Commodity plan management system supporting fourth dimension

Abstract

The invention relates to a commodity plan management system supporting a fourth dimension, which is applied to the technical field of e-commerce, and comprises the steps: obtaining the historical sales data of a commodity in a time dimension, a space dimension, a product dimension and a medium dimension required by the subsequent commodity sales prediction through a data integration module, a sales prediction module is used for predicting sales volume in three dimensions of traditional time, space and products, a fourth dimension, namely a medium dimension, can be added on the basis of the three dimensions of the traditional time, space and products to predict the sales volume of the commodities, and a prediction mode is determined according to whether the commodities contain medium attributes or not. Compared with the prior art, the accuracy of commodity sales volume prediction under the condition that commodities have medium attributes is improved; a commodity sales plan is generated through the commodity planning module according to the predicted sales data, a store is helped to reasonably plan the inventory level, the inventory cost and the storage cost are reduced, and waste caused by commodity overstock is reduced.

Description

Technical Field

[0001] The present invention relates to the technical field of e-commerce, and in particular to a commodity planning management system supporting the fourth dimension. Background Art

[0002] Accurate sales forecasts can help stores rationally plan inventory levels and optimize raw material procurement plans. By avoiding over-purchasing, they can reduce inventory and storage costs and reduce waste caused by overstocking. At the same time, sales forecasts provide a basis for stores to formulate more accurate marketing and promotion strategies. Based on the forecast results, stores can formulate pricing, promotional activities or preferential strategies for different products to increase sales and customer satisfaction.

[0003] However, existing sales forecasting technologies or methods still remain at the traditional three-dimensional analysis of time, space and product, ignoring the impact of the fourth dimension, the media dimension, on product sales, resulting in low accuracy of existing sales forecasts. Summary of the invention

[0004] In view of this, the purpose of the present invention is to provide a commodity planning management system that supports the fourth dimension, so as to solve the problem that the sales forecasting technology or method in the prior art still remains in the analysis of the traditional three dimensions, namely time, space and product, and ignores the impact of the fourth dimension, that is, the media dimension, on product sales, resulting in low accuracy of the existing sales forecast.

[0005] According to a first aspect of an embodiment of the present invention, there is provided a commodity planning management system supporting a fourth dimension, the system comprising:

[0006] Data integration module: used to obtain the historical sales data of commodities in time dimension, space dimension, product dimension and media dimension, and send the acquired historical sales data to the sales forecasting module;

[0007] Sales forecast module:

[0008] Used to input historical sales data of the commodity to be predicted in the time dimension, space dimension and product dimension into a pre-trained commodity sales prediction model, and the pre-trained commodity sales prediction model outputs sales data of different product types of the commodity to be predicted in different regions within a preset time period in the future;

[0009] It is also used to input the historical sales data of the commodity to be predicted in the time dimension, space dimension, product dimension and media dimension into the pre-trained commodity sales prediction model, and the pre-trained commodity sales prediction model outputs the media dimension sales data of different product types of the commodity to be predicted in different regions within a preset time period in the future;

[0010] Product planning module: used to generate a product sales plan based on the sales data predicted by the sales module or the media dimension sales data.

[0011] Preferably, it also includes:

[0012] Intelligent report generation module: used to generate and display reports based on the sales data or media dimension sales data generated by the sales forecasting module, or the commodity sales plan generated by the commodity planning module.

[0013] Preferably,

[0014] The construction of the pre-trained commodity sales prediction model includes:

[0015] Acquire historical sales data of the commodity, and preprocess the historical sales data of the commodity, wherein the preprocessing includes: filling missing values, filling abnormal values, and / or normalizing the historical sales data;

[0016] Extracting sales features from the preprocessed historical sales data, the sales features including: time series features, spatial region features, product type features, and media features, to obtain training set data;

[0017] A loss function is set, and the parameters of the pre-built LSTM model architecture are iteratively trained using the training set data until the preset number of iterations is met or the model loss no longer decreases, thereby obtaining a pre-trained commodity sales prediction model.

[0018] Preferably,

[0019] The data integration module includes various types of data interfaces to support the acquisition of various types of data sources.

[0020] Preferably,

[0021] The data integration module is also used to execute a data extraction strategy, which includes a data extraction frequency and an incremental extraction of data.

[0022] Preferably,

[0023] The data integration module is also used to clean the acquired data to remove duplicate data, fill in missing values ​​and format data;

[0024] The data integration module is also used to convert the acquired data into the data type required by the sales forecast module;

[0025] The data integration module is also used to perform data verification on the acquired data to ensure the consistency and integrity of the data.

[0026] Preferably,

[0027] The commodity planning module is also used to support manual modification of the commodity sales plan after generating the commodity sales plan, and save the modified data into the system database.

[0028] Preferably,

[0029] The commodity sales plan includes: historical sales data, forecast sales data and planned sales data of different product types in different regions, different media scales and different time scales, wherein the forecast sales data is initially equal to the planned sales data;

[0030] The planned sales data is manually modified through the commodity planning module.

[0031] The technical solution provided by the embodiments of the present invention may have the following beneficial effects:

[0032] This application obtains the historical sales data of commodities in the time dimension, space dimension, product dimension and media dimension required for subsequent commodity sales forecasting through the data integration module, and performs sales forecasting in the traditional three dimensions of time, space and product through the sales forecasting module. It can also add a fourth dimension, that is, the media dimension, on the basis of the traditional three dimensions of time, space and product to predict commodity sales, and determine the prediction method according to whether the commodity contains media attributes. Compared with the existing technology, the accuracy of commodity sales forecasting in the case of media attributes is improved; the commodity planning module generates a sales plan for the commodity according to the predicted sales data, so as to help stores reasonably plan inventory levels, reduce inventory costs and storage costs, and reduce waste caused by backlog of commodities.

[0033] It is to be understood that both the foregoing general description and the following detailed description are exemplary and explanatory only and are not restrictive of the invention. BRIEF DESCRIPTION OF THE DRAWINGS

[0034] The accompanying drawings, which are incorporated in and constitute a part of this specification, illustrate embodiments consistent with the invention and, together with the description, serve to explain the principles of the invention.

[0035] Figure 1 is a system schematic diagram showing a fourth-dimensional commodity planning management system according to an exemplary embodiment;

[0036] Figure 2 is a schematic diagram of sales forecast data of a certain commodity in the album dimension according to another exemplary embodiment;

[0037] Figure 3 is a schematic diagram of commodity sales plan data of a certain commodity in the album dimension according to another exemplary embodiment;

[0038] In the attached figure: 1-data integration module, 2-sales forecasting module, 3-product planning module, 4-intelligent report generation module. DETAILED DESCRIPTION

[0039] Exemplary embodiments will be described in detail herein, examples of which are shown in the accompanying drawings. When the following description refers to the drawings, the same numbers in different drawings represent the same or similar elements unless otherwise indicated. The embodiments described in the following exemplary embodiments do not represent all embodiments consistent with the present invention. Instead, they are merely examples of devices and methods consistent with some aspects of the present invention as detailed in the appended claims.

[0040] Embodiment 1

[0041] Figure 1 is a schematic diagram of a system supporting a fourth-dimensional commodity planning management system according to an exemplary embodiment. Figure 1 As shown, the system includes:

[0042] Data integration module 1: used to obtain historical sales data of commodities in time dimension, space dimension, product dimension and media dimension, and send the obtained historical sales data to sales forecasting module 2;

[0043] Sales Forecast Module 2:

[0044] Used to input historical sales data of the commodity to be predicted in the time dimension, space dimension and product dimension into a pre-trained commodity sales prediction model, and the pre-trained commodity sales prediction model outputs sales data of different product types of the commodity to be predicted in different regions within a preset time period in the future;

[0045] It is also used to input the historical sales data of the commodity to be predicted in the time dimension, space dimension, product dimension and media dimension into the pre-trained commodity sales prediction model, and the pre-trained commodity sales prediction model outputs the media dimension sales data of different product types of the commodity to be predicted in different regions within a preset time period in the future;

[0046] Commodity planning module 3: used to generate a commodity sales plan according to the sales data predicted by the sales module or the media dimension sales data;

[0047] Intelligent report generation module 4: used to generate and display reports based on the sales data or media dimension sales data generated by the sales forecast module 2, or the commodity sales plan generated by the commodity planning module 3;

[0048] It can be understood that the core of the design of this application is to optimize the sales of commodity management by integrating and analyzing data from four key dimensions, among which the time dimension refers to the trend and cyclical changes in commodity sales over time, the spatial dimension refers to the impact of geographical location distribution on commodity sales, and the product dimension refers to the impact of the product's own characteristics on commodity sales. The product's own characteristics can be factors such as the product's model, color, shape, and material; the media dimension (the fourth dimension) refers to consumer behavior preferences, market sentiment, supply chain status, and can also be the impact of non-traditional factors such as advertising activities, major business events, or marketing media on commodity sales, for example :In addition to conventional business channels (people, goods and venues), a certain retail brand has a very important business of marketing through picture albums. Therefore, the business indicators related to picture albums become an important dimension for product analysis and planning. In this scenario, picture albums can be considered as the media dimension of the retail brand, that is, the fourth dimension. The sales data of goods participating in the fourth dimension picture album sales must have picture album tags, and the data not participating in the picture album but sold in traditional channels must have conventional dimension tags; attribute tags of picture albums: picture album type, picture album release season, picture album display width, etc. In order to facilitate the understanding of this application, the following contents of this embodiment are all explained with picture albums as the media dimension of goods;

[0049] Data Integration Module 1: This module is responsible for collecting, converting, cleaning and integrating data from different external data sources for use by the sales forecasting module in the system; Data Integration Module 1 includes the following core functions:

[0050] (1) Data extraction

[0051] Define data sources: Support multiple data source types, such as file systems and API interfaces.

[0052] Data extraction strategy: defines extraction frequency, incremental extraction mechanism, etc.; incremental extraction refers to extracting new, modified, and deleted data from the table to be extracted in the database since the last extraction. In the use of ETL tools, incremental extraction is more widely used than full extraction.

[0053] Data category: dimensional data (historical sales data under the time dimension, product dimension, location dimension and media dimension). Media data can be picture albums, such as 4 / 1P, 1P, 2P and 4P picture albums.

[0054] (2) Data conversion

[0055] Data cleaning: remove duplicate data, fill missing values, format data, etc.

[0056] Data conversion: perform arithmetic operations, convert data types, perform complex calculations, etc.

[0057] (3) Data loading

[0058] Target data storage: Load the processed data into the system backend database.

[0059] (4) Data quality monitoring

[0060] Data verification: ensure the consistency and integrity of data.

[0061] Error handling: record error logs and provide error recovery mechanisms.

[0062] Sales forecasting module 2: This module is used to forecast sales volume based on the historical sales data of commodities in four dimensions provided by the data integration module, including traditional sales volume forecast and fourth dimension sales volume forecast;

[0063] It has the following characteristics:

[0064] Time dimension analysis:

[0065] Trend analysis: identifying trends in sales over time;

[0066] Seasonality analysis: Detect sales fluctuations during specific periods (such as holidays, promotions) (time dimension);

[0067] Periodic patterns: Identify periodic patterns in sales data;

[0068] External factors to consider:

[0069] Promotions: predict the impact of promotions on sales;

[0070] Multidimensional analysis:

[0071] Product dimension: sales forecast for different categories of products;

[0072] Spatial dimension: Adjust the forecast based on sales in different regions. Different regions here can be sales changes between different stores, different business districts, or even different cities.

[0073] Media dimension: sales forecast for different fourth dimensions. For example, if the album is defined as the fourth dimension in the above example, the sales of products in different albums can be predicted.

[0074] The sales forecast module 2 can perform sales forecasts in the traditional three dimensions of time, space and product, as well as sales forecasts in the four dimensions of time, space, product and media (such as the above-mentioned album). The sales forecast uses the existing AI model. This application obtains a commodity sales forecast model by training the LSTM model architecture, and places the trained model in the system background or directly embeds it in the sales forecast module 2 for the sales forecast module 2 to call;

[0075] Among them, the training of the commodity sales prediction model includes:

[0076] Obtaining historical sales data of the product and performing preprocessing, the preprocessing including: filling missing values, and / or filling outliers, and / or normalizing the historical sales data;

[0077] Extract sales features from the preprocessed historical sales data, including time series features, spatial region features, product type features, and media features, to obtain training set data;

[0078] Set the loss function and iteratively train the parameters of the pre-built LSTM model architecture using the training set data until the preset number of iterations is met or the model loss no longer decreases, thus obtaining a pre-trained product sales prediction model;

[0079] It should be noted that in the sales forecast module 2, the user can also select data from any number of dimensions to input into the product sales forecast model and perform sales (must be one or more of the time, space, product and media dimensions). For example, the sales forecast of a certain product is performed using the time dimension and the media dimension (picture album). The forecast results are shown in the attached figure. Figure 2 As shown;

[0080] The commodity planning module 3 is used to generate a commodity sales plan based on the sales data predicted by the sales module or the sales data of the media dimension. Depending on the different dimensional data used, the commodity sales plan may include: historical sales data, predicted sales data and planned sales data of different product types in different regions, different media scales and different time scales, wherein the predicted sales data and historical sales data cannot be changed, and the planned sales data is initially the same as the predicted sales data, but the commodity planning module 3 provides a manual change interface, and the user can flexibly adjust the sales plan by manually modifying the planned sales data. Assuming that the sales volume of a certain commodity is predicted based on the time dimension and the media dimension (picture album), the corresponding sales plan data generated is as shown in the attached figure. Figure 3 As shown;

[0081] Intelligent report generation module 4: This module is used to present historical sales data with time series from different dimensional perspectives, forecasted sales data, and planned sales data in a report format based on historical sales data, forecasted sales data, and planned sales data under different dimensions; customers can use the custom business report page provided by this module to define their own reports. When the customer selects the business fields to be run and saves them, the intelligent report generation module 4 will automatically generate SQL statements dynamically according to the report definition, query data, merge data, and perform other operations, and finally output the report in Excel format.

[0082] Sales forecasts can help businesses develop better promotion strategies, such as collecting sales data from stores over the past three years, combining it with geographic location information to analyze how consumers’ purchasing preferences change with the seasons in different regions, and operational KPIs such as best-selling and slow-selling items; using media data to analyze the correlation between product sales and media in a specific time period, predict future trends, and identify user behavior patterns to discover the degree of acceptance of new products by specific user groups, and adjust product promotion strategies accordingly.

[0083] This application provides a fourth-dimensional commodity planning management system that can achieve:

[0084] Refined management: Through comprehensive analysis of the performance of goods at different times, locations, product categories and new dimensions, it helps companies accurately identify market opportunities and potential problems and develop more granular and accurate product plans.

[0085] Forecasting and Optimization: Use historical data and real-time information to forecast commodity demand, optimize inventory levels, reduce overstocking and out-of-stock situations, and improve capital turnover;

[0086] Strategy formulation: Based on multi-dimensional analysis results, we provide enterprises with customized pricing, promotion, procurement and inventory management strategy suggestions;

[0087] Decision support: Through intuitive charts and reports, provide management with data-driven decision-making basis to improve decision-making efficiency and accuracy. In short, this application aims to improve the intelligence and automation level of commodity management through comprehensive four-dimensional analysis, and enhance the company's market adaptability and competitive advantage.

[0088] It can be understood that the same or similar parts of the above embodiments can be referenced to each other, and the contents not described in detail in some embodiments can refer to the same or similar contents in other embodiments.

[0089] It should be noted that, in the description of the present invention, the terms "first", "second", etc. are only used for descriptive purposes and cannot be understood as indicating or implying relative importance. In addition, in the description of the present invention, unless otherwise specified, the meaning of "plurality" refers to at least two.

[0090] Any process or method description in a flowchart or otherwise described herein may be understood to represent a module, segment or portion of code that includes one or more executable instructions for implementing the steps of a specific logical function or process, and the scope of the preferred embodiments of the present invention includes alternative implementations in which functions may not be performed in the order shown or discussed, including performing functions in a substantially simultaneous manner or in the reverse order depending on the functions involved, which should be understood by those skilled in the art to which the embodiments of the present invention belong.

[0091] It should be understood that the various parts of the present invention can be implemented by hardware, software, firmware or a combination thereof. In the above-mentioned embodiments, a plurality of steps or methods can be implemented by software or firmware stored in a memory and executed by a suitable instruction execution system. For example, if implemented by hardware, as in another embodiment, it can be implemented by any one of the following technologies known in the art or their combination: a discrete logic circuit having a logic gate circuit for implementing a logic function for a data signal, a dedicated integrated circuit having a suitable combination of logic gate circuits, a programmable gate array (PGA), a field programmable gate array (FPGA), etc.

[0092] A person skilled in the art may understand that all or part of the steps in the method for implementing the above-mentioned embodiment may be completed by instructing related hardware through a program, and the program may be stored in a computer-readable storage medium, which, when executed, includes one or a combination of the steps of the method embodiment.

[0093] In addition, each functional unit in each embodiment of the present invention may be integrated into a processing module, or each unit may exist physically separately, or two or more units may be integrated into one module. The above-mentioned integrated module may be implemented in the form of hardware or in the form of a software functional module. If the integrated module is implemented in the form of a software functional module and sold or used as an independent product, it may also be stored in a computer-readable storage medium.

[0094] The storage medium mentioned above can be a read-only memory, a magnetic disk or an optical disk, etc.

[0095] In the description of this specification, the description with reference to the terms "one embodiment", "some embodiments", "examples", "specific examples", or "some examples" means that the specific features, structures, materials or characteristics described in conjunction with the embodiment or example are included in at least one embodiment or example of the present invention. In this specification, the schematic representation of the above terms does not necessarily refer to the same embodiment or example. Moreover, the specific features, structures, materials or characteristics described may be combined in any one or more embodiments or examples in a suitable manner.

[0096] Although the embodiments of the present invention have been shown and described above, it is to be understood that the above embodiments are exemplary and are not to be construed as limitations of the present invention. A person skilled in the art may change, modify, replace and vary the above embodiments within the scope of the present invention.

Claims

1. A commodity planning management system supporting the fourth dimension, characterized in that: The system comprises: Data integration module: used to obtain the historical sales data of commodities in time dimension, space dimension, product dimension and media dimension, and send the acquired historical sales data to the sales forecasting module; Sales forecast module: Used to input historical sales data of the commodity to be predicted in the time dimension, space dimension and product dimension into a pre-trained commodity sales prediction model, and the pre-trained commodity sales prediction model outputs sales data of different product types of the commodity to be predicted in different regions within a preset time period in the future; It is also used to input the historical sales data of the commodity to be predicted in the time dimension, space dimension, product dimension and media dimension into the pre-trained commodity sales prediction model, and the pre-trained commodity sales prediction model outputs the media dimension sales data of different product types of the commodity to be predicted in different regions within a preset time period in the future; Product planning module: used to generate a product sales plan based on the sales data predicted by the sales module or the media dimension sales data.

2. The system according to claim 1, characterized in that Also includes: Intelligent report generation module: used to generate and display reports based on the sales data or media dimension sales data generated by the sales forecasting module, or the commodity sales plan generated by the commodity planning module.

3. The system according to claim 2, characterized in that The construction of the pre-trained commodity sales prediction model includes: Acquire historical sales data of the commodity, and preprocess the historical sales data of the commodity, wherein the preprocessing includes: filling missing values, filling abnormal values, and / or normalizing the historical sales data; Extracting sales features from the preprocessed historical sales data, the sales features including: time series features, spatial region features, product type features, and media features, to obtain training set data; A loss function is set, and the parameters of the pre-built LSTM model architecture are iteratively trained using the training set data until the preset number of iterations is met or the model loss no longer decreases, thereby obtaining a pre-trained commodity sales prediction model.

4. The system according to claim 3, characterized in that The data integration module includes various types of data interfaces to support the acquisition of various types of data sources.

5. The system according to claim 4, characterized in that The data integration module is also used to execute a data extraction strategy, which includes a data extraction frequency and an incremental extraction of data.

6. The system according to claim 5, characterized in that The data integration module is also used to clean the acquired data to remove duplicate data, fill in missing values ​​and format data; The data integration module is also used to convert the acquired data into the data type required by the sales forecast module; The data integration module is also used to perform data verification on the acquired data to ensure the consistency and integrity of the data.

7. The system according to claim 6, characterized in that The commodity planning module is also used to support manual modification of the commodity sales plan after generating the commodity sales plan, and save the modified data into the system database.

8. The system according to claim 7, characterized in that The commodity sales plan includes: historical sales data, forecast sales data and planned sales data of different product types in different regions, different media scales and different time scales, wherein the forecast sales data is initially equal to the planned sales data; The planned sales data is manually modified through the commodity planning module.

Images