A data analysis method, system, and medium thereof

Abstract

The application discloses a data analysis method and system and a medium thereof, and relates to the field of data analysis, and comprises the following specific steps: collecting data to be analyzed, drawing a time column chart according to classified and summarized data, displaying data information by using the time column chart, controlling the time column chart, displaying and controlling the time column chart, analyzing data according to the time column chart, and generating a data analysis report, correlating data based on a market basket, performing correlation analysis on the data, and generating a data analysis report. The application uses a data analysis method, adopts a display mode of a time column chart, takes time as an X axis and a numerical value as a Y axis, makes the change trend of sales data obvious at a glance, helps decision makers quickly understand information behind the data, and enables the change trend of sales data to be obvious at a glance through line drawing processing on the time column chart, which helps decision makers quickly understand information behind the data.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of data analysis, in particular to a data analysis method and system and a medium thereof. BACKGROUND

[0002] Data analysis of sales is a crucial part of enterprise management and decision-making process. Through the analysis of sales data, enterprises can gain a deep understanding of market trends, customer behavior, product performance, etc., and thus develop more effective sales strategies and marketing plans.

[0003] With the advent of the era of big data, the amount of data generated by enterprises in their daily operations is growing exponentially. Data analysis has become an important tool for enterprise decision-making, especially the analysis of sales data, which is of great significance for optimizing operations, improving sales performance and formulating market strategies. Traditional data analysis methods often have some limitations, such as low data processing efficiency, non-intuitive analysis results, lack of real-time performance, etc., which makes it difficult for enterprises to quickly respond to market changes.

[0004] Currently, many enterprises rely on static reports and simple statistical tools for sales data analysis, which makes it difficult for decision-makers to extract valuable information from complex data. In addition, existing sales data analysis tools often cannot effectively integrate multi-dimensional data, resulting in one-sidedness and incompleteness of the analysis results.

[0005] Therefore, a data analysis method, system and medium are proposed to solve or alleviate the above problems. SUMMARY

[0006] The present application aims to provide a data analysis method, system and medium to solve the problems raised in the background.

[0007] To achieve the above-mentioned purpose, the present application provides the following technical solution: a data analysis method, system and medium, comprising the following specific steps:

[0008] S1: collecting the data to be analyzed and classifying and summarizing the data;

[0009] S2: drawing a time bar chart based on the classified and summarized data, using the time bar chart to display data information, the time bar chart taking time as the X-axis and numerical value as the Y-axis;

[0010] S3: controlling the time bar chart for fusion, line drawing, comparison and modification operations of different types of time bar charts, wherein before the line drawing operation, a visibility algorithm is applied to convert the time series data into a complex network graph to identify and filter noise data points, the visibility algorithm constructs a network based on the visibility edges of adjacent data points, and the edge weight is dynamically calculated and determined by the Y value difference and X time interval between data points.

[0011] S4: Displaying and controlling the time column chart and storing the time column chart data;

[0012] S5: Analyzing the data according to the time column chart and generating a data analysis report, wherein the analysis includes calculating a data fluctuation anomaly index based on node degree centrality of a complex network graph;

[0013] S6: Correlating the data based on a market basket and performing a correlation analysis to generate a data analysis report, wherein the correlation analysis adopts a market basket weighted correlation formula: weight = (promotion day influence factor x fluctuation rate) / (1 + time attenuation coefficient);

[0014] S7: Comprehensive analysis to generate a data analysis report.

[0015] Preferably, the data collected in S1 includes time, sales, sales cost and region, the classified and summarized data is subjected to a constraint condition of period time, sales, sales cost and region, a classified storage folder is established, the classified data is stored, and a data tag is established according to the data inside the classified storage folder.

[0016] Preferably, the drawing of the time column chart in S2 is to take time as the X-axis and value as the Y-axis, input the data tag in S1 into the time column chart, use the column chart to show the value at each time point, the height of the column represents the value size, generate a classified time column chart, and the classified time column chart represents the sales time column chart and the sales cost time column chart of a single period and a single region.

[0017] Preferably, the fusion of different types of time column charts in S3 is to fuse the classified time column charts, and the sales time column chart and the sales cost time column chart of a single region in a single period are fused to generate a profit time column chart of a single period and a single region, a profit time column chart of multiple periods and a single region, a profit time column chart of a single period and multiple regions, a profit time column chart of multiple periods and multiple regions, a sales time column chart of multiple periods and a single region, a sales time column chart of a single period and multiple regions, a sales time column chart of multiple periods and multiple regions, a sales cost time column chart of multiple periods and a single region, a sales cost time column chart of a single period and multiple regions, and a sales cost time column chart of multiple periods and multiple regions, the drawing of straight lines and bending lines on the time column chart in S3, and the drawing of the straight lines includes the highest line, the average line and the lowest line based on the complex network graph anomaly index dynamic adjustment, wherein the average line is calculated by excluding the data points with an anomaly index greater than 1.

[0018] Preferably, the display and control of the time column chart in S4 is the visual design of the time column chart, including the design of clear axes and the design of data visualization. The design of clear axes is to set clear labels for the time X-axis and the data Y-axis, indicating the unit and meaning, and to set reasonable scale intervals for the time X-axis and the data Y-axis. The design of data visualization is to set the column width corresponding to the time X-axis, and to make the adjacent columns have visual spacing. Then, the columns are filled with color, different colors are used to distinguish data series and categories, data labels are added to the column chart, specific numerical values are displayed on the top of the column, and graphical labels are set on the time column chart to retrieve the time column chart according to the graphical labels, and a database is established to store the time column chart data information.

[0019] Preferably, the correlation analysis of the data in S6 includes the following steps:

[0020] S6.1: Data collection, collecting and analyzing data corresponding to the market basket, and processing and classifying the data;

[0021] S6.2: Drawing a time column chart for the collected market basket data, and generating a time column chart corresponding to the analyzed data;

[0022] S6.3: Drawing a line on the market basket time column chart, and comparing it with the time column chart of the analyzed data to obtain the differences between the highest line, the lowest line, the average line and the bending line of the market basket time column chart and the analyzed data time column chart. The data information of the promotion day in the time column chart is removed, the value of the volatility is calculated through the profit volatility calculation formula, the data information of the promotion day is added to the time column chart, and the promotion day data information is added to the column chart according to different time units. The value of the volatility is calculated, the influence of the promotion day on the profit volatility is analyzed, and the influence factor of the promotion day is calibrated in reverse through the value of the volatility. The addition of the promotion day data information includes at least three times of iterative calibration: the first addition of basic promotion day data, the second addition of 7 days of data before the promotion day, and the third addition of 7 days of data after the promotion day. After each iteration, the volatility is recalculated and the difference is compared to calibrate the influence factor. When adding the promotion day data information, daily data needs to be collected from the market basket to ensure the accuracy of the calculation of the profit volatility;

[0023] S6.4: Generating a data analysis report according to the results of the market basket time column chart and the analyzed data time column chart.

[0024] Preferably, the comprehensive analysis in S7 is a comprehensive analysis of the sales data combined with the data analysis report in S5 and the data analysis report in S6, and the generated report includes the setting of the title, background information, research questions, analysis results and data visualization, the background information provides the background and purpose of the analysis, the research questions are specific questions and targets of the analysis, the analysis results are displayed in the form of charts and texts to highlight important findings, and the data visualization uses charts to help readers understand the results, and the charts include complex network graphs, column charts, pie charts and line charts, wherein the complex network graph shows the node connection relationship in S3 and is used to explain the root cause of data fluctuations.

[0025] The application also provides a data analysis system, which comprises:

[0026] A data collection module is used to collect, classify and summarize the analyzed data.

[0027] A chart module is used to store charts used for data analysis and support chart data filling to form data charts.

[0028] A chart control module is used to perform fusion, line drawing, comparison and modification operations on charts.

[0029] An analysis module is used to analyze data based on the chart control module and generate an analysis report.

[0030] A display module is used to display charts and analysis results generated by data analysis.

[0031] An association module is used to collect market basket data and perform comparative analysis on the analyzed data.

[0032] A report one-key generation module is used to generate a report for the analyzed question.

[0033] The application also provides a computer readable storage medium, which stores a computer program, and the program is executed by a processor to realize a data analysis method.

[0034] The application has the following technical effects and advantages:

[0035] The application uses a data analysis method and adopts a time column chart display mode to make the change trend of sales data clear at a glance, which helps decision makers quickly understand the information behind the data.

[0036] The application utilizes a data analysis method, through a correlation method based on market basket analysis, can deeply mine the relationship between sales data, identify potential sales opportunities and customer behavior patterns, thereby providing data support for market strategy, through combining multi-dimensional data analysis results, generating a comprehensive analysis report, the report not only contains analysis results, but also provides background information and research problems, which helps decision makers to fully understand the purpose and significance of analysis, through real-time data analysis and visualization display, enterprises can quickly respond to market changes, optimize sales strategy, and improve the accuracy and efficiency of decision-making. BRIEF DESCRIPTION OF DRAWINGS

[0037] Figure 1 The data analysis method flow chart of the application. DETAILED DESCRIPTION

[0038] The technical solutions in the embodiments of the application will be clearly and completely described below with reference to the drawings in the embodiments of the application. Obviously, the described embodiments are only a part of the embodiments of the application, not all the embodiments. Based on the embodiments in the application, all other embodiments obtained by those skilled in the art without creative labor are within the scope of protection of the application.

[0039] The application provides a data analysis method as shown in Figure 1 The specific steps are as follows:

[0040] S1: Collect the data to be analyzed, classify and summarize the data, check the collected data to ensure the accuracy of the data, and classify and summarize the data;

[0041] S2: According to the classified and summarized data, draw a time bar chart, use the time bar chart to display data information, and the time bar chart takes time as the X axis and value as the Y axis, so that the data information can be intuitively understood through the time bar chart;

[0042] S3: Control the time bar chart, which is used for fusion, line drawing, comparison and modification of different types of time bar charts. Before the line drawing operation, the visibility algorithm is applied to convert the time series data into a complex network graph to identify and filter noise data points. The visibility algorithm constructs a network based on the visibility edges of adjacent data points, and the edge weight is dynamically calculated and determined by the Y value difference and X time interval between data points. The dynamic calculation of edge weight by the visibility algorithm can effectively identify and filter noise data points. The setting of weight is based on the Y value difference and X time interval of adjacent data points, so that the analysis is more accurate and can better reflect the real trend and fluctuation of data;

[0043] S4: Display and control the time bar chart, and store the time bar chart data;

[0044] S5: Analyze the data according to the time column chart and generate a data analysis report, and the analysis includes calculating the data fluctuation anomaly index based on the node degree centrality of the complex network graph;

[0045] S6: Based on the market basket, the data is associated, and the data is analyzed to generate a data analysis report. The correlation analysis uses a market basket weighted correlation formula: weight = (promotion day impact factor x fluctuation rate) / (1 + time decay coefficient). The edge weight is dynamically calculated by the visibility algorithm. This dynamic weight calculation can effectively identify and filter noise data points. The setting of the weight is based on the Y value difference of the adjacent data points and the X time interval, so that the analysis is more accurate and can better reflect the real trend and fluctuation of the data.

[0046] S7: Comprehensive analysis, generate a data analysis report, and optimize the sales plan according to the analysis report.

[0047] Specifically, the data collected in S1 includes time, sales, sales cost and region. The data is classified and summarized based on the constraints of cycle time, sales, sales cost and region. The cycle time can be a week, a month or a quarter. A classified storage folder is established to store the classified data, and data tags are established based on the data inside the classified storage folder, so that the required data can be quickly retrieved according to the classified storage folder information.

[0048] Further, the time column chart in S2 is drawn with time as the X axis and numerical value as the Y axis. The data tags in S1 are input into the time column chart, and the numerical value at each time point is displayed using a column chart. The height of the column represents the numerical value. A classified time column chart is generated, which represents the sales and sales cost time column chart of a single cycle and a single region, so that the time column chart clearly shows the data information for easy viewing by personnel.

[0049] Further, the fusion of different types of time column charts in S3 is performed by classifying the time column charts, and the sales time column chart and the sales cost time column chart of a single region in a single period are fused to generate a profit time column chart of a single region in a single period, a profit time column chart of a single region in multiple periods, a profit time column chart of multiple regions in a single period, a profit time column chart of multiple regions in multiple periods, a sales time column chart of a single region in multiple periods, a sales time column chart of multiple regions in a single period, a sales time column chart of multiple regions in multiple periods, a sales cost time column chart of a single region in multiple periods, a sales cost time column chart of multiple regions in a single period, and a sales cost time column chart of multiple regions in multiple periods. The line drawing of different types of time column charts in S3 is performed on the time column chart to draw straight lines and curved lines. The drawing of straight lines includes the highest line, the average line, and the lowest line based on the dynamic adjustment of the complex network graph anomaly index. The average line is calculated by excluding data points with an anomaly index greater than 1. The profit time column chart of a single region in a single period, the profit time column chart of a single region in multiple periods, the profit time column chart of multiple regions in a single period, and the profit time column chart of multiple regions in multiple periods represent the profit charts of a single region in a single period, a single region in multiple periods, multiple regions in a single period, and multiple regions in multiple periods, respectively. When the profit in a single time unit is a negative value, the corresponding column on the time column chart faces the X-axis downward, so that personnel can intuitively view whether the profit is positive or negative. The profit time column chart of multiple regions has two display modes. One is to arrange the profit columns of multiple regions side by side in a single unit on the X-axis, and the side-by-side time column chart facilitates the intuitive comparison of the differences in profit of different regions. The other is to add the profits of multiple regions in a single unit on the X-axis, so that a column displays the sum of the profits of multiple regions. The sales time column chart of a single region in multiple periods is a combination of single-region sales time column charts in multiple single periods in chronological order. The sales cost time column chart of a single region in multiple periods is a combination of single-region sales cost time column charts in multiple single periods in chronological order. The sales time column chart and the sales cost time column chart of multiple regions have two display modes. Figure 1

[0050] ​Further, the drawing lines of different types of time column chart in S3 are the drawing of straight lines and bending lines on the time column chart. The drawing of straight lines includes the drawing of the highest line, the average line, the lowest line and the preset line. The highest line represents the highest column data on the Y axis of the time column chart. The average line represents the average column data of the time column chart. The lowest line represents the lowest column data on the Y axis of the time column chart. The preset line represents a straight line with Y equal to the preset value in the time column chart. The preset value corresponds to the sales target estimated or set by the enterprise. By changing the value of Y of the preset straight line, the position of the preset line on the time column chart can be changed. The values of Y of the highest line, the average line, the lowest line and the preset line are input in the formula of the time column chart, and the value range of X is limited, i.e. the value range of X is within the period of the time column chart, so that the corresponding high line, average line, lowest line and preset line can be generated. The drawing of bending lines is to connect the adjacent column bodies in the time column chart by straight lines, so that the apexes of the column bodies in the time column chart are connected to form bending lines. Through the bending lines, the trend of the sales data in the time column chart can be directly observed. Comparison is used for the comparison of data of the time column chart, including the comparison of time column charts of the same period, the comparison of drawing lines and the comparison of association. Modification is used for the display control of the time column chart, including the operations of enlargement, reduction and stretching, so as to facilitate the operation and observation of the time column chart. Modification is also used for the modification of the preset value.

[0051] Further, the display control of the time column chart in S4 is the visual design of the time column chart, including the design of clear axes and the design of data visualization. The design of clear axes is to set clear labels for the time X axis and the data Y axis to indicate the unit and meaning, and to set reasonable scale intervals for the time X axis and the data Y axis. The design of data visualization is to set the column width corresponding to the time X axis and to have visual intervals between adjacent column bodies to avoid the crowding of column charts in adjacent units. The column bodies are then filled with different colors to distinguish data series and categories, so that the same series or category of data information can be observed through color information. Data labels are added to the column chart to display specific values on the top of the column, thereby improving the completeness and clarity of the time column chart. Graph labels are set on the time column chart to facilitate the retrieval operation of the time column chart according to the graph labels. A database is established to store the data information of the time column chart, thereby avoiding data loss and improving the security of data use.

[0052] In particular, S5 analyzes data based on time-based histograms by comparing the heights of the lines on the histogram, specifically the preset line relative to the highest, average, and lowest lines. When the preset line is higher than the highest line, the data in the time-based histogram has not reached the preset value; when the preset line is lower than the lowest line, the data in the time-based histogram has reached the preset value. When the preset line is higher than the average line but lower than the highest line, the average data in the time-based histogram has not reached the preset value; when the preset line is lower than the average line but higher than the lowest line, the average data in the time-based histogram has reached the preset value. The volatility of profits is then calculated using the following formula:

[0053]

[0054] In the formula, For earnings volatility, The value on the Y-axis of the average line in the profit time histogram. The Y-axis value of the preset line in the time histogram. If the value is positive, then the profit within one cycle reaches the expected preset value. The larger the value, the higher the profit will be compared to the expected preset value, and vice versa. When the value is negative, it means that the profit within a period did not reach the expected preset value, and when there is no profit within a period, It is a negative value. minus It is still a negative value, and through calculation The value of can be used to obtain the difference between the specific profit amount and the expected preset value, and the volatility calculation formula can also be used to calculate the volatility of sales revenue, thus enabling calculation... The value of can be used to obtain the difference between the actual sales revenue and the expected sales revenue, and to calculate the sales revenue volatility. The value of is used to dynamically adjust the inventory.

[0055] Furthermore, the correlation analysis of data in S6 includes the following steps:

[0056] S6.1: Data collection, based on market basket data collection and analysis, and data processing and classification;

[0057] S6.2: Draw a time bar chart for the collected market basket data and merge it to generate a time bar chart corresponding to the analyzed data;

[0058] S6.3: Line drawing is performed on the market basket time bar chart, and compared with the time bar chart of the analyzed data, the differences between the highest line, the lowest line, the average line and the bending line of the market basket time bar chart and the analyzed data time bar chart are obtained, the data information of the promotion day in the time bar chart is removed, the value of the volatility is calculated through the profit volatility calculation formula, the data information of the promotion day is added in the time bar chart interval, and the promotion day data information bar chart is added according to different time intervals, the value of the volatility is calculated respectively, the influence of the promotion day on the profit volatility is analyzed, and the value of the volatility is used to reverse the influence factor of the promotion day for experimental calibration, the promotion day data information is added including at least three times of iteration calibration: the first time to add the basic promotion day data, the second time to add the data of 7 days before the promotion day, and the third time to add the data of 7 days after the promotion day, the volatility is recalculated after each iteration and the difference is compared, the influence factor is calibrated, and the promotion day data information is added, the daily data is collected from the market basket to ensure the accuracy of the calculation of the profit volatility;

[0059] S6.4: A data analysis report is generated according to the results of the market basket time bar chart and the analyzed data time bar chart.

[0060] Specifically, the comprehensive analysis in S7 is to combine the data analysis report in S5 and the data analysis report in S6 to perform comprehensive analysis on the sales data, and the generated report includes the setting of the title, the background information, the research problem, the analysis result and the data visualization, the background information provides the background and purpose of the analysis, the research problem is to clarify the specific problem and target of the analysis, the analysis result is to display the analysis result in the form of chart and text, and highlight the important findings, the data visualization is to use charts to help readers understand the results, and the charts include but are not limited to bar charts, pie charts and line charts Figure 1 The above, wherein the complex network graph displays the node connection relationship in S3, is used to explain the data volatility root, the pie chart can be used to observe the data analysis percentage data, the line chart can be used to observe the data change trend, and the generated report is used to optimize the sales strategy, so as to improve the accuracy and efficiency of decision-making.

[0061] The application further provides a data analysis system, which comprises a data collection module, a chart module, a chart control module, an analysis module, a display module, a correlation module and a report one-key generation module.

[0062] The application further provides a computer readable storage medium, which stores a computer program.

[0063] Finally, it should be noted that: the above only for the preferred embodiments of the application and not for limiting the application, although the application has been described in detail with reference to the foregoing embodiments, for those skilled in the art, it still can be modified to the technical solutions recorded in the foregoing embodiments, or equivalent replacement of some technical features, any modification, equivalent replacement, improvement, etc. within the spirit and principles of the application, should be included in the protection scope of the application.

Claims

1. A data analysis method, characterized by, Comprise the following specific steps: S1: collect the data to be analyzed, and classify and summarize the data; S2: draw a time bar chart according to the classified and summarized data, and use the time bar chart to display data information, wherein the time bar chart takes time as the X-axis and numerical value as the Y-axis; S3: control the time bar chart, which is used for fusion, line drawing, comparison and modification operations on different types of time bar charts, wherein before the line drawing operation, a visibility algorithm is applied to convert time series data into a complex network graph to identify and filter noise data points, and the visibility algorithm constructs a network based on the visibility edges of adjacent data points, and the edge weight is dynamically calculated and determined by the Y value difference and X time interval between data points; S4: display and control the time bar chart, and store the time bar chart data; S5: analyze the data according to the time bar chart, compare the line drawn on the time bar chart, that is, the height relationship between the preset line and the highest line, the average line and the lowest line, when the preset line is higher than the highest line, the data in the time bar chart does not reach the preset value, when the preset line is lower than the lowest line, the data in the time bar chart reaches the preset value, when the preset line is higher than the average line and lower than the highest line, the average data in the time bar chart does not reach the preset value, when the preset line is lower than the average line and higher than the lowest line, the average data in the time bar chart reaches the preset value, and the profit volatility is calculated by the following formula: In the formula, is the profit volatility, is the Y-axis value of the average line in the profit amount time column chart, is the Y-axis value of the preset line in the profit amount time column chart, and a data analysis report is generated, and the analysis includes calculating a data volatility anomaly index based on node degree centrality of a complex network graph; S6: based on market basket, data correlation, correlation analysis of data, generation of data analysis report, the correlation analysis adopts market basket weighted correlation formula: weight = (promotion day influence factor × volatility) / (1 + time attenuation coefficient), the correlation analysis of data includes the following steps: S6.1: data acquisition, based on market basket, collect data corresponding to analysis data, and process and classify the data collected by market basket; S6.2: draw a time bar chart for the collected market basket data, and fuse to generate a market basket time bar chart corresponding to the analysis data; S6.3: Line drawing is performed on the market basket time bar chart, and compared with the time bar chart of the analyzed data, the differences between the highest line, the lowest line, the average line and the bending line of the market basket time bar chart and the analyzed data time bar chart are obtained, the data information of the promotion day in the market basket time bar chart is removed, the value of the profit volatility rate is calculated through the profit volatility rate calculation formula, the data information of the promotion day is added to the market basket time bar chart at intervals, and the market basket time bar chart with the added promotion day data information is added according to different time intervals. The value of the profit volatility rate is calculated, the influence of the promotion day on the profit volatility rate is analyzed, and the value of the profit volatility rate is used to reverse the experimental calibration of the promotion day influence factor. The added promotion day data information includes at least three times of iterative calibration: the first time to add basic promotion day data, the second time to add 7 days of data before the promotion day, and the third time to add 7 days of data after the promotion day. The volatility rate is recalculated after each iteration and the difference is compared to calibrate the influence factor. When adding the promotion day data information, daily data needs to be collected from the market basket to ensure the accuracy of the profit volatility rate calculation. S6.4: A data analysis report is generated according to the results of the market basket time bar chart and the analyzed data time bar chart. S7: Comprehensive analysis, generate data analysis report.

2. The data analysis method of claim 1, wherein, The data collected in S1 includes time, sales, sales cost and region. The classified and summarized data is constrained by period time, sales, sales cost and region, and a classified storage folder is established to store the classified data, and data tags are established according to the data inside the classified storage folder.

3. The data analysis method of claim 2, wherein, The time bar chart in S2 is drawn with time as the X-axis and numerical value as the Y-axis. The data tags in S1 are input into the time bar chart, and the numerical value at each time point is displayed using a bar chart. The height of the bar represents the numerical value. A classified time bar chart is generated, including single-period, single-region sales and sales cost time bar charts.

4. The data analysis method of claim 3, wherein, The fusion of different types of time bar charts in S3 is performed by classified time bar charts. Single-period, single-region sales and sales cost time bar charts are fused to generate single-period, single-region profit time bar charts, multi-period, single-region profit time bar charts, single-period, multi-region profit time bar charts, multi-period, multi-region profit time bar charts, multi-period, single-region sales time bar charts, single-period, multi-region sales time bar charts, multi-period, multi-region sales time bar charts, multi-period, single-region sales cost time bar charts, single-period, multi-region sales cost time bar charts, and multi-period, multi-region sales cost time bar charts. In S3, line drawing is performed on the time bar chart to draw straight lines and bending lines. The drawing of straight lines includes the highest line, the average line and the lowest line based on the complex network graph anomaly index dynamic adjustment, wherein the average line calculation excludes data points with an anomaly index greater than 1.

5. The data analysis method of claim 4, wherein, The display control of the time column chart in S4 is the visual design of the time column chart, including the design of clear axes and the design of data visualization. The design of clear axes is to set clear labels for the time X-axis and the numerical Y-axis, indicating the unit and meaning, and to set reasonable scale intervals for the time X-axis and the numerical Y-axis. The design of data visualization is to set the column width, make the column width correspond to the time X-axis, and make the adjacent columns have visual interval. Then the column is filled with color, different colors are used to distinguish data series and categories, data labels are added on the top of the column chart, specific values are displayed on the top of the column, and graphical labels are set on the time column chart to retrieve the time column chart according to the graphical labels, and a database is established to store the time column chart data information.

6. The data analysis method of claim 5, wherein, The comprehensive analysis in S7 is a comprehensive analysis of the sales data combining the data analysis report in S5 and the data analysis report in S6. The generated report includes the setting of title, background information, research problem, analysis result and data visualization. The background information provides the background and purpose of the analysis. The research problem is to clarify the specific problem and target of the analysis. The analysis result is to display the analysis result in the form of chart and text, highlighting important findings. Data visualization uses charts to help readers understand the results. The charts include complex network diagram, column chart, pie chart and line chart. The complex network diagram shows the node connection relationship in S3, which is used to explain the root cause of data fluctuation.

7. A data analysis system implementing any one of the data analysis methods of claims 1-6. The data analysis system comprises: A data collection module for collecting, classifying and summarizing the analyzed data; A chart module for storing charts used for data analysis and supporting chart data filling to form data charts; A chart control module for fusion, line drawing, comparison and modification of charts; An analysis module for analyzing data based on the chart control module and generating analysis reports; A display module for displaying charts and analysis results generated by data analysis; An association module for collecting market basket data to analyze the analyzed data; A report one-key generation module for generating reports for the analyzed problems.

8. A computer-readable storage medium, characterized in that, The computer readable storage medium stores a computer program, which is executed by the processor to implement the data analysis method of any one of claims 1-6. The computer readable storage medium stores a computer program, which is executed by the processor to implement the data analysis method of any one of claims 1-6.

Images