Exclusive poster generation method and device, equipment and medium

Abstract

The invention belongs to the field of big data, and relates to an exclusive poster generation method, which comprises the following steps of: displaying a poster preview two-dimensional code, and triggering to obtain user information of a target user at a plurality of application ends when a scanning operation aiming at the two-dimensional code is detected; performing preference analysis on the user information to obtain preference data; based on the preference data, determining to-be-recommended content and a plurality of corresponding poster elements; obtaining poster style reference information, and generating poster dynamic elements based on the to-be-recommended content and the preference data; and based on the preference data, obtaining a target poster template from a poster template library, and generating an exclusive poster of the target user in combination with a plurality of poster elements, poster style reference information and poster dynamic elements. The invention further provides a device, equipment and a medium. In addition, the invention also relates to a block chain technology, and the user information can be stored in a block chain. The method can be applied to the business fields of financial insurance, medical health, old-age care and the like, and personalized exclusive posters can be customized for different users.

Description

Technical Field

[0001] This application relates to the field of big data technology, and particularly to a method, device, equipment and medium for generating exclusive posters. Background Art

[0002] In the field of poster generation technology, there are already various poster generation tools on the market. These tools generally support users to upload background images and freely add various components to make personalized posters, and at the same time provide a rich template library for users to choose from, greatly improving the convenience of poster production. In addition, some tools can also automatically generate posters according to the user's text input, further simplifying the production process.

[0003] However, in the field of finance and insurance, although these existing systems or tools provide diverse customization methods when configuring posters, they still have limitations in the final stage of poster generation. Specifically, the content of the posters generated by these tools is often fixed, lacking the ability to promote differently for different customers. The products and services in the finance and insurance industry are highly personalized and customized, and the needs of different customers vary in aspects such as risk protection, investment and finance, and types of insurance. Therefore, as an important carrier for publicity, posters should be able to accurately reach the target users and highlight the differential advantages of products. But the actual situation is that regardless of the type of customer, the posters generated by the system may tend to be homogenized in content and style, which is difficult to effectively attract the attention of target customers and cannot fully display the unique charm of financial insurance products.

[0004] In summary, the core technical problem of existing poster generation tools is that the content of the generated posters is fixed and cannot be personalized according to the needs of different customers. This limits the publicity effect of posters and also affects the user experience. Summary of the Invention

[0005] The purpose of the embodiments of this application is to propose a method, device, equipment and medium for generating exclusive posters to solve the problem that the content of the posters generated by existing poster generation tools is fixed and cannot be personalized according to the needs of different customers.

[0006] In the first aspect, a method for generating exclusive posters is provided, which adopts the following technical solutions:

[0007] Display a QR code for poster preview. When a scanning operation for the QR code for poster preview is detected, trigger the acquisition of user information of the target user on multiple application terminals; use a machine learning algorithm to perform a preference analysis on the user information to obtain the preference data of the target user; based on the preference data, determine the content to be recommended for the target user and multiple poster elements corresponding to the content to be recommended; obtain poster style reference information from the network, and generate dynamic poster elements for the target user based on the content to be recommended and the preference data; based on the preference data, obtain a target poster template from a preset poster template library, and combine the content to be recommended, the poster style reference information, and the dynamic poster elements to generate a personalized poster for the target user.

[0008] In a second aspect, a personalized poster generation device is provided, which adopts the following technical solution:

[0009] A display module, configured to display a QR code for poster preview. When a scanning operation for the QR code for poster preview is detected, trigger the acquisition of user information of the target user on multiple application terminals;

[0010] An analysis module, configured to use a machine learning algorithm to perform a preference analysis on the user information to obtain the preference data of the target user;

[0011] A determination module, configured to determine the content to be recommended for the target user and multiple poster elements corresponding to the content to be recommended based on the preference data;

[0012] An acquisition module, configured to obtain poster style reference information from the network, and generate dynamic poster elements for the target user based on the content to be recommended and the preference data;

[0013] A combination module, configured to obtain a target poster template from a preset poster template library based on the preference data, and combine the content to be recommended, the poster style reference information, and the dynamic poster elements to generate a personalized poster for the target user.

[0014] In a third aspect, a computer device is provided, including a memory and a processor. A computer-readable instruction is stored in the memory, and when the processor executes the computer-readable instruction, the steps of the above-mentioned personalized poster generation method are implemented.

[0015] In a fourth aspect, a computer-readable storage medium is provided. The computer-readable storage medium stores a computer-readable instruction, and the computer-readable instruction can be executed by at least one processor so that at least one processor executes the steps of the above-mentioned personalized poster generation method.

[0016] In the solution implemented by the above-mentioned exclusive poster generation method, device, equipment and medium, a new way of interacting with target users is achieved by introducing a poster preview QR code. When a user scans this QR code, the system can intelligently obtain the user's personal information on multiple application terminals, which provides a data basis for subsequent personalized poster generation. By using advanced machine learning algorithms, it deeply analyzes user preferences, accurately grasps their interests, and thus determines the content to be recommended and the corresponding poster elements. Further, it obtains real-time poster style reference information from the network, combines user preferences and the content to be recommended, and dynamically generates dynamic poster elements to make the poster content more vivid and closer to the user's preferences. At the same time, based on the preference data, it carefully selects the poster template that best matches the target user from a rich preset template library, and then integrates multiple poster elements, style reference information and dynamic elements to finally generate a personalized poster exclusive to the target user. This innovative solution not only breaks the limitation of the fixed content of traditional posters, but also significantly improves the differential publicity ability of posters, enabling posters to more effectively attract target customers, thereby optimizing the user experience and enhancing the publicity effect. BRIEF DESCRIPTION OF THE DRAWINGS

[0017] In order to more clearly illustrate the solutions in this application, the following will briefly introduce the drawings required for the description of the embodiments of this application. Obviously, the following drawings are some embodiments of this application. For those of ordinary skill in the art, without creative efforts, other drawings can also be obtained based on these drawings.

[0018] Figure 1 is an exemplary system architecture diagram to which this application can be applied;

[0019] Figure 2 is a schematic flowchart of a method for generating an exclusive poster provided by this application;

[0020] Figure 3 is a schematic structural diagram of a device for generating an exclusive poster provided by this application;

[0021] Figure 4 is a schematic structural diagram of a computer device provided by this application. DETAILED DESCRIPTION OF THE EMBODIMENTS

[0022] Unless otherwise defined, all technical and scientific terms used herein have the same meaning as commonly understood by one of ordinary skill in the technical field to which this application belongs; the terms used in the specification of this application are only for the purpose of describing specific embodiments and are not intended to limit this application; the terms "including" and "having" and any variations thereof in the specification and claims of this application and the above drawings are intended to cover non-exclusive inclusion. The terms "first", "second", etc. in the specification and claims of this application or the above drawings are used to distinguish different objects and not to describe a specific order.

[0023] References herein to "embodiments" mean that a particular feature, structure, or characteristic described in connection with the embodiments can be included in at least one embodiment of the application. The phrase appears in various places in the specification and does not necessarily refer to the same embodiment, nor is it an independent or alternative embodiment mutually exclusive of other embodiments. Those skilled in the art will explicitly and implicitly understand that the embodiments described herein can be combined with other embodiments.

[0024] To enable those skilled in the technical field to better understand the solutions of this application, the technical solutions in the embodiments of this application will be clearly and completely described below with reference to the accompanying drawings.

[0025] As Figure 1 shown, the system architecture 100 may include a terminal device 101, a network 102, and a server 103. The terminal device 101 may be a laptop computer 1011, a tablet computer 1012, or a mobile phone 1013. The network 102 is used to provide a medium for a communication link between the terminal device 101 and the server 103. The network 102 may include various connection types, such as wired, wireless communication links, or fiber optic cables, etc.

[0026] The user may use the terminal device 101 to interact with the server 103 through the network 102 to receive or send messages, etc. Various communication client applications may be installed on the terminal device 101, such as a web browser application, a shopping application, a search application, an instant messaging tool, an email client, a social platform software, etc.

[0027] The terminal device 101 can be various electronic devices with a display screen and supporting web browsing. In addition to the laptop 1011, the tablet computer 1012, or the mobile phone 1013, the terminal device 101 can also be an e-book reader, an MP3 player (Moving Picture Experts Group Audio Layer III), an MP4 (Moving Picture Experts Group Audio Layer IV) player, a laptop computer, a desktop computer, and the like.

[0028] The server 103 can be a server that provides various services, such as a background server that supports the pages displayed on the terminal device 101.

[0029] It should be noted that the exclusive poster generation method provided by the embodiments of the present application is generally executed by the server. Correspondingly, the exclusive poster generation device is generally set in the server.

[0030] It should be understood that Figure 1 the numbers of the terminal devices, the network, and the server in

[0031] are merely illustrative. According to the implementation requirements, there can be any number of terminal devices, networks, and servers. Figure 2 Continuing to refer to

[0032] , a flowchart of an embodiment of the exclusive poster generation method according to the present application is shown. The exclusive poster generation method includes the following steps:

[0033] Step S201 displays a poster preview QR code. When a scanning operation on the poster preview QR code is detected, it triggers the acquisition of the user information of the target user on multiple application terminals.

[0034] Among them, the poster preview QR code is a QR code image used to display the preview content of the poster. It is embedded in the poster generation process. Users can view the preview effect of the poster on a mobile device or a specific application by scanning this QR code. This QR code comes from the poster generation system and represents the preview link or information of the poster.

[0035] Among them, the target users are from the user database of the system or users accessing in real time, representing the objects whose personalized needs the system needs to meet, and are used to customize and push poster content that conforms to their interests. For example, fashion brand posters for young consumers.

[0036] Among them, multiple application terminals refer to application programs running on different platforms or devices, which can be social media, e-commerce platforms, browser extensions, etc. These application terminals, as the sources of user information, are used to collect and analyze the behavior data of users in different scenarios. In poster generation, the data of multiple application terminals are integrated to understand the target users more comprehensively. For example, combining the interactions of users on social media and purchase records on shopping platforms.

[0037] Among them, user information refers to various data about the target users, including basic information (such as name, age, gender), behavior data (such as browsing records, purchase history), social data (such as friend relationships, follow lists), etc. This information comes from the activities of users on multiple application terminals, representing the personal characteristics and preferences of users, and is used for the recommendation and generation of personalized poster content.

[0038] Step S202: Adopt a machine learning algorithm to conduct a preference analysis on the user information to obtain the preference data of the target user.

[0039] Among them, the machine learning algorithm is used to conduct a preference analysis on the user information to identify the potential needs and interest points of users. For example, using a clustering algorithm to divide users into different groups in order to generate customized poster content for each group.

[0040] Among them, preference analysis refers to the process of identifying user preferences and interest points through data analysis methods. It uses machine learning algorithms to mine user information to understand the preferences, purchase habits, areas of concern, etc. of the target users. The results of the preference analysis (i.e., preference data) are used to guide the generation of personalized poster content. For example, recommending relevant endowment insurance product posters for users who are concerned about endowment insurance according to the results of user preference analysis.

[0041] Among them, preference data refers to the data set about the preferences of the target user obtained through preference analysis, which includes the interest points, purchase tendencies, areas of concern, etc. of the target user. These data come from user information, representing the personalized needs of users, and are used for content recommendation and element selection in the poster generation process.

[0042] Step S203: Based on the preference data, determine the content to be recommended for the target user and multiple poster elements corresponding to the content to be recommended.

[0043] Among them, the content to be recommended refers to the content that may attract the attention of the target user determined based on the preference data of the target user, which can be products, services, event information, etc. The content to be recommended can be sourced from the internal database of the system or the external network and is used to display to the target user in a personalized poster to stimulate their interest and purchase desire. For example, a health insurance poster with a comprehensive protection plan is recommended to users who are interested in health insurance.

[0044] Among them, multiple poster elements refer to various visual elements that make up the poster, such as text, pictures, icons, colors, etc. These elements are selected and combined based on the content to be recommended and the preference data of the user to generate a personalized poster. For example, for users who like a minimalist style, the system may choose simple text and color combinations.

[0045] Step S204: Obtain poster style reference information from the network and generate dynamic elements of the poster for the target user based on the content to be recommended and the preference data.

[0046] Among them, the poster style reference information refers to the poster style data and analysis results obtained from the network, which are used to guide the poster generation system to generate a poster style that conforms to the current popular trends and aesthetic preferences for the user. This information includes color combinations, layout methods, font selections, etc. For example, by analyzing the current popular poster design trends, the system can generate a fashionable poster for the user.

[0047] Among them, the poster dynamic elements refer to the elements that can be dynamically replaced, such as insurance product names, coverage ranges, rates, promotional activities, font colors, slogans, promotional selling points, etc. These elements are selected and adjusted based on the preference data of the user and the content to be recommended to generate more personalized poster content. The dynamic elements enable the poster to present different visual effects at different times or for different users.

[0048] Step S205: Obtain the target poster template from the preset poster template library based on the preference data, and combine multiple poster elements, poster style reference information, and poster dynamic elements to generate a personalized poster for the target user.

[0049] Among them, the poster template library refers to a database that stores multiple preset poster templates. These templates include different layouts, color combinations, and element combination methods, which are used to provide users with diverse poster options.

[0050] Among them, the target poster template refers to the poster template that is screened out from the poster template library according to the preference data and needs of the target user and is the most suitable for the user. This template will be used to generate a personalized poster for the user.

[0051] Among them, the exclusive poster refers to a personalized poster generated for a user based on information such as the user's preference data, multiple poster elements corresponding to the content to be recommended, poster style reference information, and poster dynamic elements. This poster not only conforms to the user's aesthetic preferences and needs but also can effectively convey the information of the content to be recommended. For example, a promotional poster customized for a user that includes their favorite colors, current popular styles, and products.

[0052] In the embodiments of the present application, a new way of interacting with the target user is achieved by introducing a poster preview QR code. When the user scans this QR code, the system can intelligently obtain the user's personal information on multiple application terminals, which provides a data basis for subsequent personalized poster generation. Using advanced machine learning algorithms, deeply analyze the user's preferences, accurately grasp their interest points, and thus determine the content to be recommended and the corresponding poster elements. Further, obtain the poster style reference information from the network in real time, combine the user's preferences and the content to be recommended, and dynamically generate poster dynamic elements to make the poster content more vivid and closer to the user's preferences. At the same time, based on the preference data, carefully select the poster template that best matches the target user from a rich preset template library, and then integrate multiple poster elements, style reference information, and dynamic elements to finally generate a personalized poster exclusive to the target user. This innovative solution not only breaks the limitation of the fixed content of traditional posters but also significantly improves the differential publicity ability of posters, enabling posters to more effectively attract target customers, thereby optimizing the user experience and enhancing the publicity effect.

[0053] In some alternative implementation manners of this embodiment, in step S203, based on the preference data, determining the content to be recommended for the target user and multiple poster elements corresponding to the content to be recommended specifically includes the following steps:

[0054] Based on the preference data, construct a target user portrait of the target user; obtain a target historical user portrait that matches the target user portrait from a preset portrait database; obtain the target historical recommended content corresponding to the target historical user portrait, and use the target historical recommended content as the content to be recommended for the target user; obtain the text elements and image elements of the content to be recommended, and based on the text elements and image elements, generate multiple poster elements for the target user.

[0055] Among them, the target user portrait refers to a model constructed according to the preference data and other relevant information of the target user to describe the user's characteristics and behavior patterns. This portrait includes the user's attribute characteristics (such as age, gender, occupation, etc.), behavior characteristics (such as purchase habits, browsing records, etc.), and social characteristics (such as social relationships, hobbies, etc.). For example, by analyzing the user's purchase records and social media data, a portrait can be constructed to describe the user's consumption habits and interest preferences.

[0056] Among them, the target historical user portrait refers to the historical user portraits that are similar to or have the same characteristics as the current target user portrait. These portraits are used to obtain historical user data similar to the target user from the preset portrait database, so as to recommend appropriate content for the current user. For example, by analyzing the purchase records and behavior patterns of historical users, historical user portraits similar to the current user can be found, and similar insurance products or services can be recommended for them.

[0057] Among them, the target historical recommended content refers to the content that is screened from the historical recommendation records according to the target historical user portrait and may meet the interests of the current target user. These contents are used as one of the contents to be recommended for the current user. For example, by analyzing the purchase records and behavior patterns of historical users, similar or relevant insurance products or services can be recommended for the target user as the content to be recommended.

[0058] Among them, the text element refers to the text content used to convey information in the content to be recommended, such as the title, slogan, product introduction, etc.

[0059] Among them, the image element refers to the picture or graphic content used to display the visual effect in the content to be recommended, such as product pictures, background pictures, icons, etc.

[0060] In one example, when a target user browses or consults a certain insurance product (such as health insurance, car insurance) on the APP of an insurance company, the system generates a QR code containing a preview of the insurance product poster. After the target user scans the QR code, the system obtains the user information of the target user on multiple application terminals such as the insurance company APP, payment platform, and social media through a secure API interface. This information includes but is not limited to the user's age, gender, occupation, family status, historical insurance purchase records, consumption habits, etc. The system uses machine learning algorithms (such as support vector machines, neural networks, etc.) to analyze these user information for preference analysis, and obtains the insurance preference data of the user, such as insurance type preference, premium payment ability, claim service requirements, etc. Based on these preference data, the system constructs the target user portrait of the target user, including key features such as insurance needs, preference types, and risk perception levels. Next, from the preset portrait database, the system uses a similarity calculation algorithm (such as cosine similarity) to find the target historical user portrait that matches the target user portrait. These historical user portraits have been verified and are associated with specific recommended content (i.e., successful insurance product recommendation plans). After successful matching, the system obtains the target historical recommended content corresponding to the target historical user portrait, such as specific types of insurance product packages, promotional activities, etc. These recommended contents are used as the content to be recommended for the target user. The system further extracts text elements (such as insurance product names, coverage, premium information, etc.) and image elements (such as insurance product icons, promotional pictures, etc.) from the content to be recommended. Based on these elements, the system uses graphic processing software or algorithms to generate multiple poster elements for the target user, such as attractive slogans, product highlight display pictures, etc.

[0061] In one example, when a target user uses an online medical service platform, the system generates a QR code containing a preview of health consultation or product purchase posters. After the target user scans it, the system obtains information such as the user's health data, medication records, and medical treatment habits on multiple application terminals such as the medical platform, health APP, and social media through a data interface. Machine learning algorithms (such as support vector machines, neural networks, etc.) are used to analyze these information to obtain the health preference data of the target user, such as disease types, medication preferences, health awareness, etc. Based on these data, the target user portrait of the user is constructed, including key features such as their health status, medical treatment needs, and health product preferences. Similar to the financial field, the system searches for the target historical user portrait that matches the target user portrait from the preset portrait database and obtains its corresponding recommended content, such as specific types of health products, medical consultation services, etc. Text elements (such as product efficacy, usage methods, doctor recommendations, etc.) and image elements (such as product pictures, doctor headshots, etc.) are extracted from the recommended content. Using image processing technology or algorithms, combined with the health preference data in the user portrait, multiple poster elements for the target user are generated, such as health promotion slogans, product usage scenario pictures, etc.

[0062] In the embodiments of the present application, a target user profile can be constructed through preference data, achieving accurate capture of users' personalized needs. This not only improves the pertinence of poster content but also provides a solid foundation for subsequent poster generation. Secondly, match the target historical user profile from the preset profile database and obtain the corresponding historical recommended content as the content to be recommended. This innovative approach makes full use of historical data, enabling the poster content to be intelligently recommended based on the experiences of similar users, greatly enhancing the attractiveness and relevance of the poster. Finally, by extracting the text elements and image elements of the content to be recommended and generating multiple poster elements accordingly, the diversification and personalization of the poster content are realized. This content-based dynamic generation method not only enriches the expression form of the poster but also enhances the differentiated publicity ability of the poster, enabling the poster to more effectively attract the attention of target customers and improve the publicity effect.

[0063] In some alternative implementation manners of this embodiment, the step of "constructing a target user profile of the target user based on preference data" specifically includes the following steps:

[0064] Preprocess the preference data to obtain the preprocessed preference data; extract features from the preprocessed preference data to obtain attribute feature information, behavioral feature information, and social feature information; based on the attribute feature information, behavioral feature information, and social feature information, use a pre-trained profile model to generate a target user profile of the target user.

[0065] Among them, preprocessing refers to operations such as cleaning, transforming, and formatting the user data of the target user to improve the quality and usability of the data. This process includes steps such as removing duplicate data, filling in missing values, and converting data types to ensure the accuracy and integrity of the data.

[0066] Among them, the attribute feature information refers to data describing the basic attributes of users, such as age, gender, occupation, region, etc. These data are used to construct the basic part of the user profile and serve as the basis for subsequent analysis and recommendation.

[0067] Among them, the behavioral feature information refers to data describing the user's behavior patterns, such as browsing records, purchase records, click behaviors, etc. These data are used to analyze the user's preferences and needs and serve as the basis for recommended content.

[0068] Among them, the social feature information refers to data describing the user's social relationships and network behaviors, such as friend relationships, social dynamics, sharing behaviors, etc. These data are used to analyze the user's social preferences and influence and serve as the basis for personalized recommendation and social marketing.

[0069] The portrait model refers to an algorithm or model used to build and update user portraits. The model performs operations such as feature extraction and weight allocation based on user attribute feature information, behavioral feature information, and social feature information to generate user portraits.

[0070] In one example, the original preference data often has problems such as missing data, redundancy or inconsistent format. Therefore, the system first preprocesses the original preference data. The preprocessing steps include data cleaning, that is, removing invalid or redundant information, such as repeated transaction records or fields with too many missing values; data transformation, such as converting categorical data (such as occupational categories) into numerical data for subsequent processing; and data normalization to ensure that different features are comparable in numerical terms and avoid certain features from occupying too much weight in the model training process. The preprocessed preference data is more accurate and complete. The system then performs feature extraction on the preprocessed data. This process aims to extract key information that can reflect the user's personalized characteristics from massive data. The feature extraction results include attribute feature information (such as basic information such as age, gender, and occupation), behavioral feature information (such as consumption frequency, investment preferences, historical transaction amounts, insurance purchase frequency and type, etc.), and social feature information (such as social media activity, social circle type, and attention to financial insurance topics, etc.). These feature information comprehensively and deeply reflects the user's personal attributes, behavioral patterns, and social environment, providing rich data support for building accurate user portraits. Based on the extracted attribute feature information, behavior feature information and social feature information, the system uses a pre-trained portrait model to generate a target user portrait of the target user. The portrait model is trained and optimized based on a large amount of historical data, and can accurately capture the user's personalized needs and preferences, such as risk tolerance, insurance product type preference, investment period preference, etc.

[0071] The embodiment of the present application can effectively filter out noise information through the preprocessing of preference data, ensure data quality, and lay a solid foundation for subsequent analysis. Furthermore, the feature extraction link deeply explores the multi-dimensional features of the user's attributes, behaviors, and sociality. These feature information is comprehensive and detailed, and can accurately reflect the user's personalized needs. On this basis, a pre-trained portrait model is used to generate user portraits. The model, with its powerful learning ability and generalization performance, can efficiently integrate and analyze the extracted feature information, and finally generate a user portrait that is highly consistent with the actual situation of the target user. This portrait not only accurately depicts the user's preference profile, but also provides a strong basis for subsequent poster content recommendations and style customization, significantly enhancing the personalization and attractiveness of the poster, thereby effectively improving the poster's publicity effect and user experience.

[0072] In some alternative implementation manners of this embodiment, step S204, obtaining poster style reference information from the network, specifically includes the following steps:

[0073] Obtain poster data from the network; based on preset poster style rules, parse and extract the poster data to obtain poster style data; use big data tools to perform style trend analysis on the poster style data to obtain poster style reference information.

[0074] Among them, poster data refers to the original data set collected from the network, database or other sources, which contains information such as poster design elements, layout, color matching, text content, etc. These data are from existing poster samples in the market and are used for subsequent analysis and processing. It represents the diversity and design trends of posters and is used to generate attractive new posters. For example, the poster pictures downloaded from a design website and their related information constitute poster data.

[0075] Among them, poster style rules refer to the set of rules that define the poster design style and the combination method of elements. These rules are based on design aesthetics, market trends and user preferences and are used to guide how to extract and parse elements that meet specific style requirements from poster data.

[0076] Among them, parsing and extraction refer to the process of carefully analyzing the collected poster data and separating useful design elements and style features from it. This includes identifying key elements such as colors, fonts, images, layouts, etc. in the poster, as well as their combination methods and proportional relationships. This process is used to extract useful information for generating new posters from complex poster data. For example, parse the main color and secondary color from an insurance poster with multiple color combinations.

[0077] Among them, poster style data is the specific information about the poster design style obtained after parsing and extraction. It includes the quantitative descriptions of key features such as the colors used in the poster, font styles, image styles, layout modes, etc. These data represent the visual style features of the poster and are used to guide the design of new posters. For example, the style data may include the RGB values of the main color, the type and size of the font, etc.

[0078] Among them, big data tools refer to software or platforms used to process and analyze large-scale data sets. In the field of poster generation, big data tools are used to analyze poster data, market trends and user preferences to extract useful information and insights. These tools support efficient data storage, processing and analysis functions, and help generate more personalized and market-demand-compliant posters.

[0079] Among them, style trend analysis refers to using big data tools to analyze the collected poster data to identify current and future design trends. This includes analyzing the popularity of elements such as colors, fonts, layouts, etc., and their changing trends over different time periods. Style trend analysis is used to guide the design of new posters to ensure that they conform to market trends and user preferences. For example, by analysis, the popular color combinations and layout patterns in the current market are discovered.

[0080] In one example, web crawling technology can be used to collect poster data from various online channels such as major design websites and social media platforms. This data includes poster image files, design descriptions, user comments, etc. To ensure the diversity and comprehensiveness of the data, the web crawler program is set to run regularly to capture the latest poster design trends. The collected poster data is first preprocessed, including steps such as deduplication and format conversion. Then, according to the preset poster style rules (such as color combinations, layout structures, font selections, etc.), image recognition and analysis are performed on the poster images to extract key style features. At the same time, combined with the text information in the design descriptions and user comments, the poster style data is further enriched. The extracted poster style data is imported into big data analysis tools for style trend analysis. This process includes multiple steps such as data cleaning, feature extraction, clustering analysis, and association rule mining. With the support of big data technology, the currently popular poster styles can be identified, future trends can be predicted, and style options that match the preferences of target users can be recommended.

[0081] The embodiments of the present application can widely collect poster data from the network, and thus can obtain diverse and rich poster design materials. Based on the preset poster style rules, in-depth analysis and refined extraction of this data can effectively extract the core style features of various posters, such as color combinations, layout compositions, etc. Further, using big data tools to perform trend analysis on these style data can insight into the current and future poster design trends and accurately capture the key nodes of style evolution. This process not only enhances the flexibility and innovation of poster generation, but also provides a strong style reference for subsequent generation of personalized posters in combination with user preferences.

[0082] In some optional implementation manners of this embodiment, step S204, generating the poster dynamic elements of the target user based on the content to be recommended and the preference data, specifically includes the following steps:

[0083] Based on the preset weight strategy and preference data, determine the first weights of multiple user feature dimensions of the target user; based on the content to be recommended and the preference data, use the preset deep learning model to generate the initial poster dynamic elements of the target user; based on the first weights, optimize the initial poster dynamic elements to obtain the poster dynamic elements of the target user.

[0084] Among them, the weight strategy refers to the weight allocation method adopted when determining the influence degree of user feature dimensions on poster generation. Based on factors such as user preferences, behavioral characteristics, and social attributes, it assigns a relatively important weight value to each feature dimension. These weight values are used to adjust the influence of different feature dimensions when generating posters to ensure that the posters better meet the personalized needs of users. For example, for the young user group, more attention may be paid to the weights of color matching and image style.

[0085] Among them, multiple user feature dimensions refer to multiple aspects used to describe user preferences and behavioral characteristics. These dimensions can include the user's age, gender, occupation, hobbies, consumption habits, etc. In the field of poster generation, by analyzing these feature dimensions, the needs and preferences of users can be understood more accurately, so as to generate more personalized posters. For example, age and gender are important factors affecting the poster design style.

[0086] Among them, the first weight refers to the weight value calculated according to the preset weight strategy and user preference data, which is used to adjust the influence of different user feature dimensions when generating posters. These weight values reflect the importance degree of user feature dimensions on poster generation and are used to ensure that the posters better meet the personalized needs of users.

[0087] Among them, the deep learning model is a machine learning algorithm based on the neural network structure, which is used to process and analyze complex data sets. In the field of poster generation, the deep learning model can be used to learn the relationship between user preferences, poster styles, and design elements to generate personalized posters that meet user needs.

[0088] Among them, the initial poster dynamic elements refer to the set of dynamically replaceable elements initially determined based on user preferences and the content to be recommended before generating the exclusive poster for the target user. These elements may include vehicle model pictures, colors, slogans, promotional selling points, etc., which are used for optimization and adjustment according to user feature dimensions and weights in subsequent steps.

[0089] In one example, a QR code for poster preview is displayed. When the target user scans the QR code through their device, the system immediately triggers the data acquisition module to collect the target user's information from multiple application platforms (such as social media, shopping platforms, etc.). This information can include, but is not limited to, the user's browsing history, purchase records, like and comment behaviors, etc. Next, machine learning algorithms (such as random forest, support vector machine, etc.) are used to perform preference analysis on the collected user information. Through analysis, the system can identify the target user's preference degree for different types of content and form preference data. After obtaining the preference data, the system enters the stage of generating poster elements. First, based on the preset weight strategy and preference data, the first weight of the target user in multiple user feature dimensions (such as age, gender, interest preference, etc.) is determined. Subsequently, the system uses a preset deep learning model (such as convolutional neural network CNN or generative adversarial network GAN) to generate initial poster dynamic elements. These elements may include dynamic backgrounds, flashing texts or icons, etc., aiming to attract the target user's attention. During the generation process, the model will fully consider the content to be recommended and the preference data to ensure that the generated elements match the target user's interest points. Finally, based on the previously determined first weight, the initial poster dynamic elements are optimized. The optimization process can involve adjusting the color, size, position, animation effect, etc. of the elements to ensure that the final poster dynamic elements not only meet the target user's preferences but also have strong visual appeal.

[0090] In the embodiment of the present application, by combining the weight strategy and preference data, the first weight is innovatively assigned to multiple user feature dimensions of the target user, ensuring that the personalized needs of the target user can be accurately considered during the subsequent poster generation process. Based on these weights and the content to be recommended, a deep learning model is used to generate initial poster dynamic elements, which not only improves the personalization degree of the poster but also ensures the relevance of the content. Further, the initial poster dynamic elements are optimized using the first weight, making the poster dynamic elements more in line with the target user's preferences. This optimization strategy not only enhances the visual appeal of the poster but also ensures the close matching of the poster content with the target user's characteristics.

[0091] In some alternative implementation manners of this embodiment, step S204, generating the poster dynamic elements of the target user based on the content to be recommended and the preference data, specifically includes the following steps:

[0092] Display a user dimension configuration interface, where the user dimension configuration interface includes multiple dimension weight selection controls; when a trigger operation for the multiple dimension weight selection controls is detected, obtain the second weights of multiple user feature dimensions of the target user; based on the content to be recommended and preference data, use a preset deep learning model to generate initial poster dynamic elements for the target user; optimize the initial poster dynamic elements based on the second weights to obtain the poster dynamic elements of the target user.

[0093] Among them, the user dimension configuration interface refers to an interactive interface that allows customization and configuration of the weights of its feature dimensions. This interface provides multiple dimension weight selection controls, and the weight values of different feature dimensions can be adjusted by dragging sliders, selecting options, etc. The user dimension configuration interface is used to ensure that the poster generation process is more in line with the personalized needs of users and provides an intuitive and easy-to-use configuration method.

[0094] Among them, the multiple dimension weight selection controls refer to a set of controls in the user dimension configuration interface for selecting and adjusting the weights of different feature dimensions. These controls may include sliders, dropdown menus, checkboxes, etc., allowing manual configuration of the weight values. The multiple dimension weight selection controls provide a flexible configuration method, ensuring a high degree of personalization and customization in the poster generation process.

[0095] Among them, the second weight refers to the weight value of the feature dimension custom-configured by the user through the user dimension configuration interface. It is used to adjust the influence of different elements when generating the poster.

[0096] In one example, an interface containing a QR code for poster preview can be displayed. When the user scans the QR code with their device, the system triggers a series of operations to obtain the user information of the target user on multiple application platforms. This information includes, but is not limited to, the user's browsing history, purchase history, social media activities, etc., providing data support for subsequent user preference analysis. Next, the system enters the display phase of the user dimension configuration interface. This interface contains multiple dimension weight selection controls that allow poster designers to configure the weights for different user characteristic dimensions (such as age, gender, hobbies, etc.) based on the preference data of the target user. For example, if the target user is a young female user, by analyzing the preference data of this target user, it is determined that she values the fashion sense and color combination of the poster more. Therefore, the poster designer can assign higher weights to the two dimensions of "fashion elements" and "color preference". When the poster designer configures multiple dimension weight selection controls through trigger operations (such as clicking, dragging, etc.), the system will obtain and record these weight values in real time, that is, the second weights of multiple user characteristic dimensions of the target user. These weight values will serve as important reference bases in the subsequent poster generation process. After obtaining the second weights, the system begins to enter the generation phase of poster dynamic elements. First, based on the previously obtained user preference data and the content to be recommended, the system uses a preset deep learning model (such as Convolutional Neural Network CNN or Generative Adversarial Network GAN) to generate initial poster dynamic elements. These elements can include dynamic backgrounds, flashing text, rotating icons, etc., aiming to enhance the attractiveness and interactivity of the poster. Subsequently, the system will optimize the initial poster dynamic elements according to the second weights. The optimization process can involve adjusting the color, size, position, or animation effects of the elements to ensure that the final poster dynamic elements not only meet the preferences of the target user but also produce a strong visual impact.

[0097] The embodiments of this application can flexibly configure the target user characteristic dimensions by displaying the user dimension configuration interface and setting multiple dimension weight selection controls. When these controls are triggered, the system can accurately obtain the second weights on different characteristic dimensions, which provides personalized data support for the subsequent generation of poster dynamic elements. Based on the obtained second weights and the content to be recommended, using a preset deep learning model to generate initial poster dynamic elements not only ensures the close association between the elements and the content but also increases the interactivity of the poster. Further, by using the second weights to optimize the initial elements, the poster dynamic elements more conform to the personalized preferences of the target user, thus generating a stronger visual attraction.

[0098] In some alternative implementation manners of this embodiment, after obtaining a target poster template from a preset poster template library based on preference data, combining the content to be recommended, poster style reference information, and poster dynamic elements to generate a personalized poster for the target user in step S205, the following steps are further included specifically:

[0099] Obtain feedback data of the target user for the personalized poster; conduct in-depth analysis on the feedback data to generate poster optimization information, and optimize the personalized poster based on the poster optimization information.

[0100] Among them, the feedback data refers to the information about the poster effect and user satisfaction provided by the target user after using the personalized poster. Such data may include the click-through rate, comments, ratings, etc. of the target user, and are used to evaluate the attractiveness and publicity effect of the poster. For example, positive comments and high ratings provided by the user after using the poster.

[0101] Among them, the poster optimization information refers to the suggestions or guidance obtained through analysis of user feedback data and other relevant information for improving and optimizing the personalized poster. Such information may include suggestions for adjusting color combinations, optimizing layout patterns, updating promotional selling points, etc., aiming to enhance the attractiveness and publicity effect of the poster. For example, adjusting the slogan and image style in the poster according to user feedback to enhance attractiveness.

[0102] In an example, after generating a personalized poster for the target user according to a predefined process, the system can send the poster to the target user through multiple channels (such as social media, email, text message, etc.), and at the same time provide a convenient feedback mechanism to encourage the target user to evaluate the personalized poster and put forward improvement suggestions. Such feedback data includes the overall satisfaction rating of the target user for the personalized poster, the degree of preference for specific elements, and the specific improvement opinions put forward by the target user, etc. After collecting the feedback data of the target user, the system enters the in-depth analysis stage. This stage mainly uses machine learning algorithms to mine and process the feedback data to identify the general preferences and dissatisfaction of the target user with the personalized poster. For example, the system analyzes the evaluations of the target user on aspects such as the color, layout, and text content of the poster to extract the specific preferences of the target user for the poster style and content. Based on the results of the in-depth analysis, the system generates poster optimization information. Such information may include the poster elements that need to be adjusted, the color combinations recommended to be adopted, the layout improvement plan, etc. Subsequently, the system makes corresponding adjustments and optimizations to the personalized poster according to these optimization information. For example, if the system analyzes that the target user is not satisfied with the color combination of the personalized poster, it can automatically adjust the color scheme of the personalized poster to better conform to the user's aesthetic preferences.

[0103] Embodiments of the present application can continuously optimize the poster effect by collecting feedback data from target users for exclusive posters and deeply analyzing it. Specifically, it can accurately capture the preferences of target users for poster content, style preferences, and potential improvement suggestions. After being processed by machine learning algorithms, these feedback data are converted into specific poster optimization information. Based on this, the poster elements, layout, and color matching can be automatically adjusted to make the poster more in line with user preferences. This dynamic optimization mechanism not only improves the personalization of the poster but also significantly enhances its attractiveness and publicity effect. Through continuous iterative optimization, the exclusive poster can reach target users more effectively.

[0104] It should be emphasized that to further ensure the above-mentioned user information, preference data, and poster style reference information, the above-mentioned user information, preference data, and poster style reference information can also be stored in a node of a blockchain.

[0105] The blockchain referred to in the present application is a new application mode of computer technologies such as distributed data storage, peer-to-peer transmission, consensus mechanism, and encryption algorithms. Blockchain, in essence, is a decentralized database, a series of data blocks generated by using cryptographic methods. Each data block contains information about a batch of network transactions, used to verify the validity of the information (anti-counterfeiting) and generate the next block. The blockchain can include a blockchain underlying platform, a platform product service layer, and an application service layer, etc.

[0106] Those of ordinary skill in the art can understand that all or part of the processes in the methods of the above embodiments can be completed by instructing relevant hardware through computer-readable instructions. These computer-readable instructions can be stored in a computer-readable storage medium. When the program is executed, it can include the processes of the embodiments of the above methods. Among them, the aforementioned storage medium can be a non-volatile storage medium such as a magnetic disk, an optical disk, a read-only memory (ROM), etc., or a random access memory (RAM), etc.

[0107] It should be understood that although the steps in the flowchart of the accompanying drawings are shown in sequence according to the arrows, these steps are not necessarily executed in the order indicated by the arrows. Unless there is a clear indication in this article, the execution of these steps has no strict order limit, and they can be executed in other orders. Moreover, at least a part of the steps in the flowchart of the accompanying drawings can include multiple sub-steps or multiple stages. These sub-steps or stages are not necessarily executed at the same time, but can be executed at different times. Their execution order is not necessarily sequential, but can be executed alternately or in turn with at least a part of other steps or sub-steps or stages of other steps.

[0108] Further reference is made to Figure 3 , as an implementation of the method described above Figure 2 , this application provides an embodiment of an exclusive poster generation device, which corresponds to the method embodiment shown in Figure 2 , and this device can be specifically applied to various electronic devices.

[0109] As shown in Figure 3 , the exclusive poster generation device 400 of this embodiment includes: a display module 401, an analysis module 402, a determination module 403, an acquisition module 404, and a combination module 405.

[0110] Wherein:

[0111] The display module 401 is configured to display a preview QR code of the poster, and when a scanning operation on the preview QR code of the poster is detected, it triggers the acquisition of user information of the target user on multiple application terminals;

[0112] The analysis module 402 is configured to perform preference analysis on the user information by using a machine learning algorithm to obtain preference data of the target user;

[0113] The determination module 403 is configured to determine the content to be recommended for the target user and multiple poster elements corresponding to the content to be recommended based on the preference data;

[0114] The acquisition module 404 is configured to obtain poster style reference information from the network and generate dynamic poster elements of the target user based on the content to be recommended and the preference data;

[0115] The combination module 405 is configured to obtain a target poster template from a preset poster template library based on the preference data, and combine the content to be recommended, the poster style reference information, and the dynamic poster elements to generate an exclusive poster for the target user.

[0116] Embodiments of the present application can achieve a new way of interacting with target users by introducing a QR code for poster preview. When a user scans this QR code, the system can intelligently obtain the user's personal information on multiple application terminals, which provides a data basis for subsequent personalized poster generation. Using advanced machine learning algorithms, it deeply analyzes user preferences, accurately grasps their interests, and thus determines the content to be recommended and the corresponding poster elements. Further, it obtains real-time poster style reference information from the network, combines user preferences and the content to be recommended, and dynamically generates dynamic elements of the poster, making the poster content more vivid and closer to the user's preferences. At the same time, based on the preference data, it carefully selects the poster template that best matches the target user from a rich preset template library, and then integrates multiple poster elements, style reference information, and dynamic elements to finally generate a personalized poster exclusive to the target user. This innovative solution not only breaks the limitation of the fixed content of traditional posters, but also significantly improves the differentiated publicity ability of posters, enabling posters to more effectively attract target customers, thereby optimizing the user experience and enhancing the publicity effect.

[0117] In one embodiment, the determination module 403 includes:

[0118] A construction sub-module for constructing a target user portrait of the target user based on preference data;

[0119] A portrait acquisition sub-module for obtaining a target historical user portrait that matches the target user portrait from a preset portrait database;

[0120] A content acquisition sub-module for obtaining the target historical recommended content corresponding to the target historical user portrait and using the target historical recommended content as the content to be recommended for the target user;

[0121] A first generation sub-module for obtaining the text elements and image elements of the content to be recommended and generating multiple poster elements for the target user based on the text elements and image elements.

[0122] Embodiments of the present application can construct a target user portrait through preference data, achieving accurate capture of users' personalized needs. It not only improves the pertinence of poster content but also provides a solid foundation for subsequent poster generation. Secondly, it matches the target historical user portrait from a preset portrait database and obtains its corresponding historical recommended content as the content to be recommended. This innovative approach makes full use of historical data, enabling poster content to be intelligently recommended based on the experience of similar users, greatly improving the attractiveness and relevance of posters. Finally, by extracting the text elements and image elements of the content to be recommended and generating multiple poster elements accordingly, it realizes the diversification and personalization of poster content. This content-based dynamic generation method not only enriches the expression form of posters but also enhances the differentiated publicity ability of posters, enabling posters to more effectively attract the attention of target customers and improve the publicity effect.

[0123] In one embodiment, the construction sub-module is further configured to preprocess the preference data to obtain preprocessed preference data; extract features from the preprocessed preference data to obtain attribute feature information, behavioral feature information, and social feature information; and generate a target user profile of the target user based on the attribute feature information, behavioral feature information, and social feature information by using a pre-trained profiling model.

[0124] The embodiment of the present application can effectively filter out noise information through the preprocessing of preference data, ensure the data quality, and lay a solid foundation for subsequent analysis. Furthermore, the feature extraction link deeply mines multi-dimensional features such as the attributes, behaviors, and social aspects of users. These feature information are comprehensive and detailed, and can accurately reflect the personalized needs of users. On this basis, a pre-trained profiling model is used to generate a user profile. With its powerful learning ability and generalization performance, this model can efficiently integrate and analyze the extracted feature information, and finally generate a user profile that highly fits the actual situation of the target user. This profile not only accurately depicts the preference profile of the user, but also provides a strong basis for subsequent poster content recommendation and style customization, significantly enhancing the personalization degree and attractiveness of the poster, thereby effectively improving the publicity effect and user experience of the poster.

[0125] In one embodiment, the acquisition module 404 includes:

[0126] A data acquisition sub-module, configured to acquire poster data from the network;

[0127] A parsing sub-module, configured to parse and extract the poster data based on a preset poster style rule to obtain poster style data;

[0128] An analysis sub-module, configured to perform a style trend analysis on the poster style data by using a big data tool to obtain poster style reference information.

[0129] The embodiment of the present application can widely collect poster data from the network, and can obtain diverse and rich poster design materials. Based on a preset poster style rule, in-depth parsing and fine extraction of these data can effectively extract the core style features of various posters, such as color matching, layout composition, etc. Further, using a big data tool to perform a trend analysis on these style data can insight into the current and future poster design trends, and accurately capture the key nodes of style evolution. This process not only enhances the flexibility and innovation of poster generation, but also provides a strong style reference for subsequent generation of personalized posters in combination with user preferences.

[0130] In one embodiment, the acquisition module 404 includes:

[0131] A weight determination sub-module, configured to determine a first weight for multiple user feature dimensions of a target user based on a preset weight policy and preference data;

[0132] A second generation sub-module, configured to generate initial poster dynamic elements of a target user by using a preset deep learning model based on the content to be recommended and preference data;

[0133] A first optimization sub-module, configured to optimize the initial poster dynamic elements based on the first weight to obtain the poster dynamic elements of the target user.

[0134] In the embodiment of the present application, by combining the weight policy and preference data, a first weight is innovatively assigned to multiple user feature dimensions of the target user, ensuring that the personalized needs of the target user can be accurately considered in the subsequent poster generation process. Based on these weights and the content to be recommended, the initial poster dynamic elements are generated by using a deep learning model, which not only improves the personalization degree of the poster but also ensures the relevance of the content. Further, the initial poster dynamic elements are optimized by using the first weight, making the poster dynamic elements more in line with the preferences of the target user. This optimization strategy not only enhances the visual appeal of the poster but also ensures the close match between the poster content and the target user characteristics.

[0135] In one embodiment, the acquisition module 404 includes:

[0136] A display sub-module, configured to display a user dimension configuration interface, where the user dimension configuration interface includes multiple dimension weight selection controls;

[0137] A weight acquisition sub-module, configured to obtain a second weight for multiple user feature dimensions of the target user when detecting a trigger operation on the multiple dimension weight selection controls;

[0138] A third generation sub-module, configured to generate initial poster dynamic elements of the target user by using a preset deep learning model based on the content to be recommended and preference data;

[0139] A second optimization sub-module, configured to optimize the initial poster dynamic elements based on the second weight to obtain the poster dynamic elements of the target user.

[0140] Embodiments of the present application can flexibly configure the target user feature dimensions by displaying a user dimension configuration interface and setting multiple dimension weight selection controls. When these controls are triggered, the system can accurately obtain the second weights on different feature dimensions, which provides personalized data support for the generation of subsequent poster dynamic elements. Based on the obtained second weights and the content to be recommended, initial poster dynamic elements are generated using a preset deep learning model, which not only ensures the close association between the elements and the content but also increases the interactivity of the poster. Further, by using the second weights to optimize the initial elements, the poster dynamic elements are made more in line with the personalized preferences of the target users, thus generating a stronger visual attraction.

[0141] In one embodiment, the exclusive poster generation device 400 further includes:

[0142] A data acquisition module, configured to acquire feedback data of a target user for an exclusive poster;

[0143] A deep analysis module, configured to deeply analyze the feedback data to generate poster optimization information, and optimize the exclusive poster based on the poster optimization information.

[0144] Embodiments of the present application can continuously optimize the poster effect by collecting feedback data of a target user for an exclusive poster and deeply analyzing it. Specifically, it can accurately capture the target user's preferences for the poster content, style preferences, and potential improvement suggestions. After being processed by machine learning algorithms, these feedback data are converted into specific poster optimization information. Based on this, the poster elements, layout, and color matching can be automatically adjusted to make the poster more in line with the user's preferences. This dynamic optimization mechanism not only improves the personalization degree of the poster but also significantly enhances its attractiveness and publicity effect. Through continuous iterative optimization, the exclusive poster can reach the target users more effectively.

[0145] To solve the above technical problems, embodiments of the present application also provide a computer device. For details, please refer to Figure 4 , Figure 4 which is the basic structural block diagram of the computer device in this embodiment.

[0146] The computer device 6 includes a memory 61, a processor 62, and a network interface 63 that are communicatively connected to each other via a system bus. It should be noted that only the computer device 6 having a memory 61, a processor 62, and a network interface 63 is shown in the figure. However, it should be understood that it is not required to implement all the shown components, and more or fewer components can be implemented alternatively. Among them, those skilled in the art of the present technology can understand that the computer device here is a device that can automatically perform numerical calculations and / or information processing according to pre-set or stored instructions, and its hardware includes but is not limited to microprocessors, application specific integrated circuits (ASICs), field-programmable gate arrays (FPGAs), digital signal processors (DSPs), embedded devices, etc.

[0147] The computer device can be a computing device such as a desktop computer, a notebook, a palm computer, and a cloud server. The computer device can perform human-computer interaction with the user through a keyboard, a mouse, a remote control, a touchpad, a voice control device, etc.

[0148] The memory 61 includes at least one type of readable storage medium. The readable storage medium includes flash memory, a hard disk, a multimedia card, a card-type memory (such as an SD or DX memory, etc.), a random access memory (RAM), a static random access memory (SRAM), a read-only memory (ROM), an electrically erasable programmable read-only memory (EEPROM), a programmable read-only memory (PROM), a magnetic memory, a magnetic disk, an optical disk, etc. In some embodiments, the memory 61 can be an internal storage unit of the computer device 6, such as the hard disk or memory of the computer device 6. In other embodiments, the memory 61 can also be an external storage device of the computer device 6, such as a plug-in hard disk, a smart media card (SMC), a secure digital (SD) card, a flash card, etc. equipped on the computer device 6. Of course, the memory 61 can also include both the internal storage unit of the computer device 6 and its external storage device. In this embodiment, the memory 61 is generally used to store the operating system and various application software installed on the computer device 6, such as computer-readable instructions of the exclusive poster generation method. In addition, the memory 61 can also be used to temporarily store various data that have been output or will be output.

[0149] The processor 62 may be a central processing unit (CPU), a controller, a microcontroller, a microprocessor, or other data processing chips in some embodiments. The processor 62 is generally used to control the overall operation of the computer device 6. In this embodiment, the processor 62 is used to run the computer-readable instructions stored in the memory 61 or process data, such as running the computer-readable instructions of the exclusive poster generation method.

[0150] The network interface 63 may include a wireless network interface or a wired network interface, and this network interface 63 is generally used to establish a communication connection between the computer device 6 and other electronic devices.

[0151] In the embodiments of the present application, a new way of interacting with target users is realized by introducing a poster preview QR code. When the user scans this QR code, the system can intelligently obtain the user's personal information on multiple application terminals, which provides a data basis for subsequent personalized poster generation. Using advanced machine learning algorithms, deeply analyze user preferences, accurately grasp their interests, so as to determine the content to be recommended and the corresponding poster elements. Further, obtain the poster style reference information from the network in real time, combine user preferences and the content to be recommended, and dynamically generate poster dynamic elements to make the poster content more vivid and closer to the user's preferences. At the same time, based on the preference data, carefully select the poster template that best matches the target user from a rich preset template library, and then integrate multiple poster elements, style reference information and dynamic elements to finally generate a personalized poster exclusive to the target user. This innovative solution not only breaks the limitation of the fixed content of traditional posters, but also significantly improves the differential publicity ability of posters, enabling posters to more effectively attract target customers, thereby optimizing the user experience and enhancing the publicity effect.

[0152] The present application also provides another implementation manner, that is, to provide a computer-readable storage medium storing computer-readable instructions that can be executed by at least one processor, so that at least one processor executes the steps of the exclusive poster generation method as described above.

[0153] Embodiments of the present application can achieve a new way of interacting with target users by introducing a QR code for poster preview. When a user scans this QR code, the system can intelligently obtain the user's personal information on multiple application terminals, which provides a data basis for subsequent personalized poster generation. By using advanced machine learning algorithms, it deeply analyzes user preferences, accurately grasps their interests, and thus determines the content to be recommended and the corresponding poster elements. Further, it obtains real-time poster style reference information from the network, combines user preferences and the content to be recommended, and dynamically generates dynamic elements of the poster, making the poster content more vivid and closer to the user's preferences. At the same time, based on the preference data, it carefully selects the poster template that best matches the target user from a rich preset template library, and then integrates multiple poster elements, style reference information, and dynamic elements to finally generate a personalized poster exclusive to the target user. This innovative solution not only breaks the limitation of the fixed content of traditional posters but also significantly improves the differential publicity ability of posters, enabling posters to more effectively attract target customers, thereby optimizing the user experience and enhancing the publicity effect.

[0154] From the description of the above embodiments, those skilled in the art can clearly understand that the methods of the above embodiments can be implemented by means of software plus a necessary general hardware platform. Of course, they can also be implemented by hardware, but in many cases, the former is a better implementation method. Based on such an understanding, the technical solution of the present application, in essence, or the part that contributes to the prior art can be embodied in the form of a software product. This computer software product is stored in a storage medium (such as ROM / RAM, magnetic disk, optical disk) and includes several instructions for causing a terminal device (which can be a mobile phone, computer, server, air conditioner, or network device, etc.) to execute the methods of the various embodiments of the present application.

[0155] Obviously, the above-described embodiments are only a part of the embodiments of the present application, rather than all the embodiments. The accompanying drawings show the preferred embodiments of the present application, but do not limit the patent scope of the present application. The present application can be implemented in many different forms. On the contrary, the purpose of providing these embodiments is to make the understanding of the disclosed content of the present application more thorough and comprehensive. Although the present application has been described in detail with reference to the foregoing embodiments, for those skilled in the art, they can still modify the technical solutions described in the foregoing specific embodiments or perform equivalent replacements for some of the technical features. Any equivalent structure directly or indirectly using the content of the specification and drawings of the present application in other related technical fields is similarly within the scope of the patent protection of the present application. The non-company enterprise software tools or components that appear in the embodiments of the present application are only for illustrative purposes and do not represent actual use.

Claims

1. A method for generating a unique poster, characterized in that: The steps include: Displaying a poster preview QR code, and when a scanning operation on the poster preview QR code is detected, triggering acquisition of user information of the target user on multiple application terminals; Using a machine learning algorithm to perform preference analysis on the user information to obtain preference data of the target user; Based on the preference data, determining the content to be recommended for the target user and a plurality of poster elements corresponding to the content to be recommended; Acquire poster style reference information from the network, and generate poster dynamic elements for the target user based on the content to be recommended and the preference data; Based on the preference data, a target poster template is obtained from a preset poster template library, and an exclusive poster for the target user is generated by combining the multiple poster elements, the poster style reference information, and the poster dynamic elements.

2. The method according to claim 1, characterized in that The step of determining the content to be recommended to the target user and a plurality of poster elements corresponding to the content to be recommended based on the preference data specifically includes: Based on the preference data, construct a target user profile of the target user; Acquire a target historical user portrait that matches the target user portrait from a preset portrait database; Obtain target historical recommended content corresponding to the target historical user portrait, and use the target historical recommended content as content to be recommended to the target user; The text elements and the image elements of the content to be recommended are obtained, and a plurality of poster elements of the target user are generated based on the text elements and the image elements.

3. The method according to claim 2, characterized in that The step of constructing a target user portrait of the target user based on the preference data specifically includes: Preprocessing the preference data to obtain preprocessed preference data; Extracting features from the preprocessed preference data to obtain attribute feature information, behavior feature information, and social feature information; Based on the attribute feature information, the behavior feature information and the social feature information, a pre-trained portrait model is used to generate a target user portrait of the target user.

4. The method according to claim 1, characterized in that: The step of obtaining poster style reference information from the network specifically includes: Get poster data from the Internet; Based on a preset poster style rule, the poster data is parsed and extracted to obtain poster style data; Big data tools are used to perform style trend analysis on the poster style data to obtain poster style reference information.

5. The method according to claim 1, characterized in that The step of generating the poster dynamic element of the target user based on the content to be recommended and the preference data specifically includes: Determining first weights of multiple user feature dimensions of the target user based on a preset weight strategy and the preference data; Based on the content to be recommended and the preference data, a preset deep learning model is used to generate an initial poster dynamic element for the target user; Based on the first weight, the initial poster dynamic element is optimized to obtain the poster dynamic element of the target user.

6. The method according to claim 1, characterized in that The step of generating the poster dynamic element of the target user based on the content to be recommended and the preference data specifically includes: Displaying a user dimension configuration interface, wherein the user dimension configuration interface includes a plurality of dimension weight selection controls; When a trigger operation for the plurality of dimension weight selection controls is detected, second weights of the plurality of user feature dimensions of the target user are obtained; Based on the content to be recommended and the preference data, a preset deep learning model is used to generate an initial poster dynamic element for the target user; Based on the second weight, the initial poster dynamic element is optimized to obtain the poster dynamic element of the target user.

7. The method according to claim 1, characterized in that After the step of acquiring a target poster template from a preset poster template library based on the preference data, and combining the multiple poster elements, the poster style reference information, and the poster dynamic elements to generate an exclusive poster for the target user, the method further includes: Obtaining feedback data of the target user regarding the exclusive poster; The feedback data is deeply analyzed to generate poster optimization information, and the exclusive poster is optimized based on the poster optimization information.

8. A dedicated poster generation device, characterized in that: include: A display module, used for displaying a poster preview QR code, and triggering acquisition of user information of a target user on multiple application terminals when a scanning operation for the poster preview QR code is detected; An analysis module, used to perform preference analysis on the user information using a machine learning algorithm to obtain preference data of the target user; A determination module, configured to determine, based on the preference data, the content to be recommended for the target user and a plurality of poster elements corresponding to the content to be recommended; An acquisition module, used to acquire poster style reference information from the network, and generate poster dynamic elements for the target user based on the content to be recommended and the preference data; A combining module is used to obtain a target poster template from a preset poster template library based on the preference data, and to generate an exclusive poster for the target user by combining the content to be recommended, the poster style reference information, and the poster dynamic elements.

9. A computer device, characterized in that: It comprises a memory and a processor, wherein the memory stores computer-readable instructions, and when the processor executes the computer-readable instructions, the steps of the exclusive poster generation method as claimed in any one of claims 1 to 7 are implemented.

10. A computer-readable storage medium, characterized in that: The computer-readable storage medium stores computer-readable instructions, and when the computer-readable instructions are executed by a processor, the steps of the exclusive poster generation method according to any one of claims 1 to 7 are implemented.

Images