Analysis method and device based on cigarette case package design evaluation data

Abstract

The invention discloses an analysis method and device based on cigarette case package design evaluation data, and the method comprises the steps: carrying out the grouping of the first evaluation data of cigarette case package design, and obtaining the second evaluation data corresponding to the subdivided components of each design element; analyzing the second evaluation data to obtain a first analysis result; wherein the analysis at least comprises the analysis of the subdivision components of each design element on a plurality of emotion dimensions, and the plurality of emotion dimensions at least comprise high-end, simple, unique, convenient, elegant and luxury; and visualizing the first analysis result to obtain a visualized result. According to the method, the response of consumers to each design element of the cigarette case package in multiple emotion dimensions is accurately analyzed, and by means of deep data mining and system analysis, a designer can clearly know emotion cognition differences of different design elements in different consumer groups, so that demands are accurately positioned, the design decision process is optimized, blindness is avoided, and the design efficiency is improved. The design period is shortened and the cost is reduced.

Description

Technical Field

[0001] The present application relates to the field of cigarette package design, and more specifically, to an analysis method and device based on cigarette package design evaluation data. Background Art

[0002] In the field of packaging design, the traditional design model relies on the designer's personal creative inspiration and limited market experience. Designers mainly rely on their own understanding of aesthetics, brand concepts and a general understanding of the target market to conceive packaging solutions. This approach has exposed many limitations in the face of increasingly complex and changing market environments and consumer demands.

[0003] On the one hand, the lack of accurate insight into consumers’ deep emotional appeals and subtle preference differences makes it difficult to ensure that the designed packaging can stand out from many competing products and resonate strongly with consumers. For example, the color selection may be based solely on subjective feelings, without fully considering the emotional connotations conveyed by different colors in different cultural backgrounds, age groups, and consumption scenarios.

[0004] On the other hand, the traditional design process makes inefficient use of market feedback data, often only conducting simple qualitative analysis and failing to uncover hidden design trends and key influencing factors from massive amounts of consumer evaluation data.

[0005] With the advent of the digital age, consumers have generated a massive amount of evaluation data on packaging design during online shopping and social media interactions. These data contain rich potential information, but due to the lack of effective integration and analysis methods, they have not been fully transformed into an innovative driving force for packaging design.

[0006] Therefore, there is an urgent need for an innovative technical method that can systematically collect and analyze consumer data and present it visually, providing a scientific, objective and forward-looking basis for packaging design to meet the modern market's requirements for personalized and precise packaging design. Summary of the invention

[0007] The present application provides an analysis method and device based on cigarette box packaging design evaluation data, which accurately analyzes consumers' reactions to various design elements of cigarette box packaging in multiple emotional dimensions. With the help of deep data mining and system analysis, designers can clearly know the emotional cognitive differences of different design elements in different consumer groups, thereby accurately positioning needs, optimizing the design decision-making process, avoiding blindness, shortening the design cycle, and reducing costs. This helps to improve the market competitiveness of packaging, enable it to stand out among many competing products, enhance product recognition and brand communication, promote the transformation of the packaging design industry to data-driven innovation, improve customer satisfaction and loyalty, and expand commercial value space.

[0008] The present application provides an analysis method based on cigarette package design evaluation data, including:

[0009] Grouping the first evaluation data of the cigarette package design to obtain second evaluation data corresponding to the subdivided components of each design element;

[0010] Analyze the second evaluation data to obtain a first analysis result; wherein the analysis at least includes analysis of the subdivided components of each design element on multiple emotional dimensions, and the multiple emotional dimensions at least include high-end, simple, unique, convenient, elegant and luxurious;

[0011] The first analysis result is visualized to obtain a visualization result.

[0012] Preferably, the analysis method based on the cigarette box packaging design evaluation data further includes:

[0013] Receiving a selection instruction for a visualization result;

[0014] Generates and outputs analysis reports based on selected instructions.

[0015] Preferably, the analysis method based on the cigarette box packaging design evaluation data further includes:

[0016] Receive operation instructions for visualization results;

[0017] Operate the visualization results according to the operation instructions and display the operation results.

[0018] Preferably, the analysis also includes:

[0019] The second evaluation data is grouped according to the subdivided components of each personnel dimension of the data provider of the first evaluation data to form third evaluation data; wherein the personnel dimension includes at least age group, gender and education level;

[0020] analyzing the third evaluation data to obtain a second analysis result;

[0021] All second analysis results of different segmentation components under the same personnel dimension are compared to obtain the first difference.

[0022] Preferably, the analysis also includes:

[0023] Verify the first difference;

[0024] If the first difference is statistically significant, the first difference is taken as the first analysis result.

[0025] Preferably, the analysis also includes:

[0026] Cross-combining all third evaluation data under at least two personnel dimensions to form a plurality of fourth evaluation data;

[0027] analyzing the fourth evaluation data to obtain a third analysis result;

[0028] comparing different third analysis results to obtain a second difference;

[0029] Verify the second difference;

[0030] If the second difference is statistically significant, it will be used as the first analysis result.

[0031] The present application also provides an analysis device based on cigarette package design evaluation data, comprising a first grouping module, a first analysis module and a visualization module;

[0032] The first grouping module is used to group the first evaluation data of the cigarette package design to obtain the second evaluation data corresponding to the subdivided components of each design element;

[0033] The first analysis module is used to analyze the second evaluation data to obtain a first analysis result; wherein the analysis at least includes analysis of the subdivided components of each design element on multiple emotional dimensions, and the multiple emotional dimensions at least include high-end, simple, unique, convenient, elegant and luxurious;

[0034] The visualization module is used to visualize the first analysis result to obtain a visualization result.

[0035] Preferably, the analysis device based on cigarette package design evaluation data further includes a receiving module and a report forming module;

[0036] The receiving module is used for receiving a selection instruction for the visualization result;

[0037] The report generation module is used to generate and output an analysis report based on the selected instructions.

[0038] Preferably, the receiving module is further used to receive an operation instruction for the visualization result;

[0039] The analysis device also includes an operation module, which is used to operate the visualization results according to the operation instructions and display the operation results.

[0040] Preferably, the first analysis module includes a second grouping module, a second analysis module and a comparison module;

[0041] The second grouping module is used to group the second evaluation data according to the subdivided components of each personnel dimension of the data provider of the first evaluation data to form third evaluation data; wherein the personnel dimension includes at least age group, gender and education level;

[0042] The second analysis module is used to analyze the third evaluation data to obtain a second analysis result;

[0043] The comparison module is used to compare all second analysis results of different segmented components under the same personnel dimension to obtain the first difference.

[0044] Preferably, the first analysis module further includes a verification module, and the verification module is used to verify the first difference; if the first difference is statistically significant, the first difference is used as the first analysis result.

[0045] Preferably, the second grouping module is further used to cross-combine all the third evaluation data under at least two personnel dimensions to form a plurality of fourth evaluation data;

[0046] The second analysis module is also used to analyze the fourth evaluation data to obtain a third analysis result;

[0047] The comparison module is also used to compare different third analysis results to obtain a second difference;

[0048] The verification module is also used to verify the second difference; if the second difference is statistically significant, the second difference is used as the first analysis result.

[0049] Other features and advantages of the present application will become apparent from the following detailed description of exemplary embodiments of the present application with reference to the accompanying drawings. BRIEF DESCRIPTION OF THE DRAWINGS

[0050] The accompanying drawings, which are incorporated in and constitute a part of the specification, illustrate embodiments of the application and, together with the description, serve to explain the principles of the application.

[0051] Figure 1 A flow chart of the analysis method based on cigarette package design evaluation data provided in this application;

[0052] Figure 2 This is a structural diagram of the analysis device based on cigarette box packaging design evaluation data provided in this application. DETAILED DESCRIPTION

[0053] Various exemplary embodiments of the present application will now be described in detail with reference to the accompanying drawings. It should be noted that unless otherwise specifically stated, the relative arrangement of components and steps, numerical expressions and numerical values ​​set forth in these embodiments do not limit the scope of the present application.

[0054] The following description of at least one exemplary embodiment is merely illustrative in nature and is in no way intended to limit the present application, its application, or uses.

[0055] Technologies, methods, and equipment known to ordinary technicians in the relevant art may not be discussed in detail, but where appropriate, the technologies, methods, and equipment should be considered part of the specification.

[0056] In all examples shown and discussed herein, any specific values ​​should be interpreted as merely exemplary and not limiting. Therefore, other examples of the exemplary embodiments may have different values.

[0057] This application provides an analysis method and device based on cigarette box packaging design evaluation data, which accurately analyzes consumers' reactions to various design elements of cigarette box packaging in multiple emotional dimensions. With the help of deep data mining and system analysis, designers can clearly know the emotional cognitive differences of different design elements in different consumer groups, so as to accurately locate needs, optimize the design decision-making process, avoid blindness, shorten the design cycle, and reduce costs. This will help improve the market competitiveness of packaging, enable it to stand out among many competing products, strengthen product recognition and brand communication, promote the transformation of the packaging design industry to data-driven innovation, improve customer satisfaction and loyalty, and expand commercial value space. At the same time, this application also provides support for the development of personalized and customized packaging to meet the personalized needs of consumers.

[0058] like Figure 1 As shown, the analysis method based on cigarette box packaging design evaluation data provided in this application includes:

[0059] S110: Grouping the first evaluation data of the cigarette package design to obtain second evaluation data corresponding to the subdivided components of each design element.

[0060] Understandably, before the first evaluation data is grouped, the original evaluation data of the cigarette box packaging design needs to be preprocessed. As an embodiment, the original evaluation data is in the form of a questionnaire survey. The original evaluation data covers the basic information of the respondents (i.e., data providers), such as age, gender, education, etc., as well as detailed ratings of the design elements of the cigarette box packaging on multiple emotional dimensions (e.g., a 7-point scale of -3 to 3). Among them, as an embodiment, the emotional dimension includes six emotional dimensions of high-end, concise, unique, convenient, elegant, and luxurious. The design elements of the cigarette box packaging at least include the opening and closing method (the subdivision components include lateral sliding, bidirectional folding, side pressing, etc.), the font style (the subdivision components include calligraphy running script, serif fonts, regular script, small seal script, etc.), the pattern design (the subdivision components include cartoon pictures, fine brushwork, illustration style, brand logo elements, traditional elements, etc.) and color matching (the subdivision components include low-saturation monochrome, high-saturation monochrome, yellow and red combination colors, other color combination colors, etc.), etc.

[0061] Preprocessing includes reading and storing the questionnaires, as well as data cleaning. In the data cleaning phase, the integrity and consistency of the data are fully checked, and missing values ​​(such as intelligent filling using the fillna function) and outliers are accurately identified and processed (reasonable correction or elimination based on data distribution characteristics and business rules) to ensure that the data quality meets the strict requirements of subsequent analysis. At the same time, the pivot table technology is used to cleverly reorganize the data structure and optimize data storage and access methods, so as to obtain the first evaluation data and lay a solid foundation for subsequent in-depth analysis.

[0062] On the basis of the above, when grouping the first evaluation data, the problem mapping relationship in the first evaluation data is precisely defined (for example, by designing a Python dictionary structure to implement the definition), and the first evaluation data is grouped based on the subdivided components of each design element to obtain the second evaluation data. For example, for the opening and closing method, the second evaluation data of the side sliding opening and closing method, the second evaluation data of the two-way folding opening and closing method, the second evaluation data of the side pressing opening and closing method, etc. are obtained.

[0063] On this basis, each second evaluation data is stored (for example, converted into an independent CSV file), and the association between each stored questionnaire and the original evaluation data is established, including detailed scoring data and comprehensive group characteristic information. In the process of file naming and data organization, the unified and standardized naming rules and data structure standards are strictly followed to achieve efficient data management and convenient traceability.

[0064] S120: Analyze the second evaluation data to obtain a first analysis result.

[0065] As an embodiment, the analysis includes at least analysis of each subdivided component of each design element on multiple emotional dimensions.

[0066] As an embodiment, for each subdivided component of each design element, firstly, the evaluation data with each emotional dimension is extracted from the corresponding second evaluation data (for example, the evaluation data that the side sliding opening and closing mode is evaluated as high-end, the evaluation data that the side sliding opening and closing mode is evaluated as simple, the evaluation data that the side sliding opening and closing mode is evaluated as unique, the evaluation data that the side sliding opening and closing mode is evaluated as convenient, the evaluation data that the side sliding opening and closing mode is evaluated as elegant, and the evaluation data that the side sliding opening and closing mode is evaluated as luxurious), and statistical analysis is performed on it, such as calculating the average score (obtained by summing up the scores of all respondents and dividing by the number of samples) to measure the overall performance level of the design element in a certain emotional dimension; the standard deviation (reflecting the degree of dispersion of the data relative to the average value, calculated as follows: ,in For each sample score, is the average score, is the number of samples), which is used to evaluate the distribution stability of the data. These indicators can help designers quickly understand the performance characteristics of various design elements in different emotional dimensions.

[0067] On this basis, preferably, the analysis also includes:

[0068] S12011: Group the second evaluation data according to the segmented components of each personnel dimension of the data provider of the first evaluation data to form third evaluation data.

[0069] Among them, the personnel dimension includes at least age group (subdivided components include 18-25 years old, 30-45 years old and 46-60 years old; or Generation Z, Generation Y, Generation X, etc.), gender (subdivided components include male and female), and education level (subdivided components include junior high school, high school, higher vocational college, junior college, undergraduate, master's, doctoral, etc.).

[0070] Taking the side sliding opening and closing method as an example, after grouping the corresponding second evaluation data from the personnel dimension of age groups, we obtained the third evaluation data of the side sliding opening and closing method made by the respondents aged 18-25, the third evaluation data of the side sliding opening and closing method made by the respondents aged 30-45, and the third evaluation data of the side sliding opening and closing method made by the respondents aged 46-60.

[0071] S12012: Analyze the third evaluation data to obtain a second analysis result.

[0072] As an embodiment, for each third evaluation data, data statistics and analysis are performed from multiple sentiment dimensions to obtain corresponding second analysis results, including mean, median, mode, etc.

[0073] Taking the third evaluation data of the side sliding opening and closing method made by the respondents aged 18-25 as an example, the second analysis results corresponding to the third evaluation data with emotional dimensions of high-end, simple, unique, convenient, elegant and luxurious in the third evaluation data were obtained respectively.

[0074] S12013: Compare all the second analysis results of different subdivision components under the same personnel dimension to obtain the first difference. By comparing the data of different groups, the differences in preferences of different groups for design elements can be clearly revealed.

[0075] For example, with regard to the age group dimension, by comparing the analysis results of the side sliding opening and closing methods for respondents aged 18-25, 30-45, and 46-60, we can learn the preference patterns of each age group for the side sliding opening and closing method. For example, respondents aged 18-25 tend to think that the side sliding opening and closing method is elegant, respondents aged 30-45 tend to think that the side sliding opening and closing method is simple, and respondents aged 46-60 tend to think that the side sliding opening and closing method is convenient.

[0076] In this embodiment, preferably, the analysis further comprises:

[0077] S12014: Verify the first difference, such as t-test, analysis of variance, etc., and strictly verify the score differences between different groups to determine whether these differences are statistically significant (usually the significance level is set at 0.05 or 0.01).

[0078] S12015: If the first difference is statistically significant, the first difference is taken as the first analysis result.

[0079] Through a scientific hypothesis testing process, the real differences in design preferences among different groups are determined, providing a solid basis for accurately positioning target customer groups and personalized packaging design.

[0080] On the basis of the above, preferably, the analysis also includes:

[0081] S12021: Cross-combine all third evaluation data under at least two personnel dimensions to form multiple fourth evaluation data.

[0082] For instance, taking the side sliding opening and closing method as an example, the age group and gender are combined to obtain the fourth evaluation data of the side sliding opening and closing method made by male respondents aged 18-25, the fourth evaluation data of the side sliding opening and closing method made by female respondents aged 18-25, the fourth evaluation data of the side sliding opening and closing method made by male respondents aged 30-45, the fourth evaluation data of the side sliding opening and closing method made by female respondents aged 30-45, the fourth evaluation data of the side sliding opening and closing method made by male respondents aged 46-60, and the fourth evaluation data of the side sliding opening and closing method made by female respondents aged 46-60.

[0083] It is understandable that the age group, gender and education level may be combined, or the gender and education level may be combined, or the age group and education level may be combined to obtain the fourth evaluation data.

[0084] S12022: Analyze the fourth evaluation data to obtain a third analysis result. Please refer to S12012.

[0085] S12023: Compare different third analysis results to obtain a second difference. Please refer to S12013.

[0086] S12024: Verify the second difference. Please refer to S12014.

[0087] S12025: If the second difference is statistically significant, the second difference will be used as the first analysis result.

[0088] Therefore, by combining age group and gender for analysis, we can obtain the differences in the evaluation of specific design elements by men and women of different age groups; by combining the three dimensions of age group, gender and education level, we can study the consumer preference patterns under different combinations, etc. This process can achieve deep integration and analytical mining of multi-dimensional data, providing strong support for a comprehensive understanding of consumer behavior.

[0089] S130: Visualize the first analysis result to obtain a visualization result.

[0090] As an embodiment, the first analysis results of each subdivided component of each design element on multiple emotional dimensions are intuitively displayed by drawing a radar chart. In the drawing process, for each design element, the average score of each emotional dimension is first calculated, and then these average scores are mapped to a polar coordinate system, with angles representing different emotional dimensions and radii representing average scores. Then, a unique color is defined for each emotional dimension (for example, #F4CF64 for high-end, #F4AAB4 for concise, etc.), and the line width (such as setting it to 2) and the mark style (such as a circular mark 'o') are adjusted to ensure that the radar chart has good visual effects and readability. At the same time, the label position is optimized to avoid text overlap so that the chart information is clearly conveyed.

[0091] As another embodiment, a bar chart is used to display the first analysis results of different segmented components of different personnel dimensions, and the bar chart is drawn with the segmented components of the design elements as the horizontal axis and the score as the vertical axis. A predefined color dictionary is used to assign a uniform color to each emotional dimension or group to enhance the visual consistency and recognition of the chart. By comparing the heights of different bars, the preference differences between groups can be intuitively presented.

[0092] As another embodiment, a heat map is used to visualize the first analysis result obtained by the poor analysis. The heat map intuitively reflects the scoring mode under different combinations through the changes in color depth. The darker the color, the higher the score, and vice versa. During the drawing process, accurately set the color mapping range (such as using the 'YlGnBu' color mapping scheme) and mark the numerical format (for example, keep two decimal places) to ensure that the heat map can accurately convey data information. At the same time, add detailed axis labels (such as age group / gender / education level as the vertical axis and design elements as the horizontal axis) to make the chart easy to understand.

[0093] Preferably, after obtaining the visualization results, all generated visualization results are saved as high-quality image files (such as PNG format) and systematically classified and stored according to the categories of design elements. These visualization results not only provide intuitive and powerful argument support for the research report, but also provide direct design reference materials for packaging designers to help them quickly understand consumer needs and preference trends.

[0094] Preferably, in the present application, the analysis method based on the cigarette box packaging design evaluation data further includes:

[0095] S140: receiving an operation instruction for the visualization result.

[0096] S150: operating the visualization result according to the operation instruction and displaying the operation result.

[0097] Specifically, the visualization results are presented through an interactive interface that provides a series of intuitive and convenient filtering controls (implemented by selecting commands). Users can select specific education levels (such as junior high school, high school, vocational college, junior college, undergraduate, master's, doctoral, etc.), gender (male, female) or age group (18-25 years old, 30-45 years old, 46-60 years old, etc.) through the drop-down menu to achieve dynamic filtering and personalized viewing of data.

[0098] In addition, the interface can realize advanced functions of data tables, such as paging (users can easily switch pages to view different parts of data), searching (quickly locate data of interest by keywords, an operation instruction) and sorting (sort data in ascending or descending order according to specified columns, an operation instruction). It can also realize real-time update of filtering conditions and automatic refresh of data tables, ensuring that users can obtain analysis results that meet their needs in a timely manner.

[0099] Preferably, in the present application, the analysis method based on the cigarette box packaging design evaluation data further includes:

[0100] S160: receiving a selection instruction for a visualization result.

[0101] S170: Generate and output analysis reports based on selected instructions. The report interface integrates all visual charts (such as radar charts, bar charts, heat maps, etc.), and provides detailed description text for each chart to help users accurately understand the information conveyed by the chart.

[0102] To meet the needs of users to further analyze and use data, the system supports exporting the results after filtering (by selecting commands) (for example, exporting in the form of CSV format files). Users only need to click the export button to download the data displayed on the current page to the local computer for more in-depth data analysis or integration with other tools. The entire reporting system adopts a responsive design concept to ensure perfect display on different devices (such as desktop computers, tablets, mobile phones, etc.), providing users with a convenient access experience anytime, anywhere.

[0103] Based on the above, the present application also provides an analysis device based on cigarette package design evaluation data. Figure 2 As shown, the analysis device includes a first grouping module 210 , a first analysis module 220 and a visualization module 230 .

[0104] The first grouping module 210 is used to group the first evaluation data of the cigarette package design to obtain the second evaluation data corresponding to the subdivided components of each design element;

[0105] The first analysis module 220 is used to analyze the second evaluation data to obtain a first analysis result; wherein the analysis at least includes analysis of the subdivided components of each design element on multiple emotional dimensions, and the multiple emotional dimensions at least include high-end, simple, unique, convenient, elegant and luxurious;

[0106] The visualization module 230 is used to visualize the first analysis result to obtain a visualization result.

[0107] On the basis of the above, the analysis device further includes a receiving module 240 and an operating module 250. The receiving module 240 is used to receive an operating instruction for the visualization result. The operating module 250 is used to operate the visualization result according to the operating instruction and display the operation result.

[0108] On the basis of the above, preferably, the receiving module 240 is also used to receive a selection instruction for the visualization result. The analysis device also includes a report forming module 260, which is used to form and output an analysis report according to the selection instruction.

[0109] Preferably, the first analysis module 220 includes a second grouping module 2201 , a second analysis module 2202 and a comparison module 2203 .

[0110] The second grouping module 2201 is used to group the second evaluation data according to the subdivided components of each personnel dimension of the data provider of the first evaluation data to form third evaluation data; wherein the personnel dimension at least includes age group, gender and education level;

[0111] The second analysis module 2202 is used to analyze the third evaluation data to obtain a second analysis result;

[0112] The comparison module 2203 is used to compare all second analysis results of different subdivided components under the same personnel dimension to obtain the first difference.

[0113] Preferably, the first analysis module 220 further includes a verification module 2204, and the verification module 2204 is used to verify the first difference; if the first difference is statistically significant, the first difference is used as the first analysis result.

[0114] Preferably, the second grouping module 2201 is further used to cross-combine all the third evaluation data under at least two personnel dimensions to form a plurality of fourth evaluation data;

[0115] The second analysis module 2202 is also used to analyze the fourth evaluation data to obtain a third analysis result;

[0116] The comparison module 2203 is also used to compare different third analysis results to obtain second differences;

[0117] The verification module 2204 is also used to verify the second difference; if the second difference is statistically significant, the second difference is used as the first analysis result.

[0118] Although some specific embodiments of the present application have been described in detail by way of example, it should be understood by those skilled in the art that the above examples are only for illustration, not for limiting the scope of the present application. It should be understood by those skilled in the art that the above embodiments may be modified without departing from the scope and spirit of the present application. The scope of the present application is defined by the appended claims.

Claims

1. An analysis method based on cigarette package design evaluation data, characterized in that: include: Grouping the first evaluation data of the cigarette package design to obtain second evaluation data corresponding to the subdivided components of each design element; Analyze the second evaluation data to obtain a first analysis result; wherein the analysis at least includes analysis of the subdivided components of each design element on multiple emotional dimensions, and the multiple emotional dimensions at least include high-end, simplicity, uniqueness, convenience, elegance and luxury; The first analysis result is visualized to obtain a visualization result.

2. The analysis method based on cigarette package design evaluation data according to claim 1, characterized in that: Also includes: Receiving a selection instruction for a visualization result; An analysis report is generated and outputted according to the selection instructions.

3. The analysis method based on cigarette package design evaluation data according to claim 1, characterized in that: Also includes: Receive operation instructions for visualization results; The visualization result is operated according to the operation instruction, and the operation result is displayed.

4. The analysis method based on cigarette package design evaluation data according to claim 1, characterized in that: The analysis also includes: The second evaluation data is grouped according to the subdivided components of each personnel dimension of the data provider of the first evaluation data to form third evaluation data; wherein the personnel dimension includes at least age group, gender and education level; Analyzing the third evaluation data to obtain a second analysis result; All second analysis results of different segmentation components under the same personnel dimension are compared to obtain the first difference.

5. The analysis method based on cigarette package design evaluation data according to claim 4, characterized in that: The analysis also includes: verifying the first difference; If the first difference is statistically significant, the first difference is taken as the first analysis result.

6. An analysis device based on cigarette package design evaluation data, characterized in that: It includes a first grouping module, a first analysis module and a visualization module; The first grouping module is used to group the first evaluation data of the cigarette package design to obtain the second evaluation data corresponding to the subdivided components of each design element; The first analysis module is used to analyze the second evaluation data to obtain a first analysis result; wherein the analysis at least includes analysis of the subdivided components of each design element on multiple emotional dimensions, and the multiple emotional dimensions at least include high-end, simple, unique, convenient, elegant and luxurious; The visualization module is used to visualize the first analysis result to obtain a visualization result.

7. The analysis device based on cigarette package design evaluation data according to claim 6, characterized in that: Also includes a receiving module and a report forming module; The receiving module is used to receive a selection instruction for the visualization result; The report forming module is used to form and output an analysis report according to the selection instruction.

8. The analysis device based on cigarette package design evaluation data according to claim 7, characterized in that: The receiving module is also used to receive operation instructions for the visualization results; The analysis device further comprises an operation module, and the operation module is used to operate the visualization result according to the operation instruction and display the operation result.

9. The analysis device based on cigarette package design evaluation data according to claim 6, characterized in that: The first analysis module includes a second grouping module, a second analysis module and a comparison module; The second grouping module is used to group the second evaluation data according to the subdivided components of each personnel dimension of the data provider of the first evaluation data to form third evaluation data; wherein the personnel dimension at least includes age group, gender and education level; The second analysis module is used to analyze the third evaluation data to obtain a second analysis result; The comparison module is used to compare all second analysis results of different segmented components under the same personnel dimension to obtain first differences.

10. The analysis device based on cigarette package design evaluation data according to claim 9, characterized in that: The first analysis module also includes a verification module, and the verification module is used to verify the first difference; if the first difference is statistically significant, the first difference is used as the first analysis result.

Images