Retail industry automation target distribution realization method, device, equipment and medium

Abstract

The invention discloses a retail industry automatic target distribution implementation method, device and equipment and a medium, and relates to the technical field of data intelligent prediction, and the method comprises the steps: collecting sales related data, and carrying out the data cleaning and standardization processing of the collected data; the sales related data comprises historical sales data of each channel, user behavior data, inventory data and external factor data; analyzing the processed sales related data based on a time sequence analysis mode, and predicting through a deep learning model to obtain a future sales trend; and according to the predicted future sales trend, in combination with the sales target and the sales influence factors, making a sales plan and distributing the sales plan to each sales channel and sales team. According to the method, the sales trend is intelligently predicted, the sales plan is optimized, and the sales efficiency and accuracy are effectively improved.

Description

Technical Field

[0001] The present application relates to the field of data intelligent prediction technology, and specifically to a method, device, equipment and medium for realizing automated target distribution in the retail industry. Background Art

[0002] The retail industry refers to the commodity sales industry that sells products produced by industrial and agricultural producers directly to residents for daily consumption or to social groups for public consumption through buying and selling. The most common form is the retail store format, which includes department stores, specialty stores, supermarkets, convenience stores, discount stores, warehouse stores, etc.

[0003] Currently, the retail industry still relies on traditional sales data and manual experience judgment to forecast sales trends and distribute sales targets, which results in problems such as low efficiency and poor target accuracy. Summary of the invention

[0004] The present application provides a method, device, equipment and medium for realizing automated target distribution in the retail industry, which can effectively improve sales efficiency and accuracy by intelligently predicting sales trends and optimizing sales plans.

[0005] In a first aspect, an embodiment of the present application provides a method for implementing automated target distribution in the retail industry, the method comprising:

[0006] Collect sales-related data and perform data cleaning and standardization on the collected data, wherein the sales-related data includes historical sales data of each channel, user behavior data, inventory data, and external factor data;

[0007] Analyze the processed sales-related data based on time series analysis, and predict future sales trends through deep learning models;

[0008] Based on the predicted future sales trends, combined with sales targets and sales influencing factors, formulate sales plans and distribute them to various sales channels and sales teams.

[0009] In combination with the first aspect, in one implementation,

[0010] The historical sales data of each channel includes historical sales data of online shopping malls, offline stores and third-party platforms;

[0011] The external factor data includes weather data, holidays, marketing activities, and city data.

[0012] In combination with the first aspect, in one implementation,

[0013] The data cleaning is used to detect and correct erroneous, incomplete, inaccurate, and inapplicable data parts in the data, and the data cleaning methods specifically include processing missing values, deleting duplicates, and processing outliers;

[0014] The standardization process is used to convert the data into a unified standard format, and the length of the data field in the standard format meets the maximum length requirement.

[0015] In combination with the first aspect, in one implementation, the processed sales-related data is analyzed based on a time series analysis method, wherein:

[0016] The time series analysis methods include trend analysis, seasonal analysis, periodic analysis, and marketing strategy analysis;

[0017] The trend analysis is to draw a time series graph using MA or EMA to observe the trend of sales data over time;

[0018] The seasonal analysis is to consider holidays and seasonal changes, and use STL analysis to separate seasonal factors from sales data;

[0019] The periodic analysis is to consider annual, quarterly or monthly cycles, analyze the cycle length and fluctuation range, and provide training parameters for the deep learning model;

[0020] The marketing strategy analysis is to track the sales changes brought about by marketing activities based on historical and future marketing strategies, and provide training parameters for the deep learning model.

[0021] In conjunction with the first aspect, in one implementation, predicting future sales trends through a deep learning model specifically includes:

[0022] Create a deep learning model of the long short-term memory network, and adjust the deep learning model structure and parameters according to the training set data characteristics and prediction requirements;

[0023] Convert historical data into feature data for a deep learning model, wherein the historical data includes historical sales data, seasonal indicators, trend indicators, and marketing activities;

[0024] Considering the seasonality, trend, and cyclical factors of sales-related data, a training set is constructed to train the deep learning model;

[0025] Future sales trends are predicted based on the trained deep learning model.

[0026] In conjunction with the first aspect, in one implementation, formulating a sales plan based on the predicted future sales trend and in combination with sales targets and sales influencing factors and distributing it to each sales channel and sales team specifically includes:

[0027] Develop sales plans based on predicted future sales trends, combined with sales targets, inventory status, and promotional activities;

[0028] Automatically distribute the sales plan to various sales channels and sales teams;

[0029] The sales plan includes the types and quantities of goods, promotion strategies, and sales channel allocation.

[0030] In conjunction with the first aspect, in one implementation, after the sales plan is formulated and distributed to each sales channel and sales team, the method further includes:

[0031] Monitor sales data in real time, evaluate the execution of the sales plan based on the real-time sales data obtained, and adjust the parameters of the deep learning model based on the evaluation results to achieve iterative optimization of the deep learning model.

[0032] In a second aspect, an embodiment of the present application provides a device for implementing automated target distribution in the retail industry, the device comprising:

[0033] A collection module, which is used to collect sales-related data and perform data cleaning and standardization on the collected data. The sales-related data includes historical sales data of each channel, user behavior data, inventory data, and external factor data;

[0034] The forecasting module is used to analyze the processed sales-related data based on time series analysis and predict future sales trends through deep learning models;

[0035] The distribution module is used to formulate sales plans and distribute them to various sales channels and sales teams based on the predicted future sales trends, combined with sales targets and sales influencing factors.

[0036] In a third aspect, an embodiment of the present application provides a device for implementing automated target distribution in retail industry, the device comprising a processor, a memory, and a program for implementing automated target distribution in retail industry stored on the memory and executable by the processor, wherein when the program for implementing automated target distribution in retail industry is executed by the processor, the steps of the method for implementing automated target distribution in retail industry described above are implemented.

[0037] In a fourth aspect, an embodiment of the present application provides a computer-readable storage medium, on which is stored a program for implementing automated target distribution for the retail industry. When the program for implementing automated target distribution for the retail industry is executed by a processor, the steps of the method for implementing automated target distribution for the retail industry described above are implemented.

[0038] The beneficial effects brought by the technical solution provided in the embodiments of the present application include:

[0039] By collecting sales-related data and performing data cleaning and standardization on the collected data, the processed sales-related data is analyzed based on time series analysis, and future sales trends are predicted through deep learning models. Then, based on the predicted future sales trends and combined with sales targets and sales influencing factors, sales plans are formulated and distributed to various sales channels and sales teams to achieve automated distribution of sales plans, and through intelligent prediction of sales trends, sales plans are optimized to effectively improve sales efficiency and accuracy. BRIEF DESCRIPTION OF THE DRAWINGS

[0040] Figure 1 This is a flowchart of a method for implementing automated target distribution in the retail industry in this application;

[0041] Figure 2 This is a functional module diagram of the device for realizing automated target distribution in the retail industry of this application;

[0042] Figure 3 This is a schematic diagram of the hardware structure of the equipment for implementing automated target distribution in the retail industry for this application. DETAILED DESCRIPTION

[0043] In order to enable those skilled in the art to better understand the solution of the present application, the technical solution in the embodiments of the present application will be clearly and completely described below in conjunction with the drawings in the embodiments of the present application. Obviously, the described embodiments are only part of the embodiments of the present application, not all of the embodiments. Based on the embodiments in the present application, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of this application.

[0044] In order to make the objectives, technical solutions and advantages of the present application clearer, the implementation methods of the present application will be further described in detail below with reference to the accompanying drawings.

[0045] In a first aspect, an embodiment of the present application provides a method for implementing automated target distribution in the retail industry, which can automatically distribute plan targets, predict sales trends, optimize sales plans, and improve sales efficiency and accuracy.

[0046] In one embodiment, referring to Figure 1 , Figure 1 This is a flowchart of the method for implementing the automated target distribution in the retail industry in this application. Figure 1 As shown, the method for implementing automated target distribution in the retail industry includes:

[0047] S1: Collect sales-related data and perform data cleaning and standardization on the collected data, wherein the sales-related data includes historical sales data of each channel, user behavior data, inventory data, and external factor data;

[0048] Specifically, the historical sales data of each channel includes the historical sales data of online shopping malls, offline stores and third-party platforms; the external factor data includes weather data, holidays, marketing activities, and city data. City data includes information such as the city and population.

[0049] In this application, data cleaning is used to detect and correct erroneous, incomplete, inaccurate, and inapplicable data parts in the data to ensure data quality, and the data cleaning methods specifically include processing missing values ​​(deletion, filling), deleting duplicates, and processing outliers (abnormal values);

[0050] The standardization process is used to convert data into a unified standard format, and the length of the data field in the standard format meets the maximum length requirement. That is, the data is converted into a unified standard format to facilitate data comparison, analysis and modeling. For the type of data format, the following principles must be followed: the field length in the data warehouse should try to meet the maximum length requirement of the corresponding source system field. Of course, the business meaning of the field is also considered. For some source system definitions that are too long, but it is impossible to have such a long field from the actual business meaning, the warehouse will choose a suitable length definition by itself; further, in order to improve versatility, the code field should try not to use numeric type, and use STRING type more.

[0051] S2: Analyze the processed sales-related data based on time series analysis, and predict future sales trends through deep learning models;

[0052] Furthermore, the processed sales-related data is analyzed based on a time series analysis method, wherein: the time series analysis method includes trend analysis, seasonal analysis, periodic analysis, and marketing strategy analysis; the trend analysis is to draw a time series graph using MA (Moving Average) or EMA (Exponential Moving Average) to observe the trend of sales data over time; the seasonal analysis is to consider holidays and seasonal changes, and to separate seasonal factors from sales data using an STL (time series decomposition algorithm) analysis method; the periodic analysis is to consider annual, quarterly or monthly cycles, analyze cycle length and fluctuation range, and provide training parameters for a deep learning model, that is, to analyze changes in sales data in each time period, and to provide a reference for subsequent deep learning model training; the marketing strategy analysis is to track sales changes brought about by marketing activities based on historical and future marketing strategies, and to provide training parameters for a deep learning model, that is, to analyze changes in sales data brought about by marketing strategies, and to provide a reference for subsequent deep learning model training.

[0053] Furthermore, in one embodiment, the future sales trend is predicted by a deep learning model, specifically including:

[0054] S201: Create a deep learning model of long short-term memory network, and adjust the structure and parameters of the deep learning model according to the characteristics of training set data and prediction requirements;

[0055] S202: Convert historical data into feature data of a deep learning model, wherein the historical data includes historical sales data, seasonal indicators, trend indicators, and marketing activities;

[0056] S203: Considering the seasonality, trend and cyclical factors of sales-related data, a training set is constructed to train the deep learning model; that is, when training the deep learning model, the historical sales data is not simply used as a training set to train the deep learning model, but the changes in sales data with seasons, time cycles, marketing strategies and other factors are considered, and seasonality, trend, cyclical and other factors are considered to construct a training set to train the deep learning model; further, for the trained deep learning model, the parameters of the deep learning model can also be optimized to improve the accuracy of the prediction results and reduce the prediction error.

[0057] S204: Predict future sales trends based on the trained deep learning model.

[0058] S3: Based on the predicted future sales trends, combined with sales targets and sales influencing factors, formulate sales plans and distribute them to various sales channels and sales teams.

[0059] Furthermore, in one embodiment, based on the predicted future sales trend and in combination with the sales target and sales influencing factors, a sales plan is formulated and distributed to each sales channel and sales team, specifically including:

[0060] S301: Develop sales plans based on the predicted future sales trends, combined with sales targets, inventory status, and promotional activities;

[0061] S302: Automatically distribute the formulated sales plan to various sales channels and sales teams to ensure the execution and implementation of the sales plan; wherein the sales plan includes the types and quantities of goods, promotion strategies, and sales channel allocation.

[0062] It should be noted that the above-mentioned prediction of future sales trends is achieved through the deep learning model that has been trained to predict sales trends in the future, based on historical sales data, market trends, consumer behavior, competitor dynamics and other factors. For example, for a retail company A, it is predicted that in the next three months, the monthly sales of its main product A will be 1 million, 2 million, and 3 million respectively, showing a monthly growth trend.

[0063] As for sales targets, sales targets are specific sales targets set based on the company's overall strategy and market demand. The targets should be specific, measurable, achievable, and coordinated with predicted sales trends.

[0064] The sales plan can be adjusted to calculate the sales forecasted sales trend and the sales target. The feasibility and risk of the sales plan can be evaluated by simulating sales in different scenarios. In the actual implementation process, the sales plan is adjusted in time according to market feedback and sales data to ensure the achievement of sales targets. For example, during the implementation of the sales plan, the company regularly collects sales data and market feedback and finds that the sales in the first month exceeded expectations. Based on this data, the company decides to increase promotion efforts in the second month and add procurement plans in advance to cope with possible inventory shortages. At the same time, the distribution of sales channels is fine-tuned to better meet market demand.

[0065] Furthermore, after the sales plan is formulated and distributed to various sales channels and sales teams, it also includes: real-time monitoring of sales data, evaluation of the execution of the sales plan based on the real-time sales data obtained through monitoring, and adjustment of the parameters of the deep learning model based on the evaluation results, so as to achieve iterative optimization of the deep learning model and improve the accuracy and effectiveness of the sales plan. For example, when there is a large difference between the predicted sales plan and the actual sales, it is necessary to adjust the parameters of the deep learning model and the interfering factors, such as marketing activities, holidays, weather and other parameters, so as to improve the accuracy of the deep learning model prediction.

[0066] The method for implementing automated target distribution in the retail industry in the embodiment of the present application collects sales-related data and performs data cleaning and standardization on the collected data, then analyzes the processed sales-related data based on a time series analysis method, and predicts future sales trends through a deep learning model. Then, based on the predicted future sales trends and in combination with sales targets and sales influencing factors, a sales plan is formulated and distributed to each sales channel and sales team, thereby realizing automated distribution of the sales plan, and optimizing the sales plan through intelligent prediction of sales trends, thereby effectively improving sales efficiency and accuracy.

[0067] In a second aspect, an embodiment of the present application also provides a device for implementing automated target distribution in the retail industry.

[0068] In one embodiment, referring to Figure 2 , Figure 2 This is a functional module diagram of the device for implementing the automated target distribution in the retail industry of this application. Figure 2 As shown, the device for realizing automated target distribution in the retail industry includes: a collection module, a prediction module, and a distribution module.

[0069] The collection module is used to collect sales-related data and perform data cleaning and standardization on the collected data. The sales-related data includes historical sales data of each channel, user behavior data, inventory data, and external factor data; the prediction module is used to analyze the processed sales-related data based on time series analysis, and predict future sales trends through a deep learning model; the distribution module is used to formulate sales plans based on the predicted future sales trends and in combination with sales targets and sales influencing factors, and distribute them to various sales channels and sales teams.

[0070] In a third aspect, an embodiment of the present application provides a device for implementing automated target distribution in the retail industry. The device for implementing automated target distribution in the retail industry may be a personal computer (PC), a laptop computer, a server, or other device with data processing capabilities.

[0071] Reference Figure 3 , Figure 3 The hardware structure diagram of the device for realizing the automated target distribution in the retail industry involved in the embodiment of the present application is shown in FIG. In the embodiment of the present application, the device for realizing the automated target distribution in the retail industry may include a processor, a memory, a communication interface and a communication bus.

[0072] The communication bus may be of any type and is used to interconnect the processor, the memory, and the communication interface.

[0073] The communication interface includes input / output (I / O) interface, physical interface and logical interface, etc., which are used to interconnect the devices inside the retail industry automated target distribution implementation device, and the interface used to interconnect the retail industry automated target distribution implementation device with other devices (such as other computing devices or user devices). The physical interface can be an Ethernet interface, a fiber optic interface, an ATM interface, etc.; the user device can be a display, a keyboard, etc.

[0074] The memory can be various types of storage media, such as random access memory (RAM), read-only memory (ROM), non-volatile RAM (NVRAM), flash memory, optical storage, hard disk, programmable ROM (PROM), erasable PROM (EPROM), electrically erasable PROM (EEPROM), etc.

[0075] The processor may be a general-purpose processor, which may call the retail industry automation target distribution implementation program stored in the memory and execute the retail industry automation target distribution implementation method provided by the embodiment of the present application. For example, the general-purpose processor may be a central processing unit (CPU). The method executed when the retail industry automation target distribution implementation program is called may refer to the various embodiments of the retail industry automation target distribution implementation method of the present application, which will not be repeated here.

[0076] Those skilled in the art will understand that Figure 3 The hardware structure shown in the figure does not constitute a limitation on the present application, and may include more or less components than shown in the figure, or combine certain components, or arrange the components differently.

[0077] In a fourth aspect, an embodiment of the present application also provides a computer-readable storage medium.

[0078] The computer-readable storage medium of the present application stores a program for realizing automated target distribution for the retail industry, wherein when the program for realizing automated target distribution for the retail industry is executed by a processor, the steps of the method for realizing automated target distribution for the retail industry as described above are realized.

[0079] Among them, the method implemented when the retail industry automated target distribution implementation program is executed can refer to the various embodiments of the retail industry automated target distribution implementation method of the present application, and will not be repeated here.

[0080] It should be noted that the serial numbers of the above-mentioned embodiments of the present application are only for description and do not represent the advantages or disadvantages of the embodiments.

[0081] The terms "including" and "having" and any variations thereof in the specification and claims of this application and the above-mentioned drawings are intended to cover non-exclusive inclusions. For example, a process, method, system, product or device that includes a series of steps or units is not limited to the listed steps or units, but optionally includes steps or units that are not listed, or optionally includes other steps or units inherent to these processes, methods, products or devices. The terms "first", "second" and "third" are used to distinguish different objects, etc., and do not represent a sequence, nor do they limit "first", "second" and "third" to different types.

[0082] In the description of the embodiments of the present application, "exemplary", "for example" or "for example" are used to indicate examples, illustrations or descriptions. Any embodiment or design described as "exemplary", "for example" or "for example" in the embodiments of the present application should not be interpreted as being more preferred or more advantageous than other embodiments or designs. Specifically, the use of words such as "exemplary", "for example" or "for example" is intended to present related concepts in a specific way.

[0083] In the description of the embodiments of the present application, unless otherwise specified, “ / ” means or, for example, A / B can mean A or B; the “and / or” in the text is merely a description of the association relationship of associated objects, indicating that three relationships may exist, for example, A and / or B can mean: A exists alone, A and B exist at the same time, and B exists alone. In addition, in the description of the embodiments of the present application, “multiple” refers to two or more than two.

[0084] In some processes described in the embodiments of the present application, multiple operations or steps that appear in a specific order are included, but it should be understood that these operations or steps may not be executed in the order in which they appear in the embodiments of the present application or in parallel, and the sequence number of the operation is only used to distinguish the different operations, and the sequence number itself does not represent any execution order. In addition, these processes may include more or fewer operations, and these operations or steps may be executed in sequence or in parallel, and these operations or steps may be combined.

[0085] Through the description of the above implementation methods, those skilled in the art can clearly understand that the above-mentioned embodiment methods can be implemented by means of software plus a necessary general hardware platform, and of course by hardware, but in many cases the former is a better implementation method. Based on such an understanding, the technical solution of the present application is essentially or the part that contributes to the prior art can be embodied in the form of a software product, which is stored in a storage medium (such as ROM / RAM, disk, CD) as described above, and includes a number of instructions for a terminal device to execute the methods described in each embodiment of the present application.

[0086] The above are only preferred embodiments of the present application, and are not intended to limit the patent scope of the present application. Any equivalent structure or equivalent process transformation made using the contents of the present application specification and drawings, or directly or indirectly applied in other related technical fields, are also included in the patent protection scope of the present application.

Claims

1. A method for realizing automated target distribution in the retail industry, characterized in that: The method for implementing automated target distribution in the retail industry includes: Collect sales-related data and perform data cleaning and standardization on the collected data, wherein the sales-related data includes historical sales data of each channel, user behavior data, inventory data, and external factor data; Analyze the processed sales-related data based on time series analysis, and predict future sales trends through deep learning models; Based on the predicted future sales trends, combined with sales targets and sales influencing factors, formulate sales plans and distribute them to various sales channels and sales teams.

2. A method for realizing automated target distribution in the retail industry as claimed in claim 1, characterized in that: The historical sales data of each channel includes historical sales data of online shopping malls, offline stores and third-party platforms; The external factor data includes weather data, holidays, marketing activities, and city data.

3. A method for realizing automated target distribution in the retail industry as claimed in claim 1, characterized in that: The data cleaning is used to detect and correct erroneous, incomplete, inaccurate, and inapplicable data parts in the data, and the data cleaning methods specifically include processing missing values, deleting duplicates, and processing outliers; The standardization process is used to convert the data into a unified standard format, and the length of the data field in the standard format meets the maximum length requirement.

4. A method for realizing automated target distribution in retail industry as claimed in claim 1, characterized in that: The processed sales-related data is analyzed based on the time series analysis method, wherein: The time series analysis methods include trend analysis, seasonal analysis, periodic analysis, and marketing strategy analysis; The trend analysis is to draw a time series graph using MA or EMA to observe the trend of sales data over time; The seasonal analysis is to consider holidays and seasonal changes, and use STL analysis to separate seasonal factors from sales data; The periodic analysis is to consider annual, quarterly or monthly cycles, analyze the cycle length and fluctuation range, and provide training parameters for the deep learning model; The marketing strategy analysis is to track the sales changes brought about by marketing activities based on historical and future marketing strategies, and provide training parameters for the deep learning model.

5. A method for realizing automated target distribution in retail industry as claimed in claim 4, characterized in that: The prediction of future sales trends through deep learning models specifically includes: Create a deep learning model of the long short-term memory network, and adjust the deep learning model structure and parameters according to the training set data characteristics and prediction requirements; Convert historical data into feature data for a deep learning model, wherein the historical data includes historical sales data, seasonal indicators, trend indicators, and marketing activities; Considering the seasonality, trend, and cyclical factors of sales-related data, a training set is constructed to train the deep learning model; Future sales trends are predicted based on the trained deep learning model.

6. A method for realizing automated target distribution in retail industry as claimed in claim 1, characterized in that: According to the predicted future sales trends, combined with sales targets and sales influencing factors, sales plans are formulated and distributed to various sales channels and sales teams, including: Develop sales plans based on predicted future sales trends, combined with sales targets, inventory status, and promotional activities; Automatically distribute the sales plan to various sales channels and sales teams; The sales plan includes the types and quantities of goods, promotion strategies, and sales channel allocation.

7. A method for realizing automated target distribution in retail industry as claimed in claim 1, characterized in that: After the sales plan is developed and distributed to various sales channels and sales teams, it also includes: Monitor sales data in real time, evaluate the execution of the sales plan based on the real-time sales data obtained, and adjust the parameters of the deep learning model based on the evaluation results to achieve iterative optimization of the deep learning model.

8. A device for realizing automated target distribution in the retail industry, characterized in that: The retail industry automated target distribution implementation device comprises: A collection module is used to collect sales-related data and perform data cleaning and standardization on the collected data. The sales-related data includes historical sales data of each channel, user behavior data, inventory data, and external factor data; The forecasting module is used to analyze the processed sales-related data based on time series analysis and predict future sales trends through deep learning models; The distribution module is used to formulate sales plans and distribute them to various sales channels and sales teams based on the predicted future sales trends, combined with sales targets and sales influencing factors.

9. A retail industry automated target distribution implementation device, characterized in that: The retail industry automated target distribution implementation device includes a processor, a memory, and a retail industry automated target distribution implementation program stored on the memory and executable by the processor, wherein when the retail industry automated target distribution implementation program is executed by the processor, the steps of the retail industry automated target distribution implementation method 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 program for implementing automated target distribution for the retail industry, wherein when the program for implementing automated target distribution for the retail industry is executed by a processor, the steps of the method for implementing automated target distribution for the retail industry as described in any one of claims 1 to 7 are implemented.

Images