product to be marketed; and to obtain a reference quarterly weight value for each quarter based on the ratio of sales volume in each quarter to the sales volume in the quarter with the lowest sales volume in the historical daily sales data curve of the product to be marketed.

[0058] The reference degree calculation module is used to calculate the reference degree of each curve in the target curve set based on the marketing holiday weight value and the reference quarter weight value of each quarter.

[0059] The second weight value calculation module is used to calculate the marketing holiday weight value of each curve in the target curve set and the quarterly weight value of each quarter.

[0060] The reference adjustment module is used to adjust the reference of each curve based on the reference marketing holiday weight value, the reference quarterly weight value, the marketing holiday weight value of each curve and the quarterly weight value of each quarter to obtain the final reference of each curve.

[0061] A module is selected to use the historical daily sales data curve with the largest final reference degree in the target curve set as a reference sales curve.

[0062] The recommendation strategy generation module is used to generate a recommendation strategy based on marketing budget information and reference sales curve.

[0063] Among them, the similarity calculation module includes:

[0064] The sub-similarity calculation summary unit is used to count the curve segments in the historical daily sales data curve whose similarity with any element in the significant sales sub-curve set of the product to be marketed reaches a preset curve similarity, traverse all elements in the significant sales sub-curve set of the product to be marketed, and take the ratio of the counting result to the time span of the historical daily sales data curve as the similarity of the historical daily sales data curve.

[0065] In one embodiment, the reference calculation module includes: The judgment unit is used to judge the season to which the date of the curve segment that reaches the preset curve similarity in the historical daily sales data curve belongs, and to judge whether the date of the curve segment that reaches the preset curve similarity in the historical daily sales data curve belongs is a marketing holiday.

[0066] The first sub-reference degree calculation unit is used to calculate the sub-reference degree of the curve segment according to the marketing holiday weight value and the similarity of the curve segment if the date of the curve segment is a marketing holiday.

[0067] The second sub-reference degree calculation unit is used to calculate the sub-reference degree of the curve segment according to the reference quarter weight value corresponding to the season to which the date of the curve segment belongs and the similarity of the curve segment if the date of the curve segment is not a marketing holiday.

[0068] The summary calculation unit is used to calculate the sum of the sub-reference degrees of all curve segments of the historical daily sales data curve as the reference degree of the historical daily sales data curve.

[0069] The specific definition of the sales dynamic factor intelligent prediction and analysis system can be found in the above definition of the sales dynamic factor intelligent prediction and analysis method, which will not be repeated here. Each step of the above sales dynamic factor intelligent prediction and analysis method can be implemented in whole or in part by software, hardware and their combination.

[0070] Various implementations of the systems and techniques described herein can be realized in digital electronic circuit systems, integrated circuit systems, dedicated ASICs (application specific integrated circuits), computer hardware, firmware, software, and / or combinations thereof. These various implementations may include being implemented in one or more computer programs that can be executed and / or interpreted on a programmable system including at least one programmable processor, which can be a special purpose or general purpose programmable processor that can receive data and instructions from a storage system, at least one input device, and at least one output device, and transmit data and instructions to the storage system, the at least one input device, and the at least one output device.

[0071] These computer programs (also referred to as programs, software, software applications, or code) include machine instructions for programmable processors and can be implemented using high-level procedural and / or object-oriented programming languages, and / or assembly / machine languages. As used herein, the terms "machine-readable medium" and "computer-readable medium" refer to any computer program product, device, and / or means (e.g., disk, optical disk, memory, programmable logic device (PLD)) for providing machine instructions and / or data to a programmable processor, including a machine-readable medium that receives machine instructions as machine-readable signals. The term "machine-readable signal" refers to any signal for providing machine instructions and / or data to a programmable processor.

[0072] To provide interaction with a user, the systems and techniques described herein can be implemented on a computer having: a display device (e.g., a CRT (cathode ray tube) or LCD (liquid crystal display) monitor) for displaying information to the user; and a keyboard and pointing device (e.g., a mouse or trackball) through which the user can provide input to the computer. Other types of devices can also be used to provide interaction with the user; for example, the feedback provided to the user can be any form of sensory feedback (e.g., visual feedback, auditory feedback, or tactile feedback); and input from the user can be received in any form (including acoustic input, voice input, or tactile input).

[0073] The systems and techniques described herein may be implemented in a computing system that includes back-end components (e.g., as a data server), or a computing system that includes middleware components (e.g., an application server), or a computing system that includes front-end components (e.g., a user computer with a graphical user interface or a web browser through which a user can interact with implementations of the systems and techniques described herein), or a computing system that includes any combination of such back-end components, middleware components, or front-end components. The components of the system may be interconnected by any form or medium of digital data communication (e.g., a communication network). Examples of communication networks include: a local area network (LAN), a wide area network (WAN), and the Internet.

[0074] It should be understood that the various forms of processes shown above can be used to reorder, add or delete steps. For example, the steps recorded in this application can be executed in parallel, sequentially or in different orders, as long as the expected results of the technical solution disclosed in this application can be achieved, and this document is not limited here.

[0075] The above specific implementations do not constitute a limitation on the protection scope of this application. It should be understood by those skilled in the art that various modifications, combinations, sub-combinations and substitutions can be made according to design requirements and other factors. Any modifications, equivalent substitutions and improvements made within the spirit and principles of this application should be included in the protection scope of this application.

Claims

1. Intelligent prediction and analysis method of sales dynamic factors, characterized by: include: Obtain information on products to be marketed and marketing budget; Matching the historical daily sales data curve of the product to be marketed in the database according to the product to be marketed; If the time span of the historical daily sales data curve of the product to be marketed meets the preset condition, the historical daily sales data curves of other products in the database whose time span reaches the preset length are screened out; intercepting a significant sales volume sub-curve from the historical daily sales data curve of the product to be marketed as a significant sales volume sub-curve set of the product to be marketed; Calculate the similarity between the historical daily sales data curve of each other product and the significant sales sub-curve set of the product to be marketed; Filter out products whose historical daily sales data curves have similarities reaching a preset similarity to generate a qualified curve set; A reference marketing holiday weight value is obtained based on the ratio of the sales volume during marketing holidays to the average daily sales volume during non-marketing holidays in the historical daily sales data curve of the product to be marketed; a reference quarterly weight value is obtained based on the ratio of the sales volume of each quarter to the sales volume of the quarter with the lowest sales volume in the historical daily sales data curve of the product to be marketed; Calculate the reference degree of each curve in the target curve set based on the marketing holiday weight value and the reference quarter weight value of each quarter; Calculate the marketing holiday weight value of each curve in the target curve set and the quarterly weight value of each quarter; Adjusting the reference degree of each curve based on the reference marketing holiday weight value, the reference quarterly weight value, the marketing holiday weight value of each curve, and the quarterly weight value of each quarter to obtain the final reference degree of each curve; The historical daily sales data curve with the largest final reference degree in the target curve set is used as the reference sales curve; A recommendation strategy is generated based on the marketing budget information and the reference sales curve.

2. The sales dynamic factor intelligent prediction and analysis method according to claim 1, characterized in that: Calculating the similarity between the historical daily sales data curves of each other product and the significant sales sub-curve set of the product to be marketed, including: Count the curve segments in the historical daily sales data curve whose similarity with any element in the significant sales sub-curve set of the product to be marketed reaches a preset curve similarity, traverse all elements in the significant sales sub-curve set of the product to be marketed, and take the ratio of the counting result to the time span of the historical daily sales data curve as the similarity of the historical daily sales data curve.

3. The sales dynamic factor intelligent prediction and analysis method according to claim 2, characterized in that: The reference degree of each curve in the target curve set is calculated based on the marketing holiday weight value and the reference quarter weight value of each quarter, including: Determine the season to which the date of the curve segment in the historical daily sales data curve that reaches the preset curve similarity belongs, and determine whether the date of the curve segment in the historical daily sales data curve that reaches the preset curve similarity belongs is a marketing holiday; If the date of the curve segment is a marketing holiday, the sub-reference degree of the curve segment is calculated according to the marketing holiday weight value and the similarity of the curve segment.

4. The sales dynamic factor intelligent prediction and analysis method according to claim 3, characterized in that: If the date of the curve segment is not a marketing holiday, the sub-reference degree of the curve segment is calculated according to the reference quarter weight value corresponding to the season to which the date of the curve segment belongs and the similarity of the curve segment; The sum of the sub-reference degrees of all curve segments of the historical daily sales data curve is calculated as the reference degree of the historical daily sales data curve.

5. The sales dynamic factor intelligent prediction and analysis method according to claim 1, characterized in that: Based on the reference marketing holiday weight value, the reference quarterly weight value, the marketing holiday weight value of each curve, and the quarterly weight value of each quarter, the reference degree of each curve is adjusted to obtain the final reference degree of each curve, including: The final reference degree of each curve is calculated using the following formula: ， Among them, P is the final reference degree, is the reference degree, H is the reference marketing holiday weight value, is the maximum value of the reference quarter weight, h is the reference quarter weight, It is the maximum value of the quarterly weight value of each quarter.

6. A sales dynamic factor intelligent prediction and analysis system, based on the sales dynamic factor intelligent prediction and analysis method according to any one of claims 1 to 5, characterized in that: include: The acquisition module is used to obtain the information of the products to be marketed and the marketing budget; A matching module, used for matching the historical daily sales data curve of the product to be marketed in the database according to the product to be marketed; A first screening module is used to screen out historical daily sales data curves of other products in the database whose time span reaches a preset length if the time span of the historical daily sales data curve of the product to be marketed meets a preset condition; An interception module, used for intercepting a significant sales volume sub-curve in the historical daily sales data curve of the product to be marketed as a significant sales volume sub-curve set of the product to be marketed; A similarity calculation module, used to calculate the similarity between the historical daily sales data curves of each other product and the significant sales sub-curve set of the product to be marketed; The second screening module is used to screen out products whose historical daily sales data curves have similarities reaching a preset similarity to generate a qualified curve set; The first weight value calculation module is used to obtain a reference marketing holiday weight value based on the ratio of the sales volume during marketing holidays to the average daily sales volume during non-marketing holidays in the historical daily sales data curve of the product to be marketed; and obtain a reference quarterly weight value for each quarter based on the ratio of the sales volume of each quarter to the sales volume of the quarter with the lowest sales volume in the historical daily sales data curve of the product to be marketed; A reference degree calculation module is used to calculate the reference degree of each curve in the target curve set based on the marketing holiday weight value and the reference quarter weight value of each quarter; The second weight value calculation module is used to calculate the marketing holiday weight value of each curve in the target curve set and the quarterly weight value of each quarter; A reference adjustment module, for adjusting the reference of each curve based on the reference marketing holiday weight value, the reference quarterly weight value, the marketing holiday weight value of each curve, and the quarterly weight value of each quarter to obtain a final reference of each curve; A module is selected to use the historical daily sales data curve with the largest final reference degree in the target curve set as a reference sales curve; A recommendation strategy generation module is used to generate a recommendation strategy based on the marketing budget information and the reference sales curve.

7. The sales dynamic factor intelligent prediction and analysis system according to claim 6, characterized in that: Similarity calculation module, including: The sub-similarity calculation summary unit is used to count the curve segments in the historical daily sales data curve whose similarity with any element in the significant sales sub-curve set of the product to be marketed reaches a preset curve similarity, traverse all elements in the significant sales sub-curve set of the product to be marketed, and take the ratio of the counting result to the time span of the historical daily sales data curve as the similarity of the historical daily sales data curve.

8. The sales dynamic factor intelligent prediction and analysis system according to claim 6, characterized in that: Reference degree calculation module, including: A judgment unit, used to judge the season to which the date of the curve segment in the historical daily sales data curve that reaches the preset curve similarity belongs, and to judge whether the date of the curve segment in the historical daily sales data curve that reaches the preset curve similarity belongs is a marketing holiday; A first sub-reference degree calculation unit, configured to calculate the sub-reference degree of the curve segment according to the marketing holiday weight value and the similarity of the curve segment if the date of the curve segment is a marketing holiday; A second sub-reference degree calculation unit is used to calculate the sub-reference degree of the curve segment according to the reference quarter weight value corresponding to the season to which the date of the curve segment belongs and the similarity of the curve segment if the date of the curve segment is not a marketing holiday; The summary calculation unit is used to calculate the sum of the sub-reference degrees of all curve segments of the historical daily sales data curve as the reference degree of the historical daily sales data curve.

9. The sales dynamic factor intelligent prediction and analysis system according to claim 7 or 8, characterized in that: Reference adjustment module, including: The final reference degree of each curve is calculated using the following formula: ， Among them, P is the final reference degree, is the reference degree, H is the reference marketing holiday weight value, is the maximum value of the reference quarter weight, h is the reference quarter weight, It is the maximum value of the quarterly weight value of each quarter.

Images