Intelligent generating and screening system for personalized package design scheme

Abstract

The invention discloses a personalized package design scheme intelligent generation and screening system, which relates to the technical field of package design and comprises a data acquisition module, a data processing module, a user portrait analysis module, a design generation module and a screening module. Product, market and regional data are collected in multiple channels through the data acquisition module, accurate connection of a design scheme and real-time market trend is realized in combination with standardized processing of the data processing module, the problem of disjunction of design and trend in the prior art is solved, regional consumption preference data are integrated through the data acquisition and processing module, and the design efficiency is improved. The design scheme can adapt to different regional requirements, the regional adaptability is improved, user features are deeply mined through the user portrait analysis module, personalized requirements of different groups are met in a targeted mode, the user satisfaction degree is improved, through multi-dimensional verification of the screening module, the reasonability and practicability of the design scheme are ensured, the number of design iterations is reduced, and the design efficiency is improved. And the design cost is reduced.

Description

Technical Field

[0001] This invention relates to the field of packaging design technology, specifically to an intelligent generation and screening system for personalized packaging design schemes. Background Technology

[0002] Packaging is an essential component of a product, serving as a crucial carrier from production to consumption. It not only protects the product and facilitates storage and transportation, but also plays a vital role in conveying brand information and attracting consumer attention, directly impacting a product's market competitiveness and significantly influencing brand promotion and sales. Personalized packaging design, tailored to product characteristics, brand image, and consumer needs, offers unique and targeted solutions. It breaks away from the homogeneity limitations of traditional standardized packaging, incorporating exclusive elements and differentiated styles to satisfy consumers' pursuit of personalized experiences. Simultaneously, it helps brands stand out in the market, enhancing brand recognition and consumer loyalty, and has become a mainstream trend in the current packaging design field.

[0003] However, existing packaging design technologies still have certain shortcomings in use. Their design logic is simplistic, focusing primarily on product characteristics without fully considering real-time market dynamics. This results in designs that fail to align with current consumer trends. Furthermore, existing technologies lack consideration for regional consumer preferences, and uniform designs cannot adapt to the diverse aesthetics and needs of consumers in different regions. They also fail to deeply analyze user profiles, making it difficult to accurately meet the personalized needs of different age groups and consumption habits. This leads to insufficient targeting of designs, low market acceptance, and increased costs associated with repeated design iterations. Therefore, developing an intelligent generation and filtering system for personalized packaging design solutions is of great significance. Summary of the Invention

[0004] The purpose of this invention is to overcome the shortcomings of existing technologies and provide an intelligent generation and screening system for personalized packaging design schemes. This system can collect product, market, and regional data through multiple channels via a data acquisition module, and combine this with standardized processing by a data processing module to achieve precise alignment between design schemes and real-time market trends. By integrating regional consumer preference data through the data acquisition and processing module, design schemes can be adapted to different regional needs, improving regional adaptability. Furthermore, by deeply mining user characteristics through a user profile analysis module, the system can specifically meet the personalized needs of different groups, improving user satisfaction. Finally, through multi-dimensional verification by the screening module, the system ensures the rationality and practicality of the design schemes, reducing design iterations and lowering design costs.

[0005] To solve the above-mentioned technical problems, the present invention provides the following technical solution: a personalized packaging design scheme intelligent generation and screening system, the system comprising: a data acquisition module, a data processing module, a user profile analysis module, a design generation module and a screening module; The data acquisition module is used to collect raw data from multiple channels. The raw data includes basic product data, real-time market data, and regional consumer preference data. The data acquisition module transmits the collected raw data to the data processing module. The data processing module is connected to the data acquisition module. It cleans, classifies, and structurally transforms the raw data to establish a standardized data warehouse and transmits the standardized data to the design and generation module. The user profile parsing module is used to collect consumer information, extract and label the information, build a user profile database, and transmit the user profile features to the design generation module. The design generation module is connected to the data processing module and the user profile analysis module respectively. It calls the preset design element library, generates packaging design schemes based on standardized data and user profile features, and transmits the schemes to the screening module. The screening module is connected to the design generation module. It evaluates and screens design schemes based on preset indicators and outputs qualified schemes.

[0006] Furthermore, when collecting basic product data, the data acquisition module connects to the brand's product management system to obtain product type, functional characteristics, brand core tone, and packaging size limitations. When collecting real-time market data, it calls social media open interfaces, e-commerce platform comment capture tools, and competitor monitoring systems to obtain design elements associated with trending social media topics, consumer reviews of competitor packaging, and market trends in popular packaging styles. When collecting regional consumer preference data, it integrates regional market research reports, local consumer behavior analysis data, and regional e-commerce sales data to obtain the preferences of consumers in different regions for packaging colors, pattern styles, and font types. To ensure the quality of collected data, the data acquisition module performs a credibility assessment on data from each channel. The assessment formula is: ,in, Score the credibility of the data. As a base score for the credibility of the data source, The data integrity coefficient. This is the data timeliness coefficient. , , These are the weighting coefficients. Determined based on industry-wide data sources and credit rating standards. Calculated based on data field missing rate and key information coverage. The attenuation coefficient corresponding to the reference data generation time and the current time interval is determined.

[0007] Furthermore, the data processing module includes the following steps when processing data: The collected raw data was screened to remove duplicate data, erroneous data, and invalid data that was irrelevant to packaging design. Topics on social media that did not involve packaging design were filtered out, and regional consumer preference results that had statistical biases in the market research report were corrected. The filtered valid data is categorized into three types: basic product data, real-time market data, and regional consumer preference data. The unstructured data after classification is transformed into structured labels or parameters, and then the structured data is stored in a standardized data warehouse to create a data index.

[0008] Furthermore, when the data processing module performs unstructured data conversion, it converts consumers' textual evaluations of competitor packaging into style-related and color-related tags; it extracts color values, pattern element outline parameters, and font style parameters from popular packaging image data in the market; and it converts descriptive data in regional consumer preferences into color preference parameters, pattern style tags, and font type parameters for the corresponding region.

[0009] Furthermore, the user profile analysis module collects and processes consumer information by including the following steps: We acquire consumer age range and spending power data through brand membership systems, obtain consumer aesthetic preference feedback through online questionnaire survey tools, and acquire consumer purchasing habits through consumer behavior tracking data. The acquired information is used to extract features, and the characteristics of the youth group and the elderly group are divided according to age. The characteristics of those who value cost-effectiveness and pursue personalized experience are marked according to consumption habits. The extracted features are associated with consumer identifiers to form consumer-specific feature tags, which are then integrated to build a user profile database. To highlight the impact of key features on the design, the user profile analysis module calculates the weights of consumer feature tags, using the following calculation method: ,in, For feature label weights, Score the importance of the label itself. Scoring the frequency of associations between consumer behavior and tags. As a balancing coefficient, it is determined based on the correlation between label type and consumption decision. Labels with a higher impact on consumption decisions correspond to higher α values. The correlation is obtained through correlation analysis between the frequency of label occurrence and purchase conversion rate in historical consumption data.

[0010] Furthermore, when constructing the user profile database, the user profile parsing module establishes a categorized storage directory based on feature tag types, storing age-related tags, consumption habit-related tags, and aesthetic preference-related tags in their respective directories, and establishing a tag retrieval mechanism. When it is necessary to call the user profile of a specific group, the target group feature tags are input, and the age, consumption habits, and aesthetic preferences of that group are extracted through the retrieval mechanism.

[0011] Furthermore, the design generation module generates the packaging design scheme by including the following steps: Call the preset design element library, which includes a color template library, a pattern material library, a font style library, and a packaging structure type library; The standardized data transmitted by the data processing module is associated with user profile features, and design elements of the corresponding categories are matched. When the user profile is an elderly group and the corresponding area prefers soft colors, light-colored templates in the color template library and large-sized fonts in the font style library are matched. By combining matching design elements with packaging structures that correspond to product characteristics and incorporating trendy graphic elements, a complete packaging design solution can be formed. To ensure the compatibility of design elements with multi-dimensional requirements, the design generation module calculates the matching degree of design elements using the following formula: ,in, To ensure the overall matching degree of design elements, To match elements with basic product data, The matching score between elements and user profile features is used to determine the element matching score. To match elements with market trends, , , These are the weighting coefficients. The degree of constraint on packaging function is determined based on product characteristics. Calculated based on user profile tag weights. The reliability score is determined based on market trend data.

[0012] Furthermore, the design generation module calls a color template library that includes gradient color templates and solid color templates of different hues, a pattern material library that includes geometric shapes, figurative patterns and cultural element patterns, a font style library that includes editable fonts of different sizes and font types, and a packaging structure type library that includes parametric models of common packaging structures such as box, bag, can and bottle. Each sub-library supports updating element content according to new design requirements.

[0013] Furthermore, the preset indicators of the screening module include the degree of fit with the brand tone, the degree of adaptability to market trends, the degree of matching with regional consumption preferences, and the degree of satisfaction with user characteristics. During the evaluation and screening, the color and style of each design scheme are first compared with the core tone of the brand, then it is judged whether the scheme conforms to the popular style in the market, then it is checked whether the scheme matches the preferences of the target region, and finally it is confirmed whether the scheme meets the needs of the target user group. Any scheme that fails to meet any indicator is eliminated, and all schemes that meet the indicators are retained to form a qualified scheme set.

[0014] Compared with existing technologies, this intelligent generation and screening system for personalized packaging design solutions has the following advantages: This invention collects product, market, and regional data through multiple channels via a data acquisition module. Combined with standardized processing by a data processing module, it achieves precise alignment between design solutions and real-time market trends, solving the problem of design being out of sync with trends in existing technologies. By integrating regional consumer preference data through the data acquisition and processing modules, the design solutions adapt to different regional needs, improving regional adaptability. Through a user profile analysis module, it delves into user characteristics to meet the personalized needs of different groups, increasing user satisfaction. Through multi-dimensional verification by the screening module, it ensures the rationality and practicality of the design solutions, reducing design iterations and lowering design costs. Ultimately, it achieves a comprehensive improvement in the targeting, practicality, and market competitiveness of packaging design, providing effective support for brand development.

[0015] Other advantages, objectives and features of the invention will be set forth in part in the description which follows, and in part will be apparent to those skilled in the art from the following examination or study, or may be learned from the practice of the invention. Attached Figure Description

[0016] To more clearly illustrate the technical solutions in the embodiments of the present invention or the prior art, the accompanying drawings used in the description of the embodiments or the prior art will be briefly introduced below. Obviously, the drawings described below are merely some embodiments of the present invention. For those skilled in the art, other drawings can be obtained based on these drawings without any creative effort.

[0017] Figure 1 A schematic diagram of a personalized packaging design scheme intelligent generation and screening system; Figure 2 This is a flowchart of a system for intelligent generation and screening of personalized packaging design solutions. Detailed Implementation

[0018] To further illustrate the technical means and effects of the present invention in achieving its intended purpose, the following detailed description of the specific implementation methods, structures, features, and effects of the present invention, in conjunction with the accompanying drawings and preferred embodiments, is provided below.

[0019] This invention provides an intelligent generation and screening system for personalized packaging design schemes. The system comprises a data acquisition module, a data processing module, a user profile analysis module, a design generation module, and a screening module, forming a complete technical solution. (See also...) Figure 1 and Figure 2 The specific details are as follows: The data acquisition module is responsible for collecting raw data from multiple channels, covering basic product data, real-time market data, and regional consumer preference data. When collecting basic product data, it interfaces with the brand's product management system to obtain key information such as product type and functional characteristics. When collecting real-time market data, it uses tools such as social media open interfaces to obtain popular related design elements and competitor reviews. When collecting regional consumer preference data, it integrates various regional data to clarify the preferences of consumers in different regions for packaging colors, patterns, etc., while also assessing the credibility of data from each channel.

[0020] The data processing module is connected to the data acquisition module. It first filters the raw data, removes invalid, erroneous and duplicate data and corrects statistical biases. Then, it divides the valid data into categories. Subsequently, it converts unstructured data into structured labels or parameters, builds a standardized data warehouse and establishes a data index, and transmits the standardized data to the design and generation module.

[0021] The user profile analysis module collects consumer information through brand membership systems, online questionnaires, and other channels, extracts features such as age, consumption habits, and aesthetic preferences, and tags them to build a user profile database. The database is then categorized and stored according to tag type, and a retrieval mechanism is established. After calculating the feature tag weights, the user profile features are transmitted to the design generation module.

[0022] The design generation module calls upon a preset design element library, including a color template library and a pattern material library, associates standardized data with user profile characteristics, matches corresponding design elements, combines the packaging structure corresponding to product characteristics and market trend pattern elements, generates a complete packaging design scheme, and transmits it to the filtering module. At the same time, it calculates the overall matching degree of design elements.

[0023] The screening module evaluates and screens design proposals from multiple dimensions based on preset indicators such as brand tone alignment, market trend adaptability, regional consumption preference matching, and user characteristic satisfaction. Proposals that fail to meet any one indicator are eliminated, and qualified proposals that meet all indicators are output.

[0024] Example 1 This example is applied to a regionalized personalized packaging design project for a food brand. The brand plans to launch customized snack packaging targeting young and elderly consumers in different provinces. The design needs to consider the brand's core brand identity, regional consumer preferences, and current market trends, addressing the issue of uneven acceptance of traditional uniform packaging among consumers in different regions and age groups. (See also...) Figure 1 and Figure 2 This system enables the intelligent generation and precise selection of packaging design schemes, thereby improving the market adaptability of product packaging and consumer satisfaction.

[0025] During the data collection phase, the data collection module initiates multi-channel data collection. When collecting basic product data, it connects to the food brand's product management system to obtain key information such as the snack's product type being nuts, its functional characteristics being low in salt and sugar, the brand's core tone being healthy and natural, and the packaging size being limited to small and portable packaging.

[0026] When collecting real-time market data, we utilize social media open interfaces to capture design elements associated with trending food-related topics, extract consumer reviews of similar nut product packaging using e-commerce platform comment scraping tools, and leverage competitor monitoring systems to obtain current market trends in nut packaging styles, including mainstream styles such as minimalist and natural designs, along with related color schemes. When collecting regional consumer preference data, we integrate market research reports from various provinces, local consumer behavior analysis data, and regional e-commerce sales data to clarify the preferences of consumers in different provinces regarding packaging colors, pattern styles, and font types. For example, consumers in some southern provinces prefer fresh color schemes, while consumers in some northern provinces tend to favor heavier pattern styles.

[0027] To ensure the reliability of the collected data, the data acquisition module uses a reliability assessment formula to evaluate the data from each channel. The formula is as follows: ,in Score the credibility of the data. This serves as the base score for data source credibility, determined based on industry-wide data source credit rating standards. The data integrity coefficient is calculated based on the data field missing rate and key information coverage. The data timeliness coefficient is determined by the attenuation coefficient corresponding to the time interval between the data generation time and the current time. , , These are weighting coefficients, corresponding to the importance percentages of data source, completeness, and timeliness, respectively. This formula is used to filter out high-reliability data and transmit it to the data processing module.

[0028] After receiving the raw data, the data processing module performs data processing according to a preset procedure. First, the raw data is filtered to remove duplicate product parameter data, statistically incorrect regional consumer preference data, and product manufacturing process data unrelated to packaging design. Data from social media discussions about food taste that do not involve packaging design is also filtered out, and regional color preference results with statistical biases in market research reports are corrected. Subsequently, the filtered valid data is categorized into three types: basic product data, real-time market data, and regional consumer preference data.

[0029] Finally, the categorized unstructured data was transformed. For consumers' textual reviews of competitor packaging, such as "the packaging colors are too bright and glaring" or "the patterns are not simple enough," these were converted into style-related minimalist preference tags and color-related soft color preference tags. For popular packaging image data in the market, color values, pattern element outline parameters, and font style parameters were extracted. For descriptive data in regional consumer preferences, such as "I like patterns with natural plant elements" or "I prefer Song typeface," these were converted into color preference parameters, pattern style tags, and font type parameters corresponding to the region. All structured data was stored in a standardized data warehouse and a data index was created for easy retrieval later.

[0030] The user profiling module simultaneously collects and processes consumer information. It obtains data on consumers' age range and spending power through the food brand's membership system, gathers feedback on consumers' aesthetic preferences for packaging through online questionnaires, and acquires consumer purchasing habits, such as purchase frequency and channels, through consumer behavior tracking data. The acquired information is then used to extract features, categorizing consumers into youth and senior groups based on age. Youth groups are characterized by a pursuit of personalized experiences and a preference for trendy elements, while senior groups are characterized by an emphasis on practicality and a preference for simple and clear designs. Finally, based on consumption habits, consumers are identified as prioritizing cost-effectiveness and pursuing quality.

[0031] The extracted features are associated with consumer identifiers to form unique consumer feature tags. These tags are then integrated to build a user profile database. The database is categorized and stored according to feature tag type, with age-related tags, consumption habit-related tags, and aesthetic preference-related tags stored in their respective directories. A tag retrieval mechanism is also established. Simultaneously, the weight of each consumer feature tag is calculated using the following method: ,in For feature label weights, Score the importance of the label itself. Scoring the frequency of associations between consumer behavior and tags. As a balancing factor, it is determined based on the correlation between label type and consumption decision; labels with a higher influence on consumption decisions correspond to higher balancing factors. The correlation value is derived from the correlation analysis between the frequency of tag occurrences and purchase conversion rates in historical consumption data. This formula highlights the impact of key features on the design, and then the user profile features are transmitted to the design generation module.

[0032] After receiving standardized data and user profile characteristics, the design generation module initiates the packaging design scheme generation process. First, it calls upon a preset design element library, which includes a color template library, a pattern material library, a font style library, and a packaging structure type library. The color template library covers gradient color templates and solid color templates in different shades; the pattern material library contains geometric shapes, figurative patterns, and cultural element patterns; the font style library contains editable fonts of different sizes and types; and the packaging structure type library contains parametric models of common packaging structures such as box and bag shapes. Then, it associates the standardized data with user profile characteristics and matches design elements to corresponding categories. For example, for a youth group with a preference for trendy elements and bright colors in the corresponding region, it matches bright gradient templates from the color template library, trendy geometric elements from the pattern material library, and artistic fonts from the font style library; for an elderly group with a preference for soft colors and simple patterns in the corresponding region, it matches light solid color templates from the color template library, simple natural plant elements from the pattern material library, and large-size Song typeface fonts from the font style library.

[0033] Next, the matching design elements are combined with the small, portable packaging structure corresponding to the product characteristics, and trendy graphic elements are incorporated to form a complete packaging design scheme. Simultaneously, the overall matching degree of the design elements is calculated using the formula: ,in To ensure the overall matching degree of design elements, To match elements with basic product data, The matching score between elements and user profile features is used to determine the element matching score. To match elements with market trends, , , These are the weighting coefficients. The degree of constraint on packaging function is determined based on product characteristics. Calculated based on user profile tag weights. Based on the credibility score of market trend data, the design elements are determined to be compatible with multi-dimensional needs, and then the generated packaging design scheme is transmitted to the screening module.

[0034] After receiving the design proposals, the screening module conducts an evaluation and screening process based on preset indicators. These preset indicators include the degree of alignment with brand image, the degree of adaptation to market trends, the degree of matching with regional consumption preferences, and the degree of satisfaction with user characteristics.

[0035] During the evaluation, the colors and style of each design proposal are first compared with the brand's core values ​​of health and nature to verify whether they align with the overall brand image. Next, it is determined whether the proposal conforms to current market trends in nut packaging styles. Then, it is checked whether the proposal matches the color, pattern, and font preferences of consumers in the target region. Finally, it is confirmed whether the proposal meets the personalized needs of the target user group, such as the trendy needs of young people and the practical needs of the elderly. Proposals that fail to meet any of these criteria are eliminated, and only those that meet all criteria are retained, forming a set of qualified proposals, which are then output through the proposal output platform.

[0036] In summary, this embodiment, through the complete application of an intelligent generation and screening system for personalized packaging design schemes, achieves precise alignment between food packaging design and real-time market trends, solving the problem of traditional design being out of touch with trends. By integrating regional consumer preference data, packaging design schemes are precisely adapted to the consumption needs of different provinces, significantly improving regional adaptability. Furthermore, by leveraging user profile analysis to deeply understand the characteristics of consumers in different age groups, design schemes become more targeted, effectively meeting the personalized needs of both young and elderly consumers, and improving consumer satisfaction.

[0037] Example 2 This example is applied to a regionalized personalized packaging design project for a cosmetics brand's skincare products. The brand plans to launch customized skincare packaging for consumers with dry and oily skin in different climate regions. The packaging needs to consider the brand's core luxury image, consumer preferences in different climate regions, and current beauty market trends, addressing the issue of insufficient adaptability of traditional uniform packaging to different climate regions and skin types. (See also...) Figure 1 and Figure 2 This system enables the intelligent generation and precise selection of skincare product packaging design schemes, thereby improving the market acceptance of product packaging and consumers' willingness to repurchase.

[0038] During the data collection phase, the data collection module initiated multi-channel data collection. When collecting basic product data, it connected to the beauty brand's product management system to obtain key information such as the product type (moisturizing lotion and serum), functional characteristics (deep hydration and oil control), brand core style (light luxury and minimalism), and packaging size (portable bottle type). When collecting real-time market data, it used social media open interfaces to capture design elements associated with trending beauty topics, extracted consumer reviews of similar skincare product packaging using e-commerce platform comment scraping tools, and leveraged a competitor monitoring system to obtain current market trends in skincare packaging styles, including minimalist and traditional Chinese style elements, as well as related material combinations.

[0039] When collecting regional consumer preference data, market research reports from various climate regions, local consumer behavior analysis data, and regional e-commerce sales data are integrated to clarify consumers' preferences for packaging materials, colors, and font types in different climate regions. For example, consumers in humid climates prefer frosted packaging, while consumers in dry climates prefer transparent packaging. To ensure the reliability of the collected data, the data collection module uses a credibility assessment formula to evaluate data from each channel. The formula is as follows: The formula is used to filter out high-reliability data and transmit it to the data processing module.

[0040] After receiving the raw data, the data processing module performs data processing according to a preset process. First, the raw data is filtered to remove duplicate product ingredient data, statistically incorrect regional skin type preference data, and product production process data unrelated to packaging design. Data on skincare product usage effects discussed on social media that does not involve packaging design is also filtered out, and regional material preference results with statistical biases in the market research report are corrected.

[0041] The filtered valid data was then categorized into three types: basic product data, real-time market data, and regional consumer preference data. Finally, the categorized unstructured data was transformed. For consumer text reviews of competitor packaging, these were converted into material-related matte texture preference tags and color-related cool color preference tags. For popular packaging image data, color values, pattern element outline parameters, and font style parameters were extracted. For descriptive data in regional consumer preferences, these were converted into material preference parameters, pattern style tags, and font type parameters corresponding to the corresponding climate region. All structured data was stored in a standardized data warehouse and indexed for easy retrieval later.

[0042] The user profiling module simultaneously collects and processes consumer information. It obtains data on consumers' age range and spending power through the beauty brand's membership system, gathers feedback on consumers' aesthetic preferences for packaging through online questionnaires, and acquires consumer purchasing habits, such as whether they prefer portable skincare products, through consumer behavior tracking data. Feature extraction is performed on the acquired information, categorizing consumers into dry and oily skin groups. Dry skin groups are characterized by a focus on conveying moisturizing textures in packaging and a preference for gentle, hydrating designs, while oily skin groups are characterized by a focus on conveying a refreshing feel in packaging and a preference for minimalist designs. Consumer habits are also identified, highlighting a focus on quality and value for money.

[0043] The extracted features are associated with consumer identifiers to form consumer-specific feature tags. These tags are then integrated to build a user profile database. The database is categorized and stored according to feature tag type, with tags related to skin type, consumption habits, and aesthetic preferences stored in their respective directories. A tag retrieval mechanism is also established. Simultaneously, the weight of each consumer feature tag is calculated using the following method: This formula highlights the impact of key features on the design, and then the user profile features are transmitted to the design generation module.

[0044] After receiving standardized data and user profile features, the design generation module initiates the packaging design scheme generation process. First, it calls the preset design element library, which includes a color template library, a pattern material library, a font style library, and a packaging structure type library. The color template library covers gradient color templates and solid color templates of different shades; the pattern material library includes plant graphics, geometric shapes, and traditional Chinese style patterns; the font style library contains editable fonts of different sizes and types; and the packaging structure type library contains parametric models of common packaging structures such as portable bottle types and extrusion tube types.

[0045] The standardized data is then correlated with user profile characteristics to match corresponding design elements. For example, for dry skin groups in humid climates who prefer frosted textures and warm colors, warm gradient templates from the color template library, plant graphic elements from the pattern material library, and rounded fonts from the font style library are matched. For oily skin groups in dry climates who prefer transparent materials and cool colors, cool solid color templates from the color template library, geometric graphic elements from the pattern material library, and simple fonts from the font style library are matched. Next, the matched design elements are combined with the portable bottle packaging structure corresponding to the product characteristics, incorporating trendy traditional Chinese style patterns to form a complete packaging design scheme. Simultaneously, the overall matching degree of the design elements is calculated using the formula: This ensures that the design elements are compatible with multi-dimensional requirements, and then the generated packaging design scheme is transmitted to the screening module.

[0046] After receiving the design proposals, the screening module conducts an evaluation and screening process based on preset indicators. These preset indicators include the degree of alignment with brand image, the degree of adaptation to market trends, the degree of matching with regional consumption preferences, and the degree of satisfaction with user characteristics.

[0047] During the evaluation, the materials and style of each design proposal are first compared with the brand's core tone of understated luxury and simplicity to verify whether they align with the brand's overall image positioning. Next, it is determined whether the proposal conforms to current market trends in skincare packaging styles. Then, it is checked whether the proposal matches the material, color, and font preferences of consumers in the target climate region. Finally, it is confirmed whether the proposal meets the personalized needs of the target skin type group, such as the need for a moisturizing feel for dry skin and the need for a refreshing feel for oily skin. Proposals that fail to meet any of these criteria are eliminated, and only those that meet all criteria are retained, forming a set of qualified proposals, which are then output through the proposal output platform.

[0048] In summary, this embodiment, through the complete application of a personalized packaging design intelligent generation and screening system, achieves precise alignment between skincare packaging design and real-time beauty market trends, solving the problem of traditional design being out of touch with trends. By integrating consumer preference data from different climate regions, the packaging design schemes are precisely adapted to the material and color requirements of each region, significantly improving regional adaptability. Furthermore, by leveraging user profile analysis to deeply understand the characteristics of different skin types, the design schemes are made more targeted, effectively meeting the personalized needs of consumers with dry and oily skin.

[0049] The above description is merely a preferred embodiment of the present invention and is not intended to limit the present invention in any way. Although the present invention has been disclosed above with reference to preferred embodiments, it is not intended to limit the present invention. Any person skilled in the art can make some modifications or alterations to the above-disclosed technical content to create equivalent embodiments without departing from the scope of the present invention. Any simple modifications, equivalent changes and alterations made to the above embodiments based on the technical essence of the present invention without departing from the scope of the present invention shall still fall within the scope of the present invention.

Claims

1. An intelligent generation and screening system for personalized packaging design solutions, characterized by, The system comprises a data collection module, a data processing module, a user portrait analysis module, a design generation module and a screening module. The data collection module is used for collecting original data through multiple channels, and the original data includes product basic data, real-time market data and regional consumption preference data. The data processing module is connected with the data collection module, and is used for cleaning, classifying and structuring the original data, establishing a standardized data warehouse, and transmitting the standardized data to the design generation module. The user portrait analysis module is used for collecting consumer information, extracting features and labeling the information, constructing a user portrait database, and transmitting user portrait features to the design generation module. The design generation module is connected with the data processing module and the user portrait analysis module, calls a preset design element library, generates a packaging design scheme based on standardized data and user portrait features, and transmits the scheme to the screening module. The screening module is connected with the design generation module, and is used for evaluating and screening the design scheme based on preset indicators, and outputting qualified schemes.

2. The personalized packaging design proposal intelligent generation and screening system according to claim 1, characterized in that, The data collection module collects product basic data by connecting with the brand product management system to obtain product type, functional characteristics, brand core tone and packaging size limit, collects real-time market data by calling social media open interface, e-commerce platform comment grabbing tool and competitive product monitoring system to obtain social media hot topic associated design elements, competitive product packaging consumer evaluation and market popular packaging style trend, collects regional consumer preference data by integrating regional market research reports, local consumer behavior analysis data and regional e-commerce sales data to obtain different regional consumers' preference for packaging color, pattern style and font type. The data collection module evaluates the reliability of data from various channels. The evaluation formula is: wherein, is the data reliability score, is the data source reliability base score, is the data integrity coefficient, is the data timeliness coefficient, , , is the weight coefficient.

3. The personalized packaging design proposal intelligent generation and screening system according to claim 1, characterized in that, The data processing module includes the following steps when processing data: The collected original data is screened to eliminate duplicate data, error data and invalid data irrelevant to packaging design, filter topic data in social media not involving packaging design, and correct regional consumption preference results with statistical bias in market research reports. The filtered effective data is classified into product basic data, real-time market data and regional consumption preference data. The unstructured data after classification is converted into structured labels or parameters, and the structured data is stored in the standardized data warehouse to establish data index.

4. The personalized packaging design proposal intelligent generation and screening system according to claim 3, characterized in that, When the data processing module converts unstructured data, the text evaluation of consumers on competitor packaging is converted into style-related and color-related labels, the market popular packaging image data is extracted into color value, pattern element contour parameter and font style parameter, and the descriptive data in regional consumption preference is converted into color preference parameter, pattern style label and font type parameter corresponding to the region.

5. The personalized packaging design solution intelligent generation and screening system according to claim 1, characterized in that, The user portrait analysis module includes the following steps when collecting and processing consumer information: The brand member system is used to obtain consumer age interval and consumption ability data, online questionnaire research tools are used to obtain consumer aesthetic preference feedback, and consumer purchase habits are obtained through consumer behavior tracking data. The obtained information is feature-extracted, and youth group and elderly group features are classified according to age, and cost-effective and personalized experience features are labeled according to consumption habits. The extracted features are associated with consumer identification to form consumer exclusive feature labels, and the integrated user portrait database is constructed. The user portrait analysis module calculates the consumer feature label weight, and the calculation method is: wherein, is the feature label weight, is the label itself importance score, is the association frequency score of the consumer behavior and the label, is the balance coefficient.

6. The personalized packaging design proposal intelligent generation and screening system according to claim 5, characterized in that, When the user portrait analysis module constructs the user portrait database, a classified storage directory is established according to the feature label type, the age-related label, the consumption habit-related label and the aesthetic preference-related label are respectively stored in the corresponding directory, and a label retrieval mechanism is established; when a specific group of user portraits needs to be called, the target group feature label is input, and the age, consumption habit and aesthetic preference associated information of the group are extracted through the retrieval mechanism.

7. The personalized packaging design solution intelligent generation and screening system according to claim 1, characterized in that, The design generation module generates the packaging design scheme, including the following steps: A preset design element library is called, which includes a color template library, a pattern material library, a font style library and a packaging structure type library; The standardized data transmitted by the data processing module is associated with the user portrait features, and the design elements of the corresponding category are matched; when the user portrait is an old group and the corresponding regional preference is soft color, the light color template in the color template library and the large size font in the font style library are matched; The matched design elements are combined with the packaging structure corresponding to the product characteristics, and market trend related pattern elements are integrated to form a complete packaging design scheme; The design generation module calculates the design element matching degree, and the formula is: wherein, is the design element comprehensive matching degree, is the element and product basic data matching score, is the element and user portrait feature matching score, is the element and market trend matching score, , , is the weight coefficient.

8. The personalized packaging design solution intelligent generation and screening system according to claim 7, characterized in that, The color template library called by the design generation module covers gradient color templates and pure color templates of different color tones, the pattern material library includes geometric patterns, figurative patterns and cultural element patterns, the font style library includes editable fonts of different font sizes and font types, and the packaging structure type library includes common packaging structure parameterized models of box type, bag type, jar type and bottle type, and each sub-library supports updating element content according to new design requirements.

9. The personalized packaging design solution intelligent generation and screening system according to claim 1, characterized in that, The preset indicators of the screening module include the degree of fit with the brand tone, the degree of adaptation to market trends, the degree of matching with regional consumption preferences and the degree of meeting user features; during evaluation and screening, the color and style of each design scheme are compared with the core tone of the brand, then it is judged whether the scheme conforms to the market popular style, then it is checked whether the scheme matches the target regional preference, and finally it is confirmed whether the scheme meets the needs of the target user group; any scheme that does not meet any indicator is rejected, and the scheme that meets all indicators is retained to form a qualified scheme set.

Images