Product sales prediction method and system based on multi-algorithm fusion, terminal and medium

Abstract

The invention discloses a product sales prediction method and system based on multi-algorithm fusion, a terminal and a medium. The method comprises the steps of obtaining historical sales data of a to-be-sold product in the last quarter; the method comprises the following steps: acquiring a preset analysis algorithm, processing historical sales data of the last quarter based on the analysis algorithm to obtain an analysis result corresponding to the analysis algorithm, the analysis algorithm including a total sales analysis algorithm, a product category analysis algorithm and a time-phased analysis algorithm, the analysis result comprises total sales volume data, category information corresponding to the to-be-sold product and monthly sales volume data; and on the basis of the analysis result, predicting the sales data of the to-be-sold product in the next quarter to obtain a prediction result. According to the method, the historical sales data are analyzed through a plurality of analysis algorithms, the analysis results of different dimensions are obtained, and the sales volume data of the to-be-sold product at the next degree can be predicted more accurately based on the analysis results.

Description

Technical Field

[0001] The present invention relates to the technical field of sales forecasting, and in particular to a product sales forecasting method, system, terminal and medium based on multi-algorithm fusion. Background Art

[0002] Sales forecasting plays an important role in supply chain management. Currently, when predicting future sales, most people use one algorithm to predict sales. However, different algorithms have different adaptability to different product categories. A single algorithm can only analyze the results of a single dimension. Therefore, it is difficult to obtain accurate prediction results by relying on a single algorithm.

[0003] Therefore, the prior art still needs to be improved and enhanced. Summary of the invention

[0004] The technical problem to be solved by the present invention is to provide a product sales forecasting method, system, terminal and medium based on multi-algorithm fusion in view of the above-mentioned defects of the prior art. The technical solution adopted by the present invention is as follows:

[0005] In a first aspect, the present invention provides a product sales forecasting method based on multi-algorithm fusion, wherein the method comprises:

[0006] Get the historical sales data of the products for sale in the previous quarter;

[0007] Obtain a preset analysis algorithm, process the historical sales data of the previous quarter based on the analysis algorithm, and obtain analysis results corresponding to the analysis algorithm, wherein the analysis algorithm includes: a total sales analysis algorithm, a product category analysis algorithm, and a time period analysis algorithm, and the analysis results include: total sales data, category information corresponding to the products for sale, and monthly sales data;

[0008] Based on the analysis results, the sales data of the product to be sold in the next quarter is predicted to obtain a prediction result.

[0009] In one implementation, the obtaining of historical sales data of all products for sale in the previous quarter includes:

[0010] Get the previous quarter's shipment data and cargo remaining data;

[0011] Based on the loading data and the remaining goods data, the historical sales data of the product to be sold in the previous quarter is obtained.

[0012] In one implementation, the processing of the historical sales data of the previous quarter based on the analysis algorithm to obtain the analysis result corresponding to the analysis algorithm includes:

[0013] If the analysis algorithm is a total sales analysis algorithm, the historical sales data of the previous quarter are counted to obtain the total sales data of the product to be sold in the previous quarter;

[0014] The total sales data is taken as the analysis result.

[0015] In one implementation, the processing of the historical sales data of the previous quarter based on the analysis algorithm to obtain the analysis result corresponding to the analysis algorithm includes:

[0016] If the analysis algorithm is a product category analysis algorithm, obtaining the loading area of ​​the product to be sold;

[0017] Based on the loading area, the category information corresponding to the products for sale is determined, and the category information corresponding to the products for sale is used as the analysis result.

[0018] In one implementation, the processing of the historical sales data of the previous quarter based on the analysis algorithm to obtain the analysis result corresponding to the analysis algorithm includes:

[0019] If the analysis algorithm is a time-division analysis algorithm, the sales situation of the product for sale in each month is determined based on the historical sales data of the previous quarter;

[0020] Based on the sales situation of the product for sale in each month, the monthly sales data of the product for sale is determined, and the monthly sales data is used as the analysis result.

[0021] In one implementation, based on the analysis result, predicting the sales data of the product to be sold in the next quarter to obtain the prediction result includes:

[0022] Get the first weight corresponding to the total sales data and the second weight corresponding to the monthly sales data;

[0023] Based on the first weight and the second weight and the category information corresponding to the product for sale, the sales data of the product for sale in the next quarter is predicted to obtain a prediction result.

[0024] In one implementation, the forecasting of sales data of the product for sale in the next quarter based on the first weight and the second weight and the category information corresponding to the product for sale to obtain the forecast result includes:

[0025] Based on the monthly sales data, determine the expected quarterly sales data;

[0026] Performing weighted processing based on the total sales data, the first weight, the expected quarterly sales data, and the second weight to obtain sales forecast data for the product to be sold;

[0027] The sales forecast data is matched with the category information to obtain the forecast result, which reflects the sales forecast data of the products to be sold in the category information in the next quarter.

[0028] In a second aspect, an embodiment of the present invention further provides a product sales forecasting system based on multi-algorithm fusion, wherein the system comprises:

[0029] The historical sales data acquisition module is used to obtain the historical sales data of the products to be sold in the previous quarter;

[0030] The sales data multi-algorithm analysis module is used to obtain a preset analysis algorithm, process the historical sales data of the previous quarter based on the analysis algorithm, and obtain the analysis results corresponding to the analysis algorithm, wherein the analysis algorithm includes: a total sales analysis algorithm, a product category analysis algorithm, and a time period analysis algorithm, and the analysis results include: total sales data, category information corresponding to the products for sale, and monthly sales data;

[0031] The next quarter forecasting module is used to forecast the sales data of the product to be sold in the next quarter based on the analysis results to obtain a forecast result.

[0032] In the third aspect, an embodiment of the present invention further provides a terminal, wherein the terminal includes a memory, a processor, and a product sales forecasting program based on multi-algorithm fusion stored in the memory and executable on the processor, and when the processor executes the product sales forecasting program based on multi-algorithm fusion, the steps of the product sales forecasting method based on multi-algorithm fusion of any one of the above-mentioned schemes are implemented.

[0033] In a fourth aspect, an embodiment of the present invention further provides a computer-readable storage medium, wherein a product sales forecasting program based on multi-algorithm fusion is stored on the computer-readable storage medium, and when the product sales forecasting program based on multi-algorithm fusion is executed by a processor, the steps of the product sales forecasting method based on multi-algorithm fusion described in any one of the above-mentioned schemes are implemented.

[0034] Beneficial effects: Compared with the prior art, the present invention provides a product sales forecasting method based on multi-algorithm fusion. The present invention first obtains the historical sales data of the product to be sold in the previous quarter. Then, a preset analysis algorithm is obtained, and the historical sales data of the previous quarter is processed based on the analysis algorithm to obtain the analysis results corresponding to the analysis algorithm, wherein the analysis algorithm includes: a total sales analysis algorithm, a product category analysis algorithm, and a time period analysis algorithm, and the analysis results include: total sales data, category information corresponding to the product to be sold, and monthly sales data. Finally, based on the analysis results, the sales data of the product to be sold in the next quarter is predicted to obtain a prediction result. The present invention can analyze the historical sales data through multiple analysis algorithms to obtain analysis results of different dimensions, and based on these analysis results, the sales data of the product to be sold in the next quarter can be more accurately predicted. BRIEF DESCRIPTION OF THE DRAWINGS

[0035] Figure 1 A flowchart of a preferred embodiment of a product sales forecasting method based on multi-algorithm fusion provided in an embodiment of the present invention.

[0036] Figure 2 A schematic diagram of the architecture of a product sales forecasting system based on multi-algorithm fusion provided in an embodiment of the present invention.

[0037] Figure 3 A functional block diagram of a terminal provided by an embodiment of the present invention. DETAILED DESCRIPTION

[0038] In order to make the purpose, technical solution and effect of the present invention clearer and more specific, the present invention is further described in detail with reference to the accompanying drawings and examples. It should be understood that the specific embodiments described herein are only used to explain the present invention and are not used to limit the present invention.

[0039] The flowcharts shown in the accompanying drawings are only examples and do not necessarily include all the contents and operations or steps, nor must they be executed in the order described. For example, some operations or steps may also be decomposed, combined or partially merged, so the actual execution order may change according to actual conditions.

[0040] It should be understood that the terms used in this specification of the present invention are only for the purpose of describing specific embodiments and are not intended to limit the present invention. As used in the specification of the present invention and the appended claims, unless the context clearly indicates otherwise, the singular forms "a", "an" and "the" are intended to include plural forms.

[0041] It should be understood that, in order to clearly describe the technical solutions of the embodiments of the present invention, in the embodiments of the present invention, words such as "first" and "second" are used to distinguish between identical or similar items with substantially identical functions and effects. For example, the first control information and the second control information are only used to distinguish different control information, and their order is not limited.

[0042] Those skilled in the art can understand that the words "first", "second", etc. do not limit the quantity and execution order, and the words "first", "second", etc. do not necessarily limit the differences.

[0043] It should be further understood that the term “and / or” used in the present specification and the appended claims refers to any and all possible combinations of one or more of the associated listed items, and includes these combinations.

[0044] In order to solve the problems of the prior art, this embodiment provides a product sales forecasting method based on multi-algorithm fusion. The method based on this embodiment can analyze historical sales data through multiple analysis algorithms to obtain analysis results of different dimensions. Based on these analysis results, the sales data of the products to be sold in the next quarter can be more accurately predicted. In specific applications, this embodiment can obtain the historical sales data of the products to be sold in the previous quarter, and then obtain a preset analysis algorithm, process the historical sales data of the previous quarter based on the analysis algorithm, and obtain the analysis results corresponding to the analysis algorithm, wherein the analysis algorithm includes: total sales analysis algorithm, product category analysis algorithm and time period analysis algorithm, and the analysis results include: total sales data, category information corresponding to the products to be sold, and monthly sales data. Finally, based on the analysis results, the sales data of the products to be sold in the next quarter is predicted to obtain the prediction results.

[0045] The product sales prediction method based on multi-algorithm fusion of this embodiment can be applied to a terminal, which can be a smart product terminal such as a mobile phone, a computer, a smart TV, etc. Figure 1 As shown in , the product sales forecasting method based on multi-algorithm fusion includes the following steps:

[0046] Step S100: Obtain historical sales data of the product to be sold in the previous quarter.

[0047] The historical sales data in this embodiment is the sales data of the product for sale in the previous quarter, which reflects the sales volume of the product for sale in the previous quarter. The historical sales data obtained in this embodiment can be used as a reference for prediction, and prediction is made based on the historical sales data of the previous quarter to facilitate the sales volume of the next quarter.

[0048] In one implementation, when acquiring the historical sales data of the product to be sold in the previous quarter, this embodiment includes the following steps:

[0049] Step S101, obtaining the cargo data and cargo remaining data of the previous quarter;

[0050] Step S102: Based on the loading data and the remaining data of goods, obtain the historical sales data of the product to be sold in the previous quarter.

[0051] This embodiment can obtain the stocking data of the previous quarter, and the stocking data reflects the quantity of products on the shelves. In addition, this embodiment can also obtain the remaining goods data, and the remaining data reflects how much goods are left unsold. Therefore, based on the stocking data and the remaining goods data, the sales situation of the products to be sold can be determined, and the historical sales data of the products to be sold in the previous quarter can be obtained. For example, if the previous quarter is the second quarter, that is, April to June, this embodiment can obtain all the stocking data and remaining goods data of the second quarter, and then further analyze the historical sales data of the products to be sold in the second quarter.

[0052] Step S200, obtain a preset analysis algorithm, process the historical sales data of the previous quarter based on the analysis algorithm, and obtain an analysis result corresponding to the analysis algorithm, wherein the analysis algorithm includes: a total sales analysis algorithm, a product category analysis algorithm and a time period analysis algorithm, and the analysis result includes: total sales data, category information corresponding to the products for sale, and monthly sales data.

[0053] The analysis algorithm of this embodiment includes a variety of algorithms, and the historical sales data of the previous quarter are processed based on the multiple analysis algorithms respectively, so as to obtain the analysis results corresponding to each analysis algorithm. Since the analysis algorithm in this embodiment includes several different analysis algorithms, the corresponding analysis results are also different. Specifically, the analysis algorithm of this embodiment includes: a total sales analysis algorithm, a product category analysis algorithm, and a time period analysis algorithm. The corresponding analysis results include: total sales data, category information corresponding to the products for sale, and monthly sales data. This embodiment uses different analysis algorithms to produce analysis results of different dimensions based on historical sales data. Compared with the technology of using a single algorithm for prediction in the prior art, this embodiment can more accurately predict the sales data of products for sale.

[0054] Specifically, if the analysis algorithm is a total sales analysis algorithm, the historical sales data of the previous quarter is counted to obtain the total sales data of the product for sale in the previous quarter, and then the total sales data is used as the analysis result. In one implementation, the total sales analysis algorithm is a statistical algorithm, based on which the total sales data of the product for sale in the previous quarter can be counted.

[0055] When the analysis algorithm is a product category analysis algorithm, this embodiment can obtain the loading area of ​​the product for sale; based on the loading area, determine the category information corresponding to the product for sale. In actual application, the loading area reflects the storage position of the product for sale on the shelf. Generally speaking, on the shelf or container, the products for sale on the same layer belong to the same product category. In other words, the products for sale of the same product category are placed in the same area. In actual application, the product category corresponds to the storage position of the loading area, and the correspondence between the product category and the storage position is pre-set, and the storage position can be accurate to the row and storage area of ​​a certain shelf. Based on this, this embodiment can first obtain the storage position of the product for sale, and then match the storage position with the preset correspondence to determine the product category of the product for sale, and then use the category information corresponding to the product for sale as the analysis result. The product category analysis algorithm of this embodiment is a matching algorithm, which aims to match the product category of the product for sale.

[0056] When the analysis algorithm is a time-divided analysis algorithm, this embodiment can determine the sales volume of the product for sale in each month based on the historical sales data of the previous quarter, such as analyzing the sales volume of the product for sale in April, May and June respectively. Then, based on the sales situation of the product for sale in each month, the monthly sales volume data of the product for sale is determined, and the monthly sales volume data is used as the analysis result. The time-divided analysis algorithm of this embodiment is intended to analyze the monthly sales volume data in a quarter. It is an algorithm for recording in time periods. In specific applications, this embodiment can record the sales volume of each month at the end of each month, so as to obtain the monthly sales volume data of the product for sale.

[0057] Step S300: Based on the analysis result, forecast the sales data of the product to be sold in the next quarter to obtain a forecast result.

[0058] In this embodiment, since the analysis results include data from multiple dimensions, after the analysis results are integrated, the sales situation of the products for sale in the previous quarter can be more comprehensively reflected. Furthermore, based on the analysis results, this embodiment can predict the sales data of the products for sale in the next quarter to obtain the prediction results.

[0059] In one implementation, this embodiment includes the following steps when analyzing the sales data for the next quarter:

[0060] Step S301, obtaining a first weight corresponding to the total sales data and a second weight corresponding to the monthly sales data;

[0061] Step S302: Based on the first weight and the second weight and the category information corresponding to the product for sale, forecast the sales data of the product for sale in the next quarter to obtain a forecast result.

[0062] Specifically, the embodiment pre-sets a first weight corresponding to the total sales data obtained by the total sales analysis algorithm, and a second weight corresponding to the monthly sales data obtained by the time period analysis algorithm. The first weight and the second weight are set based on the influence or importance of the quarterly total sales and the monthly sales data in predicting the sales data. The greater the influence or importance, the greater the corresponding weight, and the smaller the influence or importance, the smaller the corresponding weight. For example, the total sales data of a quarter reflects the overall sales situation of a quarter, but because a quarter is composed of multiple months, the sales data of each month will have a direct impact on the overall sales situation of the quarter. Therefore, when predicting the sales data of the next quarter, the monthly sales data has a greater impact on the prediction results, so the second weight corresponding to the monthly sales data is greater than the first weight.

[0063] Further, after determining the first weight and the second weight, the present embodiment can predict the sales data of the product for sale in the next quarter based on the first weight and the second weight and the category information corresponding to the product for sale to obtain a prediction result. Specifically, the present embodiment first determines the expected quarterly sales data based on the monthly sales data. In actual application, the monthly sales data can be used as the average monthly sales data in a quarter, so the expected quarterly sales data can be obtained by multiplying the monthly sales data by 3. Then in actual application, due to the influence of weather and climate in individual months, the sales volume of a certain month may be affected. Therefore, the present embodiment can take into account the factors that affect the sales data, and then obtain more accurate expected quarterly sales data. Then, the present embodiment performs weighted processing based on the total sales data, the first weight, the expected quarterly sales data and the second weight, and the sales forecast data of the product for sale can be obtained, and the sales forecast data reflects the expected sales of the product for sale in the next quarter in a timely manner. Since the present embodiment analyzes the product category of the product to be sold, the present embodiment can correspond the sales forecast data to the category information to obtain the forecast result, which reflects the sales forecast data of the product to be sold in the category information in the next quarter. Since the present embodiment takes into account the total sales data of the previous quarter and the monthly sales data in the previous quarter when predicting the expected sales of the product to be sold in the next quarter, the sales volume forecast is achieved from different dimensions. Compared with the traditional technology that only predicts based on one algorithm, the sales forecast data analyzed by the present embodiment is more accurate.

[0064] Furthermore, the present embodiment can also obtain other products other than the above-mentioned products for sale in the category information corresponding to the products for sale, and analyze the degree of association between these products and the products for sale, and then analyze the product sales of the entire category information in the next quarter based on the determined degree of association. The degree of association in the present embodiment reflects the degree of binding between products. For example, the degree of association between cups and spoons is high. Cups and spoons are generally used together, and users who buy cups are likely to buy spoons. Therefore, the sales of cups and spoons are related. It can be seen that the present embodiment can determine the degree of association based on the function or use of the product. Based on this, after obtaining other products other than the above-mentioned products for sale in the category information corresponding to the products for sale, the present embodiment will sequentially match the functions of the other products obtained with the functions of the products for sale, and then determine the degree of association between the products for sale and other products. According to the degree of association between the products for sale and other products, the product sales of other products in the next quarter are estimated, and then combined with the estimated results of the products for sale, the product sales of the entire product category in the next quarter can be estimated, and the future sales forecast of the entire product category can be realized.

[0065] In summary, this embodiment first obtains the historical sales data of the products to be sold in the previous quarter. Then, a preset analysis algorithm is obtained, and the historical sales data of the previous quarter is processed based on the analysis algorithm to obtain the analysis results corresponding to the analysis algorithm, wherein the analysis algorithm includes: a total sales analysis algorithm, a product category analysis algorithm, and a time period analysis algorithm, and the analysis results include: total sales data, category information corresponding to the products to be sold, and monthly sales data. Finally, based on the analysis results, the sales data of the products to be sold in the next quarter is predicted to obtain the prediction results. This embodiment can analyze the historical sales data through multiple analysis algorithms to obtain analysis results of different dimensions, and based on these analysis results, the sales data of the products to be sold in the next quarter can be more accurately predicted.

[0066] Based on the above embodiments, the present invention also provides a product sales forecasting system based on multi-algorithm fusion, such as Figure 2 As shown in , the system includes: a historical sales data acquisition module 10, a sales data multi-algorithm analysis module 20 and a next quarter prediction module 30. The historical sales data acquisition module 10 is used to obtain the historical sales data of the products to be sold in the previous quarter. The sales data multi-algorithm analysis module 20 is used to obtain a preset analysis algorithm, and process the historical sales data of the previous quarter based on the analysis algorithm to obtain an analysis result corresponding to the analysis algorithm, wherein the analysis algorithm includes: a total sales analysis algorithm, a product category analysis algorithm and a time period analysis algorithm, and the analysis result includes: total sales data, category information corresponding to the products to be sold, and monthly sales data. The next quarter prediction module 30 is used to predict the sales data of the products to be sold in the next quarter based on the analysis results to obtain a prediction result.

[0067] In one implementation, the historical sales data acquisition module 10 includes:

[0068] A data acquisition unit is used to acquire the data of goods delivered and the remaining goods in the previous quarter;

[0069] The data analysis unit is used to obtain the historical sales data of the product for sale in the previous quarter based on the loading data and the remaining goods data.

[0070] In one implementation, the sales data multi-algorithm analysis module 20 includes:

[0071] A total sales volume analysis unit, for collecting statistics on the historical sales data of the previous quarter to obtain the total sales volume data of the product to be sold in the previous quarter if the analysis algorithm is the total sales volume analysis algorithm;

[0072] The first analysis result determination unit is used to use the total sales data as the analysis result.

[0073] In one implementation, the sales data multi-algorithm analysis module 20 includes:

[0074] a loading area analysis unit, configured to obtain the loading area of ​​the product to be sold if the analysis algorithm is a product category analysis algorithm;

[0075] The second analysis result determination unit is used to determine the category information corresponding to the product for sale based on the loading area, and use the category information corresponding to the product for sale as the analysis result.

[0076] In one implementation, the sales data multi-algorithm analysis module 20 includes:

[0077] A monthly sales situation determination unit, used to determine the sales situation of the product for sale in each month based on the historical sales data of the previous quarter if the analysis algorithm is a time period analysis algorithm;

[0078] The third analysis result determination unit is used to determine the monthly sales data of the product to be sold based on the sales situation of the product to be sold in each month, and use the monthly sales data as the analysis result.

[0079] In one implementation, the next quarter prediction module 30 includes:

[0080] A weight data acquisition unit, used to acquire a first weight corresponding to the total sales data and a second weight corresponding to the monthly sales data;

[0081] The prediction result determination unit is used to predict the sales data of the product for sale in the next quarter based on the first weight and the second weight and the category information corresponding to the product for sale, and obtain a prediction result.

[0082] In one implementation, the prediction result determination unit includes:

[0083] A quarterly sales data determination subunit, used to determine expected quarterly sales data based on the monthly sales data;

[0084] a sales forecast data determination subunit, configured to perform weighted processing based on the total sales data, the first weight, the expected quarterly sales data, and the second weight to obtain sales forecast data for the product to be sold;

[0085] The category information corresponding subunit is used to correspond the sales forecast data with the category information to obtain the forecast result, which reflects the sales forecast data of the products to be sold in the category information in the next quarter.

[0086] The working principles of each module in the product sales forecasting system based on multi-algorithm fusion of this embodiment are the same as the principles of each step in the above method embodiment, and will not be repeated here.

[0087] Each module in the above-mentioned product sales forecasting system based on multi-algorithm fusion can be implemented in whole or in part by software, hardware and their combination. Each of the above-mentioned modules can be embedded in or independent of the processor in the terminal in the form of hardware, or can be stored in the memory in the terminal in the form of software, so that the processor can call and execute the corresponding operations of each of the above modules.

[0088] Based on the above embodiment, the present invention further provides a terminal, the principle block diagram of the terminal can be as follows: Figure 3 The terminal may include one or more processors 100 ( Figure 3 Only one is shown), a memory 101 and a computer program 102 stored in the memory 101 and executable on one or more processors 100.

[0089] In one embodiment, the processor 100 may be a central processing unit (CPU), or other general-purpose processors, digital signal processors (DSP), application-specific integrated circuits (ASIC), field-programmable gate arrays (FPGA), or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, etc. A general-purpose processor may be a microprocessor or any conventional processor, etc.

[0090] In one embodiment, the memory 101 may be an internal storage unit of an electronic device, such as a hard disk or memory of the electronic device. The memory 101 may also be an external storage device of the electronic device, such as a plug-in hard disk, a smart memory card (SMC), a secure digital (SD) card, a flash card, etc. equipped on the electronic device. Further, the memory 101 may also include both an internal storage unit of the electronic device and an external storage device. The memory 101 is used to store computer programs and other programs and data required by the terminal. The memory 101 may also be used to temporarily store data that has been output or is to be output.

[0091] Those skilled in the art will understand that Figure 3The principle block diagram shown in the figure is only a block diagram of a partial structure related to the scheme of the present invention, and does not constitute a limitation on the terminal to which the scheme of the present invention is applied. The specific terminal may include more or fewer components than those shown in the figure, or combine certain components, or have a different arrangement of components.

[0092] Those of ordinary skill in the art can understand that all or part of the processes in the above-mentioned embodiment methods can be completed by instructing the relevant hardware through a computer program, and the computer program can be stored in a non-volatile computer-readable storage medium. When the computer program is executed, it can include the processes of the embodiments of the above-mentioned methods. Among them, any reference to memory, storage, operating database or other media used in the embodiments provided by the present invention may include non-volatile and / or volatile memory. Non-volatile memory may include read-only memory (ROM), programmable ROM (PROM), electrically programmable ROM (EPROM), electrically erasable programmable ROM (EEPROM) or flash memory. Volatile memory may include random access memory (RAM) or external cache memory. By way of illustration and not limitation, RAM is available in many forms, such as static RAM (SRAM), dynamic RAM (DRAM), synchronous DRAM (SDRAM), double data rate SDRAM (DDRSDRAM), enhanced SDRAM (ESDRAM), synchronous link DRAM (SLDRAM), RAMbus direct RAM (RDRAM), direct RAMbus dynamic RAM (DRDRAM), and RAMbus dynamic RAM (RDRAM), etc.

[0093] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention, rather than to limit it. Although the present invention has been described in detail with reference to the aforementioned embodiments, those skilled in the art should understand that they can still modify the technical solutions described in the aforementioned embodiments, or make equivalent replacements for some of the technical features therein. 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 invention.

Claims

1. A product sales forecasting method based on multi-algorithm fusion, characterized in that: The method comprises: Get the historical sales data of the products for sale in the previous quarter; Obtain a preset analysis algorithm, process the historical sales data of the previous quarter based on the analysis algorithm, and obtain analysis results corresponding to the analysis algorithm, wherein the analysis algorithm includes: a total sales analysis algorithm, a product category analysis algorithm, and a time period analysis algorithm, and the analysis results include: total sales data, category information corresponding to the products for sale, and monthly sales data; Based on the analysis results, the sales data of the product to be sold in the next quarter is predicted to obtain a prediction result.

2. The product sales forecasting method based on multi-algorithm fusion according to claim 1 is characterized in that: The above method obtains the historical sales data of all products for sale in the previous quarter, including: Get the previous quarter's shipment data and cargo remaining data; Based on the loading data and the remaining goods data, the historical sales data of the product to be sold in the previous quarter is obtained.

3. The product sales forecasting method based on multi-algorithm fusion according to claim 2 is characterized in that: The processing of the historical sales data of the previous quarter based on the analysis algorithm to obtain the analysis results corresponding to the analysis algorithm includes: If the analysis algorithm is a total sales analysis algorithm, the historical sales data of the previous quarter are counted to obtain the total sales data of the product to be sold in the previous quarter; The total sales data is taken as the analysis result.

4. The product sales forecasting method based on multi-algorithm fusion according to claim 2 is characterized in that: The processing of the historical sales data of the previous quarter based on the analysis algorithm to obtain the analysis results corresponding to the analysis algorithm includes: If the analysis algorithm is a product category analysis algorithm, obtaining the loading area of ​​the product to be sold; Based on the loading area, the category information corresponding to the products for sale is determined, and the category information corresponding to the products for sale is used as the analysis result.

5. The product sales forecasting method based on multi-algorithm fusion according to claim 2 is characterized in that: The processing of the historical sales data of the previous quarter based on the analysis algorithm to obtain the analysis results corresponding to the analysis algorithm includes: If the analysis algorithm is a time-division analysis algorithm, the sales situation of the product for sale in each month is determined based on the historical sales data of the previous quarter; Based on the sales situation of the product for sale in each month, the monthly sales data of the product for sale is determined, and the monthly sales data is used as the analysis result.

6. The product sales forecasting method based on multi-algorithm fusion according to claim 1 is characterized in that: Based on the analysis results, the sales data of the product to be sold in the next quarter is predicted to obtain the prediction results, including: Get the first weight corresponding to the total sales data and the second weight corresponding to the monthly sales data; Based on the first weight and the second weight and the category information corresponding to the product for sale, the sales data of the product for sale in the next quarter is predicted to obtain a prediction result.

7. The product sales forecasting method based on multi-algorithm fusion according to claim 1 is characterized in that: The step of predicting the sales data of the product for sale in the next quarter based on the first weight and the second weight and the category information corresponding to the product for sale to obtain a prediction result includes: Based on the monthly sales data, determine the expected quarterly sales data; Performing weighted processing based on the total sales data, the first weight, the expected quarterly sales data, and the second weight to obtain sales forecast data for the product to be sold; The sales forecast data is matched with the category information to obtain the forecast result, which reflects the sales forecast data of the products to be sold in the category information in the next quarter.

8. A product sales forecasting system based on multi-algorithm fusion, characterized in that: The system comprises: The historical sales data acquisition module is used to obtain the historical sales data of the products to be sold in the previous quarter; The sales data multi-algorithm analysis module is used to obtain a preset analysis algorithm, process the historical sales data of the previous quarter based on the analysis algorithm, and obtain the analysis results corresponding to the analysis algorithm, wherein the analysis algorithm includes: a total sales analysis algorithm, a product category analysis algorithm, and a time period analysis algorithm, and the analysis results include: total sales data, category information corresponding to the products for sale, and monthly sales data; The next quarter forecasting module is used to forecast the sales data of the product to be sold in the next quarter based on the analysis results to obtain a forecast result.

9. A terminal, characterized in that: The terminal includes a memory, a processor, and a product sales forecasting program based on multi-algorithm fusion stored in the memory and executable on the processor. When the processor executes the product sales forecasting program based on multi-algorithm fusion, the steps of the product sales forecasting method based on multi-algorithm fusion as described in any one of claims 1 to 7 are implemented.

10. A computer-readable storage medium, characterized in that: The computer-readable storage medium stores a product sales forecasting program based on multi-algorithm fusion. When the product sales forecasting program based on multi-algorithm fusion is executed by the processor, the steps of the product sales forecasting method based on multi-algorithm fusion as described in any one of claims 1-7 are implemented.

Images