Product precision sales analysis system and analysis method based on big data

Abstract

The invention relates to the technical field of market data analysis, and discloses a product precision sales analysis system and analysis method based on big data. According to the system and the method, product sales related data including sales volume, sales volume and market feedback data is acquired from a plurality of data sources through a data acquisition module, and the acquired product sales data is subjected to structured storage through a data storage module. The data processing module cleans, integrates and analyzes the stored sales data by using a big data processing technology, and the prediction analysis module performs product sales trend prediction and market demand analysis by using a prediction model based on historical data and an existing data trend. And the visual display module displays the analysis result to the user in a visual chart and report form to help the user to understand the market dynamics and the product performance, efficiently and accurately analyze the product sales data, improve the market insight and decision-making ability of the enterprise, optimize the product promotion and sales strategy, and improve the sales performance and the market competitiveness.

Description

Technical Field

[0001] The present invention relates to the technical field of market data analysis, and specifically to a product precision sales analysis system and analysis method based on big data. Background Art

[0002] Big data analysis refers to the analysis of huge amounts of data. Big data can be summarized as five Vs: volume, velocity, variety, value, and veracity. Big data (big data), an IT industry term, refers to a collection of data that cannot be captured, managed, and processed by conventional software tools within a certain time frame. It is a massive, high-growth, and diversified information asset that requires new processing models to have stronger decision-making power, insight discovery, and process optimization capabilities. In today's society, electronic information technology is developing rapidly, and more and more marketing methods have emerged in the hope of bringing more customers to companies. When collecting data, the current marketing system mainly collects users' static data by filling out registration forms, questionnaires, and telephone registrations, and analyzes the collected static data to push corresponding product information to users.

[0003] The traditional product sales method relies on a single questionnaire-based data collection method, which has low information analysis efficiency. It can only rely on the analysis of the collected data to obtain specific sales data, and cannot efficiently analyze sales data. Summary of the invention

[0004] 1. Technical issues to be resolved

[0005] In view of the deficiencies in the prior art, the present invention provides a product precision sales analysis system and analysis method based on big data, which has the advantages of obtaining product sales-related data from multiple data sources through a data acquisition module, including but not limited to sales volume, sales revenue and market feedback data; the data storage module stores the collected product sales data in a structured manner to ensure the reliability and security of the data; the data processing module uses big data processing technology to clean, integrate and analyze the stored sales data, and mines the associations and rules hidden in the data; the prediction and analysis module uses machine learning algorithms or other prediction models to predict product sales trends and analyze market demand based on historical data and existing data trends; the visualization display module displays the analysis results to users in the form of intuitive charts, reports, etc., to help users quickly understand market dynamics and product performance, efficiently and accurately analyze product sales data, enhance enterprises' insight into the market and decision-making ability, optimize product promotion and sales strategies, thereby improving sales performance and market competitiveness, etc., and solves the above-mentioned problems.

[0006] (II) Technical solution

[0007] To achieve the above-mentioned purpose, the present invention provides the following technical solutions: a product precision sales analysis system based on big data, comprising a data acquisition module, a data storage module, a data processing module, a prediction analysis module and a visualization display module;

[0008] The data acquisition module obtains product sales related data from the network data source, including sales volume data Xssj, sales revenue data Xsej and market feedback data Scfk, and cleans the above data, removes duplicate data and processes missing values ​​to obtain cleaned sales volume data Qxxs, cleaned sales revenue data Qxse and cleaned market feedback data Qxfk, and transmits the collected data to the data storage module after unifying the format of the above data;

[0009] The data storage module performs structured storage on the cleaning sales volume data Qxxs, the cleaning sales volume data Qxse and the cleaning market feedback data Qxfk in a relational database to ensure the reliability and security of the data;

[0010] The data processing module is used to retrieve the data in the above-mentioned relational database, remove noise and outliers from the cleaned sales volume data Qxxs, cleaned sales volume data Qxse and cleaned market feedback data Qxfk, obtain pure sales volume data Cjxs, pure sales volume data Cjse and pure market feedback data Cjfk, and transmit the processed data to the prediction analysis module;

[0011] The forecasting and analysis module calculates the pure sales volume standard deviation Xsjz, the pure sales volume standard deviation Sejz and the pure market feedback standard deviation Fkjz based on the pure sales volume data Cjxs, the pure sales volume data Cjse and the pure market feedback data Cjfk, and analyzes and judges the sales trend based on the above calculated values, and transmits the analysis results to the visualization display module;

[0012] The visualization display module generates a product sales trend analysis chart based on the analysis results of the prediction analysis module and displays it on the visualization interface.

[0013] Preferably, the data collection module cleans the sales volume data Xssj and processes the missing values ​​to obtain the cleaned sales volume data Qxxs according to the following formula:

[0014]

[0015] In the formula, Qxxs represents the cleaned sales data, Xssj represents the sales data, K represents the total number of data, and j represents the index of the sum.

[0016] Preferably, the data collection module cleans the sales data Xsej and processes the missing values ​​to obtain the cleaned sales data Qxse according to the following formula:

[0017]

[0018] In the formula, Qxse represents the cleaned sales data, Xsej represents the sales data, K represents the total number of data, and j represents the index of the sum.

[0019] Preferably, the data collection module cleans the market feedback data Scfk, and processes the missing values ​​to obtain the cleaned market feedback data Qxfk according to the following formula:

[0020]

[0021] In the formula, Qxfk represents the cleaning market feedback data, Scfk represents the market feedback data, K represents the total number of data, and j represents the index of the sum.

[0022] Preferably, the data processing module is used to retrieve the data in the above relational database, remove noise from the cleaned sales data Qxxs, and obtain pure sales data Cjxs. The calculation formula is as follows:

[0023]

[0024] In the formula, Cjxs i represents the i-th value of the pure sales data, n is the size of the denoising window, Indicates the data value Qxxs starting from position i to position i+n-1 j Perform the summation.

[0025] Preferably, the data processing module is used to retrieve the data in the above relational database, remove the noise from the cleaned sales data Qxse, and obtain the pure sales data Cjse. The calculation formula is as follows:

[0026]

[0027] In the formula, Cjse i represents the i-th value of the pure sales data, n is the size of the denoising window, Indicates the data value Qxse starting from position i to position i+n-1 j Perform the summation.

[0028] Preferably, the data processing module is used to retrieve the data in the above relational database, remove the noise from the cleaned market feedback data Qxfk, and obtain the pure market feedback data Cjfk. The calculation formula is as follows:

[0029]

[0030] In the formula, Cjfk i represents the i-th value of the pure market feedback data, n is the size of the denoising window, Indicates the data value Qxfk starting from position i to position i+n-1 j Perform the summation.

[0031] Preferably, the formula for calculating the standard deviation Xsjz of the pure sales volume based on the pure sales volume data Cjxs by the prediction analysis module is as follows:

[0032]

[0033] In the formula, Xsjz represents the standard deviation of pure sales volume, and N represents the total number of pure sales volume data. Represents each pure sales volume Cjxs from 1 to N i Average net sales volume The square of the difference.

[0034] Preferably, the formula for calculating the standard deviation Sejz of the net sales volume based on the net sales volume data Cjse by the forecast analysis module is as follows:

[0035]

[0036] In the formula, Sejz represents the standard deviation of pure sales, and N represents the total number of pure sales data. Represents each net sales Cjse from 1 to N i Average net sales The square of the difference.

[0037] Preferably, the formula for calculating the pure market feedback standard deviation Fkjz based on the pure market feedback data Cjfk by the prediction analysis module is as follows:

[0038]

[0039] In the formula, Fkjz represents the standard deviation of pure market feedback, and N represents the total number of pure market feedback data. Represents each pure market feedback data Cjfk from 1 to N i Average value of pure market feedback data The square of the difference;

[0040] A product precision sales analysis method based on big data, comprising the following steps:

[0041] S1. Obtain product sales-related data from the network data source through the data acquisition module, including sales volume data Xssj, sales revenue data Xsej and market feedback data Scfk, and clean the above data, remove duplicate data and process missing values ​​to obtain cleaned sales volume data Qxxs, cleaned sales revenue data Qxse and cleaned market feedback data Qxfk, and transfer the collected data to the data storage module after unifying the format of the above data;

[0042] S2, the data storage module stores the cleaned sales volume data Qxxs, the cleaned sales volume data Qxse and the cleaned market feedback data Qxfk in a structured manner in a relational database to ensure the reliability and security of the data;

[0043] S3, the data processing module is used to retrieve the data in the above relational database, remove noise and outliers from the cleaned sales volume data Qxxs, the cleaned sales volume data Qxse and the cleaned market feedback data Qxfk, obtain the pure sales volume data Cjxs, the pure sales volume data Cjse and the pure market feedback data Cjfk, and transmit the processed data to the prediction analysis module;

[0044] S4, the forecasting and analysis module calculates the pure sales volume standard deviation Xsjz, the pure sales volume standard deviation Sejz and the pure market feedback standard deviation Fkjz based on the pure sales volume data Cjxs, the pure sales volume data Cjse and the pure market feedback data Cjfk, and analyzes and judges the sales trend based on the above calculated values, and transmits the analysis results to the visualization display module;

[0045] S5. The visualization display module generates a product sales trend analysis chart based on the analysis results of the prediction analysis module and displays it in the visualization interface.

[0046] Compared with the prior art, the present invention provides a product precision sales analysis system and analysis method based on big data, which has the following beneficial effects:

[0047] The present invention obtains product sales-related data from multiple data sources through a data acquisition module, including but not limited to sales volume, sales revenue and market feedback data. The data storage module stores the collected product sales data in a structured manner to ensure the reliability and security of the data. The data processing module uses big data processing technology to clean, integrate and analyze the stored sales data, and mines the associations and rules hidden in the data. The predictive analysis module uses machine learning algorithms or other predictive models based on historical data and existing data trends to predict product sales trends and analyze market demand. The visual display module displays the analysis results to users in the form of intuitive charts, reports, etc., to help users quickly understand market dynamics and product performance, efficiently and accurately analyze product sales data, enhance enterprises' insight into the market and decision-making capabilities, optimize product promotion and sales strategies, and thus improve sales performance and market competitiveness. BRIEF DESCRIPTION OF THE DRAWINGS

[0048] Figure 1 It is a schematic diagram of the system flow of the present invention;

[0049] Figure 2 It is a schematic diagram of the steps of the method of the present invention. DETAILED DESCRIPTION

[0050] The following will be combined with the drawings in the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. Obviously, the described embodiments 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 creative work are within the scope of protection of the present invention.

[0051] In view of the problem that the traditional product sales method relies on a single questionnaire data collection, the information analysis efficiency is low, and the specific sales data can only be obtained by analyzing the collected data, and the sales data cannot be analyzed efficiently, a product precision sales analysis system based on big data is proposed. Please refer to Figure 1 The system includes a data acquisition module, a data storage module, a data processing module, a prediction and analysis module, and a visualization display module, wherein:

[0052] The data collection module obtains product sales-related data from the network data source, including sales volume data Xssj, sales revenue data Xsej, and market feedback data Scfk, and cleans the above data, removes duplicate data and processes missing values ​​to obtain cleaned sales volume data Qxxs, cleaned sales revenue data Qxse, and cleaned market feedback data Qxfk, where:

[0053] The sales volume data cleaning formula is as follows:

[0054]

[0055] Cleaning data helps to delete erroneous, duplicate, and incomplete data, thereby improving the accuracy and reliability of the data. In the formula, Qxxs represents cleaned sales data, Xssj represents sales data, K represents the total number of data, and j represents the index of the summation;

[0056] The sales data cleaning formula is as follows:

[0057]

[0058] Cleaning data helps remove errors and inconsistencies, thereby improving the accuracy of sales, which is critical for financial reporting and performance evaluation. In the formula, Qxse represents cleaned sales data, Xsej represents sales data, K represents the total number of data, and j represents the index of the sum. Cleaned sales data is easier to analyze, providing in-depth insights into sales trends, seasonal fluctuations, etc., and supporting the formulation of more effective sales strategies;

[0059] The market feedback data cleaning formula is as follows:

[0060]

[0061] Cleaning market feedback data helps to remove irrelevant, repeated or false feedback, so that the information obtained is more real and effective. In the formula, Qxfk represents clean market feedback data, Scfk represents market feedback data, K represents the total number of data, and j represents the sum index. Accurate market feedback can enable enterprises to adapt to market changes more quickly, adjust strategies or launch new products in a timely manner, thereby enhancing market competitiveness;

[0062] The data storage module stores the cleaned sales volume data Qxxs, cleaned sales revenue data Qxse, and cleaned market feedback data Qxfk in a structured manner in a relational database to ensure data reliability and security;

[0063] The data processing module is used to retrieve the data in the above relational database, remove noise and outliers from the cleaned sales volume data Qxxs, cleaned sales volume data Qxse and cleaned market feedback data Qxfk, and obtain pure sales volume data Cjxs, pure sales volume data Cjse and pure market feedback data Cjfk, where:

[0064] The calculation formula for obtaining pure sales data is as follows:

[0065]

[0066] In the formula, Cjxs i represents the i-th value of the pure sales data, n is the size of the denoising window, Indicates the data value Qxxs starting from position i to position i+n-1 j Perform summation;

[0067] The calculation formula for obtaining the net sales data is as follows:

[0068]

[0069] In the formula, Cjse i represents the i-th value of the pure sales data, n is the size of the denoising window, Indicates the data value Qxse starting from position i to position i+n-1 j Perform summation;

[0070] The calculation formula for obtaining pure market feedback data is as follows:

[0071]

[0072] In the formula, Cjfk i represents the i-th value of the pure market feedback data, n is the size of the denoising window, Indicates the data value Qxfk starting from position i to position i+n-1 j Perform summation;

[0073] By further cleaning the data and removing outliers and noise, we can obtain the corresponding pure data and ensure the accuracy and reliability of the analysis;

[0074] The forecasting and analysis module calculates the standard deviation of pure sales volume Xsjz, the standard deviation of pure sales volume Sejz and the standard deviation of pure market feedback Fkjz based on the pure sales volume data Cjxs, the pure sales volume data Cjse and the pure market feedback data Cjfk, and analyzes and judges the sales trend based on the above calculated values, where:

[0075] The formula for calculating the standard deviation of net sales volume is as follows:

[0076]

[0077] A higher standard deviation means that sales volume fluctuates more. Companies can use this to assess sales risk and uncertainty and make corresponding strategic adjustments. In the formula, Xsjz represents the standard deviation of pure sales volume, and N represents the total number of pure sales volume data. Represents each pure sales volume Cjxs from 1 to N i Average net sales volume The square of the difference between the standard deviation and the standard deviation can help enterprises identify the trend of market changes, adjust strategies in time to adapt to the new market environment, and help maintain competitive advantages;

[0078] The formula for calculating the standard deviation of net sales is as follows:

[0079]

[0080] Understanding the volatility of sales can help companies formulate financial budgets more accurately and ensure appropriate resource allocation in different sales scenarios. In the formula, Sejz represents the standard deviation of pure sales, and N represents the total number of pure sales data. Represents each net sales Cjse from 1 to N i Average net sales Based on the volatility of sales, companies can more effectively forecast demand, conduct reasonable inventory management, and reduce the risk of excess or shortage.

[0081] The formula for calculating the standard deviation of pure market feedback is as follows:

[0082]

[0083] Understanding the fluctuations in market feedback can help companies identify and manage potential business risks and avoid sales losses due to customer dissatisfaction. In the formula, Fkjz represents the standard deviation of pure market feedback, and N represents the total number of pure market feedback data. Represents each pure market feedback data Cjfk from 1 to N i Average value of pure market feedback data With the data support of standard deviation, enterprises can more clearly show the changes in market feedback and enhance the transparency of internal and external decision-making;

[0084] The sales trend analysis and judgment methods are as follows:

[0085] When the standard deviation of pure sales volume Xsjz, the standard deviation of pure sales revenue Sejz, and the standard deviation of pure market feedback Fkjz are all greater than or equal to 10, it means that the future sales of the enterprise's products are on an upward trend;

[0086] When the standard deviation of pure sales volume Xsjz, the standard deviation of pure sales revenue Sejz and the standard deviation of pure market feedback Fkjz are all less than 10, it means that the future sales of the company's products are on a downward trend.

[0087] See also Figure 2 , a product precision sales analysis method based on big data, comprising the following steps:

[0088] S1. Obtain product sales-related data from the network data source through the data acquisition module, including sales volume data Xssj, sales revenue data Xsej and market feedback data Scfk, and clean the above data, remove duplicate data and process missing values ​​to obtain cleaned sales volume data Qxxs, cleaned sales revenue data Qxse and cleaned market feedback data Qxfk, and transfer the collected data to the data storage module after unifying the format of the above data;

[0089] S2, the data storage module stores the cleaned sales volume data Qxxs, the cleaned sales volume data Qxse and the cleaned market feedback data Qxfk in a structured manner in a relational database to ensure the reliability and security of the data;

[0090] S3, the data processing module is used to retrieve the data in the above relational database, remove noise and outliers from the cleaned sales volume data Qxxs, the cleaned sales volume data Qxse and the cleaned market feedback data Qxfk, obtain the pure sales volume data Cjxs, the pure sales volume data Cjse and the pure market feedback data Cjfk, and transmit the processed data to the prediction analysis module;

[0091] S4, the forecasting and analysis module calculates the pure sales volume standard deviation Xsjz, the pure sales volume standard deviation Sejz and the pure market feedback standard deviation Fkjz based on the pure sales volume data Cjxs, the pure sales volume data Cjse and the pure market feedback data Cjfk, and analyzes and judges the sales trend based on the above calculated values, and transmits the analysis results to the visualization display module;

[0092] S5. The visualization display module generates a product sales trend analysis chart based on the analysis results of the prediction analysis module and displays it in the visualization interface.

[0093] Although embodiments of the present invention have been shown and described, it will be appreciated by those skilled in the art that various changes, modifications, substitutions and variations may be made to the embodiments without departing from the principles and spirit of the present invention, and that the scope of the present invention is defined by the appended claims and their equivalents.

Claims

1. A product precision sales analysis system based on big data, characterized by: It includes data acquisition module, data storage module, data processing module, prediction analysis module and visualization display module; The data acquisition module obtains product sales related data from the network data source, including sales volume data Xssj, sales revenue data Xsej and market feedback data Scfk, and cleans the above data, removes duplicate data and processes missing values ​​to obtain cleaned sales volume data Qxxs, cleaned sales revenue data Qxse and cleaned market feedback data Qxfk, and transmits the collected data to the data storage module after unifying the format of the above data; The data storage module performs structured storage on the cleaning sales volume data Qxxs, the cleaning sales volume data Qxse and the cleaning market feedback data Qxfk in a relational database to ensure the reliability and security of the data; The data processing module is used to retrieve the data in the above-mentioned relational database, remove noise and outliers from the cleaned sales volume data Qxxs, cleaned sales volume data Qxse and cleaned market feedback data Qxfk, obtain pure sales volume data Cjxs, pure sales volume data Cjse and pure market feedback data Cjfk, and transmit the processed data to the prediction analysis module; The forecasting and analysis module calculates the pure sales volume standard deviation Xsjz, the pure sales volume standard deviation Sejz and the pure market feedback standard deviation Fkjz based on the pure sales volume data Cjxs, the pure sales volume data Cjse and the pure market feedback data Cjfk, and analyzes and judges the sales trend based on the above calculated values, and transmits the analysis results to the visualization display module; The visualization display module generates a product sales trend analysis chart based on the analysis results of the prediction analysis module and displays it on the visualization interface.

2. According to the big data-based product precision sales analysis system of claim 1, it is characterized by: The data collection module cleans the sales volume data Xssj and processes the missing values ​​to obtain the cleaned sales volume data Qxxs according to the following formula: In the formula, Qxxs represents the cleaned sales data, Xssj represents the sales data, K represents the total number of data, and j represents the index of the sum.

3. The product precision sales analysis system based on big data according to claim 2 is characterized by: The data collection module cleans the sales data Xsej and processes the missing values ​​to obtain the cleaned sales data Qxse using the following formula: In the formula, Qxse represents the cleaned sales data, Xsej represents the sales data, K represents the total number of data, and j represents the index of the sum.

4. The product precision sales analysis system based on big data according to claim 3 is characterized by: The data collection module cleans the market feedback data Scfk and processes the missing values ​​to obtain the formula for cleaned market feedback data Qxfk as follows: In the formula, Qxfk represents the cleaning market feedback data, Scfk represents the market feedback data, K represents the total number of data, and j represents the index of the sum.

5. The product precision sales analysis system based on big data according to claim 2 is characterized by: The data processing module is used to retrieve the data in the above relational database, remove the noise from the cleaned sales data Qxxs, and obtain the pure sales data Cjxs. The calculation formula is as follows: In the formula, Cjxs i represents the i-th value of the pure sales data, n is the size of the denoising window, Indicates the data value Qxxs starting from position i to position i+n-1 j Perform the summation.

6. The product precision sales analysis system based on big data according to claim 3 is characterized by: The data processing module is used to retrieve the data in the above relational database, remove the noise from the cleaned sales data Qxse, and obtain the pure sales data Cjse. The calculation formula is as follows: In the formula, Cjse i represents the i-th value of the pure sales data, n is the size of the denoising window, Indicates the data value Qxse starting from position i to position i+n-1 j Perform the summation.

7. The product precision sales analysis system based on big data according to claim 4 is characterized by: The data processing module is used to retrieve the data in the above relational database, remove the noise from the cleaned market feedback data Qxfk, and obtain the pure market feedback data Cjfk. The calculation formula is as follows: In the formula, Cjfk i represents the i-th value of the pure market feedback data, n is the size of the denoising window, Indicates the data value Qxfk starting from position i to position i+n-1 j Perform the summation.

8. The product precision sales analysis system based on big data according to claim 5 is characterized by: The formula for calculating the standard deviation Xsjz of the pure sales volume based on the pure sales volume data Cjxs by the prediction analysis module is as follows: In the formula, Xsjz represents the standard deviation of pure sales volume, and N represents the total number of pure sales volume data. Represents each pure sales volume Cjxs from 1 to N i Average net sales volume The square of the difference.

9. The product precision sales analysis system based on big data according to claim 6 is characterized by: The formula for calculating the standard deviation Sejz of the net sales volume based on the net sales volume data Cjse by the forecast analysis module is as follows: In the formula, Sejz represents the standard deviation of pure sales, and N represents the total number of pure sales data. Represents each net sales Cjse from 1 to N i Average net sales The square of the difference.

10. The product precision sales analysis system based on big data according to claim 7, characterized in that: The formula for calculating the pure market feedback standard deviation Fkjz based on the pure market feedback data Cjfk by the prediction analysis module is as follows: In the formula, Fkjz represents the standard deviation of pure market feedback, and N represents the total number of pure market feedback data. Represents each pure market feedback data Cjfk from 1 to N i Compared with the average of pure market feedback data The square of the difference; A product accurate sales analysis method based on big data, characterized by: The following steps are involved: S1. Obtain product sales-related data from the network data source through the data acquisition module, including sales volume data Xssj, sales revenue data Xsej and market feedback data Scfk, and clean the above data, remove duplicate data and process missing values ​​to obtain cleaned sales volume data Qxxs, cleaned sales revenue data Qxse and cleaned market feedback data Qxfk, and transfer the collected data to the data storage module after unifying the format of the above data; S2, the data storage module stores the cleaned sales volume data Qxxs, the cleaned sales volume data Qxse and the cleaned market feedback data Qxfk in a structured manner in a relational database to ensure the reliability and security of the data; S3, the data processing module is used to retrieve the data in the above relational database, remove noise and outliers from the cleaned sales volume data Qxxs, the cleaned sales volume data Qxse and the cleaned market feedback data Qxfk, obtain the pure sales volume data Cjxs, the pure sales volume data Cjse and the pure market feedback data Cjfk, and transmit the processed data to the prediction analysis module; S4, the forecasting and analysis module calculates the pure sales volume standard deviation Xsjz, the pure sales volume standard deviation Sejz and the pure market feedback standard deviation Fkjz based on the pure sales volume data Cjxs, the pure sales volume data Cjse and the pure market feedback data Cjfk, and analyzes and judges the sales trend based on the above calculated values, and transmits the analysis results to the visualization display module; S5. The visualization display module generates a product sales trend analysis chart based on the analysis results of the prediction analysis module and displays it in the visualization interface.

Images