System

Abstract

A system is provided.SOLUTION: A system comprising: means for collecting information provided from a user; an artificial intelligence model for generating an optimal advertisement element for a target using the collected information; means for selecting advertisement content for each target based on the generated advertisement element; means for delivering the selected advertisement content to a user terminal; means for analyzing reaction data of the user to the advertisement content; and means for updating the artificial intelligence model using the analysis result.SELECTED DRAWING: Figure 1

Description

[Technical Field]

[0001] The technology of the present disclosure relates to a system. [Background technology]

[0002] Patent document 1 discloses a persona chatbot control method performed by at least one processor, the method including the steps of receiving a user utterance, adding the user utterance to a prompt including an instruction sentence related to a description of the chatbot character, encoding the prompt, and inputting the encoded prompt into a language model to generate a chatbot utterance in response to the user utterance. [Prior art documents] [Patent documents]

[0003] [Patent Document 1] Japanese Patent Publication No. 2022-180282 Summary of the Invention [Problem to be solved by the invention]

[0004] Modern advertising delivery systems typically perform precise targeting based on the attributes of the target. However, the more precise the targeting, the more limited the number of people to whom the ad can be delivered. With conventional methods, it is difficult to deliver ads to a wider range of targets while providing ads that are effective for each target. The present invention aims to provide a solution for providing ads that "attack" on each target, even when targeted at a wide range of targets. [Means for solving the problem]

[0005] The present invention solves the above-mentioned problems by the following means: a system including means for collecting information provided by users, an artificial intelligence model for generating optimal advertising elements for targets using the collected information, means for selecting advertising content for each target based on the generated advertising elements, means for delivering the selected advertising content to user terminals, means for analyzing user response data to the advertising content, and means for updating the artificial intelligence model using the analysis results. This makes it possible to provide effective advertising tailored to a wide range of targets, even for the same product.

[0006] "Information provided by the user" refers to data such as the user's gender, age, hobbies and preferences, internet browsing history, and purchase history that is collected in order to display advertisements.

[0007] A "collection instrument" is a hardware and software setup for obtaining and storing information from users.

[0008] An "artificial intelligence model" is a combination of statistical models and algorithms that use machine learning and deep learning technologies to generate optimal advertising elements from input data.

[0009] "Advertising elements" are the individual elements that make up advertising content, such as web commercials, images, copy, appeal content, and appearing talent.

[0010] "Advertising content" refers to a completed advertisement, including the specific advertising message, visuals, video, etc., that is displayed to the target audience.

[0011] The "selection means" refers to the algorithms and processes used to select the most effective advertising content for the target from the generated advertising elements.

[0012] The "distribution means" refers to the network and system for transmitting the selected advertising content to the user's terminal and displaying it.

[0013] A "user terminal" is a device that a user uses to connect to the Internet, such as a PC, smartphone, or tablet.

[0014] "Response data" refers to data on the actions taken by a user after viewing an advertisement, such as the number of clicks, viewing time, and purchase history.

[0015] "Means of analysis" refers to tools and algorithms for analyzing user response data and evaluating the effectiveness of advertising.

[0016] "Means of updating" refers to the process of retraining the AI ​​model based on the analysis results to help generate the next ad. [Brief explanation of the drawings]

[0017] [Figure 1] 1 is a conceptual diagram showing an example of the configuration of a data processing system according to a first embodiment. [Figure 2] 1 is a conceptual diagram showing an example of main functions of a data processing device and a smart device according to a first embodiment. [Figure 3] FIG. 10 is a conceptual diagram showing an example of the configuration of a data processing system according to a second embodiment. [Figure 4] FIG. 10 is a conceptual diagram showing an example of main functions of a data processing device and smart glasses according to a second embodiment. [Figure 5] FIG. 10 is a conceptual diagram showing an example of the configuration of a data processing system according to a third embodiment. [Figure 6] FIG. 11 is a conceptual diagram showing an example of main functions of a data processing device and a headset-type terminal according to a third embodiment. [Figure 7] FIG. 10 is a conceptual diagram showing an example of the configuration of a data processing system according to a fourth embodiment. [Figure 8] FIG. 10 is a conceptual diagram showing an example of main functions of a data processing device and a robot according to a fourth embodiment. [Figure 9] 1 shows an emotion map onto which multiple emotions are mapped. [Figure 10] 1 shows an emotion map onto which multiple emotions are mapped. [Figure 11] FIG. 3 is a sequence diagram showing a processing flow of the data processing system according to the first embodiment. [Figure 12] FIG. 10 is a sequence diagram showing the flow of processing in the data processing system in Application Example 1. [Figure 13] FIG. 10 is a sequence diagram showing the flow of processing in the data processing system according to the second embodiment when an emotion engine is combined. [Figure 14] FIG. 10 is a sequence diagram showing the flow of processing in the data processing system in Application Example 2 when an emotion engine is combined. DETAILED DESCRIPTION OF THE INVENTION

[0018] An example of an embodiment of a system according to the technology of the present disclosure will be described below with reference to the accompanying drawings.

[0019] First, the terms used in the following description will be explained.

[0020] In the following embodiments, a coded processor (hereinafter simply referred to as a "processor") may be a single arithmetic device or a combination of multiple arithmetic devices. Furthermore, a processor may be a single type of arithmetic device or a combination of multiple types of arithmetic devices. Examples of arithmetic devices include a CPU (Central Processing Unit), a GPU (Graphics Processing Unit), a GPGPU (General-Purpose computing on Graphics Processing Units), and an APU (Accelerated Processing Unit).

[0021] In the following embodiments, a coded RAM (Random Access Memory) is a memory in which information is temporarily stored and is used as a working memory by a processor.

[0022] In the following embodiments, the coded storage is one or more non-volatile storage devices that store various programs, various parameters, etc. Examples of non-volatile storage devices include flash memory (SSD (Solid State Drive)), magnetic disks (e.g., hard disks), and magnetic tapes.

[0023] In the following embodiments, a communication I / F (Interface) with a symbol is an interface including a communication processor, an antenna, etc. The communication I / F controls communication between multiple computers. Examples of communication standards applied to the communication I / F include wireless communication standards including 5G (5th Generation Mobile Communication System), Wi-Fi (registered trademark), Bluetooth (registered trademark), etc.

[0024] In the following embodiments, "A and / or B" is synonymous with "at least one of A and B." In other words, "A and / or B" means that it may be only A, only B, or a combination of A and B. Furthermore, in this specification, the same concept as "A and / or B" is also applied when three or more things are expressed connected by "and / or."

[0025] [First embodiment]

[0026] FIG. 1 shows an example of the configuration of a data processing system 10 according to the first embodiment.

[0027] 1, a data processing system 10 includes a data processing device 12 and a smart device 14. An example of the data processing device 12 is a server.

[0028] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 is an example of a "computer" according to the technology of the present disclosure. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, the RAM 30, and the storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0029] The smart device 14 includes a computer 36, a reception device 38, an output device 40, a camera 42, and a communication I / F 44. The computer 36 includes a processor 46, a RAM 48, and a storage 50. The processor 46, the RAM 48, and the storage 50 are connected to a bus 52. The reception device 38, the output device 40, and the camera 42 are also connected to the bus 52.

[0030] The reception device 38 includes a touch panel 38A, a microphone 38B, and the like, and receives user input. The touch panel 38A detects contact with an indicator (for example, a pen or a finger) to receive user input by the touch of the indicator. The microphone 38B detects the user's voice to receive user input by voice. The control unit 46A transmits data indicating the user input received by the touch panel 38A and the microphone 38B to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the data indicating the user input.

[0031] The output device 40 includes a display 40A and a speaker 40B, and presents data to the user 20 by outputting the data in a form of expression that the user 20 can perceive (for example, audio and / or text). The display 40A displays visible information such as text and images in accordance with instructions from the processor 46. The speaker 40B outputs audio in accordance with instructions from the processor 46. The camera 42 is a compact digital camera equipped with an optical system including a lens, aperture, and shutter, and an imaging element such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor.

[0032] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 control the exchange of various information between the processor 46 and the processor 28 via the network 54.

[0033] FIG. 2 shows an example of the main functions of the data processing device 12 and the smart device 14.

[0034] 2, in the data processing device 12, a specific process is performed by the processor 28. A specific processing program 56 is stored in the storage 32. The specific processing program 56 is an example of a "program" according to the technology of the present disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific process is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[0035] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[0036] In the smart device 14, the processor 46 performs the reception output process. The storage 50 stores a reception output program 60. The reception output program 60 is used in conjunction with the specific processing program 56 by the data processing system 10. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output process is realized by the processor 46 operating as the control unit 46A in accordance with the reception output program 60 executed on the RAM 48.

[0037] Next, a description will be given of the specific processing performed by the specific processing unit 290 of the data processing device 12. In the following description, the data processing device 12 will be referred to as a "server" and the smart device 14 will be referred to as a "terminal."

[0038] MODE FOR CARRYING OUT THE INVENTION

[0039] The present invention is a system for displaying optimal advertisements to users, and is implemented by the following main steps: The following describes in detail how the server, terminal, and user are involved.

[0040] User Data Collection

[0041] The server collects user data through websites and applications, including a wide range of user-provided information such as gender, age, hobbies, preferences, internet browsing history, purchase history, etc. The server stores this user data in a secure database, preparing it for later input into an artificial intelligence model.

[0042] Data Preprocessing

[0043] The server cleanses (pre-processes) the collected data, specifically removing incomplete data and noise and converting it into a unified format. This pre-processing ensures that the AI ​​model operates with high accuracy.

[0044] Artificial intelligence models for ad generation

[0045] The AI ​​model takes the pre-processed data as input and generates optimal advertising elements for each target audience, including web commercials, images, copy, appealing content, and featured talent.

[0046] For example, for data on female users in their 30s, who often have children, ads with a theme of smartphone debut are generated, while for data on male users in their 20s, ads emphasizing the benefits of point redemption are generated.

[0047] Ad element selection and optimization

[0048] The server selects the most effective ad content for each target based on the generated list of ad element candidates. This selection process utilizes past ad performance data and real-time user data. During the selection process, the selected ad elements are fine-tuned to ensure their effectiveness as the final ad content.

[0049] Ad serving

[0050] The server registers the selected advertising content in the distribution reservation system and sets a specific distribution schedule, planning to display the advertisement at the most suitable time for the target user.

[0051] The terminal (user device) displays the appropriate advertisement delivered from the server the next time the user accesses the web. For example, when a user is viewing a specific web page, an optimally targeted advertisement is displayed at the set timing.

[0052] Data collection and feedback

[0053] The device records user response data (number of clicks on ads, viewing time, purchase history, etc.) and sends it to the server. The server analyzes this response data and evaluates the effectiveness of the ads. This is reflected in the next ad generation process to continuously improve ad performance.

[0054] Specific examples

[0055] For example, for a female user in her 30s, the following ads will be generated and delivered:

[0056] 1. The server collects user data of women in their 30s (e.g., they have children and are interested in using smartphones for the first time).

[0057] 2. Based on this user data, the AI ​​model generates advertising elements (web commercials, images, copy) depicting scenes of children starting to use smartphones.

[0058] 3. The server selects these advertising elements and fine-tunes them to create optimal content.

[0059] 4. The device will display targeted ads about smartphone debuts while the user is browsing the web.

[0060] 5. When a user clicks on an ad and views details, response data is collected and sent to the server at a later date.

[0061] 6. The server analyzes the response data and uses it in the next ad generation process.

[0062] Similarly, for male users in their 20s, the system generates and delivers optimally targeted ads in a similar manner, improving the accuracy and effectiveness of ad delivery.

[0063] The processing flow will be explained below.

[0064] Step 1:

[0065] The server collects user data through websites and applications, including information provided by users such as gender, age, interests, and preferences, as well as browsing and purchasing history. This data is collected by users through web forms and account settings, and automatically through cookies and tracking pixels.

[0066] Step 2:

[0067] The server stores the collected user data in a secure database, using encryption technology to ensure data integrity and security, and the database is indexed for quick access later.

[0068] Step 3:

[0069] The server retrieves user data from the stored database and performs pre-processing on the data, which includes cleaning the data (removing incomplete data and noise) and standardizing the data (converting it into a unified format), preparing the data format for input into the artificial intelligence model.

[0070] Step 4:

[0071] The AI ​​model receives the pre-processed data and generates optimal advertising elements for each target. Specifically, the algorithm automatically generates the web commercial, images, copy, appeal content, and talent for the ad based on gender, age, and hobbies and preferences.

[0072] Step 5:

[0073] The server generates a candidate list of ad content based on the generated ad elements, which may include multiple ad elements for each target, such as multiple versions with different copy or visual elements.

[0074] Step 6:

[0075] The server selects the most effective ad content from the list of candidates, using historical ad performance data and real-time user data. For example, it prioritizes ad elements that have historically generated high click-through rates.

[0076] Step 7:

[0077] The server then uses the selected ad content to fine-tune the targeted ads, which can include small design changes or copy modifications, making the ads more appealing.

[0078] Step 8:

[0079] The server registers the optimized advertising content in the distribution reservation system and sets a distribution schedule, specifically specifying the timing of advertisement distribution based on the user's online activity time.

[0080] Step 9:

[0081] The next time the user accesses the web, the terminal (user device) displays the appropriate advertisement delivered from the server. For example, an advertisement can be displayed at a set time while the user is browsing a specific site.

[0082] Step 10:

[0083] The device records how users respond to ads, including the number of clicks, viewing time, and eventual purchases.

[0084] Step 11:

[0085] The server receives and analyzes user response data sent from the device, using statistical tools and machine learning algorithms to evaluate ad performance.

[0086] Step 12:

[0087] The server retrains the artificial intelligence model based on the analysis results, thereby updating the model so that it generates more optimal ad elements the next time an ad is generated.

[0088] In this way, the system of the present invention can provide highly accurate and effective advertisements to a wide range of targets.

[0089] Example 1

[0090] Next, a description will be given of Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the smart device 14 will be referred to as a "terminal."

[0091] Modern advertising systems are required to display optimal advertisements based on individual user information. However, existing methods lack sufficient data preprocessing, selection of advertising elements, and analysis of user responses, resulting in reduced advertising effectiveness. Furthermore, there is a lack of mechanisms for efficiently collecting user response data and continuously improving advertising effectiveness. This creates the problem of making it difficult to consistently display optimal advertisements to users.

[0092] The specific processing by the specific processing unit 290 of the data processing device 12 in the first embodiment is realized by the following means.

[0093] In this invention, the server includes means for collecting information provided by users, means for preprocessing the collected information, an artificial intelligence model for generating optimal advertising elements for targets using the preprocessed information, means for selecting advertising content for each target based on the generated advertising elements, means for delivering the selected advertising content to user terminals, means for collecting user response data to the advertising content, means for analyzing the collected response data, and means for updating the artificial intelligence model using the analysis results, thereby making it possible to always deliver optimal advertising to users and continuously improve its effectiveness.

[0094] "Information provided by users" refers to data such as gender, age, hobbies and preferences, internet browsing history, and purchase history that users provide through websites and applications.

[0095] "Preprocessing" is the process of removing incomplete data and noise from collected information and converting it into a unified format.

[0096] An "artificial intelligence model" is a collection of algorithms that learn from large amounts of data, recognize patterns, and generate advertising elements that are optimal for specific targets.

[0097] "Advertising Elements" refers to the various elements that make up an advertisement, such as digital content, visual advertisements, text advertisements, promotional content, and performers.

[0098] "Selection" refers to the process of selecting the most effective advertising content for the target from among the multiple advertising elements generated.

[0099] "Delivery" refers to the act of sending selected advertising content to a user terminal.

[0100] A "user terminal" is a device used by a user, such as a computer, smartphone, or tablet.

[0101] "Response data" refers to data such as the number of clicks a user makes on an advertisement, viewing time, and purchase history.

[0102] "Collecting" refers to the act of gathering user response data and storing it for analysis.

[0103] "Analysis" is the process of analyzing collected response data using statistical methods and machine learning techniques to evaluate the effectiveness of advertising.

[0104] "Update" is the process of improving the artificial intelligence model based on the analysis results and reflecting them in the next ad generation.

[0105] This invention provides a system for displaying optimal advertisements to users. This system is made up of three main components: a server, a terminal, and a user. The following describes in detail an embodiment of this invention.

[0106] The server first collects information provided by users through websites and applications, including gender, age, hobbies and preferences, internet browsing history, purchase history, etc. The collected data is then stored in a secure database.

[0107] The server then preprocesses the collected data. Specifically, preprocessing involves removing incomplete data and noise, converting data into a unified format, and unifying date data stored in different formats. It also removes records containing null values.

[0108] Once preprocessed, the data is input into an artificial intelligence model. This model learns from large amounts of data and generates optimal advertising elements for each target. The generated advertising elements include digital content, visual ads, text ads, promotional content, and performers. For example, the following prompt sentence is used to generate advertising elements: "Please generate an advertisement for a woman in her 30s with children about her smartphone debut."

[0109] The server then selects ad content based on the generated ad elements. This selection process takes into account past ad performance data and real-time user data. During the selection process, the server fine-tunes the generated ad elements to create the most effective ad content.

[0110] Once the selection and fine-tuning of advertising content is complete, the server delivers it to the user's device. The delivery schedule is planned to display the advertisement at the optimal time for the target user. The user's device then displays the advertisement delivered by the server the next time the user accesses the web.

[0111] The device also collects user response data to advertising content (number of clicks, viewing time, purchase history, etc.). This response data is sent to the server and analyzed by the server. The analysis results are used to evaluate the effectiveness of the advertisement and update the artificial intelligence model based on the results. This allows for more accurate advertisements to be generated in the next advertisement generation process.

[0112] For example, the following process is performed for a female user in her 30s:

[0113] 1. The server collects user data of a woman in her 30s (who has children and is interested in using a smartphone for the first time).

[0114] 2. The server preprocesses the collected data and converts it into a unified format.

[0115] 3. Based on this user data, the AI ​​model generates advertisements depicting scenes of children starting to use smartphones.

[0116] 4. The server selects and fine-tunes the generated ad elements.

[0117] 5. The device displays advertisements at the optimal time to users browsing news sites.

[0118] 6. The user clicks on the advertisement, and the response data is collected by the terminal and sent to the server.

[0119] 7. The server analyzes the response data and updates the artificial intelligence model based on the results.

[0120] In this way, the system can continually deliver the most appropriate ads to users, and continuously improve their accuracy and effectiveness.

[0121] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0122] Step 1: Collect user data

[0123] The server collects user data through websites and applications. Input includes information provided by users such as gender, age, hobbies and preferences, internet browsing history, and purchase history. This data is stored in a secure database. Specifically, the server records the pages the user views, the links they click, and the products they purchase.

[0124] Step 2: Preprocessing the data

[0125] The server preprocesses the collected user data. The input is the raw data collected in the previous step. Specific data processing involves removing incomplete data and noise and converting it into a unified format. This preprocessing step unifies date data stored in different formats, for example. Records containing NULL values ​​are also removed, resulting in cleaned data as the output.

[0126] Step 3: Running the AI ​​model to generate ads

[0127] The AI ​​model on the server receives the preprocessed data as input and generates optimal advertising elements. The prompt is "Please generate an advertisement for a woman in her 30s with children about her smartphone debut." Specifically, the model extracts patterns from the input data and generates advertising elements (digital content, visual ads, text ads, etc.) for each target as output.

[0128] Step 4: Select and optimize advertising elements

[0129] The server selects optimal advertising content from among the advertising elements generated by the AI ​​model. It uses the generated advertising elements, past advertising performance data, and real-time user data as input. Specifically, it uses statistical analysis and machine learning algorithms to evaluate the advertising elements and selects optimal advertising content as output. It also fine-tunes the selected advertising elements.

[0130] Step 5: Serving Ads

[0131] The server registers the selected advertising content in the distribution reservation system and sets a distribution schedule. The selected advertising content and timing data for its target users are used as input. Specifically, the server schedules the advertisement so that it is displayed at the optimal time for the target users. The output is the advertising content for which distribution reservation has been completed. The terminal then displays the advertisement while the user is browsing the web.

[0132] Step 6: Data collection and feedback

[0133] The terminal records user response data to advertisements and sends it to the server. Inputs include the number of clicks on the advertisements, viewing time, and purchase history. Specific data processing involves organizing this data and sending it to the server. The server analyzes this response data. The response data sent in the previous step is used as input. The output is an analysis result indicating the effectiveness of the advertisement. Based on this analysis result, the server updates the artificial intelligence model and uses it in the next advertisement generation process. This continuously improves the accuracy and effectiveness of advertisements.

[0134] (Application example 1)

[0135] Next, a description will be given of Application Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the smart device 14 will be referred to as a "terminal."

[0136] Conventional ad delivery systems have issues with the insufficient integration of user data collection, ad element generation, delivery, and effectiveness analysis, making it difficult to display optimal ads in real time. Another problem is that ad optimization within smart devices is insufficient, resulting in a lack of improvement in the user experience.

[0137] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 1 is realized by the following means.

[0138] In this invention, the server includes: means for collecting information provided by users; an artificial intelligence model for generating optimal advertising elements for targets using the collected information; means for selecting advertising content for each target based on the generated advertising elements; means for delivering the selected advertising content to user terminals; means for analyzing user response data to the advertising content; means for updating the artificial intelligence model using the analysis results; a processor for generating and optimizing advertising elements within a smart device; and an output device for displaying the advertisements generated by the processor. This makes it possible to display optimal advertisements to users in real time and maximize the effectiveness of the advertisements.

[0139] Definition of Terms

[0140] "User-provided information" refers to personal information, internet browsing history, purchase history, location information, and application usage history collected voluntarily or through the user's activity.

[0141] An "artificial intelligence model" is a machine learning algorithm that performs data analysis based on collected user information and generates optimal advertising elements for each target.

[0142] "Advertising elements" are elements that make up the content of an advertisement, including web commercials, images, copy, appealing content, featured talent, and advertising units displayed within user terminal applications.

[0143] "Advertising content" is a combination of advertising elements generated and optimized by an artificial intelligence model.

[0144] A "user terminal" is a device used by a user, such as a smartphone, tablet, PC, or smart device.

[0145] "Response data" is data that records the actions and responses (number of clicks, viewing time, purchase history, etc.) that users show to advertisements.

[0146] "Processor" means a central processing unit for generating and optimizing advertising elements within a smart device.

[0147] "Output device" means a display or screen for displaying advertisements generated on a smart device to a user.

[0148] "Application usage history" is data that records the usage of applications used by a user within a smart device.

[0149] This invention is a system that generates and displays optimized advertisements in real time within smart devices. This system collects various information provided by users, uses an artificial intelligence model to generate, select, and deliver optimal advertising elements to the target audience, and also includes a process for providing feedback based on user responses. Each element is described in detail below.

[0150] System configuration and program description

[0151] 1. Hardware Configuration

[0152] The system consists of the following hardware:

[0153] Server: Responsible for data collection, preprocessing, training of AI models, generation of advertising elements, and collection and analysis of user response data.

[0154] User terminal: Refers to smartphones, tablets, personal computers, smart devices, etc., used to display advertisements and collect user response data.

[0155] Processor: A central processing unit for generating and optimizing advertising elements within a smart device.

[0156] Output Device: A display or screen for displaying the generated advertisement to the user.

[0157] 2. Software Configuration

[0158] The system consists of the following software:

[0159] Data collection module: Collects the user's gender, age, hobbies and preferences, internet browsing history, purchase history, location information, and application usage history.

[0160] Data preprocessing module: Cleanses and normalizes the collected data and converts it into a format suitable for AI models.

[0161] AI model: A machine learning algorithm that generates optimal advertising elements for each target based on collected data. It uses libraries such as scikit-learn.

[0162] Ad element generation module: Runs the AI ​​model to generate ad elements.

[0163] Advertisement selection module: Selects the most suitable content from the generated advertising elements.

[0164] Advertisement delivery module: delivers optimized advertising content to user terminals.

[0165] Reaction data collection module: collects user reaction data and provides feedback.

[0166] Advertisement display module: displays advertisements on the output device of the user terminal.

[0167] Data processing flow and specific examples

[0168] 1. Collection of User Data

[0169] The server collects information from the user's device, such as gender, age, hobbies, preferences, internet browsing history, purchase history, location information, and application usage history. For example, for a female user in her 30s, childcare-related browsing history and purchase history are collected from her smartphone history.

[0170] 2. Data Preprocessing

[0171] The server cleanses the collected data, imputes missing data, and normalizes it, using standard data preprocessing libraries pandas and scikit-learn's StandardScaler.

[0172] 3. Ad generation

[0173] An AI model (e.g., RandomForestClassifier) ​​installed on the server runs and generates advertising elements based on the preprocessed data. For example, if there is a lot of browsing history related to childcare, advertisements for baby products will be generated.

[0174] 4. Ad selection

[0175] The server selects the best ad element from the multiple ad elements generated based on past performance data. The ad selection algorithm uses A / B testing techniques.

[0176] 5. Delivery of advertisements

[0177] The server then delivers the selected advertisements to user devices such as smartphones in real time, and they are displayed when the user opens a specific application or web page.

[0178] 6. Collecting user response data and providing feedback

[0179] The server collects response data (number of clicks, viewing time, purchase history, etc.) from the user terminal to the advertisement and provides feedback for generating the next advertisement.

[0180] Prompt Sentence Examples

[0181] Design a system that collects user data and uses AI models to generate and display optimal ads. Specifically, the system generates optimal ads based on the user's age, gender, hobbies, preferences, browsing history, purchase history, etc., and provides feedback on the effectiveness of the ads.

[0182] This makes it possible to deliver optimal ads to users in real time and maximize their effectiveness.The system is designed to improve the accuracy and effectiveness of ad delivery and enhance the user experience.

[0183] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0184] Program processing steps

[0185] Step 1:

[0186] The server collects information provided by the user's device. Specifically, it acquires the user's gender, age, hobbies and preferences, internet browsing history, purchase history, location information, and application usage history. The input data is these user attributes and behavioral data, and the output is the collected dataset.

[0187] Step 2:

[0188] The server preprocesses the collected data. Specifically, it cleanses the data (complements incomplete data and removes noise) and normalizes it. This process uses pandas and scikit-learn's StandardScaler. The input data is the dataset collected in step 1, and the output is a clean dataset after preprocessing.

[0189] Step 3:

[0190] The server runs an artificial intelligence model to generate advertising elements using the preprocessed data. For example, it uses RandomForestClassifier to perform data analysis. The input data is the preprocessed dataset, and the output is the generated advertising elements.

[0191] Step 4:

[0192] The server selects the optimal advertising content from the generated advertising elements. It determines the optimal content by verifying past performance data and real-time user data using A / B testing methods. The input data are multiple advertising elements and their performance metrics, and the output is the selected advertising content.

[0193] Step 5:

[0194] The server delivers the selected advertising content to the user device in real time, and the content is displayed when the user opens a specific application or web page. The input data is the selected advertising content, and the output is the advertisement displayed on the user device.

[0195] Step 6:

[0196] Users respond to displayed ads by clicking or viewing them. User response data (number of clicks, viewing time, purchase history, etc.) is collected. The input data is user behavior data, and the output is the collected response data.

[0197] Step 7:

[0198] The server analyzes the collected response data and updates the AI ​​model based on the results. This feedback loop optimizes the next ad generation process. The input data is the collected response data, and the output is the updated AI model.

[0199] Furthermore, an emotion engine that estimates the user's emotion may be combined. That is, the identification processing unit 290 may estimate the user's emotion using the emotion identification model 59 and perform identification processing using the user's emotion.

[0200] MODE FOR CARRYING OUT THE INVENTION

[0201] This invention is a system that collects and analyzes information, including user emotions, and displays optimal advertisements, and is implemented in the following steps. The following describes in detail how the server, terminal, and user are involved.

[0202] User Data Collection

[0203] The server collects user data through websites and applications. The collected data includes user-provided information such as gender, age, hobbies, preferences, internet browsing history, and purchase history. In addition, emotional information is collected through the user's device camera and microphone. With the user's permission, emotion recognition is performed by analyzing facial expressions and voice tone.

[0204] Data preprocessing and sentiment analysis

[0205] The server stores the collected user data in a secure database and performs preprocessing on the data. This includes removing incomplete data and noise, and standardizing the data. In parallel, the emotion engine analyzes the user's emotion data to identify their current state of mind. For example, facial expression and voice analysis determine whether the user is in a state of "happy," "excited," or "anxious."

[0206] Artificial intelligence models for ad generation

[0207] The AI ​​model generates optimal advertising elements for each target based on collected and pre-processed basic data and emotional data. These elements include web commercials, images, copy, appealing content, and featured talent. By incorporating emotional data, the model generates an ad that best suits the user's current mood.

[0208] For example, if a female user in her 30s is perceived as being in a "happy" state, a bright-toned ad about her child's first smartphone will be generated. On the other hand, if a male user in his 20s is perceived as being in an "anxious" state, a point-reward ad emphasizing a sense of security will be generated.

[0209] Ad element selection and optimization

[0210] The server selects the most effective ad content for each target based on the generated candidate list of ad elements. The selection is made using past ad performance data, real-time user data, and current user sentiment data. The selected ad elements are fine-tuned as the final ad content to enhance its appeal.

[0211] Ad serving

[0212] The server registers the selected advertising content in the distribution reservation system and sets a distribution schedule, which is planned to distribute advertisements at optimal times based on the user's online activity time and emotional data.

[0213] The terminal (user device) displays the appropriate advertisement delivered from the server the next time the user accesses the web. While the user is browsing a specific web page, the advertisement is displayed according to the emotional data.

[0214] Data collection and feedback

[0215] The device records user response data (number of clicks on ads, viewing time, purchase history, etc.) and sends it to the server. The server analyzes this response data and evaluates the effectiveness of the ads. Based on the evaluation results, the next ad generation process is updated to continuously improve ad performance.

[0216] Specific examples

[0217] For example, for a female user in her 30s, the following ads will be generated and delivered:

[0218] 1. The server collects user data of women in their 30s (e.g., they have children, they are interested in using a smartphone for the first time) and emotional data on "happiness."

[0219] 2. Based on this user data, the AI ​​model generates advertising elements (web commercials, images, copy) in upbeat tones depicting scenes of children starting to use smartphones.

[0220] 3. The server selects these advertising elements and fine-tunes them as advertising content.

[0221] 4. While the user is browsing the web, the device displays smartphone debut ads tailored to their "happiness" state.

[0222] 5. When a user clicks on an ad and views details, response data is collected and sent to the server at a later date.

[0223] 6. The server analyzes the response data and uses it in the next ad generation process.

[0224] Similarly, for male users in their 20s, targeted adaptive ads are generated that take into account their emotional data and are delivered at the appropriate time. This system further improves the accuracy and effectiveness of ad delivery.

[0225] The processing flow will be explained below.

[0226] Step 1:

[0227] The server collects user data through websites and applications, including gender, age, hobbies, preferences, internet browsing history, and purchase history. In addition, it obtains emotional information through the user's device camera and microphone, and, with the user's permission, collects facial expressions and voice tone.

[0228] Step 2:

[0229] The device captures the user's facial expressions and voice tone in real time and sends them to the emotion engine, which analyzes this data and identifies the user's emotional state. For example, if the user is smiling, it is judged to be "joy," and if the user is frowning, it is judged to be "stress."

[0230] Step 3:

[0231] The server stores the collected user data and emotion data in a secure database using encryption technology to ensure data integrity and security, and the database is indexed and managed for efficient future access.

[0232] Step 4:

[0233] The server extracts user data and emotion data from the stored database and performs pre-processing on the data, which includes removing incomplete data and noise, and standardizing the data, preparing it in a format suitable for input into the artificial intelligence model.

[0234] Step 5:

[0235] The AI ​​model receives the pre-processed data and generates optimal advertising elements for the target audience based on the user's gender, age, hobbies, preferences, internet browsing history, purchase history, and emotional state. These elements include web commercials, images, copy, appealing content, and featured talent.

[0236] Step 6:

[0237] The server then creates a candidate list of advertising content for each target based on the generated advertising elements. The candidate list includes multiple advertising elements suited to the user's current emotional state. For example, if the user is feeling "joyed," advertisements with a bright tone will be prioritized.

[0238] Step 7:

[0239] The server selects the most effective ad content from the list of candidates, using past ad performance data, real-time user data, and current user sentiment data. Ad elements that have performed particularly well in the past are likely to be selected.

[0240] Step 8:

[0241] The server then uses the selected ad content to fine-tune the targeted ad, making small design changes and copy adjustments to make the ad more appealing.

[0242] Step 9:

[0243] The server registers the optimized advertising content in the distribution reservation system and sets the distribution schedule, which is planned to display the advertisement at the most effective timing based on the user's online activity time and emotional data.

[0244] Step 10:

[0245] The next time the user accesses the web, the terminal (user device) will display an appropriate advertisement delivered from the server. For example, when the user is viewing a specific web page, an advertisement tailored to the user's emotional data will be displayed.

[0246] Step 11:

[0247] The device records the user's response to the advertisement. The recorded data includes the number of clicks on the advertisement, viewing time, purchase history, etc. These data are important elements for capturing the user's response in detail.

[0248] Step 12:

[0249] The server receives user response data sent from the device and performs detailed analysis, using statistical tools and machine learning algorithms to evaluate ad performance.

[0250] Step 13:

[0251] The server retrains the AI ​​model based on the analysis results, so that more optimal advertising elements are generated in the next ad generation process, thereby continuously improving the effectiveness of the ad.

[0252] In this way, the system of the present invention realizes highly accurate advertisement distribution that also takes into account the user's emotions.

[0253] Example 2

[0254] Next, a description will be given of Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the smart device 14 will be referred to as a "terminal."

[0255] Conventional ad delivery systems generate ad elements based only on basic information provided by users and deliver them to target users. This makes it difficult to deliver ads that take into account the user's current emotional state. As a result, the effectiveness of ads is not maximized, and there is a need to further improve the accuracy and effectiveness of ad delivery. Another issue is that ad response data is not sufficiently collected and the results are not reflected in the next ad generation process.

[0256] The specific processing by the specific processing unit 290 of the data processing device 12 in the second embodiment is realized by the following means.

[0257] In this invention, the server includes: means for collecting information and emotional information provided by a user; an artificial intelligence model for generating optimal advertising elements for a target using the collected information and emotional information; means for selecting and fine-tuning advertising content for each target based on the generated advertising elements; means for scheduling and delivering the selected and fine-tuned advertising content to a user terminal; means for collecting and analyzing user response data to the advertising content; and means for continuously updating and optimizing the artificial intelligence model using the analysis results. This makes it possible to generate and deliver target-adaptive advertisements that take into account the emotional state of the user, thereby further improving the accuracy and effectiveness of advertisement delivery.

[0258] "Information provided by the user" refers to basic information such as gender, age, hobbies and preferences, internet browsing history, and purchase history that the user provides through a website or application.

[0259] "Emotional information" is data about the user's emotional state obtained by analyzing facial expressions and vocal tones captured through the user's device camera and microphone.

[0260] An "artificial intelligence model" is an algorithm or system that generates optimal advertising elements for a target based on collected user and emotional information.

[0261] "Advertising elements" are the individual elements that make up advertising content, such as web content, images, copy, claims, and performers.

[0262] The "means for selecting and fine-tuning advertising content for each target" refers to a means for selecting the most effective advertising element for a specific target user based on the generated candidate list of advertising elements, and then fine-tuning the content.

[0263] "Scheduling and delivery means" refers to means for delivering selected and fine-tuned advertising content at appropriate times based on the user's online activity time and emotional data.

[0264] "Response data" refers to data relating to a user's response to an advertisement, such as the number of clicks, viewing time, and purchase history.

[0265] "Means for continuous updating and optimization" refers to means for continuously updating and optimizing the artificial intelligence model based on collected and analyzed reaction data.

[0266] MODE FOR CARRYING OUT THE INVENTION

[0267] The present invention provides a system that generates optimal advertising elements using basic information and emotion information provided by users and delivers them to target users. This system includes a server, a terminal, and a user, and is implemented based on the following steps:

[0268] 1. Collection of User Data

[0269] The server collects user information via websites and applications, including gender, age, hobbies and preferences, internet browsing history, and purchase history. With the user's permission, the server also uses the device's camera and microphone to analyze facial expressions and voice tone to collect emotional information. For example, if the user is smiling, the emotional information is recorded as "happy."

[0270] 2. Data preprocessing and sentiment analysis

[0271] The server stores the collected information in a secure database. After removing incomplete data and noise from the stored data and standardizing it, the emotional data is analyzed using an emotion engine. The emotion engine used in this process includes algorithms for facial expression analysis and voice analysis. For example, it can identify the user's emotional state, such as "happiness" or "anxiety," based on specific facial features.

[0272] 3. Artificial Intelligence Model for Ad Generation

[0273] The server inputs the preprocessed basic information and emotional information into the AI ​​model. For example, if the user is a woman in her 30s and in a "happy" emotional state, that information is input into the AI ​​model. This AI model uses the data to generate optimal advertising elements for each target, such as web content, images, copy, appealing content, and performers. As a specific example, if the user is a woman in her 30s and in a "happy" state, a bright-toned advertisement with the theme of her child's first smartphone will be generated.

[0274] 4. Selecting and optimizing advertising elements

[0275] Based on the generated list of ad element candidates, the server selects the most effective ad elements by utilizing historical ad performance data, real-time user data, and sentiment data. The selected ad elements are then further fine-tuned to make them more visually and content-oriented. For example, fine-tuning may be done by changing the color tone of the web content or the font of the text.

[0276] 5. Delivery of advertisements

[0277] The server registers the selected and fine-tuned advertising content in the distribution reservation system and sets a distribution schedule based on the user's online activity time and emotional data. The next time the user browses the web, the device displays the distributed advertisement. For example, if the target user is viewing a web page in a "happy" emotional state, an appropriately selected smartphone debut advertisement will be displayed.

[0278] 6. Data Collection and Feedback

[0279] The device records user response data to advertisements (number of clicks, viewing time, purchase history, etc.) and sends it to the server. The server analyzes this response data to evaluate the effectiveness of the advertisements. The evaluation results are reflected in the next advertisement generation process. This enables continuous updating and optimization of the AI ​​model and advertisement content.

[0280] Specific examples

[0281] For example, for a female user in her 30s, the following ads will be generated and delivered:

[0282] 1. The server collects user data of women in their 30s (e.g., they have children, they are interested in using a smartphone for the first time) and emotional data on "happiness."

[0283] 2. Based on this user data, the AI ​​model generates advertising elements (web commercials, images, copy) in upbeat tones depicting scenes of children starting to use smartphones.

[0284] 3. The server selects these advertising elements and fine-tunes them as advertising content.

[0285] 4. While the user is browsing the web, the device displays smartphone debut ads tailored to their "happiness" state.

[0286] 5. When a user clicks on an ad and views details, response data is collected and sent to the server at a later date.

[0287] 6. The server analyzes the response data and uses it in the next ad generation process.

[0288] Prompt Sentence Examples

[0289] "We have a user who is a woman in her 30s with a child. She is currently in a 'happy' emotional state. Please generate optimal advertising elements for this user regarding their smartphone debut."

[0290] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0291] Step 1:

[0292] The server collects user information via websites and applications. Input data includes gender, age, hobbies, preferences, internet browsing history, and purchase history provided by the user. The server stores this data in a secure database. With the user's permission, the server also uses the device camera and microphone to collect facial expressions and voice tones. For example, if the user is smiling, the server records the emotional information as "happy." The output data includes basic information and emotional information.

[0293] Step 2:

[0294] The server performs preprocessing on the data stored in a secure database. The input data includes the basic information and emotional information collected in step 1. Specific operations include removing incomplete data and noise, and standardizing the data. In parallel, the emotional information is analyzed using an emotional engine. For example, it uses facial expression analysis and voice analysis algorithms to identify the user's emotional state as "happy" or "anxious." The output data is the preprocessed basic information and analyzed emotional information.

[0295] Step 3:

[0296] The server inputs the preprocessed basic information and emotional information into the AI ​​model. Input data includes gender, age, hobbies and preferences, browsing history, purchase history, and analyzed emotional data. The AI ​​model generates optimal advertising elements based on this data. Specifically, it generates web content, images, copy, appealing content, and performers. For example, if a female user in her 30s is in a "happy" emotional state, it generates a bright-toned advertisement themed around her child's smartphone debut. The output data is a list of the generated advertising elements.

[0297] Step 4:

[0298] The server selects optimal advertising content for each target based on a candidate list of advertising elements generated by an AI model. The input data includes the list of generated advertising elements, past advertising performance data, current user data, and emotional data. Specific operations include fine-tuning the selected advertising elements, such as changing color tones and adjusting text fonts. The output data is optimized advertising content.

[0299] Step 5:

[0300] The server registers the selected and fine-tuned advertising content in the distribution reservation system and sets a distribution schedule. Input data includes the optimized advertising content, the user's online activity time, and emotional data. Specific operations involve planning the optimal timing of ad distribution based on the user's online activity time and emotional data. The next time the user browses the web, the device displays the distributed advertisement. For example, if the user is browsing the web in a "happy" emotional state, a smartphone debut advertisement will be displayed. The output data is an advertising distribution schedule.

[0301] Step 6:

[0302] The device records user response data to advertisements. Input data includes user behavior data (number of clicks, viewing time, purchase history, etc.). This response data is sent to the server. The server analyzes this data and evaluates the effectiveness of the advertisement. Specifically, it evaluates the performance of the advertisement based on the response data, and updates and optimizes the AI ​​model based on the results. The output data are the analysis results and a continuously updated AI model.

[0303] (Application example 2)

[0304] Next, a description will be given of Application Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the smart device 14 will be referred to as a "terminal."

[0305] Current ad delivery systems generate and deliver targeted ads based on data such as a user's basic information and browsing history, but they are unable to consider the user's emotional state. This makes it difficult to deliver ads that are best suited to the user's current emotional state, resulting in a lack of maximum advertising effectiveness.

[0306] The identification process by the identification processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means. In this invention, the server includes: means for collecting information and emotional data provided by users; an artificial intelligence model for generating optimal advertising elements for targets using the collected information and emotional data; means for selecting advertising content for each target based on the generated advertising elements; means for delivering the selected advertising content to user terminals; means for analyzing user response data to the advertising content; and means for updating the artificial intelligence model using the analysis results. This makes it possible to generate and deliver advertisements optimal for the user's current emotional state in real time.

[0307] "User-provided information" refers to data voluntarily provided by users, such as gender, age, hobbies and preferences, internet browsing history, and purchase history, as well as data including facial expressions and tone of voice collected to identify the user's emotional state.

[0308] "Emotion data" is data that indicates the user's current feelings and state, obtained by analyzing the user's facial expressions and voice tones.

[0309] The "artificial intelligence model" is a machine learning model that uses collected user data and emotional data to generate optimal advertising elements for each target.

[0310] "Advertising elements" are multiple elements that make up advertising content, such as visual media, still images, text, appeals, and characters.

[0311] "Advertising content" refers to the final advertising material selected from the generated advertising elements and delivered to the user.

[0312] "Response data" refers to data on the user's response to an advertisement, such as the number of clicks, viewing time, and purchase history.

[0313] "Means for updating" is a function for improving and optimizing the artificial intelligence model using collected user response data.

[0314] This invention is a system for displaying optimal advertisements using user emotion data. This system is realized mainly by a server, a terminal, and a process for collecting and analyzing user data. The implementation configuration and processing procedure of the system are described in detail below.

[0315] User Data Collection

[0316] The server collects information provided by users when they use websites and applications. Collected information includes gender, age, hobbies and preferences, internet browsing history, purchase history, and emotional data (facial expressions and voice tone) captured using the device's camera and microphone. The server captures facial expressions using OpenCV and recognizes emotions using deep learning libraries such as TensorFlow or Keras.

[0317] Data preprocessing and sentiment analysis

[0318] The collected user data is stored in a secure database on the server. Data preprocessing involves removing incomplete data and noise and standardizing the data. At the same time, an emotion recognition engine analyzes the user's facial expressions and voice tone to identify their current state of mind and emotion. This allows it to identify specific emotional states such as "happy," "excited," or "anxious."

[0319] Artificial intelligence models for ad generation

[0320] The server runs a generative AI model using the preprocessed basic data and emotion data. The generative AI model generates optimal advertising elements for each target audience. These advertising elements include visual media (e.g., web commercials), still images, text, advertising content, and characters. By utilizing the emotion data, an advertisement that best suits the user's current emotional state is generated.

[0321] Ad element selection and optimization

[0322] From the generated ad elements, the most effective ad content is selected based on historical ad performance data, real-time user data, and current user sentiment data. The selected ad elements are then fine-tuned into the final ad content. The server runs tools and algorithms to do this.

[0323] Ad serving

[0324] The server registers the selected advertising content in the distribution reservation system and sets the distribution schedule. Based on the user's online activity time and emotional data, the advertisements are planned to be distributed at the optimal timing. The user's device displays the advertisements distributed from the server the next time the user accesses the web. Appropriate advertisements are displayed to the user via a simple browser or application.

[0325] Data collection and feedback

[0326] The user's device records response data to the advertisement (number of clicks, viewing time, purchase history, etc.) and sends it to the server. The server analyzes this response data and evaluates the effectiveness of the advertisement. Based on the evaluation results, the generative AI model is updated to continuously improve the performance of the advertisement.

[0327] Specific examples

[0328] For example, if a female user in her 30s is recognized as being in a "happy" state, a cheerful advertisement about her child's first smartphone is generated. This advertisement is displayed on the user's smartphone, and response data is collected when the user clicks on the advertisement.

[0329] Example prompt for a generative AI model:

[0330] If the user is in a "happy" state, is a woman in her 30s, and is interested in technology and children, generate a "bright-toned ad related to children's smartphone debut."

[0331] If the user is in an "anxious" state, is a male in his 20s, and is concerned about security, an "advertisement offering points that emphasizes a sense of security" will be generated.

[0332] This makes it possible to generate and deliver optimal advertisements in real time based on the user's emotional state and personal data.

[0333] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[0334] Step 1:

[0335] User Data Collection

[0336] The server collects information provided by users when they use websites and applications. Inputs include gender, age, hobbies and preferences, internet browsing history, purchase history, and emotional data (facial expressions and voice tone) captured using the device camera and microphone. The server captures facial expressions using OpenCV and recognizes emotions using deep learning libraries such as TensorFlow or Keras. As output, user data and emotional data are stored in a secure database.

[0337] Step 2:

[0338] Data preprocessing and sentiment analysis

[0339] The server performs preprocessing by removing incomplete data and noise and standardizing the data. The input is the user data and emotion data collected in step 1, and the output is clear data after preprocessing. At the same time, the emotion recognition engine receives the user's facial expressions and voice tone as input and analyzes them. The output of the analysis is the user's emotional state (e.g., "happy," "excited," "anxious," etc.).

[0340] Step 3:

[0341] Artificial intelligence models for ad generation

[0342] The server runs the generative AI model using the clear data and emotion data that have been preprocessed. The input is the clear data and emotion data from the previous step, and the output is the optimal advertising elements (visual media, still images, text, appeal content, and characters) for each target. Specifically, the generative AI model generates multiple advertising elements and combines them based on the prompt text.

[0343] Step 4:

[0344] Ad element selection and optimization

[0345] The server selects the most effective ad content from the generated ad elements based on historical ad performance data, real-time user data, and current user sentiment data. The inputs are the generated ad elements, historical performance data, and real-time data. The output is optimized ad content. The server runs an algorithm to do this and fine-tunes the ad content.

[0346] Step 5:

[0347] Ad serving

[0348] The server registers the selected advertising content in the distribution reservation system and sets the distribution schedule. The input is the optimized advertising content, and the output is the advertisement delivered to the user's device. Specifically, the server determines the optimal timing based on the user's online activity time and emotional data, and instructs the device to display the advertisement the next time the user accesses the web.

[0349] Step 6:

[0350] Data collection and feedback

[0351] The user's device records response data to the ad (number of clicks, viewing time, purchase history, etc.) and sends it to the server. The input is the user's response data to the ad, and the output is feedback data recorded on the server. The server analyzes this feedback data and updates and optimizes the generative AI model. Specifically, the server analyzes the feedback data and uses it in the next ad generation process.

[0352] The specific processing unit 290 transmits the result of the specific processing to the smart device 14. In the smart device 14, the control unit 46A causes the output device 40 to output the result of the specific processing. The microphone 38B acquires audio indicating a user input regarding the result of the specific processing. The control unit 46A transmits audio data indicating the user input acquired by the microphone 38B to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the audio data.

[0353] The data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of the data generation model 58 is ChatGPT (Internet Search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search <url: https: gemini.google.com ?hl="ja">) and other generation AIs. The data generation model 58 is obtained by performing deep learning on a neural network. A prompt including an instruction is input to the data generation model 58, and inference data such as voice data indicating voice, text data indicating text, and image data indicating an image is also input. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt, and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[0354] In the above embodiment, an example in which the specific process is performed by the data processing device 12 has been given, but the technology of the present disclosure is not limited to this, and the specific process may be performed by the smart device 14.

[0355] [Second embodiment]

[0356] FIG. 3 shows an example of the configuration of a data processing system 210 according to the second embodiment.

[0357] 3, the data processing system 210 includes the data processing device 12 and smart glasses 214. An example of the data processing device 12 is a server.

[0358] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 is an example of a "computer" according to the technology of the present disclosure. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, the RAM 30, and the storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0359] The smart glasses 214 include a computer 36, a microphone 238, a speaker 240, a camera 42, and a communication I / F 44. The computer 36 includes a processor 46, a RAM 48, and a storage 50. The processor 46, the RAM 48, and the storage 50 are connected to a bus 52. The microphone 238, the speaker 240, and the camera 42 are also connected to the bus 52.

[0360] The microphone 238 receives instructions and the like from the user 20 by receiving voice uttered by the user 20. The microphone 238 captures the voice uttered by the user 20, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio in accordance with instructions from the processor 46.

[0361] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an imaging element such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the surroundings of user 20 (for example, an imaging range defined by an angle of view equivalent to the field of vision of a typical healthy person).

[0362] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 are responsible for the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is carried out in a secure state.

[0363] Fig. 4 shows an example of the main functions of the data processing device 12 and the smart glasses 214. As shown in Fig. 4, in the data processing device 12, a specific process is performed by the processor 28. A specific process program 56 is stored in the storage 32.

[0364] The specific processing program 56 is an example of a "program" according to the technology of the present disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[0365] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[0366] In the smart glasses 214, the reception output process is performed by the processor 46. A reception output program 60 is stored in the storage 50. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output process is realized by the processor 46 operating as the control unit 46A in accordance with the reception output program 60 executed on the RAM 48.

[0367] Next, a description will be given of the identification process performed by the identification processing unit 290 of the data processing device 12. In the following description, the data processing device 12 will be referred to as the "server" and the smart glasses 214 will be referred to as the "terminal."

[0368] MODE FOR CARRYING OUT THE INVENTION

[0369] The present invention is a system for displaying optimal advertisements to users, and is implemented by the following main steps: The following describes in detail how the server, terminal, and user are involved.

[0370] User Data Collection

[0371] The server collects user data through websites and applications, including a wide range of user-provided information such as gender, age, hobbies, preferences, internet browsing history, purchase history, etc. The server stores this user data in a secure database, preparing it for later input into an artificial intelligence model.

[0372] Data Preprocessing

[0373] The server cleanses (pre-processes) the collected data, specifically removing incomplete data and noise and converting it into a unified format. This pre-processing ensures that the AI ​​model operates with high accuracy.

[0374] Artificial intelligence models for ad generation

[0375] The AI ​​model takes the pre-processed data as input and generates optimal advertising elements for each target audience, including web commercials, images, copy, appealing content, and featured talent.

[0376] For example, for data on female users in their 30s, who often have children, ads with a theme of smartphone debut are generated, while for data on male users in their 20s, ads emphasizing the benefits of point redemption are generated.

[0377] Ad element selection and optimization

[0378] The server selects the most effective ad content for each target based on the generated list of ad element candidates. This selection process utilizes past ad performance data and real-time user data. During the selection process, the selected ad elements are fine-tuned to ensure their effectiveness as the final ad content.

[0379] Ad serving

[0380] The server registers the selected advertising content in the distribution reservation system and sets a specific distribution schedule, planning to display the advertisement at the most suitable time for the target user.

[0381] The terminal (user device) displays the appropriate advertisement delivered from the server the next time the user accesses the web. For example, when a user is viewing a specific web page, an optimally targeted advertisement is displayed at the set timing.

[0382] Data collection and feedback

[0383] The device records user response data (number of clicks on ads, viewing time, purchase history, etc.) and sends it to the server. The server analyzes this response data and evaluates the effectiveness of the ads. This is reflected in the next ad generation process to continuously improve ad performance.

[0384] Specific examples

[0385] For example, for a female user in her 30s, the following ads will be generated and delivered:

[0386] 1. The server collects user data of women in their 30s (e.g., they have children and are interested in using smartphones for the first time).

[0387] 2. Based on this user data, the AI ​​model generates advertising elements (web commercials, images, copy) depicting scenes of children starting to use smartphones.

[0388] 3. The server selects these advertising elements and fine-tunes them to create optimal content.

[0389] 4. The device will display targeted ads about smartphone debuts while the user is browsing the web.

[0390] 5. When a user clicks on an ad and views details, response data is collected and sent to the server at a later date.

[0391] 6. The server analyzes the response data and uses it in the next ad generation process.

[0392] Similarly, for male users in their 20s, the system generates and delivers optimally targeted ads in a similar manner, improving the accuracy and effectiveness of ad delivery.

[0393] The processing flow will be explained below.

[0394] Step 1:

[0395] The server collects user data through websites and applications, including information provided by users such as gender, age, interests, and preferences, as well as browsing and purchasing history. This data is collected by users through web forms and account settings, and automatically through cookies and tracking pixels.

[0396] Step 2:

[0397] The server stores the collected user data in a secure database, using encryption technology to ensure data integrity and security, and the database is indexed for quick access later.

[0398] Step 3:

[0399] The server retrieves user data from the stored database and performs pre-processing on the data, which includes cleaning the data (removing incomplete data and noise) and standardizing the data (converting it into a unified format), preparing the data format for input into the artificial intelligence model.

[0400] Step 4:

[0401] The AI ​​model receives the pre-processed data and generates optimal advertising elements for each target. Specifically, the algorithm automatically generates the web commercial, images, copy, appeal content, and talent for the ad based on gender, age, and hobbies and preferences.

[0402] Step 5:

[0403] The server generates a candidate list of ad content based on the generated ad elements, which may include multiple ad elements for each target, such as multiple versions with different copy or visual elements.

[0404] Step 6:

[0405] The server selects the most effective ad content from the list of candidates, using historical ad performance data and real-time user data. For example, it prioritizes ad elements that have historically generated high click-through rates.

[0406] Step 7:

[0407] The server then uses the selected ad content to fine-tune the targeted ads, which can include small design changes or copy modifications, making the ads more appealing.

[0408] Step 8:

[0409] The server registers the optimized advertising content in the distribution reservation system and sets a distribution schedule, specifically specifying the timing of advertisement distribution based on the user's online activity time.

[0410] Step 9:

[0411] The next time the user accesses the web, the terminal (user device) displays the appropriate advertisement delivered from the server. For example, an advertisement can be displayed at a set time while the user is browsing a specific site.

[0412] Step 10:

[0413] The device records how users respond to ads, including the number of clicks, viewing time, and eventual purchases.

[0414] Step 11:

[0415] The server receives and analyzes user response data sent from the device, using statistical tools and machine learning algorithms to evaluate ad performance.

[0416] Step 12:

[0417] The server retrains the artificial intelligence model based on the analysis results, thereby updating the model so that it generates more optimal ad elements the next time an ad is generated.

[0418] In this way, the system of the present invention can provide highly accurate and effective advertisements to a wide range of targets.

[0419] Example 1

[0420] Next, a description will be given of Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the smart glasses 214 will be referred to as a "terminal."

[0421] Modern advertising systems are required to display optimal advertisements based on individual user information. However, existing methods lack sufficient data preprocessing, selection of advertising elements, and analysis of user responses, resulting in reduced advertising effectiveness. Furthermore, there is a lack of mechanisms for efficiently collecting user response data and continuously improving advertising effectiveness. This creates the problem of making it difficult to consistently display optimal advertisements to users.

[0422] The specific processing by the specific processing unit 290 of the data processing device 12 in the first embodiment is realized by the following means.

[0423] In this invention, the server includes means for collecting information provided by users, means for preprocessing the collected information, an artificial intelligence model for generating optimal advertising elements for targets using the preprocessed information, means for selecting advertising content for each target based on the generated advertising elements, means for delivering the selected advertising content to user terminals, means for collecting user response data to the advertising content, means for analyzing the collected response data, and means for updating the artificial intelligence model using the analysis results, thereby making it possible to always deliver optimal advertising to users and continuously improve its effectiveness.

[0424] "Information provided by users" refers to data such as gender, age, hobbies and preferences, internet browsing history, and purchase history that users provide through websites and applications.

[0425] "Preprocessing" is the process of removing incomplete data and noise from collected information and converting it into a unified format.

[0426] An "artificial intelligence model" is a collection of algorithms that learn from large amounts of data, recognize patterns, and generate advertising elements that are optimal for specific targets.

[0427] "Advertising Elements" refers to the various elements that make up an advertisement, such as digital content, visual advertisements, text advertisements, promotional content, and performers.

[0428] "Selection" refers to the process of selecting the most effective advertising content for the target from among the multiple advertising elements generated.

[0429] "Delivery" refers to the act of sending selected advertising content to a user terminal.

[0430] A "user terminal" is a device used by a user, such as a computer, smartphone, or tablet.

[0431] "Response data" refers to data such as the number of clicks a user makes on an advertisement, viewing time, and purchase history.

[0432] "Collecting" refers to the act of gathering user response data and storing it for analysis.

[0433] "Analysis" is the process of analyzing collected response data using statistical methods and machine learning techniques to evaluate the effectiveness of advertising.

[0434] "Update" is the process of improving the artificial intelligence model based on the analysis results and reflecting them in the next ad generation.

[0435] This invention provides a system for displaying optimal advertisements to users. This system is made up of three main components: a server, a terminal, and a user. The following describes in detail an embodiment of this invention.

[0436] The server first collects information provided by users through websites and applications, including gender, age, hobbies and preferences, internet browsing history, purchase history, etc. The collected data is then stored in a secure database.

[0437] The server then preprocesses the collected data. Specifically, preprocessing involves removing incomplete data and noise, converting data into a unified format, and unifying date data stored in different formats. It also removes records containing null values.

[0438] Once preprocessed, the data is input into an artificial intelligence model. This model learns from large amounts of data and generates optimal advertising elements for each target. The generated advertising elements include digital content, visual ads, text ads, promotional content, and performers. For example, the following prompt sentence is used to generate advertising elements: "Please generate an advertisement for a woman in her 30s with children about her smartphone debut."

[0439] The server then selects ad content based on the generated ad elements. This selection process takes into account past ad performance data and real-time user data. During the selection process, the server fine-tunes the generated ad elements to create the most effective ad content.

[0440] Once the selection and fine-tuning of advertising content is complete, the server delivers it to the user's device. The delivery schedule is planned to display the advertisement at the optimal time for the target user. The user's device then displays the advertisement delivered by the server the next time the user accesses the web.

[0441] The device also collects user response data to advertising content (number of clicks, viewing time, purchase history, etc.). This response data is sent to the server and analyzed by the server. The analysis results are used to evaluate the effectiveness of the advertisement and update the artificial intelligence model based on the results. This allows for more accurate advertisements to be generated in the next advertisement generation process.

[0442] For example, the following process is performed for a female user in her 30s:

[0443] 1. The server collects user data of a woman in her 30s (who has children and is interested in using a smartphone for the first time).

[0444] 2. The server preprocesses the collected data and converts it into a unified format.

[0445] 3. Based on this user data, the AI ​​model generates advertisements depicting scenes of children starting to use smartphones.

[0446] 4. The server selects and fine-tunes the generated ad elements.

[0447] 5. The device displays advertisements at the optimal time to users browsing news sites.

[0448] 6. The user clicks on the advertisement, and the response data is collected by the terminal and sent to the server.

[0449] 7. The server analyzes the response data and updates the artificial intelligence model based on the results.

[0450] In this way, the system can continually deliver the most appropriate ads to users, and continuously improve their accuracy and effectiveness.

[0451] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0452] Step 1: Collect user data

[0453] The server collects user data through websites and applications. Input includes information provided by users such as gender, age, hobbies and preferences, internet browsing history, and purchase history. This data is stored in a secure database. Specifically, the server records the pages the user views, the links they click, and the products they purchase.

[0454] Step 2: Preprocessing the data

[0455] The server preprocesses the collected user data. The input is the raw data collected in the previous step. Specific data processing involves removing incomplete data and noise and converting it into a unified format. This preprocessing step unifies date data stored in different formats, for example. Records containing NULL values ​​are also removed, resulting in cleaned data as the output.

[0456] Step 3: Running the AI ​​model to generate ads

[0457] The AI ​​model on the server receives the preprocessed data as input and generates optimal advertising elements. The prompt is "Please generate an advertisement for a woman in her 30s with children about her smartphone debut." Specifically, the model extracts patterns from the input data and generates advertising elements (digital content, visual ads, text ads, etc.) for each target as output.

[0458] Step 4: Select and optimize advertising elements

[0459] The server selects optimal advertising content from among the advertising elements generated by the AI ​​model. It uses the generated advertising elements, past advertising performance data, and real-time user data as input. Specifically, it uses statistical analysis and machine learning algorithms to evaluate the advertising elements and selects optimal advertising content as output. It also fine-tunes the selected advertising elements.

[0460] Step 5: Serving Ads

[0461] The server registers the selected advertising content in the distribution reservation system and sets a distribution schedule. The selected advertising content and timing data for its target users are used as input. Specifically, the server schedules the advertisement so that it is displayed at the optimal time for the target users. The output is the advertising content for which distribution reservation has been completed. The terminal then displays the advertisement while the user is browsing the web.

[0462] Step 6: Data collection and feedback

[0463] The terminal records user response data to advertisements and sends it to the server. Inputs include the number of clicks on the advertisements, viewing time, and purchase history. Specific data processing involves organizing this data and sending it to the server. The server analyzes this response data. The response data sent in the previous step is used as input. The output is an analysis result indicating the effectiveness of the advertisement. Based on this analysis result, the server updates the artificial intelligence model and uses it in the next advertisement generation process. This continuously improves the accuracy and effectiveness of advertisements.

[0464] (Application example 1)

[0465] Next, a description will be given of Application Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the smart glasses 214 will be referred to as a "terminal."

[0466] Conventional ad delivery systems have issues with the insufficient integration of user data collection, ad element generation, delivery, and effectiveness analysis, making it difficult to display optimal ads in real time. Another problem is that ad optimization within smart devices is insufficient, resulting in a lack of improvement in the user experience.

[0467] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 1 is realized by the following means.

[0468] In this invention, the server includes: means for collecting information provided by users; an artificial intelligence model for generating optimal advertising elements for targets using the collected information; means for selecting advertising content for each target based on the generated advertising elements; means for delivering the selected advertising content to user terminals; means for analyzing user response data to the advertising content; means for updating the artificial intelligence model using the analysis results; a processor for generating and optimizing advertising elements within a smart device; and an output device for displaying the advertisements generated by the processor. This makes it possible to display optimal advertisements to users in real time and maximize the effectiveness of the advertisements.

[0469] Definition of Terms

[0470] "User-provided information" refers to personal information, internet browsing history, purchase history, location information, and application usage history collected voluntarily or through the user's activity.

[0471] An "artificial intelligence model" is a machine learning algorithm that performs data analysis based on collected user information and generates optimal advertising elements for each target.

[0472] "Advertising elements" are elements that make up the content of an advertisement, including web commercials, images, copy, appealing content, featured talent, and advertising units displayed within user terminal applications.

[0473] "Advertising content" is a combination of advertising elements generated and optimized by an artificial intelligence model.

[0474] A "user terminal" is a device used by a user, such as a smartphone, tablet, PC, or smart device.

[0475] "Response data" is data that records the actions and responses (number of clicks, viewing time, purchase history, etc.) that users show to advertisements.

[0476] "Processor" means a central processing unit for generating and optimizing advertising elements within a smart device.

[0477] "Output device" means a display or screen for displaying advertisements generated on a smart device to a user.

[0478] "Application usage history" is data that records the usage of applications used by a user within a smart device.

[0479] This invention is a system that generates and displays optimized advertisements in real time within smart devices. This system collects various information provided by users, uses an artificial intelligence model to generate, select, and deliver optimal advertising elements to the target audience, and also includes a process for providing feedback based on user responses. Each element is described in detail below.

[0480] System configuration and program description

[0481] 1. Hardware Configuration

[0482] The system consists of the following hardware:

[0483] Server: Responsible for data collection, preprocessing, training of AI models, generation of advertising elements, and collection and analysis of user response data.

[0484] User terminal: Refers to smartphones, tablets, personal computers, smart devices, etc., used to display advertisements and collect user response data.

[0485] Processor: A central processing unit for generating and optimizing advertising elements within a smart device.

[0486] Output Device: A display or screen for displaying the generated advertisement to the user.

[0487] 2. Software Configuration

[0488] The system consists of the following software:

[0489] Data collection module: Collects the user's gender, age, hobbies and preferences, internet browsing history, purchase history, location information, and application usage history.

[0490] Data preprocessing module: Cleanses and normalizes the collected data and converts it into a format suitable for AI models.

[0491] AI model: A machine learning algorithm that generates optimal advertising elements for each target based on collected data. It uses libraries such as scikit-learn.

[0492] Ad element generation module: Runs the AI ​​model to generate ad elements.

[0493] Advertisement selection module: Selects the most suitable content from the generated advertising elements.

[0494] Advertisement delivery module: delivers optimized advertising content to user terminals.

[0495] Reaction data collection module: collects user reaction data and provides feedback.

[0496] Advertisement display module: displays advertisements on the output device of the user terminal.

[0497] Data processing flow and specific examples

[0498] 1. Collection of User Data

[0499] The server collects information from the user's device, such as gender, age, hobbies, preferences, internet browsing history, purchase history, location information, and application usage history. For example, for a female user in her 30s, childcare-related browsing history and purchase history are collected from her smartphone history.

[0500] 2. Data Preprocessing

[0501] The server cleanses the collected data, imputes missing data, and normalizes it, using standard data preprocessing libraries pandas and scikit-learn's StandardScaler.

[0502] 3. Ad generation

[0503] An AI model (e.g., RandomForestClassifier) ​​installed on the server runs and generates advertising elements based on the preprocessed data. For example, if there is a lot of browsing history related to childcare, advertisements for baby products will be generated.

[0504] 4. Ad selection

[0505] The server selects the best ad element from the multiple ad elements generated based on past performance data. The ad selection algorithm uses A / B testing techniques.

[0506] 5. Delivery of advertisements

[0507] The server then delivers the selected advertisements to user devices such as smartphones in real time, and they are displayed when the user opens a specific application or web page.

[0508] 6. Collecting user response data and providing feedback

[0509] The server collects response data (number of clicks, viewing time, purchase history, etc.) from the user terminal to the advertisement and provides feedback for generating the next advertisement.

[0510] Prompt Sentence Examples

[0511] Design a system that collects user data and uses AI models to generate and display optimal ads. Specifically, the system generates optimal ads based on the user's age, gender, hobbies, preferences, browsing history, purchase history, etc., and provides feedback on the effectiveness of the ads.

[0512] This makes it possible to deliver optimal ads to users in real time and maximize their effectiveness.The system is designed to improve the accuracy and effectiveness of ad delivery and enhance the user experience.

[0513] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0514] Program processing steps

[0515] Step 1:

[0516] The server collects information provided by the user's device. Specifically, it acquires the user's gender, age, hobbies and preferences, internet browsing history, purchase history, location information, and application usage history. The input data is these user attributes and behavioral data, and the output is the collected dataset.

[0517] Step 2:

[0518] The server preprocesses the collected data. Specifically, it cleanses the data (complements incomplete data and removes noise) and normalizes it. This process uses pandas and scikit-learn's StandardScaler. The input data is the dataset collected in step 1, and the output is a clean dataset after preprocessing.

[0519] Step 3:

[0520] The server runs an artificial intelligence model to generate advertising elements using the preprocessed data. For example, it uses RandomForestClassifier to perform data analysis. The input data is the preprocessed dataset, and the output is the generated advertising elements.

[0521] Step 4:

[0522] The server selects the optimal advertising content from the generated advertising elements. It determines the optimal content by verifying past performance data and real-time user data using A / B testing methods. The input data are multiple advertising elements and their performance metrics, and the output is the selected advertising content.

[0523] Step 5:

[0524] The server delivers the selected advertising content to the user device in real time, and the content is displayed when the user opens a specific application or web page. The input data is the selected advertising content, and the output is the advertisement displayed on the user device.

[0525] Step 6:

[0526] Users respond to displayed ads by clicking or viewing them. User response data (number of clicks, viewing time, purchase history, etc.) is collected. The input data is user behavior data, and the output is the collected response data.

[0527] Step 7:

[0528] The server analyzes the collected response data and updates the AI ​​model based on the results. This feedback loop optimizes the next ad generation process. The input data is the collected response data, and the output is the updated AI model.

[0529] Furthermore, an emotion engine that estimates the user's emotion may be further combined. That is, the identification processing unit 290 may estimate the user's emotion using the emotion identification model 59, and perform identification processing using the user's emotion.

[0530] MODE FOR CARRYING OUT THE INVENTION

[0531] This invention is a system that collects and analyzes information, including user emotions, and displays optimal advertisements, and is implemented in the following steps. The following describes in detail how the server, terminal, and user are involved.

[0532] User Data Collection

[0533] The server collects user data through websites and applications. The collected data includes user-provided information such as gender, age, hobbies, preferences, internet browsing history, and purchase history. In addition, emotional information is collected through the user's device camera and microphone. With the user's permission, emotion recognition is performed by analyzing facial expressions and voice tone.

[0534] Data preprocessing and sentiment analysis

[0535] The server stores the collected user data in a secure database and performs preprocessing on the data. This includes removing incomplete data and noise, and standardizing the data. In parallel, the emotion engine analyzes the user's emotion data to identify their current state of mind. For example, facial expression and voice analysis determine whether the user is in a state of "happy," "excited," or "anxious."

[0536] Artificial intelligence models for ad generation

[0537] The AI ​​model generates optimal advertising elements for each target based on collected and pre-processed basic data and emotional data. These elements include web commercials, images, copy, appealing content, and featured talent. By incorporating emotional data, the model generates an ad that best suits the user's current mood.

[0538] For example, if a female user in her 30s is perceived as being in a "happy" state, a bright-toned ad about her child's first smartphone will be generated. On the other hand, if a male user in his 20s is perceived as being in an "anxious" state, a point-reward ad emphasizing a sense of security will be generated.

[0539] Ad element selection and optimization

[0540] The server selects the most effective ad content for each target based on the generated candidate list of ad elements. The selection is made using past ad performance data, real-time user data, and current user sentiment data. The selected ad elements are fine-tuned as the final ad content to enhance its appeal.

[0541] Ad serving

[0542] The server registers the selected advertising content in the distribution reservation system and sets a distribution schedule, which is planned to distribute advertisements at optimal times based on the user's online activity time and emotional data.

[0543] The terminal (user device) displays the appropriate advertisement delivered from the server the next time the user accesses the web. While the user is browsing a specific web page, the advertisement is displayed according to the emotional data.

[0544] Data collection and feedback

[0545] The device records user response data (number of clicks on ads, viewing time, purchase history, etc.) and sends it to the server. The server analyzes this response data and evaluates the effectiveness of the ads. Based on the evaluation results, the next ad generation process is updated to continuously improve ad performance.

[0546] Specific examples

[0547] For example, for a female user in her 30s, the following ads will be generated and delivered:

[0548] 1. The server collects user data of women in their 30s (e.g., they have children, they are interested in using a smartphone for the first time) and emotional data on "happiness."

[0549] 2. Based on this user data, the AI ​​model generates advertising elements (web commercials, images, copy) in upbeat tones depicting scenes of children starting to use smartphones.

[0550] 3. The server selects these advertising elements and fine-tunes them as advertising content.

[0551] 4. While the user is browsing the web, the device displays smartphone debut ads tailored to their "happiness" state.

[0552] 5. When a user clicks on an ad and views details, response data is collected and sent to the server at a later date.

[0553] 6. The server analyzes the response data and uses it in the next ad generation process.

[0554] Similarly, for male users in their 20s, targeted adaptive ads are generated that take into account their emotional data and are delivered at the appropriate time. This system further improves the accuracy and effectiveness of ad delivery.

[0555] The processing flow will be explained below.

[0556] Step 1:

[0557] The server collects user data through websites and applications, including gender, age, hobbies, preferences, internet browsing history, and purchase history. In addition, it obtains emotional information through the user's device camera and microphone, and, with the user's permission, collects facial expressions and voice tone.

[0558] Step 2:

[0559] The device captures the user's facial expressions and voice tone in real time and sends them to the emotion engine, which analyzes this data and identifies the user's emotional state. For example, if the user is smiling, it is judged to be "joy," and if the user is frowning, it is judged to be "stress."

[0560] Step 3:

[0561] The server stores the collected user data and emotion data in a secure database using encryption technology to ensure data integrity and security, and the database is indexed and managed for efficient future access.

[0562] Step 4:

[0563] The server extracts user data and emotion data from the stored database and performs pre-processing on the data, which includes removing incomplete data and noise, and standardizing the data, preparing it in a format suitable for input into the artificial intelligence model.

[0564] Step 5:

[0565] The AI ​​model receives the pre-processed data and generates optimal advertising elements for the target audience based on the user's gender, age, hobbies, preferences, internet browsing history, purchase history, and emotional state. These elements include web commercials, images, copy, appealing content, and featured talent.

[0566] Step 6:

[0567] The server then creates a candidate list of advertising content for each target based on the generated advertising elements. The candidate list includes multiple advertising elements suited to the user's current emotional state. For example, if the user is feeling "joyed," advertisements with a bright tone will be prioritized.

[0568] Step 7:

[0569] The server selects the most effective ad content from the list of candidates, using past ad performance data, real-time user data, and current user sentiment data. Ad elements that have performed particularly well in the past are likely to be selected.

[0570] Step 8:

[0571] The server then uses the selected ad content to fine-tune the targeted ad, making small design changes and copy adjustments to make the ad more appealing.

[0572] Step 9:

[0573] The server registers the optimized advertising content in the distribution reservation system and sets the distribution schedule, which is planned to display the advertisement at the most effective timing based on the user's online activity time and emotional data.

[0574] Step 10:

[0575] The next time the user accesses the web, the terminal (user device) will display an appropriate advertisement delivered from the server. For example, when the user is viewing a specific web page, an advertisement tailored to the user's emotional data will be displayed.

[0576] Step 11:

[0577] The device records the user's response to the advertisement. The recorded data includes the number of clicks on the advertisement, viewing time, purchase history, etc. These data are important elements for capturing the user's response in detail.

[0578] Step 12:

[0579] The server receives user response data sent from the device and performs detailed analysis, using statistical tools and machine learning algorithms to evaluate ad performance.

[0580] Step 13:

[0581] The server retrains the AI ​​model based on the analysis results, so that more optimal advertising elements are generated in the next ad generation process, thereby continuously improving the effectiveness of the ad.

[0582] In this way, the system of the present invention realizes highly accurate advertisement distribution that also takes into account the user's emotions.

[0583] Example 2

[0584] Next, a description will be given of Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the smart glasses 214 will be referred to as a "terminal."

[0585] Conventional ad delivery systems generate ad elements based only on basic information provided by users and deliver them to target users. This makes it difficult to deliver ads that take into account the user's current emotional state. As a result, the effectiveness of ads is not maximized, and there is a need to further improve the accuracy and effectiveness of ad delivery. Another issue is that ad response data is not sufficiently collected and the results are not reflected in the next ad generation process.

[0586] The specific processing by the specific processing unit 290 of the data processing device 12 in the second embodiment is realized by the following means.

[0587] In this invention, the server includes: means for collecting information and emotional information provided by a user; an artificial intelligence model for generating optimal advertising elements for a target using the collected information and emotional information; means for selecting and fine-tuning advertising content for each target based on the generated advertising elements; means for scheduling and delivering the selected and fine-tuned advertising content to a user terminal; means for collecting and analyzing user response data to the advertising content; and means for continuously updating and optimizing the artificial intelligence model using the analysis results. This makes it possible to generate and deliver target-adaptive advertisements that take into account the emotional state of the user, thereby further improving the accuracy and effectiveness of advertisement delivery.

[0588] "Information provided by the user" refers to basic information such as gender, age, hobbies and preferences, internet browsing history, and purchase history that the user provides through a website or application.

[0589] "Emotional information" is data about the user's emotional state obtained by analyzing facial expressions and vocal tones captured through the user's device camera and microphone.

[0590] An "artificial intelligence model" is an algorithm or system that generates optimal advertising elements for a target based on collected user and emotional information.

[0591] "Advertising elements" are the individual elements that make up advertising content, such as web content, images, copy, claims, and performers.

[0592] The "means for selecting and fine-tuning advertising content for each target" refers to a means for selecting the most effective advertising element for a specific target user based on the generated candidate list of advertising elements, and then fine-tuning the content.

[0593] "Scheduling and delivery means" refers to means for delivering selected and fine-tuned advertising content at appropriate times based on the user's online activity time and emotional data.

[0594] "Response data" refers to data relating to a user's response to an advertisement, such as the number of clicks, viewing time, and purchase history.

[0595] "Means for continuous updating and optimization" refers to means for continuously updating and optimizing the artificial intelligence model based on collected and analyzed reaction data.

[0596] MODE FOR CARRYING OUT THE INVENTION

[0597] The present invention provides a system that generates optimal advertising elements using basic information and emotion information provided by users and delivers them to target users. This system includes a server, a terminal, and a user, and is implemented based on the following steps:

[0598] 1. Collection of User Data

[0599] The server collects user information via websites and applications, including gender, age, hobbies and preferences, internet browsing history, and purchase history. With the user's permission, the server also uses the device's camera and microphone to analyze facial expressions and voice tone to collect emotional information. For example, if the user is smiling, the emotional information is recorded as "happy."

[0600] 2. Data preprocessing and sentiment analysis

[0601] The server stores the collected information in a secure database. After removing incomplete data and noise from the stored data and standardizing it, the emotional data is analyzed using an emotion engine. The emotion engine used in this process includes algorithms for facial expression analysis and voice analysis. For example, it can identify the user's emotional state, such as "happiness" or "anxiety," based on specific facial features.

[0602] 3. Artificial Intelligence Model for Ad Generation

[0603] The server inputs the preprocessed basic information and emotional information into the AI ​​model. For example, if the user is a woman in her 30s and in a "happy" emotional state, that information is input into the AI ​​model. This AI model uses the data to generate optimal advertising elements for each target, such as web content, images, copy, appealing content, and performers. As a specific example, if the user is a woman in her 30s and in a "happy" state, a bright-toned advertisement with the theme of her child's first smartphone will be generated.

[0604] 4. Selecting and optimizing advertising elements

[0605] Based on the generated list of ad element candidates, the server selects the most effective ad elements by utilizing historical ad performance data, real-time user data, and sentiment data. The selected ad elements are then further fine-tuned to make them more visually and content-oriented. For example, fine-tuning may be done by changing the color tone of the web content or the font of the text.

[0606] 5. Delivery of advertisements

[0607] The server registers the selected and fine-tuned advertising content in the distribution reservation system and sets a distribution schedule based on the user's online activity time and emotional data. The next time the user browses the web, the device displays the distributed advertisement. For example, if the target user is viewing a web page in a "happy" emotional state, an appropriately selected smartphone debut advertisement will be displayed.

[0608] 6. Data Collection and Feedback

[0609] The device records user response data to advertisements (number of clicks, viewing time, purchase history, etc.) and sends it to the server. The server analyzes this response data to evaluate the effectiveness of the advertisements. The evaluation results are reflected in the next advertisement generation process. This enables continuous updating and optimization of the AI ​​model and advertisement content.

[0610] Specific examples

[0611] For example, for a female user in her 30s, the following ads will be generated and delivered:

[0612] 1. The server collects user data of women in their 30s (e.g., they have children, they are interested in using a smartphone for the first time) and emotional data on "happiness."

[0613] 2. Based on this user data, the AI ​​model generates advertising elements (web commercials, images, copy) in upbeat tones depicting scenes of children starting to use smartphones.

[0614] 3. The server selects these advertising elements and fine-tunes them as advertising content.

[0615] 4. While the user is browsing the web, the device displays smartphone debut ads tailored to their "happiness" state.

[0616] 5. When a user clicks on an ad and views details, response data is collected and sent to the server at a later date.

[0617] 6. The server analyzes the response data and uses it in the next ad generation process.

[0618] Prompt Sentence Examples

[0619] "We have a user who is a woman in her 30s with a child. She is currently in a 'happy' emotional state. Please generate optimal advertising elements for this user regarding their smartphone debut."

[0620] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0621] Step 1:

[0622] The server collects user information via websites and applications. Input data includes gender, age, hobbies, preferences, internet browsing history, and purchase history provided by the user. The server stores this data in a secure database. With the user's permission, the server also uses the device camera and microphone to collect facial expressions and voice tones. For example, if the user is smiling, the server records the emotional information as "happy." The output data includes basic information and emotional information.

[0623] Step 2:

[0624] The server performs preprocessing on the data stored in a secure database. The input data includes the basic information and emotional information collected in step 1. Specific operations include removing incomplete data and noise, and standardizing the data. In parallel, the emotional information is analyzed using an emotional engine. For example, it uses facial expression analysis and voice analysis algorithms to identify the user's emotional state as "happy" or "anxious." The output data is the preprocessed basic information and analyzed emotional information.

[0625] Step 3:

[0626] The server inputs the preprocessed basic information and emotional information into the AI ​​model. Input data includes gender, age, hobbies and preferences, browsing history, purchase history, and analyzed emotional data. The AI ​​model generates optimal advertising elements based on this data. Specifically, it generates web content, images, copy, appealing content, and performers. For example, if a female user in her 30s is in a "happy" emotional state, it generates a bright-toned advertisement themed around her child's smartphone debut. The output data is a list of the generated advertising elements.

[0627] Step 4:

[0628] The server selects optimal advertising content for each target based on a candidate list of advertising elements generated by an AI model. The input data includes the list of generated advertising elements, past advertising performance data, current user data, and emotional data. Specific operations include fine-tuning the selected advertising elements, such as changing color tones and adjusting text fonts. The output data is optimized advertising content.

[0629] Step 5:

[0630] The server registers the selected and fine-tuned advertising content in the distribution reservation system and sets a distribution schedule. Input data includes the optimized advertising content, the user's online activity time, and emotional data. Specific operations involve planning the optimal timing of ad distribution based on the user's online activity time and emotional data. The next time the user browses the web, the device displays the distributed advertisement. For example, if the user is browsing the web in a "happy" emotional state, a smartphone debut advertisement will be displayed. The output data is an advertising distribution schedule.

[0631] Step 6:

[0632] The device records user response data to advertisements. Input data includes user behavior data (number of clicks, viewing time, purchase history, etc.). This response data is sent to the server. The server analyzes this data and evaluates the effectiveness of the advertisement. Specifically, it evaluates the performance of the advertisement based on the response data, and updates and optimizes the AI ​​model based on the results. The output data are the analysis results and a continuously updated AI model.

[0633] (Application example 2)

[0634] Next, a description will be given of Application Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the smart glasses 214 will be referred to as a "terminal."

[0635] Current ad delivery systems generate and deliver targeted ads based on data such as a user's basic information and browsing history, but they are unable to consider the user's emotional state. This makes it difficult to deliver ads that are best suited to the user's current emotional state, resulting in a lack of maximum advertising effectiveness.

[0636] The identification process by the identification processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means. In this invention, the server includes: means for collecting information and emotional data provided by users; an artificial intelligence model for generating optimal advertising elements for targets using the collected information and emotional data; means for selecting advertising content for each target based on the generated advertising elements; means for delivering the selected advertising content to user terminals; means for analyzing user response data to the advertising content; and means for updating the artificial intelligence model using the analysis results. This makes it possible to generate and deliver advertisements optimal for the user's current emotional state in real time.

[0637] "User-provided information" refers to data voluntarily provided by users, such as gender, age, hobbies and preferences, internet browsing history, and purchase history, as well as data including facial expressions and tone of voice collected to identify the user's emotional state.

[0638] "Emotion data" is data that indicates the user's current feelings and state, obtained by analyzing the user's facial expressions and voice tones.

[0639] The "artificial intelligence model" is a machine learning model that uses collected user data and emotional data to generate optimal advertising elements for each target.

[0640] "Advertising elements" are multiple elements that make up advertising content, such as visual media, still images, text, appeals, and characters.

[0641] "Advertising content" refers to the final advertising material selected from the generated advertising elements and delivered to the user.

[0642] "Response data" refers to data on the user's response to an advertisement, such as the number of clicks, viewing time, and purchase history.

[0643] "Means for updating" is a function for improving and optimizing the artificial intelligence model using collected user response data.

[0644] This invention is a system for displaying optimal advertisements using user emotion data. This system is realized mainly by a server, a terminal, and a process for collecting and analyzing user data. The implementation configuration and processing procedure of the system are described in detail below.

[0645] User Data Collection

[0646] The server collects information provided by users when they use websites and applications. Collected information includes gender, age, hobbies and preferences, internet browsing history, purchase history, and emotional data (facial expressions and voice tone) captured using the device's camera and microphone. The server captures facial expressions using OpenCV and recognizes emotions using deep learning libraries such as TensorFlow or Keras.

[0647] Data preprocessing and sentiment analysis

[0648] The collected user data is stored in a secure database on the server. Data preprocessing involves removing incomplete data and noise and standardizing the data. At the same time, an emotion recognition engine analyzes the user's facial expressions and voice tone to identify their current state of mind and emotion. This allows it to identify specific emotional states such as "happy," "excited," or "anxious."

[0649] Artificial intelligence models for ad generation

[0650] The server runs a generative AI model using the preprocessed basic data and emotion data. The generative AI model generates optimal advertising elements for each target audience. These advertising elements include visual media (e.g., web commercials), still images, text, advertising content, and characters. By utilizing the emotion data, an advertisement that best suits the user's current emotional state is generated.

[0651] Ad element selection and optimization

[0652] From the generated ad elements, the most effective ad content is selected based on historical ad performance data, real-time user data, and current user sentiment data. The selected ad elements are then fine-tuned into the final ad content. The server runs tools and algorithms to do this.

[0653] Ad serving

[0654] The server registers the selected advertising content in the distribution reservation system and sets the distribution schedule. Based on the user's online activity time and emotional data, the advertisements are planned to be distributed at the optimal timing. The user's device displays the advertisements distributed from the server the next time the user accesses the web. Appropriate advertisements are displayed to the user via a simple browser or application.

[0655] Data collection and feedback

[0656] The user's device records response data to the advertisement (number of clicks, viewing time, purchase history, etc.) and sends it to the server. The server analyzes this response data and evaluates the effectiveness of the advertisement. Based on the evaluation results, the generative AI model is updated to continuously improve the performance of the advertisement.

[0657] Specific examples

[0658] For example, if a female user in her 30s is recognized as being in a "happy" state, a cheerful advertisement about her child's first smartphone is generated. This advertisement is displayed on the user's smartphone, and response data is collected when the user clicks on the advertisement.

[0659] Example prompt for a generative AI model:

[0660] If the user is in a "happy" state, is a woman in her 30s, and is interested in technology and children, generate a "bright-toned ad related to children's smartphone debut."

[0661] If the user is in an "anxious" state, is a male in his 20s, and is concerned about security, an "advertisement offering points that emphasizes a sense of security" will be generated.

[0662] This makes it possible to generate and deliver optimal advertisements in real time based on the user's emotional state and personal data.

[0663] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[0664] Step 1:

[0665] User Data Collection

[0666] The server collects information provided by users when they use websites and applications. Inputs include gender, age, hobbies and preferences, internet browsing history, purchase history, and emotional data (facial expressions and voice tone) captured using the device camera and microphone. The server captures facial expressions using OpenCV and recognizes emotions using deep learning libraries such as TensorFlow or Keras. As output, user data and emotional data are stored in a secure database.

[0667] Step 2:

[0668] Data preprocessing and sentiment analysis

[0669] The server performs preprocessing by removing incomplete data and noise and standardizing the data. The input is the user data and emotion data collected in step 1, and the output is clear data after preprocessing. At the same time, the emotion recognition engine receives the user's facial expressions and voice tone as input and analyzes them. The output of the analysis is the user's emotional state (e.g., "happy," "excited," "anxious," etc.).

[0670] Step 3:

[0671] Artificial intelligence models for ad generation

[0672] The server runs the generative AI model using the clear data and emotion data that have been preprocessed. The input is the clear data and emotion data from the previous step, and the output is the optimal advertising elements (visual media, still images, text, appeal content, and characters) for each target. Specifically, the generative AI model generates multiple advertising elements and combines them based on the prompt text.

[0673] Step 4:

[0674] Ad element selection and optimization

[0675] The server selects the most effective ad content from the generated ad elements based on historical ad performance data, real-time user data, and current user sentiment data. The inputs are the generated ad elements, historical performance data, and real-time data. The output is optimized ad content. The server runs an algorithm to do this and fine-tunes the ad content.

[0676] Step 5:

[0677] Ad serving

[0678] The server registers the selected advertising content in the distribution reservation system and sets the distribution schedule. The input is the optimized advertising content, and the output is the advertisement delivered to the user's device. Specifically, the server determines the optimal timing based on the user's online activity time and emotional data, and instructs the device to display the advertisement the next time the user accesses the web.

[0679] Step 6:

[0680] Data collection and feedback

[0681] The user's device records response data to the ad (number of clicks, viewing time, purchase history, etc.) and sends it to the server. The input is the user's response data to the ad, and the output is feedback data recorded on the server. The server analyzes this feedback data and updates and optimizes the generative AI model. Specifically, the server analyzes the feedback data and uses it in the next ad generation process.

[0682] The specific processing unit 290 transmits the result of the specific processing to the smart glasses 214. In the smart glasses 214, the control unit 46A causes the speaker 240 to output the result of the specific processing. The microphone 238 acquires audio indicating a user input regarding the result of the specific processing. The control unit 46A transmits audio data indicating the user input acquired by the microphone 238 to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the audio data.

[0683] The data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of the data generation model 58 is ChatGPT (Internet Search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search <url: https: gemini.google.com ?hl="ja">) and other generation AIs. The data generation model 58 is obtained by performing deep learning on a neural network. A prompt including an instruction is input to the data generation model 58, and inference data such as voice data indicating voice, text data indicating text, and image data indicating an image is also input. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt, and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[0684] In the above embodiment, an example in which the specific processing is performed by the data processing device 12 has been given, but the technology of the present disclosure is not limited to this, and the specific processing may be performed by the smart glasses 214.

[0685] [Third embodiment]

[0686] FIG. 5 shows an example of the configuration of a data processing system 310 according to the third embodiment.

[0687] 5, the data processing system 310 includes the data processing device 12 and a headset terminal 314. An example of the data processing device 12 is a server.

[0688] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 is an example of a "computer" according to the technology of the present disclosure. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, the RAM 30, and the storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0689] The headset type terminal 314 includes a computer 36, a microphone 238, a speaker 240, a camera 42, a communication I / F 44, and a display 343. The computer 36 includes a processor 46, a RAM 48, and a storage 50. The processor 46, the RAM 48, and the storage 50 are connected to a bus 52. The microphone 238, the speaker 240, the camera 42, and the display 343 are also connected to the bus 52.

[0690] The microphone 238 receives instructions and the like from the user 20 by receiving voice uttered by the user 20. The microphone 238 captures the voice uttered by the user 20, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio in accordance with instructions from the processor 46.

[0691] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an imaging element such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the surroundings of user 20 (for example, an imaging range defined by an angle of view equivalent to the field of vision of a typical healthy person).

[0692] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 are responsible for the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is carried out in a secure state.

[0693] Fig. 6 shows an example of the main functions of the data processing device 12 and the headset type terminal 314. As shown in Fig. 6, in the data processing device 12, a specific process is performed by the processor 28. A specific process program 56 is stored in the storage 32.

[0694] The specific processing program 56 is an example of a "program" according to the technology of the present disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[0695] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[0696] In the headset type terminal 314, a reception output process is performed by the processor 46. A reception output program 60 is stored in the storage 50. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output process is realized by the processor 46 operating as the control unit 46A in accordance with the reception output program 60 executed on the RAM 48.

[0697] Next, a description will be given of the identification process performed by the identification processing unit 290 of the data processing device 12. In the following description, the data processing device 12 will be referred to as the "server" and the headset type terminal 314 will be referred to as the "terminal."

[0698] MODE FOR CARRYING OUT THE INVENTION

[0699] The present invention is a system for displaying optimal advertisements to users, and is implemented by the following main steps: The following describes in detail how the server, terminal, and user are involved.

[0700] User Data Collection

[0701] The server collects user data through websites and applications, including a wide range of user-provided information such as gender, age, hobbies, preferences, internet browsing history, purchase history, etc. The server stores this user data in a secure database, preparing it for later input into an artificial intelligence model.

[0702] Data Preprocessing

[0703] The server cleanses (pre-processes) the collected data, specifically removing incomplete data and noise and converting it into a unified format. This pre-processing ensures that the AI ​​model operates with high accuracy.

[0704] Artificial intelligence models for ad generation

[0705] The AI ​​model takes the pre-processed data as input and generates optimal advertising elements for each target audience, including web commercials, images, copy, appealing content, and featured talent.

[0706] For example, for data on female users in their 30s, who often have children, ads with a theme of smartphone debut are generated, while for data on male users in their 20s, ads emphasizing the benefits of point redemption are generated.

[0707] Ad element selection and optimization

[0708] The server selects the most effective ad content for each target based on the generated list of ad element candidates. This selection process utilizes past ad performance data and real-time user data. During the selection process, the selected ad elements are fine-tuned to ensure their effectiveness as the final ad content.

[0709] Ad serving

[0710] The server registers the selected advertising content in the distribution reservation system and sets a specific distribution schedule, planning to display the advertisement at the most suitable time for the target user.

[0711] The terminal (user device) displays the appropriate advertisement delivered from the server the next time the user accesses the web. For example, when a user is viewing a specific web page, an optimally targeted advertisement is displayed at the set timing.

[0712] Data collection and feedback

[0713] The device records user response data (number of clicks on ads, viewing time, purchase history, etc.) and sends it to the server. The server analyzes this response data and evaluates the effectiveness of the ads. This is reflected in the next ad generation process to continuously improve ad performance.

[0714] Specific examples

[0715] For example, for a female user in her 30s, the following ads will be generated and delivered:

[0716] 1. The server collects user data of women in their 30s (e.g., they have children and are interested in using smartphones for the first time).

[0717] 2. Based on this user data, the AI ​​model generates advertising elements (web commercials, images, copy) depicting scenes of children starting to use smartphones.

[0718] 3. The server selects these advertising elements and fine-tunes them to create optimal content.

[0719] 4. The device will display targeted ads about smartphone debuts while the user is browsing the web.

[0720] 5. When a user clicks on an ad and views details, response data is collected and sent to the server at a later date.

[0721] 6. The server analyzes the response data and uses it in the next ad generation process.

[0722] Similarly, for male users in their 20s, the system generates and delivers optimally targeted ads in a similar manner, improving the accuracy and effectiveness of ad delivery.

[0723] The processing flow will be explained below.

[0724] Step 1:

[0725] The server collects user data through websites and applications, including information provided by users such as gender, age, interests, and preferences, as well as browsing and purchasing history. This data is collected by users through web forms and account settings, and automatically through cookies and tracking pixels.

[0726] Step 2:

[0727] The server stores the collected user data in a secure database, using encryption technology to ensure data integrity and security, and the database is indexed for quick access later.

[0728] Step 3:

[0729] The server retrieves user data from the stored database and performs pre-processing on the data, which includes cleaning the data (removing incomplete data and noise) and standardizing the data (converting it into a unified format), preparing the data format for input into the artificial intelligence model.

[0730] Step 4:

[0731] The AI ​​model receives the pre-processed data and generates optimal advertising elements for each target. Specifically, the algorithm automatically generates the web commercial, images, copy, appeal content, and talent for the ad based on gender, age, and hobbies and preferences.

[0732] Step 5:

[0733] The server generates a candidate list of ad content based on the generated ad elements, which may include multiple ad elements for each target, such as multiple versions with different copy or visual elements.

[0734] Step 6:

[0735] The server selects the most effective ad content from the list of candidates, using historical ad performance data and real-time user data. For example, it prioritizes ad elements that have historically generated high click-through rates.

[0736] Step 7:

[0737] The server then uses the selected ad content to fine-tune the targeted ads, which can include small design changes or copy modifications, making the ads more appealing.

[0738] Step 8:

[0739] The server registers the optimized advertising content in the distribution reservation system and sets a distribution schedule, specifically specifying the timing of advertisement distribution based on the user's online activity time.

[0740] Step 9:

[0741] The next time the user accesses the web, the terminal (user device) displays the appropriate advertisement delivered from the server. For example, an advertisement can be displayed at a set time while the user is browsing a specific site.

[0742] Step 10:

[0743] The device records how users respond to ads, including the number of clicks, viewing time, and eventual purchases.

[0744] Step 11:

[0745] The server receives and analyzes user response data sent from the device, using statistical tools and machine learning algorithms to evaluate ad performance.

[0746] Step 12:

[0747] The server retrains the artificial intelligence model based on the analysis results, thereby updating the model so that it generates more optimal ad elements the next time an ad is generated.

[0748] In this way, the system of the present invention can provide highly accurate and effective advertisements to a wide range of targets.

[0749] Example 1

[0750] Next, a description will be given of Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the headset type terminal 314 will be referred to as a "terminal."

[0751] Modern advertising systems are required to display optimal advertisements based on individual user information. However, existing methods lack sufficient data preprocessing, selection of advertising elements, and analysis of user responses, resulting in reduced advertising effectiveness. Furthermore, there is a lack of mechanisms for efficiently collecting user response data and continuously improving advertising effectiveness. This creates the problem of making it difficult to consistently display optimal advertisements to users.

[0752] The specific processing by the specific processing unit 290 of the data processing device 12 in the first embodiment is realized by the following means.

[0753] In this invention, the server includes means for collecting information provided by users, means for preprocessing the collected information, an artificial intelligence model for generating optimal advertising elements for targets using the preprocessed information, means for selecting advertising content for each target based on the generated advertising elements, means for delivering the selected advertising content to user terminals, means for collecting user response data to the advertising content, means for analyzing the collected response data, and means for updating the artificial intelligence model using the analysis results, thereby making it possible to always deliver optimal advertising to users and continuously improve its effectiveness.

[0754] "Information provided by users" refers to data such as gender, age, hobbies and preferences, internet browsing history, and purchase history that users provide through websites and applications.

[0755] "Preprocessing" is the process of removing incomplete data and noise from collected information and converting it into a unified format.

[0756] An "artificial intelligence model" is a collection of algorithms that learn from large amounts of data, recognize patterns, and generate advertising elements that are optimal for specific targets.

[0757] "Advertising Elements" refers to the various elements that make up an advertisement, such as digital content, visual advertisements, text advertisements, promotional content, and performers.

[0758] "Selection" refers to the process of selecting the most effective advertising content for the target from among the multiple advertising elements generated.

[0759] "Delivery" refers to the act of sending selected advertising content to a user terminal.

[0760] A "user terminal" is a device used by a user, such as a computer, smartphone, or tablet.

[0761] "Response data" refers to data such as the number of clicks a user makes on an advertisement, viewing time, and purchase history.

[0762] "Collecting" refers to the act of gathering user response data and storing it for analysis.

[0763] "Analysis" is the process of analyzing collected response data using statistical methods and machine learning techniques to evaluate the effectiveness of advertising.

[0764] "Update" is the process of improving the artificial intelligence model based on the analysis results and reflecting them in the next ad generation.

[0765] This invention provides a system for displaying optimal advertisements to users. This system is made up of three main components: a server, a terminal, and a user. The following describes in detail an embodiment of this invention.

[0766] The server first collects information provided by users through websites and applications, including gender, age, hobbies and preferences, internet browsing history, purchase history, etc. The collected data is then stored in a secure database.

[0767] The server then preprocesses the collected data. Specifically, preprocessing involves removing incomplete data and noise, converting data into a unified format, and unifying date data stored in different formats. It also removes records containing null values.

[0768] Once preprocessed, the data is input into an artificial intelligence model. This model learns from large amounts of data and generates optimal advertising elements for each target. The generated advertising elements include digital content, visual ads, text ads, promotional content, and performers. For example, the following prompt sentence is used to generate advertising elements: "Please generate an advertisement for a woman in her 30s with children about her smartphone debut."

[0769] The server then selects ad content based on the generated ad elements. This selection process takes into account past ad performance data and real-time user data. During the selection process, the server fine-tunes the generated ad elements to create the most effective ad content.

[0770] Once the selection and fine-tuning of advertising content is complete, the server delivers it to the user's device. The delivery schedule is planned to display the advertisement at the optimal time for the target user. The user's device then displays the advertisement delivered by the server the next time the user accesses the web.

[0771] The device also collects user response data to advertising content (number of clicks, viewing time, purchase history, etc.). This response data is sent to the server and analyzed by the server. The analysis results are used to evaluate the effectiveness of the advertisement and update the artificial intelligence model based on the results. This allows for more accurate advertisements to be generated in the next advertisement generation process.

[0772] For example, the following process is performed for a female user in her 30s:

[0773] 1. The server collects user data of a woman in her 30s (who has children and is interested in using a smartphone for the first time).

[0774] 2. The server preprocesses the collected data and converts it into a unified format.

[0775] 3. Based on this user data, the AI ​​model generates advertisements depicting scenes of children starting to use smartphones.

[0776] 4. The server selects and fine-tunes the generated ad elements.

[0777] 5. The device displays advertisements at the optimal time to users browsing news sites.

[0778] 6. The user clicks on the advertisement, and the response data is collected by the terminal and sent to the server.

[0779] 7. The server analyzes the response data and updates the artificial intelligence model based on the results.

[0780] In this way, the system can continually deliver the most appropriate ads to users, and continuously improve their accuracy and effectiveness.

[0781] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0782] Step 1: Collect user data

[0783] The server collects user data through websites and applications. Input includes information provided by users such as gender, age, hobbies and preferences, internet browsing history, and purchase history. This data is stored in a secure database. Specifically, the server records the pages the user views, the links they click, and the products they purchase.

[0784] Step 2: Preprocessing the data

[0785] The server preprocesses the collected user data. The input is the raw data collected in the previous step. Specific data processing involves removing incomplete data and noise and converting it into a unified format. This preprocessing step unifies date data stored in different formats, for example. Records containing NULL values ​​are also removed, resulting in cleaned data as the output.

[0786] Step 3: Running the AI ​​model to generate ads

[0787] The AI ​​model on the server receives the preprocessed data as input and generates optimal advertising elements. The prompt is "Please generate an advertisement for a woman in her 30s with children about her smartphone debut." Specifically, the model extracts patterns from the input data and generates advertising elements (digital content, visual ads, text ads, etc.) for each target as output.

[0788] Step 4: Select and optimize advertising elements

[0789] The server selects optimal advertising content from among the advertising elements generated by the AI ​​model. It uses the generated advertising elements, past advertising performance data, and real-time user data as input. Specifically, it uses statistical analysis and machine learning algorithms to evaluate the advertising elements and selects optimal advertising content as output. It also fine-tunes the selected advertising elements.

[0790] Step 5: Serving Ads

[0791] The server registers the selected advertising content in the distribution reservation system and sets a distribution schedule. The selected advertising content and timing data for its target users are used as input. Specifically, the server schedules the advertisement so that it is displayed at the optimal time for the target users. The output is the advertising content for which distribution reservation has been completed. The terminal then displays the advertisement while the user is browsing the web.

[0792] Step 6: Data collection and feedback

[0793] The terminal records user response data to advertisements and sends it to the server. Inputs include the number of clicks on the advertisements, viewing time, and purchase history. Specific data processing involves organizing this data and sending it to the server. The server analyzes this response data. The response data sent in the previous step is used as input. The output is an analysis result indicating the effectiveness of the advertisement. Based on this analysis result, the server updates the artificial intelligence model and uses it in the next advertisement generation process. This continuously improves the accuracy and effectiveness of advertisements.

[0794] (Application example 1)

[0795] Next, a description will be given of Application Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the headset type terminal 314 will be referred to as a "terminal."

[0796] Conventional ad delivery systems have issues with the insufficient integration of user data collection, ad element generation, delivery, and effectiveness analysis, making it difficult to display optimal ads in real time. Another problem is that ad optimization within smart devices is insufficient, resulting in a lack of improvement in the user experience.

[0797] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 1 is realized by the following means.

[0798] In this invention, the server includes: means for collecting information provided by users; an artificial intelligence model for generating optimal advertising elements for targets using the collected information; means for selecting advertising content for each target based on the generated advertising elements; means for delivering the selected advertising content to user terminals; means for analyzing user response data to the advertising content; means for updating the artificial intelligence model using the analysis results; a processor for generating and optimizing advertising elements within a smart device; and an output device for displaying the advertisements generated by the processor. This makes it possible to display optimal advertisements to users in real time and maximize the effectiveness of the advertisements.

[0799] Definition of Terms

[0800] "User-provided information" refers to personal information, internet browsing history, purchase history, location information, and application usage history collected voluntarily or through the user's activity.

[0801] An "artificial intelligence model" is a machine learning algorithm that performs data analysis based on collected user information and generates optimal advertising elements for each target.

[0802] "Advertising elements" are elements that make up the content of an advertisement, including web commercials, images, copy, appealing content, featured talent, and advertising units displayed within user terminal applications.

[0803] "Advertising content" is a combination of advertising elements generated and optimized by an artificial intelligence model.

[0804] A "user terminal" is a device used by a user, such as a smartphone, tablet, PC, or smart device.

[0805] "Response data" is data that records the actions and responses (number of clicks, viewing time, purchase history, etc.) that users show to advertisements.

[0806] "Processor" means a central processing unit for generating and optimizing advertising elements within a smart device.

[0807] "Output device" means a display or screen for displaying advertisements generated on a smart device to a user.

[0808] "Application usage history" is data that records the usage of applications used by a user within a smart device.

[0809] This invention is a system that generates and displays optimized advertisements in real time within smart devices. This system collects various information provided by users, uses an artificial intelligence model to generate, select, and deliver optimal advertising elements to the target audience, and also includes a process for providing feedback based on user responses. Each element is described in detail below.

[0810] System configuration and program description

[0811] 1. Hardware Configuration

[0812] The system consists of the following hardware:

[0813] Server: Responsible for data collection, preprocessing, training of AI models, generation of advertising elements, and collection and analysis of user response data.

[0814] User terminal: Refers to smartphones, tablets, personal computers, smart devices, etc., used to display advertisements and collect user response data.

[0815] Processor: A central processing unit for generating and optimizing advertising elements within a smart device.

[0816] Output Device: A display or screen for displaying the generated advertisement to the user.

[0817] 2. Software Configuration

[0818] The system consists of the following software:

[0819] Data collection module: Collects the user's gender, age, hobbies and preferences, internet browsing history, purchase history, location information, and application usage history.

[0820] Data preprocessing module: Cleanses and normalizes the collected data and converts it into a format suitable for AI models.

[0821] AI model: A machine learning algorithm that generates optimal advertising elements for each target based on collected data. It uses libraries such as scikit-learn.

[0822] Ad element generation module: Runs the AI ​​model to generate ad elements.

[0823] Advertisement selection module: Selects the most suitable content from the generated advertising elements.

[0824] Advertisement delivery module: delivers optimized advertising content to user terminals.

[0825] Reaction data collection module: collects user reaction data and provides feedback.

[0826] Advertisement display module: displays advertisements on the output device of the user terminal.

[0827] Data processing flow and specific examples

[0828] 1. Collection of User Data

[0829] The server collects information from the user's device, such as gender, age, hobbies, preferences, internet browsing history, purchase history, location information, and application usage history. For example, for a female user in her 30s, childcare-related browsing history and purchase history are collected from her smartphone history.

[0830] 2. Data Preprocessing

[0831] The server cleanses the collected data, imputes missing data, and normalizes it, using standard data preprocessing libraries pandas and scikit-learn's StandardScaler.

[0832] 3. Ad generation

[0833] An AI model (e.g., RandomForestClassifier) ​​installed on the server runs and generates advertising elements based on the preprocessed data. For example, if there is a lot of browsing history related to childcare, advertisements for baby products will be generated.

[0834] 4. Ad selection

[0835] The server selects the best ad element from the multiple ad elements generated based on past performance data. The ad selection algorithm uses A / B testing techniques.

[0836] 5. Delivery of advertisements

[0837] The server then delivers the selected advertisements to user devices such as smartphones in real time, and they are displayed when the user opens a specific application or web page.

[0838] 6. Collecting user response data and providing feedback

[0839] The server collects response data (number of clicks, viewing time, purchase history, etc.) from the user terminal to the advertisement and provides feedback for generating the next advertisement.

[0840] Prompt Sentence Examples

[0841] Design a system that collects user data and uses AI models to generate and display optimal ads. Specifically, the system generates optimal ads based on the user's age, gender, hobbies, preferences, browsing history, purchase history, etc., and provides feedback on the effectiveness of the ads.

[0842] This makes it possible to deliver optimal ads to users in real time and maximize their effectiveness.The system is designed to improve the accuracy and effectiveness of ad delivery and enhance the user experience.

[0843] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0844] Program processing steps

[0845] Step 1:

[0846] The server collects information provided by the user's device. Specifically, it acquires the user's gender, age, hobbies and preferences, internet browsing history, purchase history, location information, and application usage history. The input data is these user attributes and behavioral data, and the output is the collected dataset.

[0847] Step 2:

[0848] The server preprocesses the collected data. Specifically, it cleanses the data (complements incomplete data and removes noise) and normalizes it. This process uses pandas and scikit-learn's StandardScaler. The input data is the dataset collected in step 1, and the output is a clean dataset after preprocessing.

[0849] Step 3:

[0850] The server runs an artificial intelligence model to generate advertising elements using the preprocessed data. For example, it uses RandomForestClassifier to perform data analysis. The input data is the preprocessed dataset, and the output is the generated advertising elements.

[0851] Step 4:

[0852] The server selects the optimal advertising content from the generated advertising elements. It determines the optimal content by verifying past performance data and real-time user data using A / B testing methods. The input data are multiple advertising elements and their performance metrics, and the output is the selected advertising content.

[0853] Step 5:

[0854] The server delivers the selected advertising content to the user device in real time, and the content is displayed when the user opens a specific application or web page. The input data is the selected advertising content, and the output is the advertisement displayed on the user device.

[0855] Step 6:

[0856] Users respond to displayed ads by clicking or viewing them. User response data (number of clicks, viewing time, purchase history, etc.) is collected. The input data is user behavior data, and the output is the collected response data.

[0857] Step 7:

[0858] The server analyzes the collected response data and updates the AI ​​model based on the results. This feedback loop optimizes the next ad generation process. The input data is the collected response data, and the output is the updated AI model.

[0859] Furthermore, an emotion engine that estimates the user's emotion may be further combined. That is, the identification processing unit 290 may estimate the user's emotion using the emotion identification model 59, and perform identification processing using the user's emotion.

[0860] MODE FOR CARRYING OUT THE INVENTION

[0861] This invention is a system that collects and analyzes information, including user emotions, and displays optimal advertisements, and is implemented in the following steps. The following describes in detail how the server, terminal, and user are involved.

[0862] User Data Collection

[0863] The server collects user data through websites and applications. The collected data includes user-provided information such as gender, age, hobbies, preferences, internet browsing history, and purchase history. In addition, emotional information is collected through the user's device camera and microphone. With the user's permission, emotion recognition is performed by analyzing facial expressions and voice tone.

[0864] Data preprocessing and sentiment analysis

[0865] The server stores the collected user data in a secure database and performs preprocessing on the data. This includes removing incomplete data and noise, and standardizing the data. In parallel, the emotion engine analyzes the user's emotion data to identify their current state of mind. For example, facial expression and voice analysis determine whether the user is in a state of "happy," "excited," or "anxious."

[0866] Artificial intelligence models for ad generation

[0867] The AI ​​model generates optimal advertising elements for each target based on collected and pre-processed basic data and emotional data. These elements include web commercials, images, copy, appealing content, and featured talent. By incorporating emotional data, the model generates an ad that best suits the user's current mood.

[0868] For example, if a female user in her 30s is perceived as being in a "happy" state, a bright-toned ad about her child's first smartphone will be generated. On the other hand, if a male user in his 20s is perceived as being in an "anxious" state, a point-reward ad emphasizing a sense of security will be generated.

[0869] Ad element selection and optimization

[0870] The server selects the most effective ad content for each target based on the generated candidate list of ad elements. The selection is made using past ad performance data, real-time user data, and current user sentiment data. The selected ad elements are fine-tuned as the final ad content to enhance its appeal.

[0871] Ad serving

[0872] The server registers the selected advertising content in the distribution reservation system and sets a distribution schedule, which is planned to distribute advertisements at optimal times based on the user's online activity time and emotional data.

[0873] The terminal (user device) displays the appropriate advertisement delivered from the server the next time the user accesses the web. While the user is browsing a specific web page, the advertisement is displayed according to the emotional data.

[0874] Data collection and feedback

[0875] The device records user response data (number of clicks on ads, viewing time, purchase history, etc.) and sends it to the server. The server analyzes this response data and evaluates the effectiveness of the ads. Based on the evaluation results, the next ad generation process is updated to continuously improve ad performance.

[0876] Specific examples

[0877] For example, for a female user in her 30s, the following ads will be generated and delivered:

[0878] 1. The server collects user data of women in their 30s (e.g., they have children, they are interested in using a smartphone for the first time) and emotional data on "happiness."

[0879] 2. Based on this user data, the AI ​​model generates advertising elements (web commercials, images, copy) in upbeat tones depicting scenes of children starting to use smartphones.

[0880] 3. The server selects these advertising elements and fine-tunes them as advertising content.

[0881] 4. While the user is browsing the web, the device displays smartphone debut ads tailored to their "happiness" state.

[0882] 5. When a user clicks on an ad and views details, response data is collected and sent to the server at a later date.

[0883] 6. The server analyzes the response data and uses it in the next ad generation process.

[0884] Similarly, for male users in their 20s, targeted adaptive ads are generated that take into account their emotional data and are delivered at the appropriate time. This system further improves the accuracy and effectiveness of ad delivery.

[0885] The processing flow will be explained below.

[0886] Step 1:

[0887] The server collects user data through websites and applications, including gender, age, hobbies, preferences, internet browsing history, and purchase history. In addition, it obtains emotional information through the user's device camera and microphone, and, with the user's permission, collects facial expressions and voice tone.

[0888] Step 2:

[0889] The device captures the user's facial expressions and voice tone in real time and sends them to the emotion engine, which analyzes this data and identifies the user's emotional state. For example, if the user is smiling, it is judged to be "joy," and if the user is frowning, it is judged to be "stress."

[0890] Step 3:

[0891] The server stores the collected user data and emotion data in a secure database using encryption technology to ensure data integrity and security, and the database is indexed and managed for efficient future access.

[0892] Step 4:

[0893] The server extracts user data and emotion data from the stored database and performs pre-processing on the data, which includes removing incomplete data and noise, and standardizing the data, preparing it in a format suitable for input into the artificial intelligence model.

[0894] Step 5:

[0895] The AI ​​model receives the pre-processed data and generates optimal advertising elements for the target audience based on the user's gender, age, hobbies, preferences, internet browsing history, purchase history, and emotional state. These elements include web commercials, images, copy, appealing content, and featured talent.

[0896] Step 6:

[0897] The server then creates a candidate list of advertising content for each target based on the generated advertising elements. The candidate list includes multiple advertising elements suited to the user's current emotional state. For example, if the user is feeling "joyed," advertisements with a bright tone will be prioritized.

[0898] Step 7:

[0899] The server selects the most effective ad content from the list of candidates, using past ad performance data, real-time user data, and current user sentiment data. Ad elements that have performed particularly well in the past are likely to be selected.

[0900] Step 8:

[0901] The server then uses the selected ad content to fine-tune the targeted ad, making small design changes and copy adjustments to make the ad more appealing.

[0902] Step 9:

[0903] The server registers the optimized advertising content in the distribution reservation system and sets the distribution schedule, which is planned to display the advertisement at the most effective timing based on the user's online activity time and emotional data.

[0904] Step 10:

[0905] The next time the user accesses the web, the terminal (user device) will display an appropriate advertisement delivered from the server. For example, when the user is viewing a specific web page, an advertisement tailored to the user's emotional data will be displayed.

[0906] Step 11:

[0907] The device records the user's response to the advertisement. The recorded data includes the number of clicks on the advertisement, viewing time, purchase history, etc. These data are important elements for capturing the user's response in detail.

[0908] Step 12:

[0909] The server receives user response data sent from the device and performs detailed analysis, using statistical tools and machine learning algorithms to evaluate ad performance.

[0910] Step 13:

[0911] The server retrains the AI ​​model based on the analysis results, so that more optimal advertising elements are generated in the next ad generation process, thereby continuously improving the effectiveness of the ad.

[0912] In this way, the system of the present invention realizes highly accurate advertisement distribution that also takes into account the user's emotions.

[0913] Example 2

[0914] Next, a description will be given of Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the headset type terminal 314 will be referred to as a "terminal."

[0915] Conventional ad delivery systems generate ad elements based only on basic information provided by users and deliver them to target users. This makes it difficult to deliver ads that take into account the user's current emotional state. As a result, the effectiveness of ads is not maximized, and there is a need to further improve the accuracy and effectiveness of ad delivery. Another issue is that ad response data is not sufficiently collected and the results are not reflected in the next ad generation process.

[0916] The specific processing by the specific processing unit 290 of the data processing device 12 in the second embodiment is realized by the following means.

[0917] In this invention, the server includes: means for collecting information and emotional information provided by a user; an artificial intelligence model for generating optimal advertising elements for a target using the collected information and emotional information; means for selecting and fine-tuning advertising content for each target based on the generated advertising elements; means for scheduling and delivering the selected and fine-tuned advertising content to a user terminal; means for collecting and analyzing user response data to the advertising content; and means for continuously updating and optimizing the artificial intelligence model using the analysis results. This makes it possible to generate and deliver target-adaptive advertisements that take into account the emotional state of the user, thereby further improving the accuracy and effectiveness of advertisement delivery.

[0918] "Information provided by the user" refers to basic information such as gender, age, hobbies and preferences, internet browsing history, and purchase history that the user provides through a website or application.

[0919] "Emotional information" is data about the user's emotional state obtained by analyzing facial expressions and vocal tones captured through the user's device camera and microphone.

[0920] An "artificial intelligence model" is an algorithm or system that generates optimal advertising elements for a target based on collected user and emotional information.

[0921] "Advertising elements" are the individual elements that make up advertising content, such as web content, images, copy, claims, and performers.

[0922] The "means for selecting and fine-tuning advertising content for each target" refers to a means for selecting the most effective advertising element for a specific target user based on the generated candidate list of advertising elements, and then fine-tuning the content.

[0923] "Scheduling and delivery means" refers to means for delivering selected and fine-tuned advertising content at appropriate times based on the user's online activity time and emotional data.

[0924] "Response data" refers to data relating to a user's response to an advertisement, such as the number of clicks, viewing time, and purchase history.

[0925] "Means for continuous updating and optimization" refers to means for continuously updating and optimizing the artificial intelligence model based on collected and analyzed reaction data.

[0926] MODE FOR CARRYING OUT THE INVENTION

[0927] The present invention provides a system that generates optimal advertising elements using basic information and emotion information provided by users and delivers them to target users. This system includes a server, a terminal, and a user, and is implemented based on the following steps:

[0928] 1. Collection of User Data

[0929] The server collects user information via websites and applications, including gender, age, hobbies and preferences, internet browsing history, and purchase history. With the user's permission, the server also uses the device's camera and microphone to analyze facial expressions and voice tone to collect emotional information. For example, if the user is smiling, the emotional information is recorded as "happy."

[0930] 2. Data preprocessing and sentiment analysis

[0931] The server stores the collected information in a secure database. After removing incomplete data and noise from the stored data and standardizing it, the emotional data is analyzed using an emotion engine. The emotion engine used in this process includes algorithms for facial expression analysis and voice analysis. For example, it can identify the user's emotional state, such as "happiness" or "anxiety," based on specific facial features.

[0932] 3. Artificial Intelligence Model for Ad Generation

[0933] The server inputs the preprocessed basic information and emotional information into the AI ​​model. For example, if the user is a woman in her 30s and in a "happy" emotional state, that information is input into the AI ​​model. This AI model uses the data to generate optimal advertising elements for each target, such as web content, images, copy, appealing content, and performers. As a specific example, if the user is a woman in her 30s and in a "happy" state, a bright-toned advertisement with the theme of her child's first smartphone will be generated.

[0934] 4. Selecting and optimizing advertising elements

[0935] Based on the generated list of ad element candidates, the server selects the most effective ad elements by utilizing historical ad performance data, real-time user data, and sentiment data. The selected ad elements are then further fine-tuned to make them more visually and content-oriented. For example, fine-tuning may be done by changing the color tone of the web content or the font of the text.

[0936] 5. Delivery of advertisements

[0937] The server registers the selected and fine-tuned advertising content in the distribution reservation system and sets a distribution schedule based on the user's online activity time and emotional data. The next time the user browses the web, the device displays the distributed advertisement. For example, if the target user is viewing a web page in a "happy" emotional state, an appropriately selected smartphone debut advertisement will be displayed.

[0938] 6. Data Collection and Feedback

[0939] The device records user response data to advertisements (number of clicks, viewing time, purchase history, etc.) and sends it to the server. The server analyzes this response data to evaluate the effectiveness of the advertisements. The evaluation results are reflected in the next advertisement generation process. This enables continuous updating and optimization of the AI ​​model and advertisement content.

[0940] Specific examples

[0941] For example, for a female user in her 30s, the following ads will be generated and delivered:

[0942] 1. The server collects user data of women in their 30s (e.g., they have children, they are interested in using a smartphone for the first time) and emotional data on "happiness."

[0943] 2. Based on this user data, the AI ​​model generates advertising elements (web commercials, images, copy) in upbeat tones depicting scenes of children starting to use smartphones.

[0944] 3. The server selects these advertising elements and fine-tunes them as advertising content.

[0945] 4. While the user is browsing the web, the device displays smartphone debut ads tailored to their "happiness" state.

[0946] 5. When a user clicks on an ad and views details, response data is collected and sent to the server at a later date.

[0947] 6. The server analyzes the response data and uses it in the next ad generation process.

[0948] Prompt Sentence Examples

[0949] "We have a user who is a woman in her 30s with a child. She is currently in a 'happy' emotional state. Please generate optimal advertising elements for this user regarding their smartphone debut."

[0950] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0951] Step 1:

[0952] The server collects user information via websites and applications. Input data includes gender, age, hobbies, preferences, internet browsing history, and purchase history provided by the user. The server stores this data in a secure database. With the user's permission, the server also uses the device camera and microphone to collect facial expressions and voice tones. For example, if the user is smiling, the server records the emotional information as "happy." The output data includes basic information and emotional information.

[0953] Step 2:

[0954] The server performs preprocessing on the data stored in a secure database. The input data includes the basic information and emotional information collected in step 1. Specific operations include removing incomplete data and noise, and standardizing the data. In parallel, the emotional information is analyzed using an emotional engine. For example, it uses facial expression analysis and voice analysis algorithms to identify the user's emotional state as "happy" or "anxious." The output data is the preprocessed basic information and analyzed emotional information.

[0955] Step 3:

[0956] The server inputs the preprocessed basic information and emotional information into the AI ​​model. Input data includes gender, age, hobbies and preferences, browsing history, purchase history, and analyzed emotional data. The AI ​​model generates optimal advertising elements based on this data. Specifically, it generates web content, images, copy, appealing content, and performers. For example, if a female user in her 30s is in a "happy" emotional state, it generates a bright-toned advertisement themed around her child's smartphone debut. The output data is a list of the generated advertising elements.

[0957] Step 4:

[0958] The server selects optimal advertising content for each target based on a candidate list of advertising elements generated by an AI model. The input data includes the list of generated advertising elements, past advertising performance data, current user data, and emotional data. Specific operations include fine-tuning the selected advertising elements, such as changing color tones and adjusting text fonts. The output data is optimized advertising content.

[0959] Step 5:

[0960] The server registers the selected and fine-tuned advertising content in the distribution reservation system and sets a distribution schedule. Input data includes the optimized advertising content, the user's online activity time, and emotional data. Specific operations involve planning the optimal timing of ad distribution based on the user's online activity time and emotional data. The next time the user browses the web, the device displays the distributed advertisement. For example, if the user is browsing the web in a "happy" emotional state, a smartphone debut advertisement will be displayed. The output data is an advertising distribution schedule.

[0961] Step 6:

[0962] The device records user response data to advertisements. Input data includes user behavior data (number of clicks, viewing time, purchase history, etc.). This response data is sent to the server. The server analyzes this data and evaluates the effectiveness of the advertisement. Specifically, it evaluates the performance of the advertisement based on the response data, and updates and optimizes the AI ​​model based on the results. The output data are the analysis results and a continuously updated AI model.

[0963] (Application example 2)

[0964] Next, a description will be given of Application Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the headset type terminal 314 will be referred to as a "terminal."

[0965] Current ad delivery systems generate and deliver targeted ads based on data such as a user's basic information and browsing history, but they are unable to consider the user's emotional state. This makes it difficult to deliver ads that are best suited to the user's current emotional state, resulting in a lack of maximum advertising effectiveness.

[0966] The identification process by the identification processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means. In this invention, the server includes: means for collecting information and emotional data provided by users; an artificial intelligence model for generating optimal advertising elements for targets using the collected information and emotional data; means for selecting advertising content for each target based on the generated advertising elements; means for delivering the selected advertising content to user terminals; means for analyzing user response data to the advertising content; and means for updating the artificial intelligence model using the analysis results. This makes it possible to generate and deliver advertisements optimal for the user's current emotional state in real time.

[0967] "User-provided information" refers to data voluntarily provided by users, such as gender, age, hobbies and preferences, internet browsing history, and purchase history, as well as data including facial expressions and tone of voice collected to identify the user's emotional state.

[0968] "Emotion data" is data that indicates the user's current feelings and state, obtained by analyzing the user's facial expressions and voice tones.

[0969] The "artificial intelligence model" is a machine learning model that uses collected user data and emotional data to generate optimal advertising elements for each target.

[0970] "Advertising elements" are multiple elements that make up advertising content, such as visual media, still images, text, appeals, and characters.

[0971] "Advertising content" refers to the final advertising material selected from the generated advertising elements and delivered to the user.

[0972] "Response data" refers to data on the user's response to an advertisement, such as the number of clicks, viewing time, and purchase history.

[0973] "Means for updating" is a function for improving and optimizing the artificial intelligence model using collected user response data.

[0974] This invention is a system for displaying optimal advertisements using user emotion data. This system is realized mainly by a server, a terminal, and a process for collecting and analyzing user data. The implementation configuration and processing procedure of the system are described in detail below.

[0975] User Data Collection

[0976] The server collects information provided by users when they use websites and applications. Collected information includes gender, age, hobbies and preferences, internet browsing history, purchase history, and emotional data (facial expressions and voice tone) captured using the device's camera and microphone. The server captures facial expressions using OpenCV and recognizes emotions using deep learning libraries such as TensorFlow or Keras.

[0977] Data preprocessing and sentiment analysis

[0978] The collected user data is stored in a secure database on the server. Data preprocessing involves removing incomplete data and noise and standardizing the data. At the same time, an emotion recognition engine analyzes the user's facial expressions and voice tone to identify their current state of mind and emotion. This allows it to identify specific emotional states such as "happy," "excited," or "anxious."

[0979] Artificial intelligence models for ad generation

[0980] The server runs a generative AI model using the preprocessed basic data and emotion data. The generative AI model generates optimal advertising elements for each target audience. These advertising elements include visual media (e.g., web commercials), still images, text, advertising content, and characters. By utilizing the emotion data, an advertisement that best suits the user's current emotional state is generated.

[0981] Ad element selection and optimization

[0982] From the generated ad elements, the most effective ad content is selected based on historical ad performance data, real-time user data, and current user sentiment data. The selected ad elements are then fine-tuned into the final ad content. The server runs tools and algorithms to do this.

[0983] Ad serving

[0984] The server registers the selected advertising content in the distribution reservation system and sets the distribution schedule. Based on the user's online activity time and emotional data, the advertisements are planned to be distributed at the optimal timing. The user's device displays the advertisements distributed from the server the next time the user accesses the web. Appropriate advertisements are displayed to the user via a simple browser or application.

[0985] Data collection and feedback

[0986] The user's device records response data to the advertisement (number of clicks, viewing time, purchase history, etc.) and sends it to the server. The server analyzes this response data and evaluates the effectiveness of the advertisement. Based on the evaluation results, the generative AI model is updated to continuously improve the performance of the advertisement.

[0987] Specific examples

[0988] For example, if a female user in her 30s is recognized as being in a "happy" state, a cheerful advertisement about her child's first smartphone is generated. This advertisement is displayed on the user's smartphone, and response data is collected when the user clicks on the advertisement.

[0989] Example prompt for a generative AI model:

[0990] If the user is in a "happy" state, is a woman in her 30s, and is interested in technology and children, generate a "bright-toned ad related to children's smartphone debut."

[0991] If the user is in an "anxious" state, is a male in his 20s, and is concerned about security, an "advertisement offering points that emphasizes a sense of security" will be generated.

[0992] This makes it possible to generate and deliver optimal advertisements in real time based on the user's emotional state and personal data.

[0993] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[0994] Step 1:

[0995] User Data Collection

[0996] The server collects information provided by users when they use websites and applications. Inputs include gender, age, hobbies and preferences, internet browsing history, purchase history, and emotional data (facial expressions and voice tone) captured using the device camera and microphone. The server captures facial expressions using OpenCV and recognizes emotions using deep learning libraries such as TensorFlow or Keras. As output, user data and emotional data are stored in a secure database.

[0997] Step 2:

[0998] Data preprocessing and sentiment analysis

[0999] The server performs preprocessing by removing incomplete data and noise and standardizing the data. The input is the user data and emotion data collected in step 1, and the output is clear data after preprocessing. At the same time, the emotion recognition engine receives the user's facial expressions and voice tone as input and analyzes them. The output of the analysis is the user's emotional state (e.g., "happy," "excited," "anxious," etc.).

[1000] Step 3:

[1001] Artificial intelligence models for ad generation

[1002] The server runs the generative AI model using the clear data and emotion data that have been preprocessed. The input is the clear data and emotion data from the previous step, and the output is the optimal advertising elements (visual media, still images, text, appeal content, and characters) for each target. Specifically, the generative AI model generates multiple advertising elements and combines them based on the prompt text.

[1003] Step 4:

[1004] Ad element selection and optimization

[1005] The server selects the most effective ad content from the generated ad elements based on historical ad performance data, real-time user data, and current user sentiment data. The inputs are the generated ad elements, historical performance data, and real-time data. The output is optimized ad content. The server runs an algorithm to do this and fine-tunes the ad content.

[1006] Step 5:

[1007] Ad serving

[1008] The server registers the selected advertising content in the distribution reservation system and sets the distribution schedule. The input is the optimized advertising content, and the output is the advertisement delivered to the user's device. Specifically, the server determines the optimal timing based on the user's online activity time and emotional data, and instructs the device to display the advertisement the next time the user accesses the web.

[1009] Step 6:

[1010] Data collection and feedback

[1011] The user's device records response data to the ad (number of clicks, viewing time, purchase history, etc.) and sends it to the server. The input is the user's response data to the ad, and the output is feedback data recorded on the server. The server analyzes this feedback data and updates and optimizes the generative AI model. Specifically, the server analyzes the feedback data and uses it in the next ad generation process.

[1012] The specific processing unit 290 transmits the result of the specific processing to the headset type terminal 314. In the headset type terminal 314, the control unit 46A causes the speaker 240 and the display 343 to output the result of the specific processing. The microphone 238 acquires audio indicating a user input regarding the result of the specific processing. The control unit 46A transmits audio data indicating the user input acquired by the microphone 238 to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the audio data.

[1013] The data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of the data generation model 58 is ChatGPT (Internet Search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search <url: https: gemini.google.com ?hl="ja">) and other generation AIs. The data generation model 58 is obtained by performing deep learning on a neural network. A prompt including an instruction is input to the data generation model 58, and inference data such as voice data indicating voice, text data indicating text, and image data indicating an image is also input. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt, and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[1014] In the above embodiment, an example was given in which the specific processing is performed by the data processing device 12, but the technology of the present disclosure is not limited to this, and the specific processing may be performed by the headset type terminal 314.

[1015] [Fourth embodiment]

[1016] FIG. 7 shows an example of the configuration of a data processing system 410 according to the fourth embodiment.

[1017] 7, a data processing system 410 includes a data processing device 12 and a robot 414. An example of the data processing device 12 is a server.

[1018] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 is an example of a "computer" according to the technology of the present disclosure. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, the RAM 30, and the storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[1019] The robot 414 includes a computer 36, a microphone 238, a speaker 240, a camera 42, a communication I / F 44, and a control target 443. The computer 36 includes a processor 46, a RAM 48, and a storage 50. The processor 46, the RAM 48, and the storage 50 are connected to a bus 52. The microphone 238, the speaker 240, the camera 42, and the control target 443 are also connected to the bus 52.

[1020] The microphone 238 receives instructions and the like from the user 20 by receiving voice uttered by the user 20. The microphone 238 captures the voice uttered by the user 20, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio in accordance with instructions from the processor 46.

[1021] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an imaging element such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the surroundings of user 20 (for example, an imaging range defined by an angle of view equivalent to the field of vision of a typical healthy person).

[1022] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 are responsible for the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is carried out in a secure state.

[1023] The control object 443 includes a display device, LEDs in the eyes, and motors for driving the arms, hands, and feet. The posture and gestures of the robot 414 are controlled by controlling the motors of the arms, hands, and feet. Some of the emotions of the robot 414 can be expressed by controlling these motors. In addition, the facial expressions of the robot 414 can also be expressed by controlling the light emission state of the LEDs in the eyes of the robot 414.

[1024] Fig. 8 shows an example of the main functions of the data processing device 12 and the robot 414. As shown in Fig. 8, in the data processing device 12, a specific process is performed by the processor 28. A specific process program 56 is stored in the storage 32.

[1025] The specific processing program 56 is an example of a "program" according to the technology of the present disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[1026] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[1027] In the robot 414, the processor 46 performs the reception output process. A reception output program 60 is stored in the storage 50. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output process is realized by the processor 46 operating as the control unit 46A in accordance with the reception output program 60 executed on the RAM 48.

[1028] Next, a description will be given of the specific processing performed by the specific processing unit 290 of the data processing device 12. In the following description, the data processing device 12 will be referred to as a "server" and the robot 414 will be referred to as a "terminal."

[1029] MODE FOR CARRYING OUT THE INVENTION

[1030] The present invention is a system for displaying optimal advertisements to users, and is implemented by the following main steps: The following describes in detail how the server, terminal, and user are involved.

[1031] User Data Collection

[1032] The server collects user data through websites and applications, including a wide range of user-provided information such as gender, age, hobbies, preferences, internet browsing history, purchase history, etc. The server stores this user data in a secure database, preparing it for later input into an artificial intelligence model.

[1033] Data Preprocessing

[1034] The server cleanses (pre-processes) the collected data, specifically removing incomplete data and noise and converting it into a unified format. This pre-processing ensures that the AI ​​model operates with high accuracy.

[1035] Artificial intelligence models for ad generation

[1036] The AI ​​model takes the pre-processed data as input and generates optimal advertising elements for each target audience, including web commercials, images, copy, appealing content, and featured talent.

[1037] For example, for data on female users in their 30s, who often have children, ads with a theme of smartphone debut are generated, while for data on male users in their 20s, ads emphasizing the benefits of point redemption are generated.

[1038] Ad element selection and optimization

[1039] The server selects the most effective ad content for each target based on the generated list of ad element candidates. This selection process utilizes past ad performance data and real-time user data. During the selection process, the selected ad elements are fine-tuned to ensure their effectiveness as the final ad content.

[1040] Ad serving

[1041] The server registers the selected advertising content in the distribution reservation system and sets a specific distribution schedule, planning to display the advertisement at the most suitable time for the target user.

[1042] The terminal (user device) displays the appropriate advertisement delivered from the server the next time the user accesses the web. For example, when a user is viewing a specific web page, an optimally targeted advertisement is displayed at the set timing.

[1043] Data collection and feedback

[1044] The device records user response data (number of clicks on ads, viewing time, purchase history, etc.) and sends it to the server. The server analyzes this response data and evaluates the effectiveness of the ads. This is reflected in the next ad generation process to continuously improve ad performance.

[1045] Specific examples

[1046] For example, for a female user in her 30s, the following ads will be generated and delivered:

[1047] 1. The server collects user data of women in their 30s (e.g., they have children and are interested in using smartphones for the first time).

[1048] 2. Based on this user data, the AI ​​model generates advertising elements (web commercials, images, copy) depicting scenes of children starting to use smartphones.

[1049] 3. The server selects these advertising elements and fine-tunes them to create optimal content.

[1050] 4. The device will display targeted ads about smartphone debuts while the user is browsing the web.

[1051] 5. When a user clicks on an ad and views details, response data is collected and sent to the server at a later date.

[1052] 6. The server analyzes the response data and uses it in the next ad generation process.

[1053] Similarly, for male users in their 20s, the system generates and delivers optimally targeted ads in a similar manner, improving the accuracy and effectiveness of ad delivery.

[1054] The processing flow will be explained below.

[1055] Step 1:

[1056] The server collects user data through websites and applications, including information provided by users such as gender, age, interests, and preferences, as well as browsing and purchasing history. This data is collected by users through web forms and account settings, and automatically through cookies and tracking pixels.

[1057] Step 2:

[1058] The server stores the collected user data in a secure database, using encryption technology to ensure data integrity and security, and the database is indexed for quick access later.

[1059] Step 3:

[1060] The server retrieves user data from the stored database and performs pre-processing on the data, which includes cleaning the data (removing incomplete data and noise) and standardizing the data (converting it into a unified format), preparing the data format for input into the artificial intelligence model.

[1061] Step 4:

[1062] The AI ​​model receives the pre-processed data and generates optimal advertising elements for each target. Specifically, the algorithm automatically generates the web commercial, images, copy, appeal content, and talent for the ad based on gender, age, and hobbies and preferences.

[1063] Step 5:

[1064] The server generates a candidate list of ad content based on the generated ad elements, which may include multiple ad elements for each target, such as multiple versions with different copy or visual elements.

[1065] Step 6:

[1066] The server selects the most effective ad content from the list of candidates, using historical ad performance data and real-time user data. For example, it prioritizes ad elements that have historically generated high click-through rates.

[1067] Step 7:

[1068] The server then uses the selected ad content to fine-tune the targeted ads, which can include small design changes or copy modifications, making the ads more appealing.

[1069] Step 8:

[1070] The server registers the optimized advertising content in the distribution reservation system and sets a distribution schedule, specifically specifying the timing of advertisement distribution based on the user's online activity time.

[1071] Step 9:

[1072] The next time the user accesses the web, the terminal (user device) displays the appropriate advertisement delivered from the server. For example, an advertisement can be displayed at a set time while the user is browsing a specific site.

[1073] Step 10:

[1074] The device records how users respond to ads, including the number of clicks, viewing time, and eventual purchases.

[1075] Step 11:

[1076] The server receives and analyzes user response data sent from the device, using statistical tools and machine learning algorithms to evaluate ad performance.

[1077] Step 12:

[1078] The server retrains the artificial intelligence model based on the analysis results, thereby updating the model so that it generates more optimal ad elements the next time an ad is generated.

[1079] In this way, the system of the present invention can provide highly accurate and effective advertisements to a wide range of targets.

[1080] Example 1

[1081] Next, a description will be given of Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the robot 414 will be referred to as a "terminal."

[1082] Modern advertising systems are required to display optimal advertisements based on individual user information. However, existing methods lack sufficient data preprocessing, selection of advertising elements, and analysis of user responses, resulting in reduced advertising effectiveness. Furthermore, there is a lack of mechanisms for efficiently collecting user response data and continuously improving advertising effectiveness. This creates the problem of making it difficult to consistently display optimal advertisements to users.

[1083] The specific processing by the specific processing unit 290 of the data processing device 12 in the first embodiment is realized by the following means.

[1084] In this invention, the server includes means for collecting information provided by users, means for preprocessing the collected information, an artificial intelligence model for generating optimal advertising elements for targets using the preprocessed information, means for selecting advertising content for each target based on the generated advertising elements, means for delivering the selected advertising content to user terminals, means for collecting user response data to the advertising content, means for analyzing the collected response data, and means for updating the artificial intelligence model using the analysis results, thereby making it possible to always deliver optimal advertising to users and continuously improve its effectiveness.

[1085] "Information provided by users" refers to data such as gender, age, hobbies and preferences, internet browsing history, and purchase history that users provide through websites and applications.

[1086] "Preprocessing" is the process of removing incomplete data and noise from collected information and converting it into a unified format.

[1087] An "artificial intelligence model" is a collection of algorithms that learn from large amounts of data, recognize patterns, and generate advertising elements that are optimal for specific targets.

[1088] "Advertising Elements" refers to the various elements that make up an advertisement, such as digital content, visual advertisements, text advertisements, promotional content, and performers.

[1089] "Selection" refers to the process of selecting the most effective advertising content for the target from among the multiple advertising elements generated.

[1090] "Delivery" refers to the act of sending selected advertising content to a user terminal.

[1091] A "user terminal" is a device used by a user, such as a computer, smartphone, or tablet.

[1092] "Response data" refers to data such as the number of clicks a user makes on an advertisement, viewing time, and purchase history.

[1093] "Collecting" refers to the act of gathering user response data and storing it for analysis.

[1094] "Analysis" is the process of analyzing collected response data using statistical methods and machine learning techniques to evaluate the effectiveness of advertising.

[1095] "Update" is the process of improving the artificial intelligence model based on the analysis results and reflecting them in the next ad generation.

[1096] This invention provides a system for displaying optimal advertisements to users. This system is made up of three main components: a server, a terminal, and a user. The following describes in detail an embodiment of this invention.

[1097] The server first collects information provided by users through websites and applications, including gender, age, hobbies and preferences, internet browsing history, purchase history, etc. The collected data is then stored in a secure database.

[1098] The server then preprocesses the collected data. Specifically, preprocessing involves removing incomplete data and noise, converting data into a unified format, and unifying date data stored in different formats. It also removes records containing null values.

[1099] Once preprocessed, the data is input into an artificial intelligence model. This model learns from large amounts of data and generates optimal advertising elements for each target. The generated advertising elements include digital content, visual ads, text ads, promotional content, and performers. For example, the following prompt sentence is used to generate advertising elements: "Please generate an advertisement for a woman in her 30s with children about her smartphone debut."

[1100] The server then selects ad content based on the generated ad elements. This selection process takes into account past ad performance data and real-time user data. During the selection process, the server fine-tunes the generated ad elements to create the most effective ad content.

[1101] Once the selection and fine-tuning of advertising content is complete, the server delivers it to the user's device. The delivery schedule is planned to display the advertisement at the optimal time for the target user. The user's device then displays the advertisement delivered by the server the next time the user accesses the web.

[1102] The device also collects user response data to advertising content (number of clicks, viewing time, purchase history, etc.). This response data is sent to the server and analyzed by the server. The analysis results are used to evaluate the effectiveness of the advertisement and update the artificial intelligence model based on the results. This allows for more accurate advertisements to be generated in the next advertisement generation process.

[1103] For example, the following process is performed for a female user in her 30s:

[1104] 1. The server collects user data of a woman in her 30s (who has children and is interested in using a smartphone for the first time).

[1105] 2. The server preprocesses the collected data and converts it into a unified format.

[1106] 3. Based on this user data, the AI ​​model generates advertisements depicting scenes of children starting to use smartphones.

[1107] 4. The server selects and fine-tunes the generated ad elements.

[1108] 5. The device displays advertisements at the optimal time to users browsing news sites.

[1109] 6. The user clicks on the advertisement, and the response data is collected by the terminal and sent to the server.

[1110] 7. The server analyzes the response data and updates the artificial intelligence model based on the results.

[1111] In this way, the system can continually deliver the most appropriate ads to users, and continuously improve their accuracy and effectiveness.

[1112] The flow of the identification process in the first embodiment will be described with reference to FIG.

[1113] Step 1: Collect user data

[1114] The server collects user data through websites and applications. Input includes information provided by users such as gender, age, hobbies and preferences, internet browsing history, and purchase history. This data is stored in a secure database. Specifically, the server records the pages the user views, the links they click, and the products they purchase.

[1115] Step 2: Preprocessing the data

[1116] The server preprocesses the collected user data. The input is the raw data collected in the previous step. Specific data processing involves removing incomplete data and noise and converting it into a unified format. This preprocessing step unifies date data stored in different formats, for example. Records containing NULL values ​​are also removed, resulting in cleaned data as the output.

[1117] Step 3: Running the AI ​​model to generate ads

[1118] The AI ​​model on the server receives the preprocessed data as input and generates optimal advertising elements. The prompt is "Please generate an advertisement for a woman in her 30s with children about her smartphone debut." Specifically, the model extracts patterns from the input data and generates advertising elements (digital content, visual ads, text ads, etc.) for each target as output.

[1119] Step 4: Select and optimize advertising elements

[1120] The server selects optimal advertising content from among the advertising elements generated by the AI ​​model. It uses the generated advertising elements, past advertising performance data, and real-time user data as input. Specifically, it uses statistical analysis and machine learning algorithms to evaluate the advertising elements and selects optimal advertising content as output. It also fine-tunes the selected advertising elements.

[1121] Step 5: Serving Ads

[1122] The server registers the selected advertising content in the distribution reservation system and sets a distribution schedule. The selected advertising content and timing data for its target users are used as input. Specifically, the server schedules the advertisement so that it is displayed at the optimal time for the target users. The output is the advertising content for which distribution reservation has been completed. The terminal then displays the advertisement while the user is browsing the web.

[1123] Step 6: Data collection and feedback

[1124] The terminal records user response data to advertisements and sends it to the server. Inputs include the number of clicks on the advertisements, viewing time, and purchase history. Specific data processing involves organizing this data and sending it to the server. The server analyzes this response data. The response data sent in the previous step is used as input. The output is an analysis result indicating the effectiveness of the advertisement. Based on this analysis result, the server updates the artificial intelligence model and uses it in the next advertisement generation process. This continuously improves the accuracy and effectiveness of advertisements.

[1125] (Application example 1)

[1126] Next, a description will be given of Application Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the robot 414 will be referred to as a "terminal."

[1127] Conventional ad delivery systems have issues with the insufficient integration of user data collection, ad element generation, delivery, and effectiveness analysis, making it difficult to display optimal ads in real time. Another problem is that ad optimization within smart devices is insufficient, resulting in a lack of improvement in the user experience.

[1128] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 1 is realized by the following means.

[1129] In this invention, the server includes: means for collecting information provided by users; an artificial intelligence model for generating optimal advertising elements for targets using the collected information; means for selecting advertising content for each target based on the generated advertising elements; means for delivering the selected advertising content to user terminals; means for analyzing user response data to the advertising content; means for updating the artificial intelligence model using the analysis results; a processor for generating and optimizing advertising elements within a smart device; and an output device for displaying the advertisements generated by the processor. This makes it possible to display optimal advertisements to users in real time and maximize the effectiveness of the advertisements.

[1130] Definition of Terms

[1131] "User-provided information" refers to personal information, internet browsing history, purchase history, location information, and application usage history collected voluntarily or through the user's activity.

[1132] An "artificial intelligence model" is a machine learning algorithm that performs data analysis based on collected user information and generates optimal advertising elements for each target.

[1133] "Advertising elements" are elements that make up the content of an advertisement, including web commercials, images, copy, appealing content, featured talent, and advertising units displayed within user terminal applications.

[1134] "Advertising content" is a combination of advertising elements generated and optimized by an artificial intelligence model.

[1135] A "user terminal" is a device used by a user, such as a smartphone, tablet, PC, or smart device.

[1136] "Response data" is data that records the actions and responses (number of clicks, viewing time, purchase history, etc.) that users show to advertisements.

[1137] "Processor" means a central processing unit for generating and optimizing advertising elements within a smart device.

[1138] "Output device" means a display or screen for displaying advertisements generated on a smart device to a user.

[1139] "Application usage history" is data that records the usage of applications used by a user within a smart device.

[1140] This invention is a system that generates and displays optimized advertisements in real time within smart devices. This system collects various information provided by users, uses an artificial intelligence model to generate, select, and deliver optimal advertising elements to the target audience, and also includes a process for providing feedback based on user responses. Each element is described in detail below.

[1141] System configuration and program description

[1142] 1. Hardware Configuration

[1143] The system consists of the following hardware:

[1144] Server: Responsible for data collection, preprocessing, training of AI models, generation of advertising elements, and collection and analysis of user response data.

[1145] User terminal: Refers to smartphones, tablets, personal computers, smart devices, etc., used to display advertisements and collect user response data.

[1146] Processor: A central processing unit for generating and optimizing advertising elements within a smart device.

[1147] Output Device: A display or screen for displaying the generated advertisement to the user.

[1148] 2. Software Configuration

[1149] The system consists of the following software:

[1150] Data collection module: Collects the user's gender, age, hobbies and preferences, internet browsing history, purchase history, location information, and application usage history.

[1151] Data preprocessing module: Cleanses and normalizes the collected data and converts it into a format suitable for AI models.

[1152] AI model: A machine learning algorithm that generates optimal advertising elements for each target based on collected data. It uses libraries such as scikit-learn.

[1153] Ad element generation module: Runs the AI ​​model to generate ad elements.

[1154] Advertisement selection module: Selects the most suitable content from the generated advertising elements.

[1155] Advertisement delivery module: delivers optimized advertising content to user terminals.

[1156] Reaction data collection module: collects user reaction data and provides feedback.

[1157] Advertisement display module: displays advertisements on the output device of the user terminal.

[1158] Data processing flow and specific examples

[1159] 1. Collection of User Data

[1160] The server collects information from the user's device, such as gender, age, hobbies, preferences, internet browsing history, purchase history, location information, and application usage history. For example, for a female user in her 30s, childcare-related browsing history and purchase history are collected from her smartphone history.

[1161] 2. Data Preprocessing

[1162] The server cleanses the collected data, imputes missing data, and normalizes it, using standard data preprocessing libraries pandas and scikit-learn's StandardScaler.

[1163] 3. Ad generation

[1164] An AI model (e.g., RandomForestClassifier) ​​installed on the server runs and generates advertising elements based on the preprocessed data. For example, if there is a lot of browsing history related to childcare, advertisements for baby products will be generated.

[1165] 4. Ad selection

[1166] The server selects the best ad element from the multiple ad elements generated based on past performance data. The ad selection algorithm uses A / B testing techniques.

[1167] 5. Delivery of advertisements

[1168] The server then delivers the selected advertisements to user devices such as smartphones in real time, and they are displayed when the user opens a specific application or web page.

[1169] 6. Collecting user response data and providing feedback

[1170] The server collects response data (number of clicks, viewing time, purchase history, etc.) from the user terminal to the advertisement and provides feedback for generating the next advertisement.

[1171] Prompt Sentence Examples

[1172] Design a system that collects user data and uses AI models to generate and display optimal ads. Specifically, the system generates optimal ads based on the user's age, gender, hobbies, preferences, browsing history, purchase history, etc., and provides feedback on the effectiveness of the ads.

[1173] This makes it possible to deliver optimal ads to users in real time and maximize their effectiveness.The system is designed to improve the accuracy and effectiveness of ad delivery and enhance the user experience.

[1174] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[1175] Program processing steps

[1176] Step 1:

[1177] The server collects information provided by the user's device. Specifically, it acquires the user's gender, age, hobbies and preferences, internet browsing history, purchase history, location information, and application usage history. The input data is these user attributes and behavioral data, and the output is the collected dataset.

[1178] Step 2:

[1179] The server preprocesses the collected data. Specifically, it cleanses the data (complements incomplete data and removes noise) and normalizes it. This process uses pandas and scikit-learn's StandardScaler. The input data is the dataset collected in step 1, and the output is a clean dataset after preprocessing.

[1180] Step 3:

[1181] The server runs an artificial intelligence model to generate advertising elements using the preprocessed data. For example, it uses RandomForestClassifier to perform data analysis. The input data is the preprocessed dataset, and the output is the generated advertising elements.

[1182] Step 4:

[1183] The server selects the optimal advertising content from the generated advertising elements. It determines the optimal content by verifying past performance data and real-time user data using A / B testing methods. The input data are multiple advertising elements and their performance metrics, and the output is the selected advertising content.

[1184] Step 5:

[1185] The server delivers the selected advertising content to the user device in real time, and the content is displayed when the user opens a specific application or web page. The input data is the selected advertising content, and the output is the advertisement displayed on the user device.

[1186] Step 6:

[1187] Users respond to displayed ads by clicking or viewing them. User response data (number of clicks, viewing time, purchase history, etc.) is collected. The input data is user behavior data, and the output is the collected response data.

[1188] Step 7:

[1189] The server analyzes the collected response data and updates the AI ​​model based on the results. This feedback loop optimizes the next ad generation process. The input data is the collected response data, and the output is the updated AI model.

[1190] Furthermore, an emotion engine that estimates the user's emotion may be further combined. That is, the identification processing unit 290 may estimate the user's emotion using the emotion identification model 59, and perform identification processing using the user's emotion.

[1191] MODE FOR CARRYING OUT THE INVENTION

[1192] This invention is a system that collects and analyzes information, including user emotions, and displays optimal advertisements, and is implemented in the following steps. The following describes in detail how the server, terminal, and user are involved.

[1193] User Data Collection

[1194] The server collects user data through websites and applications. The collected data includes user-provided information such as gender, age, hobbies, preferences, internet browsing history, and purchase history. In addition, emotional information is collected through the user's device camera and microphone. With the user's permission, emotion recognition is performed by analyzing facial expressions and voice tone.

[1195] Data preprocessing and sentiment analysis

[1196] The server stores the collected user data in a secure database and performs preprocessing on the data. This includes removing incomplete data and noise, and standardizing the data. In parallel, the emotion engine analyzes the user's emotion data to identify their current state of mind. For example, facial expression and voice analysis determine whether the user is in a state of "happy," "excited," or "anxious."

[1197] Artificial intelligence models for ad generation

[1198] The AI ​​model generates optimal advertising elements for each target based on collected and pre-processed basic data and emotional data. These elements include web commercials, images, copy, appealing content, and featured talent. By incorporating emotional data, the model generates an ad that best suits the user's current mood.

[1199] For example, if a female user in her 30s is perceived as being in a "happy" state, a bright-toned ad about her child's first smartphone will be generated. On the other hand, if a male user in his 20s is perceived as being in an "anxious" state, a point-reward ad emphasizing a sense of security will be generated.

[1200] Ad element selection and optimization

[1201] The server selects the most effective ad content for each target based on the generated candidate list of ad elements. The selection is made using past ad performance data, real-time user data, and current user sentiment data. The selected ad elements are fine-tuned as the final ad content to enhance its appeal.

[1202] Ad serving

[1203] The server registers the selected advertising content in the distribution reservation system and sets a distribution schedule, which is planned to distribute advertisements at optimal times based on the user's online activity time and emotional data.

[1204] The terminal (user device) displays the appropriate advertisement delivered from the server the next time the user accesses the web. While the user is browsing a specific web page, the advertisement is displayed according to the emotional data.

[1205] Data collection and feedback

[1206] The device records user response data (number of clicks on ads, viewing time, purchase history, etc.) and sends it to the server. The server analyzes this response data and evaluates the effectiveness of the ads. Based on the evaluation results, the next ad generation process is updated to continuously improve ad performance.

[1207] Specific examples

[1208] For example, for a female user in her 30s, the following ads will be generated and delivered:

[1209] 1. The server collects user data of women in their 30s (e.g., they have children, they are interested in using a smartphone for the first time) and emotional data on "happiness."

[1210] 2. Based on this user data, the AI ​​model generates advertising elements (web commercials, images, copy) in upbeat tones depicting scenes of children starting to use smartphones.

[1211] 3. The server selects these advertising elements and fine-tunes them as advertising content.

[1212] 4. While the user is browsing the web, the device displays smartphone debut ads tailored to their "happiness" state.

[1213] 5. When a user clicks on an ad and views details, response data is collected and sent to the server at a later date.

[1214] 6. The server analyzes the response data and uses it in the next ad generation process.

[1215] Similarly, for male users in their 20s, targeted adaptive ads are generated that take into account their emotional data and are delivered at the appropriate time. This system further improves the accuracy and effectiveness of ad delivery.

[1216] The processing flow will be explained below.

[1217] Step 1:

[1218] The server collects user data through websites and applications, including gender, age, hobbies, preferences, internet browsing history, and purchase history. In addition, it obtains emotional information through the user's device camera and microphone, and, with the user's permission, collects facial expressions and voice tone.

[1219] Step 2:

[1220] The device captures the user's facial expressions and voice tone in real time and sends them to the emotion engine, which analyzes this data and identifies the user's emotional state. For example, if the user is smiling, it is judged to be "joy," and if the user is frowning, it is judged to be "stress."

[1221] Step 3:

[1222] The server stores the collected user data and emotion data in a secure database using encryption technology to ensure data integrity and security, and the database is indexed and managed for efficient future access.

[1223] Step 4:

[1224] The server extracts user data and emotion data from the stored database and performs pre-processing on the data, which includes removing incomplete data and noise, and standardizing the data, preparing it in a format suitable for input into the artificial intelligence model.

[1225] Step 5:

[1226] The AI ​​model receives the pre-processed data and generates optimal advertising elements for the target audience based on the user's gender, age, hobbies, preferences, internet browsing history, purchase history, and emotional state. These elements include web commercials, images, copy, appealing content, and featured talent.

[1227] Step 6:

[1228] The server then creates a candidate list of advertising content for each target based on the generated advertising elements. The candidate list includes multiple advertising elements suited to the user's current emotional state. For example, if the user is feeling "joyed," advertisements with a bright tone will be prioritized.

[1229] Step 7:

[1230] The server selects the most effective ad content from the list of candidates, using past ad performance data, real-time user data, and current user sentiment data. Ad elements that have performed particularly well in the past are likely to be selected.

[1231] Step 8:

[1232] The server then uses the selected ad content to fine-tune the targeted ad, making small design changes and copy adjustments to make the ad more appealing.

[1233] Step 9:

[1234] The server registers the optimized advertising content in the distribution reservation system and sets the distribution schedule, which is planned to display the advertisement at the most effective timing based on the user's online activity time and emotional data.

[1235] Step 10:

[1236] The next time the user accesses the web, the terminal (user device) will display an appropriate advertisement delivered from the server. For example, when the user is viewing a specific web page, an advertisement tailored to the user's emotional data will be displayed.

[1237] Step 11:

[1238] The device records the user's response to the advertisement. The recorded data includes the number of clicks on the advertisement, viewing time, purchase history, etc. These data are important elements for capturing the user's response in detail.

[1239] Step 12:

[1240] The server receives user response data sent from the device and performs detailed analysis, using statistical tools and machine learning algorithms to evaluate ad performance.

[1241] Step 13:

[1242] The server retrains the AI ​​model based on the analysis results, so that more optimal advertising elements are generated in the next ad generation process, thereby continuously improving the effectiveness of the ad.

[1243] In this way, the system of the present invention realizes highly accurate advertisement distribution that also takes into account the user's emotions.

[1244] Example 2

[1245] Next, a description will be given of Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the robot 414 will be referred to as a "terminal."

[1246] Conventional ad delivery systems generate ad elements based only on basic information provided by users and deliver them to target users. This makes it difficult to deliver ads that take into account the user's current emotional state. As a result, the effectiveness of ads is not maximized, and there is a need to further improve the accuracy and effectiveness of ad delivery. Another issue is that ad response data is not sufficiently collected and the results are not reflected in the next ad generation process.

[1247] The specific processing by the specific processing unit 290 of the data processing device 12 in the second embodiment is realized by the following means.

[1248] In this invention, the server includes: means for collecting information and emotional information provided by a user; an artificial intelligence model for generating optimal advertising elements for a target using the collected information and emotional information; means for selecting and fine-tuning advertising content for each target based on the generated advertising elements; means for scheduling and delivering the selected and fine-tuned advertising content to a user terminal; means for collecting and analyzing user response data to the advertising content; and means for continuously updating and optimizing the artificial intelligence model using the analysis results. This makes it possible to generate and deliver target-adaptive advertisements that take into account the emotional state of the user, thereby further improving the accuracy and effectiveness of advertisement delivery.

[1249] "Information provided by the user" refers to basic information such as gender, age, hobbies and preferences, internet browsing history, and purchase history that the user provides through a website or application.

[1250] "Emotional information" is data about the user's emotional state obtained by analyzing facial expressions and vocal tones captured through the user's device camera and microphone.

[1251] An "artificial intelligence model" is an algorithm or system that generates optimal advertising elements for a target based on collected user and emotional information.

[1252] "Advertising elements" are the individual elements that make up advertising content, such as web content, images, copy, claims, and performers.

[1253] The "means for selecting and fine-tuning advertising content for each target" refers to a means for selecting the most effective advertising element for a specific target user based on the generated candidate list of advertising elements, and then fine-tuning the content.

[1254] "Scheduling and delivery means" refers to means for delivering selected and fine-tuned advertising content at appropriate times based on the user's online activity time and emotional data.

[1255] "Response data" refers to data relating to a user's response to an advertisement, such as the number of clicks, viewing time, and purchase history.

[1256] "Means for continuous updating and optimization" refers to means for continuously updating and optimizing the artificial intelligence model based on collected and analyzed reaction data.

[1257] MODE FOR CARRYING OUT THE INVENTION

[1258] The present invention provides a system that generates optimal advertising elements using basic information and emotion information provided by users and delivers them to target users. This system includes a server, a terminal, and a user, and is implemented based on the following steps:

[1259] 1. Collection of User Data

[1260] The server collects user information via websites and applications, including gender, age, hobbies and preferences, internet browsing history, and purchase history. With the user's permission, the server also uses the device's camera and microphone to analyze facial expressions and voice tone to collect emotional information. For example, if the user is smiling, the emotional information is recorded as "happy."

[1261] 2. Data preprocessing and sentiment analysis

[1262] The server stores the collected information in a secure database. After removing incomplete data and noise from the stored data and standardizing it, the emotional data is analyzed using an emotion engine. The emotion engine used in this process includes algorithms for facial expression analysis and voice analysis. For example, it can identify the user's emotional state, such as "happiness" or "anxiety," based on specific facial features.

[1263] 3. Artificial Intelligence Model for Ad Generation

[1264] The server inputs the preprocessed basic information and emotional information into the AI ​​model. For example, if the user is a woman in her 30s and in a "happy" emotional state, that information is input into the AI ​​model. This AI model uses the data to generate optimal advertising elements for each target, such as web content, images, copy, appealing content, and performers. As a specific example, if the user is a woman in her 30s and in a "happy" state, a bright-toned advertisement with the theme of her child's first smartphone will be generated.

[1265] 4. Selecting and optimizing advertising elements

[1266] Based on the generated list of ad element candidates, the server selects the most effective ad elements by utilizing historical ad performance data, real-time user data, and sentiment data. The selected ad elements are then further fine-tuned to make them more visually and content-oriented. For example, fine-tuning may be done by changing the color tone of the web content or the font of the text.

[1267] 5. Delivery of advertisements

[1268] The server registers the selected and fine-tuned advertising content in the distribution reservation system and sets a distribution schedule based on the user's online activity time and emotional data. The next time the user browses the web, the device displays the distributed advertisement. For example, if the target user is viewing a web page in a "happy" emotional state, an appropriately selected smartphone debut advertisement will be displayed.

[1269] 6. Data Collection and Feedback

[1270] The device records user response data to advertisements (number of clicks, viewing time, purchase history, etc.) and sends it to the server. The server analyzes this response data to evaluate the effectiveness of the advertisements. The evaluation results are reflected in the next advertisement generation process. This enables continuous updating and optimization of the AI ​​model and advertisement content.

[1271] Specific examples

[1272] For example, for a female user in her 30s, the following ads will be generated and delivered:

[1273] 1. The server collects user data of women in their 30s (e.g., they have children, they are interested in using a smartphone for the first time) and emotional data on "happiness."

[1274] 2. Based on this user data, the AI ​​model generates advertising elements (web commercials, images, copy) in upbeat tones depicting scenes of children starting to use smartphones.

[1275] 3. The server selects these advertising elements and fine-tunes them as advertising content.

[1276] 4. While the user is browsing the web, the device displays smartphone debut ads tailored to their "happiness" state.

[1277] 5. When a user clicks on an ad and views details, response data is collected and sent to the server at a later date.

[1278] 6. The server analyzes the response data and uses it in the next ad generation process.

[1279] Prompt Sentence Examples

[1280] "We have a user who is a woman in her 30s with a child. She is currently in a 'happy' emotional state. Please generate optimal advertising elements for this user regarding their smartphone debut."

[1281] The flow of the identification process in the second embodiment will be described with reference to FIG.

[1282] Step 1:

[1283] The server collects user information via websites and applications. Input data includes gender, age, hobbies, preferences, internet browsing history, and purchase history provided by the user. The server stores this data in a secure database. With the user's permission, the server also uses the device camera and microphone to collect facial expressions and voice tones. For example, if the user is smiling, the server records the emotional information as "happy." The output data includes basic information and emotional information.

[1284] Step 2:

[1285] The server performs preprocessing on the data stored in a secure database. The input data includes the basic information and emotional information collected in step 1. Specific operations include removing incomplete data and noise, and standardizing the data. In parallel, the emotional information is analyzed using an emotional engine. For example, it uses facial expression analysis and voice analysis algorithms to identify the user's emotional state as "happy" or "anxious." The output data is the preprocessed basic information and analyzed emotional information.

[1286] Step 3:

[1287] The server inputs the preprocessed basic information and emotional information into the AI ​​model. Input data includes gender, age, hobbies and preferences, browsing history, purchase history, and analyzed emotional data. The AI ​​model generates optimal advertising elements based on this data. Specifically, it generates web content, images, copy, appealing content, and performers. For example, if a female user in her 30s is in a "happy" emotional state, it generates a bright-toned advertisement themed around her child's smartphone debut. The output data is a list of the generated advertising elements.

[1288] Step 4:

[1289] The server selects optimal advertising content for each target based on a candidate list of advertising elements generated by an AI model. The input data includes the list of generated advertising elements, past advertising performance data, current user data, and emotional data. Specific operations include fine-tuning the selected advertising elements, such as changing color tones and adjusting text fonts. The output data is optimized advertising content.

[1290] Step 5:

[1291] The server registers the selected and fine-tuned advertising content in the distribution reservation system and sets a distribution schedule. Input data includes the optimized advertising content, the user's online activity time, and emotional data. Specific operations involve planning the optimal timing of ad distribution based on the user's online activity time and emotional data. The next time the user browses the web, the device displays the distributed advertisement. For example, if the user is browsing the web in a "happy" emotional state, a smartphone debut advertisement will be displayed. The output data is an advertising distribution schedule.

[1292] Step 6:

[1293] The device records user response data to advertisements. Input data includes user behavior data (number of clicks, viewing time, purchase history, etc.). This response data is sent to the server. The server analyzes this data and evaluates the effectiveness of the advertisement. Specifically, it evaluates the performance of the advertisement based on the response data, and updates and optimizes the AI ​​model based on the results. The output data are the analysis results and a continuously updated AI model.

[1294] (Application example 2)

[1295] Next, a description will be given of Application Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the robot 414 will be referred to as a "terminal."

[1296] Current ad delivery systems generate and deliver targeted ads based on data such as a user's basic information and browsing history, but they are unable to consider the user's emotional state. This makes it difficult to deliver ads that are best suited to the user's current emotional state, resulting in a lack of maximum advertising effectiveness.

[1297] The identification process by the identification processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means. In this invention, the server includes: means for collecting information and emotional data provided by users; an artificial intelligence model for generating optimal advertising elements for targets using the collected information and emotional data; means for selecting advertising content for each target based on the generated advertising elements; means for delivering the selected advertising content to user terminals; means for analyzing user response data to the advertising content; and means for updating the artificial intelligence model using the analysis results. This makes it possible to generate and deliver advertisements optimal for the user's current emotional state in real time.

[1298] "User-provided information" refers to data voluntarily provided by users, such as gender, age, hobbies and preferences, internet browsing history, and purchase history, as well as data including facial expressions and tone of voice collected to identify the user's emotional state.

[1299] "Emotion data" is data that indicates the user's current feelings and state, obtained by analyzing the user's facial expressions and voice tones.

[1300] The "artificial intelligence model" is a machine learning model that uses collected user data and emotional data to generate optimal advertising elements for each target.

[1301] "Advertising elements" are multiple elements that make up advertising content, such as visual media, still images, text, appeals, and characters.

[1302] "Advertising content" refers to the final advertising material selected from the generated advertising elements and delivered to the user.

[1303] "Response data" refers to data on the user's response to an advertisement, such as the number of clicks, viewing time, and purchase history.

[1304] "Means for updating" is a function for improving and optimizing the artificial intelligence model using collected user response data.

[1305] This invention is a system for displaying optimal advertisements using user emotion data. This system is realized mainly by a server, a terminal, and a process for collecting and analyzing user data. The implementation configuration and processing procedure of the system are described in detail below.

[1306] User Data Collection

[1307] The server collects information provided by users when they use websites and applications. Collected information includes gender, age, hobbies and preferences, internet browsing history, purchase history, and emotional data (facial expressions and voice tone) captured using the device's camera and microphone. The server captures facial expressions using OpenCV and recognizes emotions using deep learning libraries such as TensorFlow or Keras.

[1308] Data preprocessing and sentiment analysis

[1309] The collected user data is stored in a secure database on the server. Data preprocessing involves removing incomplete data and noise and standardizing the data. At the same time, an emotion recognition engine analyzes the user's facial expressions and voice tone to identify their current state of mind and emotion. This allows it to identify specific emotional states such as "happy," "excited," or "anxious."

[1310] Artificial intelligence models for ad generation

[1311] The server runs a generative AI model using the preprocessed basic data and emotion data. The generative AI model generates optimal advertising elements for each target audience. These advertising elements include visual media (e.g., web commercials), still images, text, advertising content, and characters. By utilizing the emotion data, an advertisement that best suits the user's current emotional state is generated.

[1312] Ad element selection and optimization

[1313] From the generated ad elements, the most effective ad content is selected based on historical ad performance data, real-time user data, and current user sentiment data. The selected ad elements are then fine-tuned into the final ad content. The server runs tools and algorithms to do this.

[1314] Ad serving

[1315] The server registers the selected advertising content in the distribution reservation system and sets the distribution schedule. Based on the user's online activity time and emotional data, the advertisements are planned to be distributed at the optimal timing. The user's device displays the advertisements distributed from the server the next time the user accesses the web. Appropriate advertisements are displayed to the user via a simple browser or application.

[1316] Data collection and feedback

[1317] The user's device records response data to the advertisement (number of clicks, viewing time, purchase history, etc.) and sends it to the server. The server analyzes this response data and evaluates the effectiveness of the advertisement. Based on the evaluation results, the generative AI model is updated to continuously improve the performance of the advertisement.

[1318] Specific examples

[1319] For example, if a female user in her 30s is recognized as being in a "happy" state, a cheerful advertisement about her child's first smartphone is generated. This advertisement is displayed on the user's smartphone, and response data is collected when the user clicks on the advertisement.

[1320] Example prompt for a generative AI model:

[1321] If the user is in a "happy" state, is a woman in her 30s, and is interested in technology and children, generate a "bright-toned ad related to children's smartphone debut."

[1322] If the user is in an "anxious" state, is a male in his 20s, and is concerned about security, an "advertisement offering points that emphasizes a sense of security" will be generated.

[1323] This makes it possible to generate and deliver optimal advertisements in real time based on the user's emotional state and personal data.

[1324] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[1325] Step 1:

[1326] User Data Collection

[1327] The server collects information provided by users when they use websites and applications. Inputs include gender, age, hobbies and preferences, internet browsing history, purchase history, and emotional data (facial expressions and voice tone) captured using the device camera and microphone. The server captures facial expressions using OpenCV and recognizes emotions using deep learning libraries such as TensorFlow or Keras. As output, user data and emotional data are stored in a secure database.

[1328] Step 2:

[1329] Data preprocessing and sentiment analysis

[1330] The server performs preprocessing by removing incomplete data and noise and standardizing the data. The input is the user data and emotion data collected in step 1, and the output is clear data after preprocessing. At the same time, the emotion recognition engine receives the user's facial expressions and voice tone as input and analyzes them. The output of the analysis is the user's emotional state (e.g., "happy," "excited," "anxious," etc.).

[1331] Step 3:

[1332] Artificial intelligence models for ad generation

[1333] The server runs the generative AI model using the clear data and emotion data that have been preprocessed. The input is the clear data and emotion data from the previous step, and the output is the optimal advertising elements (visual media, still images, text, appeal content, and characters) for each target. Specifically, the generative AI model generates multiple advertising elements and combines them based on the prompt text.

[1334] Step 4:

[1335] Ad element selection and optimization

[1336] The server selects the most effective ad content from the generated ad elements based on historical ad performance data, real-time user data, and current user sentiment data. The inputs are the generated ad elements, historical performance data, and real-time data. The output is optimized ad content. The server runs an algorithm to do this and fine-tunes the ad content.

[1337] Step 5:

[1338] Ad serving

[1339] The server registers the selected advertising content in the distribution reservation system and sets the distribution schedule. The input is the optimized advertising content, and the output is the advertisement delivered to the user's device. Specifically, the server determines the optimal timing based on the user's online activity time and emotional data, and instructs the device to display the advertisement the next time the user accesses the web.

[1340] Step 6:

[1341] Data collection and feedback

[1342] The user's device records response data to the ad (number of clicks, viewing time, purchase history, etc.) and sends it to the server. The input is the user's response data to the ad, and the output is feedback data recorded on the server. The server analyzes this feedback data and updates and optimizes the generative AI model. Specifically, the server analyzes the feedback data and uses it in the next ad generation process.

[1343] The specific processing unit 290 transmits the result of the specific processing to the robot 414. In the robot 414, the control unit 46A causes the speaker 240 and the control target 443 to output the result of the specific processing. The microphone 238 acquires voice indicating a user input regarding the result of the specific processing. The control unit 46A transmits voice data indicating the user input acquired by the microphone 238 to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the voice data.

[1344] The data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of the data generation model 58 is ChatGPT (Internet Search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search <url: https: gemini.google.com ?hl="ja">) and other generation AIs. The data generation model 58 is obtained by performing deep learning on a neural network. A prompt including an instruction is input to the data generation model 58, and inference data such as voice data indicating voice, text data indicating text, and image data indicating an image is also input. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt, and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[1345] In the above embodiment, an example was given in which the specific processing is performed by the data processing device 12, but the technology of the present disclosure is not limited to this, and the specific processing may be performed by the robot 414.

[1346] The emotion identification model 59 as an emotion engine may determine the user's emotion according to a specific mapping. Specifically, the emotion identification model 59 may determine the user's emotion according to an emotion map (see FIG. 9), which is a specific mapping. Similarly, the emotion identification model 59 may determine the robot's emotion, and the identification processing unit 290 may perform identification processing using the robot's emotion.

[1347] FIG. 9 is a diagram illustrating an emotion map 400 on which multiple emotions are mapped. In the emotion map 400, emotions are arranged in concentric circles radiating from the center. Emotions closer to the center of the concentric circles are more primitive. Emotions representing states and actions arising from a state of mind are arranged on the outer edges of the concentric circles. The concept of emotion includes both affect and mental states. Emotions generally generated from reactions occurring in the brain are arranged on the left side of the concentric circles. Emotions generally induced by situational judgment are arranged on the right side of the concentric circles. Emotions generally generated from reactions occurring in the brain and induced by situational judgment are arranged on the upper and lower sides of the concentric circles. Furthermore, the emotion of "pleasure" is arranged on the upper side of the concentric circles, and the emotion of "discomfort" is arranged on the lower side. In this way, in the emotion map 400, multiple emotions are mapped based on the structure by which emotions are generated, and emotions that tend to occur simultaneously are mapped close to each other.

[1348] These emotions are distributed in the 3 o'clock direction on emotion map 400, and typically fluctuate between relief and anxiety. In the right half of emotion map 400, situational awareness dominates over internal sensations, resulting in a sense of calm.

[1349] The inside of emotion map 400 represents what is going on in the mind, and the outside of emotion map 400 represents behavior, so the further you go outside emotion map 400, the more visible the emotions become (the more they are expressed in behavior).

[1350] Human emotions are based on various balances, such as posture and blood sugar levels. When these balances deviate from the ideal, a state of discomfort is indicated, and when they approach the ideal, a state of pleasure is indicated. Emotions can also be created for robots, automobiles, and motorcycles, based on various balances, such as posture and remaining battery life. When these balances deviate from the ideal, a state of discomfort is indicated, and when they approach the ideal, a state of pleasure is indicated. An emotion map can be generated, for example, based on Dr. Mitsuyoshi's emotion map (Research on Voice Emotion Recognition and Emotional Brain Physiological Signal Analysis Systems, Tokushima University, Doctoral Dissertation: https: / / ci.nii.ac.jp / naid / 500000375379). The left half of the emotion map lists emotions belonging to the "reaction" domain, where sensation is dominant. The right half of the emotion map lists emotions belonging to the "situation" domain, where situational awareness is dominant.

[1351] The emotion map defines two emotions that promote learning. One is a negative emotion on the situation side, around the middle of "repentance" or "reflection." In other words, this occurs when the robot experiences negative emotions such as "I never want to feel this way again" or "I don't want to be scolded again." The other is a positive emotion on the response side, around "desire." In other words, this occurs when the robot experiences positive feelings such as "I want more" or "I want to know more."

[1352] The emotion identification model 59 inputs user input into a pre-trained neural network, obtains emotion values ​​indicating each emotion shown in the emotion map 400, and determines the user's emotion. This neural network is pre-trained based on multiple pieces of training data that are combinations of user input and emotion values ​​indicating each emotion shown in the emotion map 400. Furthermore, this neural network is trained so that emotions that are located close to each other have similar values, as in the emotion map 900 shown in FIG. 10. FIG. 10 shows an example in which multiple emotions, "relieved," "calm," and "reassuring," have similar emotion values.

[1353] The system according to the present disclosure has been described above mainly with respect to the functions of the data processing device 12, but the system according to the present disclosure is not necessarily implemented on a server. The system according to the present disclosure may be implemented as a general information processing system. The present disclosure may be implemented, for example, as a software program running on a personal computer or an application running on a smartphone, etc. The method according to the present disclosure may be provided to users in the form of SaaS (Software as a Service).

[1354] In the above embodiment, an example was given in which the specific processing is performed by one computer 22, but the technology of the present disclosure is not limited to this, and the specific processing may be distributed and performed by a plurality of computers including the computer 22. For example, the data generation model 58 may be provided in an external device of the data processing device 12, and data may be generated in the external device in accordance with input data.

[1355] In the above embodiment, an example in which the specific processing program 56 is stored in the storage 32 has been described, but the technology of the present disclosure is not limited to this. For example, the specific processing program 56 may be stored in a portable, computer-readable, non-transitory storage medium such as a USB (Universal Serial Bus) memory. The specific processing program 56 stored in the non-transitory storage medium is installed in the computer 22 of the data processing device 12. The processor 28 executes the specific processing in accordance with the specific processing program 56.

[1356] Alternatively, the specific processing program 56 may be stored in a storage device such as a server connected to the data processing device 12 via the network 54, and the specific processing program 56 may be downloaded and installed on the computer 22 in response to a request from the data processing device 12.

[1357] It is not necessary to store all of the specific processing program 56 in a storage device such as a server connected to the data processing device 12 via the network 54, or to store all of the specific processing program 56 in the storage 32; only a portion of the specific processing program 56 may be stored.

[1358] The hardware resource for executing a specific process can be any of the following processors: An example of a processor is a CPU, which is a general-purpose processor that functions as a hardware resource for executing a specific process by executing software, i.e., a program. Another example of a processor is a dedicated electrical circuit, such as an FPGA (Field-Programmable Gate Array), a PLD (Programmable Logic Device), or an ASIC (Application Specific Integrated Circuit), which is a processor with a circuit configuration designed specifically for executing a specific process. Each processor has built-in or connected memory, and each processor uses the memory to execute the specific process.

[1359] The hardware resource that executes the specific processing may be configured with one of these various processors, or may be configured with a combination of two or more processors of the same or different types (for example, a combination of multiple FPGAs, or a combination of a CPU and an FPGA). Also, the hardware resource that executes the specific processing may be a single processor.

[1360] As an example of a system configured with a single processor, first, one processor is configured by combining one or more CPUs and software, and this processor functions as a hardware resource that executes a specific process. Second, there is a system that uses a processor that realizes the functions of an entire system including multiple hardware resources that execute a specific process on a single IC chip, as typified by SoC (System-on-a-chip). In this way, a specific process is realized using one or more of the above-mentioned various processors as hardware resources.

[1361] Furthermore, the hardware structure of these various processors can be, more specifically, an electric circuit that combines circuit elements such as semiconductor devices. The specific processing described above is merely an example. Therefore, it goes without saying that unnecessary steps may be deleted, new steps may be added, or the processing order may be rearranged, without departing from the spirit of the invention.

[1362] The above-described description and illustrations are a detailed explanation of the parts related to the technology of the present disclosure and are merely an example of the technology of the present disclosure. For example, the above description of the configuration, functions, actions, and effects is an explanation of an example of the configuration, functions, actions, and effects of the parts related to the technology of the present disclosure. Therefore, it goes without saying that unnecessary parts may be deleted, new elements may be added, or replacements may be made to the above-described description and illustrations within the scope of the gist of the technology of the present disclosure. Furthermore, to avoid confusion and facilitate understanding of the parts related to the technology of the present disclosure, the above-described description and illustrations omit explanations of common technical knowledge that do not require particular explanation to enable the implementation of the technology of the present disclosure.

[1363] All publications, patent applications, and technical standards mentioned in this specification are herein incorporated by reference to the same extent as if each individual publication, patent application, or technical standard was specifically and individually indicated to be incorporated by reference.

[1364] The following is further disclosed regarding the above embodiment.

[1365] (Claim 1)

[1366] a means for collecting user-provided information;

[1367] an artificial intelligence model for generating optimal advertising elements for the target using the collected information;

[1368] a means for selecting advertising content for each target based on the generated advertising elements;

[1369] means for delivering the selected advertising content to a user terminal;

[1370] means for analyzing user response data to the advertising content;

[1371] means for updating the artificial intelligence model using the analysis results;

[1372] A system including:

[1373] (Claim 2)

[1374] 2. The system of claim 1, wherein the collected information includes gender, age, hobbies and preferences, internet browsing history, and purchase history.

[1375] (Claim 3)

[1376] 2. The system according to claim 1, wherein the generated advertising elements include a web commercial, an image, a copy, a promotional content, and a featured talent.

[1377] "Example 1"

[1378] (Claim 1)

[1379] a means for collecting user-provided information;

[1380] means for pre-processing the collected information;

[1381] an artificial intelligence model for generating optimal advertising elements for the target using the pre-processed information;

[1382] a means for selecting advertising content for each target based on the generated advertising elements;

[1383] means for delivering the selected advertising content to a user terminal;

[1384] means for collecting user response data to the advertising content;

[1385] means for analyzing the collected reaction data;

[1386] means for updating the artificial intelligence model using the analysis results;

[1387] A system including:

[1388] (Claim 2)

[1389] 2. The system of claim 1, wherein the collected information includes gender, age, hobbies and preferences, internet browsing history, and purchase history.

[1390] (Claim 3)

[1391] 10. The system of claim 1, wherein the generated advertising elements include digital content, visual advertisements, text advertisements, promotional content, and performers.

[1392] "Application Example 1"

[1393] Rewritten claims

[1394] (Claim 1)

[1395] a means for collecting user-provided information;

[1396] an artificial intelligence model for generating optimal advertising elements for the target using the collected information;

[1397] a means for selecting advertising content for each target based on the generated advertising elements;

[1398] means for delivering the selected advertising content to a user terminal;

[1399] means for analyzing user response data to the advertising content;

[1400] means for updating the artificial intelligence model using the analysis results;

[1401] a processor for generating and optimizing advertising elements within the smart device;

[1402] an output device for displaying advertisements generated by the processor;

[1403] A system including:

[1404] (Claim 2)

[1405] 2. The system of claim 1, wherein the collected information includes gender, age, hobbies and preferences, internet browsing history and purchase history, as well as location information and application usage history.

[1406] (Claim 3)

[1407] 2. The system of claim 1, wherein the generated advertising elements include an advertising unit that is displayed within a specific application on a user terminal, in addition to a web commercial, an image, a copy, a promotional content, and a featured talent.

[1408] "Example 2: Combining Emotion Engines"

[1409] (Claim 1)

[1410] a means for collecting user-provided information;

[1411] an artificial intelligence model for generating optimal advertising elements for the target using the collected information and emotional information;

[1412] A means for selecting and fine-tuning advertising content for each target based on the generated advertising elements;

[1413] a scheduling and distribution means for distributing the selected and fine-tuned advertising content to a user terminal;

[1414] means for collecting and analyzing user response data to the advertising content;

[1415] means for continuously updating and optimizing the artificial intelligence model using the analysis results;

[1416] A system including:

[1417] (Claim 2)

[1418] 2. The system of claim 1, wherein the collected information and emotional information includes gender, age, hobbies and preferences, internet browsing history, purchase history, and emotional data based on voice tone and facial expression.

[1419] (Claim 3)

[1420] 2. The system of claim 1, wherein the generated advertising elements include web content, images, copy, claims, and performers.

[1421] "Application example 2 when combining emotion engines"

[1422] (Claim 1)

[1423] means for collecting user-provided information and emotional data;

[1424] an artificial intelligence model for generating optimal advertising elements for the target using the collected information and emotional data;

[1425] a means for selecting advertising content for each target based on the generated advertising elements;

[1426] means for delivering the selected advertising content to a user terminal;

[1427] means for analyzing user response data to the advertising content;

[1428] means for updating the artificial intelligence model using the analysis results;

[1429] A system including:

[1430] (Claim 2)

[1431] 2. The system of claim 1, wherein the collected information includes gender, age, hobbies and preferences, internet browsing history, purchase history, and emotion recognition data.

[1432] (Claim 3)

[1433] 10. The system of claim 1, wherein the generated advertising elements include visual media, still images, text, claims, and characters. [Explanation of symbols]

[1434] 10, 210, 310, 410 Data Processing Systems 12 Data Processing Device 14 Smart Devices 214 Smart Glasses 314 Headset-type terminal 414 Robot< / url:> < / url:> < / url:> < / url:>

Claims

1. a means for collecting user-provided information; an artificial intelligence model for generating optimal advertising elements for the target using the collected information; a means for selecting advertising content for each target based on the generated advertising elements; means for delivering the selected advertising content to a user terminal; means for analyzing user response data to the advertising content; means for updating the artificial intelligence model using the analysis results; A system including:

2. The system according to claim 1 , wherein the collected information includes gender, age, hobbies and preferences, internet browsing history, and purchase history.

3. The system according to claim 1 , wherein the generated advertising elements include a web commercial, an image, a copy, a promotional content, and a featured talent.

Images