Big data artificial intelligence analysis platform

Abstract

The invention relates to the technical field of artificial intelligence, in particular to a big data artificial intelligence analysis platform, which comprises the steps of analyzing the historical sales quantity of commodities, determining all predicted sales quantities in a prediction period, determining a hot time period according to all predicted sales quantities in the prediction period in combination with the historical sales quantity of the commodities, and determining the sales quantity of the commodities based on the hot time period. Analyzing the continuity of the hot time periods in the prediction period, determining a storage time point when a continuous signal is generated, a storage time point when a non-continuous signal is generated and a commodity storage amount, and carrying out deduplication analysis on the hot time periods of all types of commodities; and determining the sales distribution duration of the commodities in the less-commodity hot time period and the sales distribution duration of the commodities in the multi-commodity hot time period, so that the utilization efficiency of sales resources is improved by distinguishing different hot time periods and reasonably distributing the sales durations.

Description

Technical Field

[0001] The present invention relates to the field of artificial intelligence technology, and in particular to a big data artificial intelligence analysis platform. Background Art

[0002] With the rapid development of information technology, the era of big data has arrived. Big data artificial intelligence analysis platforms have been widely used in various fields such as finance, healthcare, and transportation, providing strong support for decision-making.

[0003] However, existing big data artificial intelligence analysis platforms have many problems. On the one hand, it is impossible to determine the popular time periods and the continuity of popular time periods within the forecast period, making it difficult for companies to understand the changing patterns of market demand and adjust sales strategies and inventory management strategies in a timely manner. In addition, factors such as the shelf life and production date of the goods are not fully considered, and it is impossible to reasonably determine the storage time and storage volume of the goods, which leads to the expiration or deterioration of the goods during storage, resulting in waste of resources and economic losses. On the other hand, the unreasonable allocation of sales time for different types of sales goods in the existing technology will lead to unreasonable sales time arrangements for the goods and inefficient use of sales resources.

[0004] To this end, we propose a big data artificial intelligence analysis platform. Summary of the Invention

[0005] The purpose of the present invention is to provide a big data artificial intelligence analysis platform to solve at least one of the above-mentioned problems in the prior art.

[0006] The present invention provides a big data artificial intelligence analysis platform, comprising:

[0007] Forecasting data module: Analyzes the historical sales volume of the product and determines all forecast sales within the forecast period;

[0008] Popular period determination module: determines the popular period based on all predicted sales within the forecast period and the historical sales volume of the product;

[0009] Continuity analysis module: Based on the popular time periods, analyze the continuity of the popular time periods within the forecast period;

[0010] Product storage module: Based on the continuity analysis results of popular time periods, the product's shelf life and production date are analyzed to determine the storage time point when the continuity signal is generated, the storage time point when the discontinuity signal is generated, and the product storage quantity;

[0011] Time period deduplication module: Deduplication analyzes the popular time periods of all product categories and determines the sales allocation duration of products in popular time periods with a small number of products and the sales allocation duration of products in popular time periods with a large number of products.

[0012] Beneficial effects of the present invention:

[0013] 1. The present invention determines all predicted sales volumes within a forecast period by analyzing the historical sales volume of a product. Based on all predicted sales volumes within the forecast period and the historical sales volume of the product, a popular time period is determined. The present invention obtains all predicted sales volumes within the forecast period by continuously moving a sliding window and calculating a new moving average, thereby achieving dynamic tracking and forecasting of sales data. As time goes by, new data is continuously incorporated into the sliding window, and the forecast results can promptly reflect market trends.

[0014] 2. The present invention analyzes the continuity of popular time periods within the forecast period, analyzes the shelf life and production date of the product based on the continuity analysis results of the popular time periods, and determines the storage time point when the continuity signal is generated, the storage time point when the discontinuity signal is generated, and the storage quantity of the product; the present invention analyzes the continuity of popular time periods within the forecast period, and can provide enterprises with important information about the stability of market demand, reasonably determine the storage time point when the continuity signal is generated, the storage time point when the discontinuity signal is generated, and the storage quantity and storage quantity of the product, so as to ensure that the product is sold in the best condition and reduce inventory costs at the same time.

[0015] 3. The present invention determines the sales allocation duration of commodities in the popular time periods of all categories of commodities through deduplication analysis, and the sales allocation duration of commodities in the popular time periods of fewer commodities and the sales allocation duration of commodities in the popular time periods of more commodities. The present invention realizes the refined management of commodity sales by distinguishing different popular time periods and reasonably allocating sales durations. It can arrange the sales time of commodities more reasonably according to the characteristics of different popular time periods and the conditions of commodities, and improve the utilization efficiency of sales resources. BRIEF DESCRIPTION OF THE DRAWINGS

[0016] In order to more clearly illustrate the technical solutions in the embodiments of the present invention, the following briefly introduces the drawings required for use in the description of the embodiments. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without creative work.

[0017] Figure 1 This is a system block diagram of a big data artificial intelligence analysis platform according to an embodiment of the present invention;

[0018] Figure 2 This is a flow chart of a big data artificial intelligence analysis method according to an embodiment of the present invention;

[0019] Figure 3 This is a schematic diagram of the structure of a big data artificial intelligence analysis device according to an embodiment of the present invention;

[0020] Figure numerals: 3, computer device; 301, processor; 302, memory; 303, computer program. DETAILED DESCRIPTION

[0021] In order to enable those skilled in the art to better understand the solutions of the present invention, the technical solutions in the embodiments of the present invention will be clearly and completely described below in conjunction with the drawings in the embodiments of the present invention. Obviously, the embodiments described are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without making creative efforts should fall within the scope of protection of the present invention.

[0022] Example 1

[0023] Figure 1 This is a system block diagram of a big data artificial intelligence analysis platform provided in the first embodiment of the present invention. A big data artificial intelligence analysis platform can be implemented by software and / or hardware, and can be configured in a big data artificial intelligence analysis device. Alternatively, the big data artificial intelligence analysis device can be an electronic device, such as a laptop, desktop computer, or smart tablet, although this embodiment of the present invention does not limit this.

[0024] See also Figure 1 As shown, a big data artificial intelligence analysis platform specifically includes:

[0025] Forecasting data module: Analyzes the historical sales volume of the product and determines all forecast sales within the forecast period;

[0026] Get the sales quantity of the product in the historical period;

[0027] It should be noted that historical periods include but are not limited to six months and one year;

[0028] Based on any product, the moving sliding window average method is used to smooth the historical sales volume. The specific process is as follows:

[0029] Divide the historical period into several time periods with equal time intervals, record them as historical periods, and count the sales volume of the products in the historical periods, record them as historical sales volume;

[0030] It should be noted that historical sales volume refers to the sales volume of a certain product in the current period and is not accumulated based on historical quantities;

[0031] All historical sales in the historical period are integrated into a sales quantity set according to the time series. The size of the sliding window is set to N. N consecutive historical sales are selected in sequence. The N historical sales in the sliding window are summed and averaged to obtain the moving average of the current sliding window.

[0032] Preset the forecast period and divide the forecast period into several time periods with equal time intervals, which are recorded as forecast periods;

[0033] It should be noted that the time interval of the forecast period is the same as that of the historical period;

[0034] Extract the moving average value corresponding to the forecast period as the forecast sales volume for the forecast period, move the sliding window along the time axis by one historical sales volume, and calculate the moving average value of the new sliding window again. Repeat this process until all forecast sales volumes within the forecast period are obtained.

[0035] Popular period determination module: determines the popular period based on all predicted sales within the forecast period and the historical sales volume of the product;

[0036] Obtain the sales volume of goods in multiple historical periods, sum and average the sales volume of goods in multiple historical periods, and obtain the historical sales average;

[0037] Compare the forecasted sales volume with the historical sales average by:

[0038] If the predicted sales volume ≥ the historical sales average, the corresponding predicted period will be marked as a popular period;

[0039] If the predicted sales volume is less than the historical sales average, the corresponding forecast period will be marked as a non-popular period and no processing will be performed;

[0040] The technical solution of this embodiment is as follows: the present invention determines all predicted sales volumes within a forecast period by analyzing the historical sales volume of the product, and determines the popular time period based on all predicted sales volumes within the forecast period in combination with the historical sales volume of the product; the present invention obtains all predicted sales volumes within the forecast period by continuously moving the sliding window and calculating a new moving average, thereby realizing dynamic tracking and forecasting of sales data. As time goes by, new data is continuously incorporated into the sliding window, and the forecast results can promptly reflect the changing trends of the market.

[0041] Example 2

[0042] See also Figure 1 As shown, a big data artificial intelligence analysis platform specifically includes:

[0043] Continuity analysis module: Based on the popular time periods, analyze the continuity of the popular time periods within the forecast period;

[0044] In some embodiments, the marking results of all prediction time periods in the prediction cycle are integrated into a time period list, the time period list is traversed, and the index corresponding to the first popular time period in the time period list is marked as r;

[0045] It should be noted that if there is no popular time period in the time period list, no processing will be performed;

[0046] Starting from index r, traverse all forecast periods after index r and check whether each subsequent forecast period is a popular period, until the first non-popular period or the end of the list;

[0047] Count the number of popular time periods between the start time of the first popular time period and the start time of the first non-popular time period. If the number of popular time periods between the start time of the first popular time period and the start time of the first non-popular time period is ≥ 2, it means that the first popular time period is continuous, and a continuity signal is generated.

[0048] If the number of hot periods between the start time point of the first hot period and the start time point of the first non-hot period = 1, a discontinuity signal is generated;

[0049] Product storage module: Based on the continuity analysis results of popular time periods, the product's shelf life and production date are analyzed to determine the storage time point when the continuity signal is generated, the storage time point when the discontinuity signal is generated, and the product storage quantity;

[0050] Obtain the product's shelf life and production date, and calculate the product's remaining shelf life (RSL) using the formula: RSL = SL - (CT - PD), where SL represents the product's shelf life, CT represents the current date, and PD represents the product's production date.

[0051] Based on the continuity signal, the time period between the start time of the first popular period and the start time of the first non-popular period is extracted and recorded as the continuous period;

[0052] Compare the duration corresponding to the consecutive time period with the duration corresponding to the remaining shelf life, specifically:

[0053] If the duration of the continuous period is greater than or equal to the duration of the remaining shelf life, the start time of the continuous period is used as the earliest storage time, and the end time of the continuous period is subtracted from the time corresponding to the remaining shelf life to obtain the latest storage time. Any time between the earliest and latest storage time can be used as the storage time.

[0054] The predicted sales volume of all popular time periods between the popular time period corresponding to the storage time point and the popular time period corresponding to the remaining shelf life expiration time point is summed to obtain the product storage volume;

[0055] It should be noted that all popular time periods between the popular time period corresponding to the storage time point and the popular time period corresponding to the time point at which the remaining shelf life expires include the popular time period corresponding to the storage time point and the popular time period corresponding to the time point at which the remaining shelf life expires;

[0056] If the duration of the continuous period is less than the duration of the remaining shelf life, the starting time of the continuous period is used as the storage time point, and the predicted sales volume corresponding to all popular periods in the continuous period is extracted and summed to obtain the product storage volume;

[0057] Based on the discontinuous signal, the duration corresponding to the popular period is compared with the duration corresponding to the remaining shelf life, specifically:

[0058] If the duration corresponding to the popular period is ≥ the duration corresponding to the remaining shelf life, the start time of the popular period is used as the earliest storage time point, and the end time point of the popular period is subtracted from the time point corresponding to the remaining shelf life to obtain the latest storage time point. Any time point between the earliest storage time point and the latest storage time point can be used as the storage time point. The historical sales volume between the same storage time point and the end time point of the popular period is counted and used as the product storage volume;

[0059] If the duration of the popular period is less than the duration of the remaining shelf life, the start time of the popular period is used as the storage time point, and the predicted sales volume of the popular period is used as the product storage volume;

[0060] The technical solution of this embodiment is: based on the popular time periods, the continuity of the popular time periods is analyzed within the forecast period, and according to the continuity analysis results of the popular time periods, the shelf life and production date of the goods are analyzed to determine the storage time point when the continuity signal is generated, the storage time point when the discontinuity signal is generated, and the storage quantity of the goods; by analyzing the continuity of the popular time periods within the forecast period, the present invention can provide enterprises with important information about the stability of market demand, reasonably determine the storage time point when the continuity signal is generated, the storage time point when the discontinuity signal is generated, and the storage quantity and storage quantity of the goods, and ensure that the goods are sold in the best condition while reducing inventory costs.

[0061] Example 3

[0062] See also Figure 1 As shown, a big data artificial intelligence analysis platform specifically includes:

[0063] Time period deduplication module: Deduplication analysis of popular time periods for all product categories to determine the sales allocation duration for products in popular time periods with fewer products and the sales allocation duration for products in popular time periods with more products;

[0064] Based on the popular time periods of all products, duplicates are removed to obtain the target popular time period;

[0065] For example, assuming that the popular time periods for product 1 are (ab), (cd), and (ef), and the popular time periods for product 2 are (ab), (ef), and (xy), then the target popular time periods after deduplication are (ab), (cd), (ef), and (xy).

[0066] Based on any target popular time period;

[0067] Count the number of product types included in the target popular time period and compare it with the number of all product types to obtain the product type ratio within the target popular time period;

[0068] comparing the product category ratio with a product category ratio threshold;

[0069] If the product variety ratio is greater than or equal to the product variety ratio threshold, the target popular period is marked as a multi-product popular period;

[0070] If the product variety ratio is less than the product variety ratio threshold, the target popular period will be marked as a less-product popular period;

[0071] For products in the rare and popular time period, if the number of product types in the rare and popular time period is equal to 1, no processing is performed. If the number of product types in the rare and popular time period is greater than 1, the sales distribution time of the products included in the rare and popular time period is calculated by comparing the duration of the rare and popular time period with the number of product types.

[0072] For example, assuming that the number of commodity types included in the rare product hot period is 2, then for the two commodities in the rare product hot period, the sales allocation time of each commodity is 1 / 2 of the corresponding time of the rare product hot period;

[0073] Based on any product during a popular time period of multiple products;

[0074] Obtain the predicted sales volume of the product during the multi-product popular period and compare it with the predicted total sales volume during the multi-product popular period to obtain the distribution coefficient of the sales distribution time of the product during the multi-product popular period;

[0075] The predicted total sales volume during a multi-product popular period is obtained by summing the predicted sales volumes of all products during the multi-product popular period.

[0076] The sales distribution time of the product in the multi-product popular period is multiplied by the distribution coefficient of the sales distribution time of the product in the multi-product popular period and the duration corresponding to the multi-product popular period to obtain the sales distribution time of the product in the multi-product popular period;

[0077] The technical solution of this embodiment is: deduplication analysis of the popular time periods of all categories of goods, and determination of the sales allocation duration of goods in the popular time periods with a small number of goods and the sales allocation duration of goods in the popular time periods with a large number of goods. The present invention achieves refined management of commodity sales by distinguishing different popular time periods and reasonably allocating sales durations. It can arrange the sales time of goods more reasonably according to the characteristics of different popular time periods and the conditions of goods, thereby improving the utilization efficiency of sales resources.

[0078] Example 4

[0079] See also Figure 2 As shown, a big data artificial intelligence analysis method specifically includes the following steps:

[0080] Step 1: Analyze the historical sales volume of the product and determine the total forecast sales volume within the forecast period;

[0081] Step 2: Determine the popular time period based on all predicted sales within the forecast period and the product's historical sales volume;

[0082] Step 3: Based on the popular time periods, analyze the continuity of the popular time periods within the forecast period;

[0083] Step 4: Based on the continuity analysis results of the popular time period, analyze the shelf life and production date of the product, determine the storage time point when the continuity signal is generated, the storage time point when the discontinuity signal is generated, and the storage quantity of the product;

[0084] Step 5: De-duplication and analyze the popular time periods for all product categories to determine the sales distribution duration of products in popular time periods with a small number of products and the sales distribution duration of products in popular time periods with a large number of products.

[0085] Example 5

[0086] Reference Figure 3 An embodiment of the present invention further provides a computer device 3, comprising: a memory 302, a processor 301, and a computer program 303 stored on the memory 302. When the computer program 303 is executed on the processor 301, a big data artificial intelligence analysis module as described in any one of the above systems is implemented.

[0087] The computer device 3 may be a desktop computer, a notebook computer, a PDA, a cloud server or other computing devices. The computer device 3 may include, but is not limited to, a processor 301 and a memory 302. Those skilled in the art will understand that Figure 3 This is merely an example of the computer device 3 and does not constitute a limitation on the computer device 3 . The computer device 3 may include more or fewer components than shown in the figure, or a combination of certain components, or different components. For example, the computer device 3 may also include input and output devices, network access devices, etc.

[0088] The processor 301 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, or discrete hardware components. A general-purpose processor may be a microprocessor or any conventional processor.

[0089] In some embodiments, the memory 302 may be an internal storage unit of the computer device 3, such as a hard disk or memory of the computer device 3. In other embodiments, the memory 302 may also be an external storage device of the computer device 3, such as a plug-in hard disk, a Smart Media Card (SMC), a Secure Digital (SD) card, a Flash Card, etc. equipped on the computer device 3. Furthermore, the memory 302 may include both an internal storage unit of the computer device 3 and an external storage device. The memory 302 is used to store an operating system, application programs, a boot loader, data, and other programs, such as the program code of the computer program. The memory 302 may also be used to temporarily store data that has been output or is about to be output.

[0090] Example 6

[0091] An embodiment of the present invention also provides a computer-readable storage medium on which a computer program is stored. When the computer program is executed by a processor, it implements a big data artificial intelligence analysis module as described in any of the above systems.

[0092] In this embodiment, if the integrated unit is implemented as 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 present application implements all or part of the process in the above-mentioned method embodiment by instructing the relevant hardware through a computer program. The computer program can be stored in a computer-readable storage medium. When executed by a processor, the computer program can implement the steps of each of the above-mentioned method embodiments. The computer program includes computer program code, which can be in source code form, object code form, executable file, or some intermediate form. The computer-readable medium can at least include: any entity or device capable of carrying computer program code to the camera / terminal device, recording medium, computer memory, read-only memory (ROM), random access memory (RAM), electric carrier signal, telecommunication signal, and software distribution medium. For example, a USB flash drive, mobile hard drive, magnetic disk, or optical disk. In some jurisdictions, based on legislation and patent practice, computer-readable media cannot be electric carrier signals or telecommunication signals.

[0093] In the above embodiments, the description of each embodiment has its own focus. For parts that are not described or recorded in detail in a certain embodiment, reference can be made to the relevant description of other embodiments.

[0094] Those skilled in the art will appreciate that the units and algorithm steps of each example described in conjunction with the embodiments disclosed herein can be implemented in electronic hardware, or a combination of computer software and electronic hardware. Whether these functions are performed in hardware or software depends on the specific application and design constraints of the technical solution. Professional and technical personnel can use different methods to implement the described functions for each specific application, but such implementation should not be considered beyond the scope of this application.

[0095] In the embodiments disclosed in this application, it should be understood that the disclosed apparatus / terminal device and method can be implemented in other ways. For example, the apparatus / terminal device embodiments described above are merely illustrative. For example, the division of the modules or units is merely a logical functional division. In actual implementation, other division methods may be used, such as combining or integrating multiple units or components into another system, or ignoring or not implementing certain features.

[0096] On the other hand, the mutual coupling or direct coupling or communication connection shown or discussed may be an indirect coupling or communication connection through some interface, device or unit, which may be electrical, mechanical or other forms.

[0097] The units described as separate components may or may not be physically separate, and the components shown as units may or may not be physical units, that is, they may be located in one place or distributed across multiple network units. Some or all of these units may be selected to achieve the purpose of this embodiment according to actual needs.

[0098] The above formulas are all dimensionless and numerical calculations. The formulas are obtained by collecting a large amount of data and performing software simulation to obtain the most recent real situation. The preset parameters in the formulas are set by technicians in this field according to actual conditions.

[0099] The above is a detailed description of an embodiment of the present invention. However, the content described is only a preferred embodiment of the present invention and should not be considered to limit the scope of the present invention. All equivalent changes and improvements made within the scope of the present invention should still fall within the scope of the patent coverage of the present invention.

Claims

1. A big data artificial intelligence analysis platform, characterized by: include: Analyze the historical sales volume of the product in the historical period and determine the total forecast sales volume in the forecast period; Based on all the predicted sales volume within the forecast period and the historical sales volume of the product, determine the popular time period and analyze the continuity of the popular time period within the forecast period; Based on the continuity analysis results of popular time periods, analyze the shelf life and production date of the product, determine the storage time point when the continuity signal is generated, the storage time point when the discontinuity signal is generated, and the storage quantity of the product; De-duplication analysis is performed on the popular time periods for all product categories to determine the sales allocation duration for products in popular time periods with a small number of products and the sales allocation duration for products in popular time periods with a large number of products.

2. A big data artificial intelligence analysis platform according to claim 1, characterized in that: Divide the historical period into several historical periods, count the sales quantity of the goods in the historical period, and record it as the historical sales volume; preset the forecast period, and divide the forecast period into several forecast periods; Use the sliding window average method to calculate the moving average corresponding to the forecast period as the forecast sales volume for the forecast period. Similarly, determine all the forecast sales volumes within the forecast period.

3. A big data artificial intelligence analysis platform according to claim 2, characterized in that: Obtain the sales quantity of goods in multiple historical periods, sum and average them to obtain the historical sales average; if the predicted sales volume ≥ the historical sales average, mark the corresponding predicted period as a popular period.

4. A big data artificial intelligence analysis platform according to claim 3, characterized in that: Integrate the marked results of all prediction periods into a period list, and traverse all prediction periods after the first popular period in the period list until the first non-popular period or the end of the list; If the number of popular periods between the start time of the first popular period and the start time of the first non-popular period is ≥ 2, a continuity signal is generated; If the number of hot periods between the start time point of the first hot period and the start time point of the first non-hot period=1, a discontinuity signal is generated.

5. A big data artificial intelligence analysis platform according to claim 4, characterized in that: Get the remaining shelf life of the product, extract the time period between the start time of the first popular period and the start time of the first non-popular period, and record it as a continuous period; If the duration of the continuous period is greater than or equal to the duration of the remaining shelf life, the start time of the continuous period is used as the earliest storage time, and the difference between the end time of the continuous period and the time point corresponding to the remaining shelf life is processed to obtain the latest storage time. Any time point between the earliest storage time point and the latest storage time point is used as the storage time point; If the duration corresponding to the continuous period is less than the duration corresponding to the remaining shelf life, the starting time point of the continuous period will be used as the storage time point.

6. A big data artificial intelligence analysis platform according to claim 4, characterized in that: Based on the discontinuous signal, if the duration corresponding to the popular period is ≥ the duration corresponding to the remaining shelf life, the start time of the popular period is used as the earliest storage time point, and the difference between the end time of the popular period and the time point corresponding to the remaining shelf life is processed to obtain the latest storage time point. Any time point between the earliest storage time point and the latest storage time point is used as the storage time point; If the duration corresponding to the popular period is less than the duration corresponding to the remaining shelf life, the start time of the popular period will be used as the storage time point.

7. A big data artificial intelligence analysis platform according to claim 4, characterized in that: Based on the continuity signal, if the duration corresponding to the continuous period is ≥ the duration corresponding to the remaining shelf life, the predicted sales volumes of all popular periods between the popular period corresponding to the storage time point and the popular period corresponding to the time point when the remaining shelf life arrives are summed to obtain the product storage volume. If the duration corresponding to the continuous period is < the duration corresponding to the remaining shelf life, the predicted sales volumes of all popular periods in the continuous period are extracted and summed to obtain the product storage volume.

8. A big data artificial intelligence analysis platform according to claim 4, characterized in that: Based on non-continuous signals, if the duration corresponding to the popular period is ≥ the duration corresponding to the remaining shelf life, the historical sales volume between the same historical storage time point and the end time point of the popular period is counted and used as the product storage volume. If the duration corresponding to the popular period is < the duration corresponding to the remaining shelf life, the predicted sales volume of the popular period is used as the product storage volume.

9. The big data artificial intelligence analysis platform according to claim 4, characterized in that: Remove duplicates from the popular time periods of all products to obtain the target popular time period; Count the number of product types within the target popular time period and compare it with the number of all product types to obtain the product type ratio within the target popular time period. Compare the product type ratio with the product type ratio threshold to determine the popular time period with many products and the popular time period with few products. For products in the popular time period with few products, if the number of product types is greater than 1, the duration corresponding to the popular time period with few products is ratioed with the number of product types to obtain the sales distribution duration of the products included in the popular time period with few products.

10. A big data artificial intelligence analysis platform according to claim 9, characterized in that: Obtain the predicted sales volume of the product during the multi-product popular period and compare it with the predicted total sales volume to obtain the allocation coefficient. The predicted total sales volume is obtained by summing the predicted sales volume of all products during the multi-product popular period. The distribution coefficient is multiplied by the duration corresponding to the multi-product popular period to obtain the sales distribution duration of the products in the multi-product popular period.

Images