system

Abstract

We provide the system. [Solution] A terminal that accepts user input, A computing device that controls the response generated based on the input, A control means that dynamically switches video content in response to the generated response, A means of providing compensation to users through the video content, A system that includes this.

Description

Technical Field

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

Background Art

[0002] Patent Document 1 discloses a method for controlling a persona chatbot, which is performed by at least one processor, and includes steps of receiving a user utterance, adding the user utterance to a prompt including an instruction sentence related to an explanation of a 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

Summary of the Invention

Problems to be Solved by the Invention

[0004] In conventional advertising systems, it is impossible to flexibly respond to the interests and needs of viewers, and the attention and effects of advertisements are limited. In addition, there is a problem that viewers have few opportunities to actively participate in advertisements, and it is difficult for advertising agencies to differentiate themselves.

Means for Solving the Problems

[0005] The present invention provides a system that uses a terminal for receiving an input from a user and generates a response by an arithmetic device based on the input. Furthermore, by including control means for dynamically switching video content according to the generated response and means for providing a reward to the user by the video content, viewer participation is promoted and a flexible and effective advertising experience is realized.

[0006] A "terminal that accepts user input" refers to a digital device that can receive and process information from users.

[0007] A "processing unit" refers to a machine or system that has the function of processing received data and executing instructed processes.

[0008] "Generated response" refers to the reaction or output result produced by the computing unit based on the input information from the user.

[0009] "A control means for dynamically switching video content" refers to a system or mechanism that has the ability to change video material in real time in response to user responses or actions.

[0010] A "virtual character" refers to a human-like character created by a computer that can interact with users.

[0011] "Means of providing rewards" refers to methods or mechanisms that provide some form of compensation to users based on their actions or interactions. [Brief explanation of the drawing]

[0012] [Figure 1] This is a conceptual diagram showing an example of the configuration of a data processing system according to the first embodiment. [Figure 2] This is a conceptual diagram showing an example of the essential functions of a data processing device and a smart device according to the first embodiment. [Figure 3] This is a conceptual diagram showing an example of the configuration of a data processing system according to the second embodiment. [Figure 4] This is a conceptual diagram showing an example of the main functions of a data processing device and smart glasses according to the second embodiment. [Figure 5] This is a conceptual diagram showing an example of the configuration of a data processing system according to the third embodiment. [Figure 6]It is a conceptual diagram showing an example of the main functions of a data processing device and a headset-type terminal according to the third embodiment. [Figure 7] It is a conceptual diagram showing an example of the configuration of a data processing system according to the fourth embodiment. [Figure 8] It is a conceptual diagram showing an example of the main functions of a data processing device and a robot according to the fourth embodiment. [Figure 9] It shows an emotion map to which a plurality of emotions are mapped. [Figure 10] It shows an emotion map to which a plurality of emotions are mapped. [Figure 11] It is a sequence diagram showing the processing flow of the data processing system in Example 1. [Figure 12] It is a sequence diagram showing the processing flow of the data processing system in Application Example 1. [Figure 13] It is a sequence diagram showing the processing flow of the data processing system in Example 2 when an emotion engine is combined. [Figure 14] It is a sequence diagram showing the processing flow of the data processing system in Application Example 2 when an emotion engine is combined.

Modes for Carrying Out the Invention

[0013] Hereinafter, an example of an embodiment of a system according to the technology of the present disclosure will be described with reference to the accompanying drawings.

[0014] First, the language used in the following description will be explained.

[0015] In the following embodiments, the labeled processor (hereinafter simply referred to as "processor") may be a single arithmetic unit or a combination of multiple arithmetic units. Also, the processor may be a single type of arithmetic unit or a combination of multiple types of arithmetic units. Examples of arithmetic units include a CPU (Central Processing Unit), a GPU (Graphics Processing Unit), a GPGPU (General-Purpose computing on Graphics Processing Units), an APU (Accelerated Processing Unit), and the like.

[0016] In the following embodiments, the labeled RAM (Random Access Memory) is a memory in which information is temporarily stored and is used as a work memory by the processor.

[0017] In the following embodiments, the labeled storage is one or more non-volatile storage devices that store various programs and various parameters, etc. Examples of non-volatile storage devices include flash memory (SSD (Solid State Drive)), magnetic disks (e.g., hard disks), or magnetic tapes, etc.

[0018] In the following embodiments, the labeled communication I / F (Interface) is an interface that includes a communication processor and 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), or Bluetooth (registered trademark), etc.

[0019] In the following embodiments, "A and / or B" is synonymous with "at least one of A and B." That is, "A and / or B" means that it may be A alone, or B alone, or a combination of A and B. Furthermore, in this specification, the same concept as "A and / or B" applies when expressing three or more things linked by "and / or."

[0020] [First Embodiment]

[0021] Figure 1 shows an example of the configuration of the data processing system 10 according to the first embodiment.

[0022] As shown in Figure 1, the 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.

[0023] The data processing device 12 comprises a computer 22, a database 24, and a communication interface 26. The computer 22 is an example of a "computer" related to the technology of this disclosure. The computer 22 comprises a processor 28, RAM 30, and storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication interface 26 are also connected to the bus 34. The communication interface 26 is connected to a network 54. An example of the network 54 is a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0024] The smart device 14 comprises a computer 36, a reception device 38, an output device 40, a camera 42, and a communication interface 44. The computer 36 comprises a processor 46, RAM 48, and storage 50. The processor 46, RAM 48, and storage 50 are connected to a bus 52. The reception device 38, output device 40, and camera 42 are also connected to the bus 52.

[0025] The reception device 38 is equipped with a touch panel 38A and a microphone 38B, etc., and receives user input. The touch panel 38A receives user input by detecting contact with an object (e.g., a pen or finger). The microphone 38B receives user input by detecting the user's voice. The control unit 46A transmits data indicating the user input received by the touch panel 38A and 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.

[0026] 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 perceptible to the user 20 (e.g., audio and / or text). The display 40A displays visible information such as text and images according to instructions from the processor 46. The speaker 40B outputs audio according to instructions from the processor 46. The camera 42 is a small digital camera equipped with an optical system such as a lens, aperture, and shutter, and an image sensor such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor.

[0027] Communication interface 44 is connected to network 54. Communication interfaces 44 and 26 are responsible for the exchange of various types of information between processor 46 and processor 28 via network 54.

[0028] Figure 2 shows an example of the main functions of the data processing device 12 and the smart device 14.

[0029] As shown in Figure 2, in the data processing device 12, a specific processing 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" related to the technology of this 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 according to the specific processing program 56 executed on the RAM 30.

[0030] The storage 32 stores the data generation model 58 and the emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[0031] In the smart device 14, the processor 46 performs the reception output processing. The storage 50 stores the reception output program 60. The reception output program 60 is used in conjunction with a 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 processing is realized by the processor 46 operating as a control unit 46A according to the reception output program 60 executed on the RAM 48.

[0032] Next, the specific processing performed by the specific processing unit 290 of the data processing device 12 will be described. In the following description, the data processing device 12 will be referred to as the "server" and the smart device 14 as the "terminal".

[0033] The present invention provides an interactive advertising system that can communicate with users, and a specific embodiment thereof is shown below.

[0034] The system consists of a terminal that accepts input via user voice or button presses, and a server.

[0035] First, the device connects to the server via the internet and requests an advertisement video. The server selects optimized advertisement content based on the user's profile information and browsing history, and sends that information to the device. The device then plays the advertisement video based on the received information.

[0036] The advertising videos include virtual humans, who have the ability to ask questions to the user. Users can respond using voice commands or on-screen options via their device. For example, in a cosmetics advertisement, the virtual human might ask, "What is your skin type?"

[0037] The device sends the user's response to the server in real time. The server analyzes the received response using natural language processing and regenerates corresponding advertisement content. If the user answers "dry skin," the next advertisement video for the most suitable moisturizing cream will be played.

[0038] It also features a function that provides rewards in response to user interactions. Once an interaction is complete, the server sends information about the reward or benefit to the device, which the user can then view on their device.

[0039] This system configuration allows advertising agencies to directly approach users' interests and provides viewers with a new advertising experience where they can enjoy ads tailored to their preferences.

[0040] The following describes the processing flow.

[0041] Step 1:

[0042] The device connects to the server via the internet and sends a request for an advertising video along with the user's information to the server.

[0043] Step 2:

[0044] Based on the user information received by the server, it selects an advertising video optimized for that user. The selection takes into account the user's profile and past viewing history.

[0045] Step 3:

[0046] The server sends the data and URL of the selected advertisement video to the device.

[0047] Step 4:

[0048] The device uses the data received from the server to start playing the advertisement video.

[0049] Step 5:

[0050] A virtual human appears in the video, posing specific questions to the user and requesting a response.

[0051] Step 6:

[0052] The user responds to the virtual human's questions with voice or selects options on the screen.

[0053] Step 7:

[0054] The terminal sends user response data to the server in real time.

[0055] Step 8:

[0056] The server analyzes the response data it receives and uses natural language processing to understand the user's intent.

[0057] Step 9:

[0058] The server selects the next appropriate video ad sequence based on the user's response and sends that information to the device.

[0059] Step 10:

[0060] The device plays a new advertisement video sent from the server.

[0061] Step 11:

[0062] Once the interaction with the user is complete, the server generates reward information and sends it to the device.

[0063] Step 12:

[0064] The device displays information on the screen to the user regarding the receipt of rewards and how to use them.

[0065] (Example 1)

[0066] Next, we will describe Example 1. In the following description, the data processing device 12 will be referred to as the "server," and the smart device 14 will be referred to as the "terminal."

[0067] Traditional advertising systems could only deliver advertisements to users in a one-way manner, making it difficult to provide dynamic and personalized advertising experiences based on users' interests and attributes. Furthermore, there were limitations to methods for improving viewership and increasing user engagement, creating a need for an interactive and flexible system to maximize advertising effectiveness.

[0068] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 1 is realized by the following means.

[0069] In this invention, the server includes means for selecting optimized video information based on the user's attribute information and past history information, means for dynamically adjusting the video content in response to the generated response, and means for utilizing a generative AI model that provides new video content based on the generated response. This enables personalized advertising experiences based on the user's interests and attributes.

[0070] "Users" refer to individual individuals who operate and access the system, and who receive advertising content through their interactions.

[0071] "Input" refers to the information and operations that users provide through their devices, and includes various forms such as voice and touch input.

[0072] A "terminal" is a device used by users for interactive operations, and includes mobile computing devices such as smartphones and tablets.

[0073] An "information processing device" refers to a device that performs necessary calculations and data processing based on received input and generates a response.

[0074] "Attribute information" refers to characteristics and profile information about users, including data such as age, gender, and preferences.

[0075] "History information" refers to records of users' past actions and interactions, and is data that enables the provision of more relevant content based on this information.

[0076] "Visual information" refers to the video and image data that make up advertisements and content, and is presented to users visually.

[0077] A "generative AI model" refers to a computational model that uses artificial intelligence to dynamically generate new content and responses based on input data.

[0078] A "virtual character" refers to a computer-generated person or character that appears in video content for the purpose of interactive dialogue.

[0079] "Rewards" refer to the benefits or incentives that users can receive when they complete an interaction within the system.

[0080] This invention provides an interactive advertising platform that can communicate with users. This system consists of a terminal that receives user input and a server that processes the information.

[0081] First, users request advertising videos by connecting to a server via the internet using a device such as a smartphone or tablet. The device accepts the user's voice input and touch input and sends this input to the server.

[0082] The server analyzes the user's attribute and history information received. This includes, for example, the types of advertisements the user has viewed in the past and the preferences registered in their user profile. An AI algorithm is used to select the most suitable video information. This selection process utilizes software that converts speech input into text using natural language processing technology.

[0083] The advertising video features a virtual human character who asks the user specific questions and facilitates interaction through dialogue. The user can respond using voice or on-screen options. The server then analyzes the response and generates a new advertising video optimized for that response using a new generative AI model. This new video is sent to the device, and the user watches it. For example, in a cosmetics advertisement, the user might be asked, "What is your skin type?" and if they answer that they have dry skin, an advertisement for moisturizing products will then be displayed.

[0084] Furthermore, once the user interaction is complete, the server calculates the reward and sends that information to the device. This reward is provided as points or coupons, which the user can use at a later date.

[0085] Examples of prompts include, "Generate an ad for the best moisturizing cream for people with dry skin," or "Generate an ad for a health food that can be recommended to a user who is aiming to lose weight."

[0086] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0087] Step 1:

[0088] The user requests an advertisement video via their device. The device accepts the user's voice input and button presses. It receives user input (e.g., a voice command such as "Please start the advertisement") and sends this information to the server via the internet in the form of a request. The output is request data sent to the server based on the user's advertisement viewing request.

[0089] Step 2:

[0090] Based on the requests received by the server, the system analyzes the user's profile and history information. It takes request data sent from the device as input. It then searches the database for user attribute information (e.g., past ad viewing history, registered profile) and selects the most suitable ad. The selected ad content is then returned as output.

[0091] Step 3:

[0092] The device receives advertising data sent from the server and plays the advertising video on the screen. The input is advertising content information sent from the server. Specifically, the video data is displayed on the device's screen, presenting it visually to the user. The output is an advertising video that the user can view.

[0093] Step 4:

[0094] The user responds to a question posed by a virtual character in the advertisement. The device accepts the user's voice and on-screen selections as input. For example, when the virtual character asks, "What is your skin type?", the user might answer "Dry skin" by voice. The output is the user's response data.

[0095] Step 5:

[0096] The terminal sends user responses to the server in real time. It receives dialogue data between the user and a virtual character as input. In the case of voice input, speech recognition software is used to convert it to text, and the data is sent to the server. The output is user response data for analysis.

[0097] Step 6:

[0098] Based on the response received by the server, analysis is performed using natural language processing. A generative AI model is used to generate new advertising content that is optimal for the response. The input is response data from the user. The server analyzes the response content using natural language processing and creates a new advertising video using a generative AI model. The output is the newly generated advertising content.

[0099] Step 7:

[0100] The device receives and plays a new advertising video. It receives new advertising content data from the server as input. Specifically, it displays the newly generated video on the device screen and offers the user the next advertisement. The output is the next viewable advertising video.

[0101] Step 8:

[0102] Once the user interaction is complete, the server calculates the reward and sends that information to the device. The input is the user's interaction history, which is used to calculate the reward and prepare the data. The reward information is then sent to the device for the user to review. The output is the reward information that the user can view on their device.

[0103] (Application Example 1)

[0104] Next, we will explain Application Example 1. In the following explanation, the data processing device 12 will be referred to as the "server," and the smart device 14 will be referred to as the "terminal."

[0105] The present invention aims to improve the user experience in advertising by providing technology that dynamically updates advertising content through interactive communication while delivering optimal advertisements based on user characteristics and interests. Conventional advertising systems have the problem of only providing content unilaterally, making it difficult to update content immediately in response to user reactions, and thus failing to provide information that is useful to users. Therefore, there is a need to develop a new system that solves these problems and has functions to further enhance user engagement.

[0106] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 1 is realized by the following means.

[0107] In this invention, the server includes an information processing device that receives user input, a computing device that controls the response generated based on the input, control means that dynamically switches video information according to the generated response, and means that uses a virtual character to ask questions to the user and dynamically update the advertising content based on the questions. This makes it possible to improve the user experience by providing advertisements that match the user's interests and characteristics, while also providing real-time content updates and rewards.

[0108] An "information processing device that accepts user input" is a device that allows users to input data through voice, button operations, etc., and has the role of transmitting that input information to a server.

[0109] A "computer that controls the generated response" is a device that performs calculations to generate the optimal response based on the user's input information.

[0110] A "dynamic video information switching control method" is a control method that has the function of changing the displayed advertisements and content in real time based on user responses.

[0111] "Methods for questioning users using virtual characters" refer to methods in which virtual character models that operate on a screen ask questions or engage in dialogue with users.

[0112] "Means for dynamically updating ad content" refers to a means of providing a function that changes and optimizes the displayed ad content in real time, reflecting information obtained from users.

[0113] This invention employs a system configuration combining terminals and servers to realize an interactive advertising system that can converse with users. This system primarily utilizes speech recognition and natural language processing technologies to provide advertising content optimized for the user.

[0114] The terminal functions as an information processing device, such as a smartphone equipped with a microphone, and accepts input via the user's voice or button presses. This input information is transmitted to a server via the internet. The server uses computing power to select the most suitable advertising content based on the user's profile information and past behavioral history. To do this, the server uses a database and machine learning models to perform data analysis and recommend advertisements relevant to the user.

[0115] The advertising content selected by the server is sent to the device as video information and played. A virtual character is displayed in the video and asks questions to the user. For example, in an advertisement for a beauty product, interaction such as "What is your skin type?" is possible. The device sends the user's response back to the server in real time, and the server analyzes this using natural language processing, updates the advertising content, and sends it again.

[0116] Furthermore, based on user interaction, the server sets rewards and benefits and sends reward information to the device. This configuration allows users to view ads tailored to their preferences, improving their engagement with advertisements.

[0117] A concrete example is a scenario where, when a user uses an application, a virtual human asks, "How are you feeling today?", and fashion-related advertisements are customized based on the user's response. An example of a prompt for a generative AI model would be, "Ask the user 'How are you feeling today?' and customize fashion-related advertisements based on their response."

[0118] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0119] Step 1:

[0120] The device accepts voice input and button presses from the user. This input data is collected through the smartphone's microphone and touchscreen and recorded as audio data. This provides basic data to understand what kind of information the user is seeking.

[0121] Step 2:

[0122] The device uses speech recognition software to convert voice input into text. Here, a speech recognition library (e.g., Google® Speech Recognition API) is used to analyze the voice data and generate corresponding text data. At this stage, voice data is received as input, and text data is generated as output.

[0123] Step 3:

[0124] The terminal sends the generated text data to the server over the internet. This transmission uses the standard HTTP protocol, and the user's text response is sent for further analysis on the server side. The input includes text data converted from speech, and the output is the transfer of that text data to the server.

[0125] Step 4:

[0126] The server generates a response using natural language processing techniques based on the received text data. Here, a generative AI model is used to select the advertising content that best suits the user's statements. In this process, the user's text data is used as input, and advertising content to be presented to the user is generated as output.

[0127] Step 5:

[0128] The server sends the selected advertising content back to the device. In this communication, advertising information is sent to the device as digital data. The data must be in a format suitable for the device's interface. The input includes optimized advertising content, and the output is the information displayed on the device.

[0129] Step 6:

[0130] The device displays the received advertising content on its screen and maintains interaction with the user using a virtual character. This ensures that the user receives the most relevant advertising message directly. For example, if the virtual character asks, "What is your skin type?" and the user answers, "Dry skin," an advertisement for a suitable moisturizing cream will be displayed. At this stage, the input is advertising information sent from the server, and the output is an updated advertising screen based on the user's actions.

[0131] Furthermore, an emotion engine that estimates the user's emotions may be incorporated. That is, the identification processing unit 290 may use the emotion identification model 59 to estimate the user's emotions and perform identification processing using the user's emotions.

[0132] This invention is an interactive advertising system that uses an emotion engine to recognize user emotions, and consists of a terminal that receives user input and a server. It also includes a virtual human for interacting with the user and control means for dynamically switching video content in response to the generated response.

[0133] First, the device connects to the server via the internet and requests an advertisement video. The server selects appropriate advertisement content based on the user's profile information and past interaction history, and delivers that information to the device. The device receives this information and plays the advertisement video.

[0134] As a user watches a video, the emotion engine analyzes the user's facial expressions and tone of voice, and evaluates their emotions in real time. For example, if the user shows curiosity, the emotion engine sends that information to the server.

[0135] The server can dynamically adjust ad content based on data from the emotion engine and instruct the virtual human to respond in a way that matches the user's emotions. For example, if the user shows interest in a product description, the virtual human will provide more detailed information.

[0136] Furthermore, when a user completes an interaction, the content and method of rewards are also adjusted based on their emotions. For example, if a user expresses positive emotions, they may be offered special offers or additional points.

[0137] In this way, incorporating an emotion engine makes advertisements more personalized and effective. By interacting with users based on their emotions, advertising agencies can achieve higher viewer satisfaction and more effective messaging.

[0138] The following describes the processing flow.

[0139] Step 1:

[0140] The device connects to the server via the internet and sends a request for an advertising video to the server. This request includes the user's profile information.

[0141] Step 2:

[0142] The server selects the most suitable advertising content based on the user's profile information. The selected advertising data is then sent to the device.

[0143] Step 3:

[0144] The device uses data received from the server to begin playing an advertisement video. This video contains a virtual human.

[0145] Step 4:

[0146] An emotion engine operates on the device, analyzing the user's facial expressions and voice tone in real time to generate emotion data.

[0147] Step 5:

[0148] The device sends the generated emotion data to the server.

[0149] Step 6:

[0150] The server analyzes emotional data and adjusts the currently playing advertisement content accordingly. This includes selecting video sequences based on emotions and modifying the virtual human's responses.

[0151] Step 7:

[0152] Users interact with a virtual human, responding to questions verbally and selecting options on the screen.

[0153] Step 8:

[0154] The terminal sends the user's response data back to the server.

[0155] Step 9:

[0156] The server analyzes user responses and sentiment data to determine what advertisement to play next and what compensation to offer.

[0157] Step 10:

[0158] Once the user completes the interaction, the server generates reward information and sends it to the device, including any perks or coupons.

[0159] Step 11:

[0160] The device displays reward information to the user and prompts them to check how to use the rewards and confirm their points.

[0161] (Example 2)

[0162] Next, we will describe Example 2. In the following description, the data processing device 12 will be referred to as the "server" and the smart device 14 as the "terminal".

[0163] Modern advertising faces challenges in effectively appealing to users because it fails to adequately address their individual emotions and preferences. In particular, advertising is often one-way and does not fully utilize user interaction, resulting in low viewer satisfaction. Furthermore, there is a problem with the inappropriate provision of rewards and benefits based on user emotions.

[0164] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means.

[0165] In this invention, the server includes an information processing device that receives user input, a computing means that controls the response generated based on the input, and a conversion means that dynamically switches visual content according to the generated response. This makes it possible to provide advertising content that is in line with the user's emotions and to improve viewer satisfaction.

[0166] An "information processing device" is a device that receives input from a user and performs a specified function.

[0167] "Computation means" refers to electronic equipment or software that generates a response based on user input and controls the content of that response.

[0168] "Conversion means" refers to a processing device or software for dynamically switching visual content in response to the generated response.

[0169] "Means of providing compensation" refers to a process or system for providing benefits or rewards to users through visual content.

[0170] "Analysis means" refers to technology or software used to analyze a user's facial expressions and voice to identify their emotions.

[0171] "Improvement measures" refer to processes or systems for adjusting visual content based on analyzed sentiment data.

[0172] "Natural language understanding means" refers to technology or software that processes a user's voice input and generates a response that a computer can understand.

[0173] A "virtual character" is a digitally generated character placed within visual content to interact with the user.

[0174] This invention is a system that recognizes user emotions and dynamically adjusts advertising content. This system has two main components: a terminal that receives user input and a server that processes information.

[0175] The terminal acquires user input via camera and microphone and sends the necessary data for emotion analysis to the server. The terminal has dedicated emotion recognition software installed, which analyzes facial expressions and voice tone in real time. The results of this analysis are quickly transmitted to the server.

[0176] The server evaluates the user's emotional state based on the received data and selects appropriate advertising content. The server has a recommendation system implemented that uses machine learning algorithms to determine the optimal content, taking into account user profile information and past interaction history.

[0177] The selected advertising content interacts with the user using a virtual character, and the advertising content is adjusted to match the user's emotions. For example, if a user shows interest in a product, the server can instruct the virtual character to provide further product information.

[0178] As a concrete example, suppose a user is viewing travel-related advertisements on their device, and the emotion engine detects the user's curiosity. Based on this information, the server dynamically adjusts the virtual character to provide content including detailed information and perks for the travel destination.

[0179] To enhance the effectiveness of this system, prompts generated using AI models are extremely helpful. An example of a prompt would be: "Please suggest a scenario for providing detailed information when a user expresses interest in a product. This information would be provided by a virtual character."

[0180] Thus, the system of the present invention is designed to realize an emotion-based, personalized advertising experience, thereby increasing user engagement and satisfaction.

[0181] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0182] Step 1:

[0183] The device receives advertising requests from users and sends them to the server as data packets along with profile information. It receives the user's selected advertising categories and profile data as input, and sends advertising requests to the server as output. In this process, the device plays the role of establishing a connection with the server via the internet.

[0184] Step 2:

[0185] The server processes ad requests received from the device and selects appropriate ad content based on the user's profile data and past browsing history. This selection uses a recommendation algorithm based on database queries and generative AI models. It receives profile data and ad requests from the device as input, and identifies and sends appropriate ad content to the device as output.

[0186] Step 3:

[0187] The device receives advertising content sent from the server and displays it to the user as visual content. Simultaneously, the device uses its camera and microphone to acquire data on the user's facial expressions and voice in real time. This data is used as input for emotion analysis, and the analysis results are generated as output. Specifically, the emotion engine identifies the user's emotional state by analyzing changes in the user's facial expressions and tone of voice.

[0188] Step 4:

[0189] The server receives sentiment analysis data sent from the terminal and dynamically adjusts the advertisement content. In this process, the user's sentiment data is taken as input, and the adjusted advertisement content is generated as output. Based on this data, the server updates the dialogue and visual content of the virtual character and resends it to the user.

[0190] Step 5:

[0191] When a user completes an interaction with an advertisement, the server determines a reward based on the user's past emotional data and notifies the user via their device. The server uses past emotional data and interaction completion information as input, and provides the user with information about rewards or points as output. This step improves the user experience and encourages repeat use.

[0192] (Application Example 2)

[0193] Next, we will explain application example 2. In the following explanation, the data processing device 12 will be referred to as a "server" and the smart device 14 as a "terminal".

[0194] Conventional advertising systems have struggled to provide personalized advertisements that take into account the emotions of users. As a result, they have suffered from insufficient appeal to viewers and insufficient advertising effectiveness. The present invention aims to solve the above problem by dynamically adjusting the content of advertisements based on the emotions of users and providing an interactive advertising experience that captures the interest of viewers.

[0195] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means.

[0196] In this invention, the server includes an emotion analysis means for analyzing the user's emotions, a means for dynamically generating advertising information based on the emotion data acquired by the emotion analysis means, and a means for presenting the advertising information to the user through a virtual character. This makes it possible to personalize advertisements according to the user's emotions and provide an engaging advertising experience through a virtual character.

[0197] An "information processing device" is a device that receives input from users and processes the data.

[0198] A "computational device" is a device that executes a specified process and generates and controls responses.

[0199] "Visual content" refers to dynamic video information displayed to the user.

[0200] A "control mechanism" is a function for overseeing and controlling the entire system.

[0201] "Means of providing rewards" refers to functions that offer benefits or incentives to users.

[0202] "Emotional analysis means" refers to a function that analyzes the user's emotions and acquires that information.

[0203] "Means for dynamically generating advertising information based on emotional data" refers to a function that changes and generates advertising content based on analyzed emotional data.

[0204] A "virtual character" is a computer-generated character that behaves like a human.

[0205] The system for implementing this invention includes an information processing device, a computing device, and emotion analysis means. A terminal receives user input, and this data is processed by the information processing device. The user's emotions are analyzed by the emotion analysis means installed in the information processing device, and this emotion data is transmitted to a server. The server dynamically generates advertising content in response using the computing device. This process utilizes computer vision technology and voice analysis software. Specifically, smart glasses equipped with a camera and microphone are used to analyze facial expressions and voice using software such as OpenCV or Praat. The server generates visual content based on this data and presents it to the user through a virtual person.

[0206] As a concrete example, when a user is walking in a city, smart glasses display information about nearby stores and analyze the user's emotions. If the user shows interest, a virtual character introduces special offers from those stores.

[0207] An example of a prompt message is: "When the user walks past the cafe through their smart glasses, perform real-time sentiment analysis, and if they show interest, have a virtual character recommend the day's menu."

[0208] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0209] Step 1:

[0210] The device receives input from the user. This input is captured by the camera and microphone and includes video and audio of the user's face. The device collects this data and transmits it to an emotion analysis system.

[0211] Step 2:

[0212] The sentiment analysis system installed in the device analyzes the collected input data. In this step, OpenCV is used to recognize facial expressions and Praat is used to analyze voice tone. The sentiment analysis system then identifies the user's emotions and generates the results as data.

[0213] Step 3:

[0214] Emotional data obtained through emotion analysis is sent to the server. The server receives this input data and performs data processing and calculations to generate advertising content optimized for the user. Specifically, it uses a generative AI model to design advertising content based on the user's emotions.

[0215] Step 4:

[0216] The server generates advertising content, which is then sent to the device. The device uses a virtual character to interactively present advertising information to the user. At this time, the advertisement is designed to combine visual and auditory elements to better capture the user's interest.

[0217] Step 5:

[0218] When a user responds to an ad, the device receives that input again and analyzes the data. Based on the analysis results, the server further adjusts the ad content and generates and presents a new interaction.

[0219] 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 user input for the result of the specific processing. The control unit 46A transmits the audio data indicating 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.

[0220] Data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of data generation model 58 is ChatGPT (registered trademark) (Internet search).<URL: https: / / openai.com / blog / chatgpt> ), Gemini (registered trademark) (Internet search) <url: https: gemini.google.com ?hl="ja">Examples of generative AI include the following. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 is input with prompts containing instructions, and with inference data such as audio data representing speech, text data representing text, and image data representing images. The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference results in data formats such as audio data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[0221] In the above embodiment, an example was given in which specific processing is performed by the data processing device 12, but the technology of this disclosure is not limited thereto, and the specific processing may also be performed by the smart device 14.

[0222] [Second Embodiment]

[0223] Figure 3 shows an example of the configuration of the data processing system 210 according to the second embodiment.

[0224] As shown in Figure 3, the data processing system 210 includes a data processing device 12 and smart glasses 214. An example of the data processing device 12 is a server.

[0225] The data processing device 12 comprises a computer 22, a database 24, and a communication interface 26. The computer 22 is an example of a "computer" related to the technology of this disclosure. The computer 22 comprises a processor 28, RAM 30, and storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication interface 26 are also connected to the bus 34. The communication interface 26 is connected to a network 54. An example of the network 54 is a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0226] The smart glasses 214 include a computer 36, a microphone 238, a speaker 240, a camera 42, and a communication interface 44. The computer 36 includes a processor 46, RAM 48, and storage 50. The processor 46, RAM 48, and storage 50 are connected to a bus 52. The microphone 238, speaker 240, and camera 42 are also connected to the bus 52.

[0227] The microphone 238 receives voice signals from the user 20 and receives instructions from the user 20. The microphone 238 captures the voice signals from the user 20, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to the instructions from the processor 46.

[0228] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an image sensor such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the area around the user 20 (for example, an imaging range defined by a field of view equivalent to the width of a typical healthy person's field of vision).

[0229] Communication interface 44 is connected to network 54. Communication interfaces 44 and 26 are responsible for the exchange of various information between processor 46 and processor 28 via network 54. The exchange of various information between processor 46 and processor 28 using communication interfaces 44 and 26 is performed in a secure manner.

[0230] Figure 4 shows an example of the main functions of the data processing device 12 and the smart glasses 214. As shown in Figure 4, the data processing device 12 performs specific processing using the processor 28. The storage 32 stores the specific processing program 56.

[0231] The specific processing program 56 is an example of a "program" relating to the technology of this 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.

[0232] The storage 32 stores the data generation model 58 and the emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[0233] In the smart glasses 214, the processor 46 performs the reception output processing. The storage 50 stores the reception output program 60. 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 processing is realized by the processor 46 operating as a control unit 46A according to the reception output program 60 executed on the RAM 48.

[0234] Next, the identification processing performed by the identification processing unit 290 of the data processing device 12 will be described. 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".

[0235] The present invention provides an interactive advertising system that can communicate with users, and a specific embodiment thereof is shown below.

[0236] The system consists of a terminal that accepts input via user voice or button presses, and a server.

[0237] First, the device connects to the server via the internet and requests an advertisement video. The server selects optimized advertisement content based on the user's profile information and browsing history, and sends that information to the device. The device then plays the advertisement video based on the received information.

[0238] The advertising videos include virtual humans, who have the ability to ask questions to the user. Users can respond using voice commands or on-screen options via their device. For example, in a cosmetics advertisement, the virtual human might ask, "What is your skin type?"

[0239] The device sends the user's response to the server in real time. The server analyzes the received response using natural language processing and regenerates corresponding advertisement content. If the user answers "dry skin," the next advertisement video for the most suitable moisturizing cream will be played.

[0240] It also features a function that provides rewards in response to user interactions. Once an interaction is complete, the server sends information about the reward or benefit to the device, which the user can then view on their device.

[0241] This system configuration allows advertising agencies to directly approach users' interests and provides viewers with a new advertising experience where they can enjoy ads tailored to their preferences.

[0242] The following describes the processing flow.

[0243] Step 1:

[0244] The device connects to the server via the internet and sends a request for an advertising video along with the user's information to the server.

[0245] Step 2:

[0246] Based on the user information received by the server, it selects an advertising video optimized for that user. The selection takes into account the user's profile and past viewing history.

[0247] Step 3:

[0248] The server sends the data and URL of the selected advertisement video to the device.

[0249] Step 4:

[0250] The device uses the data received from the server to start playing the advertisement video.

[0251] Step 5:

[0252] A virtual human appears in the video, posing specific questions to the user and requesting a response.

[0253] Step 6:

[0254] The user responds to the virtual human's questions with voice or selects options on the screen.

[0255] Step 7:

[0256] The terminal sends user response data to the server in real time.

[0257] Step 8:

[0258] The server analyzes the response data it receives and uses natural language processing to understand the user's intent.

[0259] Step 9:

[0260] The server selects the next appropriate video ad sequence based on the user's response and sends that information to the device.

[0261] Step 10:

[0262] The device plays a new advertisement video sent from the server.

[0263] Step 11:

[0264] Once the interaction with the user is complete, the server generates reward information and sends it to the device.

[0265] Step 12:

[0266] The device displays information on the screen to the user regarding the receipt of rewards and how to use them.

[0267] (Example 1)

[0268] Next, we will describe Example 1. 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."

[0269] Traditional advertising systems could only deliver advertisements to users in a one-way manner, making it difficult to provide dynamic and personalized advertising experiences based on users' interests and attributes. Furthermore, there were limitations to methods for improving viewership and increasing user engagement, creating a need for an interactive and flexible system to maximize advertising effectiveness.

[0270] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 1 is realized by the following means.

[0271] In this invention, the server includes means for selecting optimized video information based on the user's attribute information and past history information, means for dynamically adjusting the video content in response to the generated response, and means for utilizing a generative AI model that provides new video content based on the generated response. This enables personalized advertising experiences based on the user's interests and attributes.

[0272] "Users" refer to individual individuals who operate and access the system, and who receive advertising content through their interactions.

[0273] "Input" refers to the information and operations that users provide through their devices, and includes various forms such as voice and touch input.

[0274] A "terminal" is a device used by users for interactive operations, and includes mobile computing devices such as smartphones and tablets.

[0275] An "information processing device" refers to a device that performs necessary calculations and data processing based on received input and generates a response.

[0276] "Attribute information" refers to characteristics and profile information about users, including data such as age, gender, and preferences.

[0277] "History information" refers to records of users' past actions and interactions, and is data that enables the provision of more relevant content based on this information.

[0278] "Visual information" refers to the video and image data that make up advertisements and content, and is presented to users visually.

[0279] A "generative AI model" refers to a computational model that uses artificial intelligence to dynamically generate new content and responses based on input data.

[0280] A "virtual character" refers to a computer-generated person or character that appears in video content for the purpose of interactive dialogue.

[0281] "Rewards" refer to the benefits or incentives that users can receive when they complete an interaction within the system.

[0282] This invention provides an interactive advertising platform that can communicate with users. This system consists of a terminal that receives user input and a server that processes the information.

[0283] First, the user uses a terminal such as a smartphone or tablet to connect to the server via the Internet to request an advertising video. The terminal accepts the user's voice input and touch operations and transmits these inputs to the server.

[0284] The server analyzes the received user attribute information and history information. This includes, for example, what genres of advertisements the user has viewed in the past and the preference information registered in the user profile. An AI algorithm is used to select the most suitable video information. For this selection, software that converts voice input to text using natural language processing technology is helpful.

[0285] In the advertising video, a virtual human, a virtual character, appears, asks specific questions to the user, and promotes interaction in a dialogue format. The user can respond using voice or options on the screen. The server analyzes the response again and uses a new generation AI model to generate a new advertising video optimized for the response. This new video is transmitted to the terminal, and the user watches it. As a specific example, in a cosmetics advertisement, the question "What is your skin type?" is asked, and if the answer is dry skin, an advertisement for a moisturizing product is displayed next.

[0286] Furthermore, when the user's interaction is completed, the server calculates the reward and transmits the information to the terminal. This reward is provided as points or coupons and can be used by the user at a later date.

[0287] Examples of prompt sentences include "Please generate an advertisement for the optimal moisturizing cream for people with dry skin" or "Please generate an advertisement for health foods that can be recommended to users aiming for weight loss."

[0288] The flow of the specific process in Example 1 will be described using FIG. 11.

[0289] Step 1:

[0290] The user requests an advertisement video via their device. The device accepts the user's voice input and button presses. It receives user input (e.g., a voice command such as "Please start the advertisement") and sends this information to the server via the internet in the form of a request. The output is request data sent to the server based on the user's advertisement viewing request.

[0291] Step 2:

[0292] Based on the requests received by the server, the system analyzes the user's profile and history information. It takes request data sent from the device as input. It then searches the database for user attribute information (e.g., past ad viewing history, registered profile) and selects the most suitable ad. The selected ad content is then returned as output.

[0293] Step 3:

[0294] The device receives advertising data sent from the server and plays the advertising video on the screen. The input is advertising content information sent from the server. Specifically, the video data is displayed on the device's screen, presenting it visually to the user. The output is an advertising video that the user can view.

[0295] Step 4:

[0296] The user responds to a question posed by a virtual character in the advertisement. The device accepts the user's voice and on-screen selections as input. For example, when the virtual character asks, "What is your skin type?", the user might answer "Dry skin" by voice. The output is the user's response data.

[0297] Step 5:

[0298] The terminal sends user responses to the server in real time. It receives dialogue data between the user and a virtual character as input. In the case of voice input, speech recognition software is used to convert it to text, and the data is sent to the server. The output is user response data for analysis.

[0299] Step 6:

[0300] Based on the response received by the server, analysis is performed using natural language processing. A generative AI model is used to generate new advertising content that is optimal for the response. The input is response data from the user. The server analyzes the response content using natural language processing and creates a new advertising video using a generative AI model. The output is the newly generated advertising content.

[0301] Step 7:

[0302] The device receives and plays a new advertising video. It receives new advertising content data from the server as input. Specifically, it displays the newly generated video on the device screen and offers the user the next advertisement. The output is the next viewable advertising video.

[0303] Step 8:

[0304] Once the user interaction is complete, the server calculates the reward and sends that information to the device. The input is the user's interaction history, which is used to calculate the reward and prepare the data. The reward information is then sent to the device for the user to review. The output is the reward information that the user can view on their device.

[0305] (Application Example 1)

[0306] Next, we will explain Application Example 1. In the following explanation, the data processing device 12 will be referred to as the "server," and the smart glasses 214 will be referred to as the "terminal."

[0307] The purpose of the present invention is to provide a technology for providing an optimal advertisement based on user characteristics and interests while dynamically updating advertisement content through interactive interaction in order to improve the user experience in advertisements. In conventional advertising systems, there has been a problem that it is difficult to perform immediate updates according to user reactions only through one-way content provision, and useful information cannot be provided to users. Therefore, there is a need to develop a new system that solves these problems and further has a function of enhancing user engagement.

[0308] The specific processing by the specific processing unit 290 of the data processing device 12 in Application Example 1 is realized by the following means.

[0309] In this invention, the server includes an information processing device that receives user input, a computing device that controls a response generated based on the input, a control means that dynamically switches video information according to the generated response, and means that uses a virtual character to ask the user a question and dynamically updates the advertisement content based on the question. Thereby, while providing an advertisement that matches the interests and characteristics of the user, it is possible to improve the user experience through real-time content update and reward provision.

[0310] The "information processing device that receives user input" is a device through which a user can input data through voice, button operations, etc., and has a role of transmitting the input information to the server.

[0311] The "computing device that controls the generated response" is a device that performs operations for generating an optimal response based on the user input information.

[0312] The "control means that dynamically switches video information" is a control means having a function of changing in real time the advertisement or content displayed based on the response from the user.

[0313] "Methods for questioning users using virtual characters" refer to methods in which virtual character models that operate on a screen ask questions or engage in dialogue with users.

[0314] "Means for dynamically updating ad content" refers to a means of providing a function that changes and optimizes the displayed ad content in real time, reflecting information obtained from users.

[0315] This invention employs a system configuration combining terminals and servers to realize an interactive advertising system that can converse with users. This system primarily utilizes speech recognition and natural language processing technologies to provide advertising content optimized for the user.

[0316] The terminal functions as an information processing device, such as a smartphone equipped with a microphone, and accepts input via the user's voice or button presses. This input information is transmitted to a server via the internet. The server uses computing power to select the most suitable advertising content based on the user's profile information and past behavioral history. To do this, the server uses a database and machine learning models to perform data analysis and recommend advertisements relevant to the user.

[0317] The advertising content selected by the server is sent to the device as video information and played. A virtual character is displayed in the video and asks questions to the user. For example, in an advertisement for a beauty product, interaction such as "What is your skin type?" is possible. The device sends the user's response back to the server in real time, and the server analyzes this using natural language processing, updates the advertising content, and sends it again.

[0318] Furthermore, based on user interaction, the server sets rewards and benefits and sends reward information to the device. This configuration allows users to view ads tailored to their preferences, improving their engagement with advertisements.

[0319] A concrete example is a scenario where, when a user uses an application, a virtual human asks, "How are you feeling today?", and fashion-related advertisements are customized based on the user's response. An example of a prompt for a generative AI model would be, "Ask the user 'How are you feeling today?' and customize fashion-related advertisements based on their response."

[0320] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0321] Step 1:

[0322] The device accepts voice input and button presses from the user. This input data is collected through the smartphone's microphone and touchscreen and recorded as audio data. This provides basic data to understand what kind of information the user is seeking.

[0323] Step 2:

[0324] The device uses speech recognition software to convert voice input into text. Here, a speech recognition library (e.g., Google Speech Recognition API) is used to analyze the voice data and generate corresponding text data. At this stage, voice data is received as input, and text data is generated as output.

[0325] Step 3:

[0326] The terminal sends the generated text data to the server over the internet. This transmission uses the standard HTTP protocol, and the user's text response is sent for further analysis on the server side. The input includes text data converted from speech, and the output is the transfer of that text data to the server.

[0327] Step 4:

[0328] The server generates a response using natural language processing techniques based on the received text data. Here, a generative AI model is used to select the advertising content that best suits the user's statements. In this process, the user's text data is used as input, and advertising content to be presented to the user is generated as output.

[0329] Step 5:

[0330] The server sends the selected advertising content back to the device. In this communication, advertising information is sent to the device as digital data. The data must be in a format suitable for the device's interface. The input includes optimized advertising content, and the output is the information displayed on the device.

[0331] Step 6:

[0332] The device displays the received advertising content on its screen and maintains interaction with the user using a virtual character. This ensures that the user receives the most relevant advertising message directly. For example, if the virtual character asks, "What is your skin type?" and the user answers, "Dry skin," an advertisement for a suitable moisturizing cream will be displayed. At this stage, the input is advertising information sent from the server, and the output is an updated advertising screen based on the user's actions.

[0333] Furthermore, an emotion engine that estimates the user's emotions may be incorporated. That is, the identification processing unit 290 may use the emotion identification model 59 to estimate the user's emotions and perform identification processing using the user's emotions.

[0334] This invention is an interactive advertising system that uses an emotion engine to recognize user emotions, and consists of a terminal that receives user input and a server. It also includes a virtual human for interacting with the user and control means for dynamically switching video content in response to the generated response.

[0335] First, the device connects to the server via the internet and requests an advertisement video. The server selects appropriate advertisement content based on the user's profile information and past interaction history, and delivers that information to the device. The device receives this information and plays the advertisement video.

[0336] As a user watches a video, the emotion engine analyzes the user's facial expressions and tone of voice, and evaluates their emotions in real time. For example, if the user shows curiosity, the emotion engine sends that information to the server.

[0337] The server can dynamically adjust ad content based on data from the emotion engine and instruct the virtual human to respond in a way that matches the user's emotions. For example, if the user shows interest in a product description, the virtual human will provide more detailed information.

[0338] Furthermore, when a user completes an interaction, the content and method of rewards are also adjusted based on their emotions. For example, if a user expresses positive emotions, they may be offered special offers or additional points.

[0339] In this way, incorporating an emotion engine makes advertisements more personalized and effective. By interacting with users based on their emotions, advertising agencies can achieve higher viewer satisfaction and more effective messaging.

[0340] The following describes the processing flow.

[0341] Step 1:

[0342] The device connects to the server via the internet and sends a request for an advertising video to the server. This request includes the user's profile information.

[0343] Step 2:

[0344] The server selects the most suitable advertising content based on the user's profile information. The selected advertising data is then sent to the device.

[0345] Step 3:

[0346] The device uses data received from the server to begin playing an advertisement video. This video contains a virtual human.

[0347] Step 4:

[0348] An emotion engine operates on the device, analyzing the user's facial expressions and voice tone in real time to generate emotion data.

[0349] Step 5:

[0350] The device sends the generated emotion data to the server.

[0351] Step 6:

[0352] The server analyzes emotional data and adjusts the currently playing advertisement content accordingly. This includes selecting video sequences based on emotions and modifying the virtual human's responses.

[0353] Step 7:

[0354] Users interact with a virtual human, responding to questions verbally and selecting options on the screen.

[0355] Step 8:

[0356] The terminal sends the user's response data back to the server.

[0357] Step 9:

[0358] The server analyzes user responses and sentiment data to determine what advertisement to play next and what compensation to offer.

[0359] Step 10:

[0360] Once the user completes the interaction, the server generates reward information and sends it to the device, including any perks or coupons.

[0361] Step 11:

[0362] The device displays reward information to the user and prompts them to check how to use the rewards and confirm their points.

[0363] (Example 2)

[0364] Next, we will describe Example 2. 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".

[0365] Modern advertising faces challenges in effectively appealing to users because it fails to adequately address their individual emotions and preferences. In particular, advertising is often one-way and does not fully utilize user interaction, resulting in low viewer satisfaction. Furthermore, there is a problem with the inappropriate provision of rewards and benefits based on user emotions.

[0366] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means.

[0367] In this invention, the server includes an information processing device that receives user input, a computing means that controls the response generated based on the input, and a conversion means that dynamically switches visual content according to the generated response. This makes it possible to provide advertising content that is in line with the user's emotions and to improve viewer satisfaction.

[0368] An "information processing device" is a device that receives input from a user and performs a specified function.

[0369] "Computation means" refers to electronic equipment or software that generates a response based on user input and controls the content of that response.

[0370] "Conversion means" refers to a processing device or software for dynamically switching visual content in response to the generated response.

[0371] "Means of providing compensation" refers to a process or system for providing benefits or rewards to users through visual content.

[0372] "Analysis means" refers to technology or software used to analyze a user's facial expressions and voice to identify their emotions.

[0373] "Improvement measures" refer to processes or systems for adjusting visual content based on analyzed sentiment data.

[0374] "Natural language understanding means" refers to technology or software that processes a user's voice input and generates a response that a computer can understand.

[0375] A "virtual character" is a digitally generated character placed within visual content to interact with the user.

[0376] This invention is a system that recognizes user emotions and dynamically adjusts advertising content. This system has two main components: a terminal that receives user input and a server that processes information.

[0377] The terminal acquires user input via camera and microphone and sends the necessary data for emotion analysis to the server. The terminal has dedicated emotion recognition software installed, which analyzes facial expressions and voice tone in real time. The results of this analysis are quickly transmitted to the server.

[0378] The server evaluates the user's emotional state based on the received data and selects appropriate advertising content. The server has a recommendation system implemented that uses machine learning algorithms to determine the optimal content, taking into account user profile information and past interaction history.

[0379] The selected advertising content interacts with the user using a virtual character, and the advertising content is adjusted to match the user's emotions. For example, if a user shows interest in a product, the server can instruct the virtual character to provide further product information.

[0380] As a concrete example, suppose a user is viewing travel-related advertisements on their device, and the emotion engine detects the user's curiosity. Based on this information, the server dynamically adjusts the virtual character to provide content including detailed information and perks for the travel destination.

[0381] To enhance the effectiveness of this system, prompts generated using AI models are extremely helpful. An example of a prompt would be: "Please suggest a scenario for providing detailed information when a user expresses interest in a product. This information would be provided by a virtual character."

[0382] Thus, the system of the present invention is designed to realize an emotion-based, personalized advertising experience, thereby increasing user engagement and satisfaction.

[0383] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0384] Step 1:

[0385] The device receives advertising requests from users and sends them to the server as data packets along with profile information. It receives the user's selected advertising categories and profile data as input, and sends advertising requests to the server as output. In this process, the device plays the role of establishing a connection with the server via the internet.

[0386] Step 2:

[0387] The server processes ad requests received from the device and selects appropriate ad content based on the user's profile data and past browsing history. This selection uses a recommendation algorithm based on database queries and generative AI models. It receives profile data and ad requests from the device as input, and identifies and sends appropriate ad content to the device as output.

[0388] Step 3:

[0389] The device receives advertising content sent from the server and displays it to the user as visual content. Simultaneously, the device uses its camera and microphone to acquire data on the user's facial expressions and voice in real time. This data is used as input for emotion analysis, and the analysis results are generated as output. Specifically, the emotion engine identifies the user's emotional state by analyzing changes in the user's facial expressions and tone of voice.

[0390] Step 4:

[0391] The server receives sentiment analysis data sent from the terminal and dynamically adjusts the advertisement content. In this process, the user's sentiment data is taken as input, and the adjusted advertisement content is generated as output. Based on this data, the server updates the dialogue and visual content of the virtual character and resends it to the user.

[0392] Step 5:

[0393] When a user completes an interaction with an advertisement, the server determines a reward based on the user's past emotional data and notifies the user via their device. The server uses past emotional data and interaction completion information as input, and provides the user with information about rewards or points as output. This step improves the user experience and encourages repeat use.

[0394] (Application Example 2)

[0395] Next, we will explain application example 2. In the following explanation, the data processing device 12 will be referred to as the "server," and the smart glasses 214 will be referred to as the "terminal."

[0396] Conventional advertising systems have struggled to provide personalized advertisements that take into account the emotions of users. As a result, they have suffered from insufficient appeal to viewers and insufficient advertising effectiveness. The present invention aims to solve the above problem by dynamically adjusting the content of advertisements based on the emotions of users and providing an interactive advertising experience that captures the interest of viewers.

[0397] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means.

[0398] In this invention, the server includes an emotion analysis means for analyzing the user's emotions, a means for dynamically generating advertising information based on the emotion data acquired by the emotion analysis means, and a means for presenting the advertising information to the user through a virtual character. This makes it possible to personalize advertisements according to the user's emotions and provide an engaging advertising experience through a virtual character.

[0399] An "information processing device" is a device that receives input from users and processes the data.

[0400] A "computational device" is a device that executes a specified process and generates and controls responses.

[0401] "Visual content" refers to dynamic video information displayed to the user.

[0402] A "control mechanism" is a function for overseeing and controlling the entire system.

[0403] "Means of providing rewards" refers to functions that offer benefits or incentives to users.

[0404] "Emotional analysis means" refers to a function that analyzes the user's emotions and acquires that information.

[0405] "Means for dynamically generating advertising information based on emotional data" refers to a function that changes and generates advertising content based on analyzed emotional data.

[0406] A "virtual character" is a computer-generated character that behaves like a human.

[0407] The system for implementing this invention includes an information processing device, a computing device, and emotion analysis means. A terminal receives user input, and this data is processed by the information processing device. The user's emotions are analyzed by the emotion analysis means installed in the information processing device, and this emotion data is transmitted to a server. The server dynamically generates advertising content in response using the computing device. This process utilizes computer vision technology and voice analysis software. Specifically, smart glasses equipped with a camera and microphone are used to analyze facial expressions and voice using software such as OpenCV or Praat. The server generates visual content based on this data and presents it to the user through a virtual person.

[0408] As a concrete example, when a user is walking in a city, smart glasses display information about nearby stores and analyze the user's emotions. If the user shows interest, a virtual character introduces special offers from those stores.

[0409] An example of a prompt message is: "When the user walks past the cafe through their smart glasses, perform real-time sentiment analysis, and if they show interest, have a virtual character recommend the day's menu."

[0410] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0411] Step 1:

[0412] The device receives input from the user. This input is captured by the camera and microphone and includes video and audio of the user's face. The device collects this data and transmits it to an emotion analysis system.

[0413] Step 2:

[0414] The sentiment analysis system installed in the device analyzes the collected input data. In this step, OpenCV is used to recognize facial expressions and Praat is used to analyze voice tone. The sentiment analysis system then identifies the user's emotions and generates the results as data.

[0415] Step 3:

[0416] Emotional data obtained through emotion analysis is sent to the server. The server receives this input data and performs data processing and calculations to generate advertising content optimized for the user. Specifically, it uses a generative AI model to design advertising content based on the user's emotions.

[0417] Step 4:

[0418] The server generates advertising content, which is then sent to the device. The device uses a virtual character to interactively present advertising information to the user. At this time, the advertisement is designed to combine visual and auditory elements to better capture the user's interest.

[0419] Step 5:

[0420] When a user responds to an ad, the device receives that input again and analyzes the data. Based on the analysis results, the server further adjusts the ad content and generates and presents a new interaction.

[0421] 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 user input for the result of the specific processing. The control unit 46A transmits the audio data indicating user input acquired by the microphone 238 to the data processing unit 12. In the data processing unit 12, the specific processing unit 290 acquires the audio data.

[0422] Data generation model 58 is a type of so-called generative AI (Artificial Intelligence). One example of data generation model 58 is ChatGPT (Internet search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search) <url: https: gemini.google.com ?hl="ja">Examples of generative AI include the following. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 is input with prompts containing instructions, and with inference data such as audio data representing speech, text data representing text, and image data representing images. The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference results in data formats such as audio data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[0423] In the above embodiment, an example was given in which specific processing is performed by the data processing device 12, but the technology of this disclosure is not limited thereto, and the specific processing may also be performed by the smart glasses 214.

[0424] [Third Embodiment]

[0425] Figure 5 shows an example of the configuration of the data processing system 310 according to the third embodiment.

[0426] As shown in Figure 5, the data processing system 310 includes a data processing device 12 and a headset terminal 314. An example of the data processing device 12 is a server.

[0427] The data processing device 12 comprises a computer 22, a database 24, and a communication interface 26. The computer 22 is an example of a "computer" related to the technology of this disclosure. The computer 22 comprises a processor 28, RAM 30, and storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication interface 26 are also connected to the bus 34. The communication interface 26 is connected to a network 54. An example of the network 54 is a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0428] The headset terminal 314 includes a computer 36, a microphone 238, a speaker 240, a camera 42, a communication interface 44, and a display 343. The computer 36 includes a processor 46, RAM 48, and storage 50. The processor 46, RAM 48, and storage 50 are connected to a bus 52. The microphone 238, speaker 240, camera 42, and display 343 are also connected to the bus 52.

[0429] The microphone 238 receives voice signals from the user 20 and receives instructions from the user 20. The microphone 238 captures the voice signals from the user 20, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to the instructions from the processor 46.

[0430] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an image sensor such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the area around the user 20 (for example, an imaging range defined by a field of view equivalent to the width of a typical healthy person's field of vision).

[0431] Communication interface 44 is connected to network 54. Communication interfaces 44 and 26 are responsible for the exchange of various information between processor 46 and processor 28 via network 54. The exchange of various information between processor 46 and processor 28 using communication interfaces 44 and 26 is performed in a secure manner.

[0432] Figure 6 shows an example of the main functions of the data processing device 12 and the headset terminal 314. As shown in Figure 6, the data processing device 12 performs specific processing using the processor 28. The storage 32 stores the specific processing program 56.

[0433] The specific processing program 56 is an example of a "program" relating to the technology of this 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.

[0434] The storage 32 stores the data generation model 58 and the emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[0435] In the headset terminal 314, the processor 46 performs the reception output processing. The storage 50 stores the reception output program 60. 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 processing is realized by the processor 46 operating as a control unit 46A according to the reception output program 60 executed on the RAM 48.

[0436] Next, the specific processing performed by the specific processing unit 290 of the data processing device 12 will be described. In the following description, the data processing device 12 will be referred to as the "server" and the headset terminal 314 will be referred to as the "terminal".

[0437] The present invention provides an interactive advertising system that can communicate with users, and a specific embodiment thereof is shown below.

[0438] The system consists of a terminal that accepts input via user voice or button presses, and a server.

[0439] First, the device connects to the server via the internet and requests an advertisement video. The server selects optimized advertisement content based on the user's profile information and browsing history, and sends that information to the device. The device then plays the advertisement video based on the received information.

[0440] The advertising videos include virtual humans, who have the ability to ask questions to the user. Users can respond using voice commands or on-screen options via their device. For example, in a cosmetics advertisement, the virtual human might ask, "What is your skin type?"

[0441] The device sends the user's response to the server in real time. The server analyzes the received response using natural language processing and regenerates corresponding advertisement content. If the user answers "dry skin," the next advertisement video for the most suitable moisturizing cream will be played.

[0442] It also features a function that provides rewards in response to user interactions. Once an interaction is complete, the server sends information about the reward or benefit to the device, which the user can then view on their device.

[0443] This system configuration allows advertising agencies to directly approach users' interests and provides viewers with a new advertising experience where they can enjoy ads tailored to their preferences.

[0444] The following describes the processing flow.

[0445] Step 1:

[0446] The device connects to the server via the internet and sends a request for an advertising video along with the user's information to the server.

[0447] Step 2:

[0448] Based on the user information received by the server, it selects an advertising video optimized for that user. The selection takes into account the user's profile and past viewing history.

[0449] Step 3:

[0450] The server sends the data and URL of the selected advertisement video to the device.

[0451] Step 4:

[0452] The device uses the data received from the server to start playing the advertisement video.

[0453] Step 5:

[0454] A virtual human appears in the video, posing specific questions to the user and requesting a response.

[0455] Step 6:

[0456] The user responds to the virtual human's questions with voice or selects options on the screen.

[0457] Step 7:

[0458] The terminal sends user response data to the server in real time.

[0459] Step 8:

[0460] The server analyzes the response data it receives and uses natural language processing to understand the user's intent.

[0461] Step 9:

[0462] The server selects the next appropriate video ad sequence based on the user's response and sends that information to the device.

[0463] Step 10:

[0464] The device plays a new advertisement video sent from the server.

[0465] Step 11:

[0466] Once the interaction with the user is complete, the server generates reward information and sends it to the device.

[0467] Step 12:

[0468] The device displays information on the screen to the user regarding the receipt of rewards and how to use them.

[0469] (Example 1)

[0470] Next, we will describe Example 1. 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."

[0471] Traditional advertising systems could only deliver advertisements to users in a one-way manner, making it difficult to provide dynamic and personalized advertising experiences based on users' interests and attributes. Furthermore, there were limitations to methods for improving viewership and increasing user engagement, creating a need for an interactive and flexible system to maximize advertising effectiveness.

[0472] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 1 is realized by the following means.

[0473] In this invention, the server includes means for selecting optimized video information based on the user's attribute information and past history information, means for dynamically adjusting the video content in response to the generated response, and means for utilizing a generative AI model that provides new video content based on the generated response. This enables personalized advertising experiences based on the user's interests and attributes.

[0474] "Users" refer to individual individuals who operate and access the system, and who receive advertising content through their interactions.

[0475] "Input" refers to the information and operations that users provide through their devices, and includes various forms such as voice and touch input.

[0476] A "terminal" is a device used by users for interactive operations, and includes mobile computing devices such as smartphones and tablets.

[0477] An "information processing device" refers to a device that performs necessary calculations and data processing based on received input and generates a response.

[0478] "Attribute information" refers to characteristics and profile information about users, including data such as age, gender, and preferences.

[0479] "History information" refers to records of users' past actions and interactions, and is data that enables the provision of more relevant content based on this information.

[0480] "Visual information" refers to the video and image data that make up advertisements and content, and is presented to users visually.

[0481] A "generative AI model" refers to a computational model that uses artificial intelligence to dynamically generate new content and responses based on input data.

[0482] A "virtual character" refers to a computer-generated person or character that appears in video content for the purpose of interactive dialogue.

[0483] "Rewards" refer to the benefits or incentives that users can receive when they complete an interaction within the system.

[0484] This invention provides an interactive advertising platform that can communicate with users. This system consists of a terminal that receives user input and a server that processes the information.

[0485] First, users request advertising videos by connecting to a server via the internet using a device such as a smartphone or tablet. The device accepts the user's voice input and touch input and sends this input to the server.

[0486] The server analyzes the user's attribute and history information received. This includes, for example, the types of advertisements the user has viewed in the past and the preferences registered in their user profile. An AI algorithm is used to select the most suitable video information. This selection process utilizes software that converts speech input into text using natural language processing technology.

[0487] The advertising video features a virtual human character who asks the user specific questions and facilitates interaction through dialogue. The user can respond using voice or on-screen options. The server then analyzes the response and generates a new advertising video optimized for that response using a new generative AI model. This new video is sent to the device, and the user watches it. For example, in a cosmetics advertisement, the user might be asked, "What is your skin type?" and if they answer that they have dry skin, an advertisement for moisturizing products will then be displayed.

[0488] Furthermore, once the user interaction is complete, the server calculates the reward and sends that information to the device. This reward is provided as points or coupons, which the user can use at a later date.

[0489] Examples of prompts include, "Generate an ad for the best moisturizing cream for people with dry skin," or "Generate an ad for a health food that can be recommended to a user who is aiming to lose weight."

[0490] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0491] Step 1:

[0492] The user requests an advertisement video via their device. The device accepts the user's voice input and button presses. It receives user input (e.g., a voice command such as "Please start the advertisement") and sends this information to the server via the internet in the form of a request. The output is request data sent to the server based on the user's advertisement viewing request.

[0493] Step 2:

[0494] Based on the requests received by the server, the system analyzes the user's profile and history information. It takes request data sent from the device as input. It then searches the database for user attribute information (e.g., past ad viewing history, registered profile) and selects the most suitable ad. The selected ad content is then returned as output.

[0495] Step 3:

[0496] The device receives advertising data sent from the server and plays the advertising video on the screen. The input is advertising content information sent from the server. Specifically, the video data is displayed on the device's screen, presenting it visually to the user. The output is an advertising video that the user can view.

[0497] Step 4:

[0498] The user responds to a question posed by a virtual character in the advertisement. The device accepts the user's voice and on-screen selections as input. For example, when the virtual character asks, "What is your skin type?", the user might answer "Dry skin" by voice. The output is the user's response data.

[0499] Step 5:

[0500] The terminal sends user responses to the server in real time. It receives dialogue data between the user and a virtual character as input. In the case of voice input, speech recognition software is used to convert it to text, and the data is sent to the server. The output is user response data for analysis.

[0501] Step 6:

[0502] Based on the response received by the server, analysis is performed using natural language processing. A generative AI model is used to generate new advertising content that is optimal for the response. The input is response data from the user. The server analyzes the response content using natural language processing and creates a new advertising video using a generative AI model. The output is the newly generated advertising content.

[0503] Step 7:

[0504] The device receives and plays a new advertising video. It receives new advertising content data from the server as input. Specifically, it displays the newly generated video on the device screen and offers the user the next advertisement. The output is the next viewable advertising video.

[0505] Step 8:

[0506] Once the user interaction is complete, the server calculates the reward and sends that information to the device. The input is the user's interaction history, which is used to calculate the reward and prepare the data. The reward information is then sent to the device for the user to review. The output is the reward information that the user can view on their device.

[0507] (Application Example 1)

[0508] Next, we will explain Application Example 1. In the following explanation, 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."

[0509] The present invention aims to improve the user experience in advertising by providing technology that dynamically updates advertising content through interactive communication while delivering optimal advertisements based on user characteristics and interests. Conventional advertising systems have the problem of only providing content unilaterally, making it difficult to update content immediately in response to user reactions, and thus failing to provide information that is useful to users. Therefore, there is a need to develop a new system that solves these problems and has functions to further enhance user engagement.

[0510] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 1 is realized by the following means.

[0511] In this invention, the server includes an information processing device that receives user input, a computing device that controls the response generated based on the input, control means that dynamically switches video information according to the generated response, and means that uses a virtual character to ask questions to the user and dynamically update the advertising content based on the questions. This makes it possible to improve the user experience by providing advertisements that match the user's interests and characteristics, while also providing real-time content updates and rewards.

[0512] An "information processing device that accepts user input" is a device that allows users to input data through voice, button operations, etc., and has the role of transmitting that input information to a server.

[0513] A "computer that controls the generated response" is a device that performs calculations to generate the optimal response based on the user's input information.

[0514] A "dynamic video information switching control method" is a control method that has the function of changing the displayed advertisements and content in real time based on user responses.

[0515] "Methods for questioning users using virtual characters" refer to methods in which virtual character models that operate on a screen ask questions or engage in dialogue with users.

[0516] "Means for dynamically updating ad content" refers to a means of providing a function that changes and optimizes the displayed ad content in real time, reflecting information obtained from users.

[0517] This invention employs a system configuration combining terminals and servers to realize an interactive advertising system that can converse with users. This system primarily utilizes speech recognition and natural language processing technologies to provide advertising content optimized for the user.

[0518] The terminal functions as an information processing device, such as a smartphone equipped with a microphone, and accepts input via the user's voice or button presses. This input information is transmitted to a server via the internet. The server uses computing power to select the most suitable advertising content based on the user's profile information and past behavioral history. To do this, the server uses a database and machine learning models to perform data analysis and recommend advertisements relevant to the user.

[0519] The advertising content selected by the server is sent to the device as video information and played. A virtual character is displayed in the video and asks questions to the user. For example, in an advertisement for a beauty product, interaction such as "What is your skin type?" is possible. The device sends the user's response back to the server in real time, and the server analyzes this using natural language processing, updates the advertising content, and sends it again.

[0520] Furthermore, based on user interaction, the server sets rewards and benefits and sends reward information to the device. This configuration allows users to view ads tailored to their preferences, improving their engagement with advertisements.

[0521] A concrete example is a scenario where, when a user uses an application, a virtual human asks, "How are you feeling today?", and fashion-related advertisements are customized based on the user's response. An example of a prompt for a generative AI model would be, "Ask the user 'How are you feeling today?' and customize fashion-related advertisements based on their response."

[0522] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0523] Step 1:

[0524] The device accepts voice input and button presses from the user. This input data is collected through the smartphone's microphone and touchscreen and recorded as audio data. This provides basic data to understand what kind of information the user is seeking.

[0525] Step 2:

[0526] The device uses speech recognition software to convert voice input into text. Here, a speech recognition library (e.g., Google Speech Recognition API) is used to analyze the voice data and generate corresponding text data. At this stage, voice data is received as input, and text data is generated as output.

[0527] Step 3:

[0528] The terminal sends the generated text data to the server over the internet. This transmission uses the standard HTTP protocol, and the user's text response is sent for further analysis on the server side. The input includes text data converted from speech, and the output is the transfer of that text data to the server.

[0529] Step 4:

[0530] The server generates a response using natural language processing techniques based on the received text data. Here, a generative AI model is used to select the advertising content that best suits the user's statements. In this process, the user's text data is used as input, and advertising content to be presented to the user is generated as output.

[0531] Step 5:

[0532] The server sends the selected advertising content back to the device. In this communication, advertising information is sent to the device as digital data. The data must be in a format suitable for the device's interface. The input includes optimized advertising content, and the output is the information displayed on the device.

[0533] Step 6:

[0534] The device displays the received advertising content on its screen and maintains interaction with the user using a virtual character. This ensures that the user receives the most relevant advertising message directly. For example, if the virtual character asks, "What is your skin type?" and the user answers, "Dry skin," an advertisement for a suitable moisturizing cream will be displayed. At this stage, the input is advertising information sent from the server, and the output is an updated advertising screen based on the user's actions.

[0535] Furthermore, an emotion engine that estimates the user's emotions may be incorporated. That is, the identification processing unit 290 may use the emotion identification model 59 to estimate the user's emotions and perform identification processing using the user's emotions.

[0536] This invention is an interactive advertising system that uses an emotion engine to recognize user emotions, and consists of a terminal that receives user input and a server. It also includes a virtual human for interacting with the user and control means for dynamically switching video content in response to the generated response.

[0537] First, the device connects to the server via the internet and requests an advertisement video. The server selects appropriate advertisement content based on the user's profile information and past interaction history, and delivers that information to the device. The device receives this information and plays the advertisement video.

[0538] As a user watches a video, the emotion engine analyzes the user's facial expressions and tone of voice, and evaluates their emotions in real time. For example, if the user shows curiosity, the emotion engine sends that information to the server.

[0539] The server can dynamically adjust ad content based on data from the emotion engine and instruct the virtual human to respond in a way that matches the user's emotions. For example, if the user shows interest in a product description, the virtual human will provide more detailed information.

[0540] Furthermore, when a user completes an interaction, the content and method of rewards are also adjusted based on their emotions. For example, if a user expresses positive emotions, they may be offered special offers or additional points.

[0541] In this way, incorporating an emotion engine makes advertisements more personalized and effective. By interacting with users based on their emotions, advertising agencies can achieve higher viewer satisfaction and more effective messaging.

[0542] The following describes the processing flow.

[0543] Step 1:

[0544] The device connects to the server via the internet and sends a request for an advertising video to the server. This request includes the user's profile information.

[0545] Step 2:

[0546] The server selects the most suitable advertising content based on the user's profile information. The selected advertising data is then sent to the device.

[0547] Step 3:

[0548] The device uses data received from the server to begin playing an advertisement video. This video contains a virtual human.

[0549] Step 4:

[0550] An emotion engine operates on the device, analyzing the user's facial expressions and voice tone in real time to generate emotion data.

[0551] Step 5:

[0552] The device sends the generated emotion data to the server.

[0553] Step 6:

[0554] The server analyzes emotional data and adjusts the currently playing advertisement content accordingly. This includes selecting video sequences based on emotions and modifying the virtual human's responses.

[0555] Step 7:

[0556] Users interact with a virtual human, responding to questions verbally and selecting options on the screen.

[0557] Step 8:

[0558] The terminal sends the user's response data back to the server.

[0559] Step 9:

[0560] The server analyzes user responses and sentiment data to determine what advertisement to play next and what compensation to offer.

[0561] Step 10:

[0562] Once the user completes the interaction, the server generates reward information and sends it to the device, including any perks or coupons.

[0563] Step 11:

[0564] The device displays reward information to the user and prompts them to check how to use the rewards and confirm their points.

[0565] (Example 2)

[0566] Next, we will describe Example 2. 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."

[0567] Modern advertising faces challenges in effectively appealing to users because it fails to adequately address their individual emotions and preferences. In particular, advertising is often one-way and does not fully utilize user interaction, resulting in low viewer satisfaction. Furthermore, there is a problem with the inappropriate provision of rewards and benefits based on user emotions.

[0568] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means.

[0569] In this invention, the server includes an information processing device that receives user input, a computing means that controls the response generated based on the input, and a conversion means that dynamically switches visual content according to the generated response. This makes it possible to provide advertising content that is in line with the user's emotions and to improve viewer satisfaction.

[0570] An "information processing device" is a device that receives input from a user and performs a specified function.

[0571] "Computation means" refers to electronic equipment or software that generates a response based on user input and controls the content of that response.

[0572] "Conversion means" refers to a processing device or software for dynamically switching visual content in response to the generated response.

[0573] "Means of providing compensation" refers to a process or system for providing benefits or rewards to users through visual content.

[0574] "Analysis means" refers to technology or software used to analyze a user's facial expressions and voice to identify their emotions.

[0575] "Improvement measures" refer to processes or systems for adjusting visual content based on analyzed sentiment data.

[0576] "Natural language understanding means" refers to technology or software that processes a user's voice input and generates a response that a computer can understand.

[0577] A "virtual character" is a digitally generated character placed within visual content to interact with the user.

[0578] This invention is a system that recognizes user emotions and dynamically adjusts advertising content. This system has two main components: a terminal that receives user input and a server that processes information.

[0579] The terminal acquires user input via camera and microphone and sends the necessary data for emotion analysis to the server. The terminal has dedicated emotion recognition software installed, which analyzes facial expressions and voice tone in real time. The results of this analysis are quickly transmitted to the server.

[0580] The server evaluates the user's emotional state based on the received data and selects appropriate advertising content. The server has a recommendation system implemented that uses machine learning algorithms to determine the optimal content, taking into account user profile information and past interaction history.

[0581] The selected advertising content interacts with the user using a virtual character, and the advertising content is adjusted to match the user's emotions. For example, if a user shows interest in a product, the server can instruct the virtual character to provide further product information.

[0582] As a concrete example, suppose a user is viewing travel-related advertisements on their device, and the emotion engine detects the user's curiosity. Based on this information, the server dynamically adjusts the virtual character to provide content including detailed information and perks for the travel destination.

[0583] To enhance the effectiveness of this system, prompts generated using AI models are extremely helpful. An example of a prompt would be: "Please suggest a scenario for providing detailed information when a user expresses interest in a product. This information would be provided by a virtual character."

[0584] Thus, the system of the present invention is designed to realize an emotion-based, personalized advertising experience, thereby increasing user engagement and satisfaction.

[0585] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0586] Step 1:

[0587] The device receives advertising requests from users and sends them to the server as data packets along with profile information. It receives the user's selected advertising categories and profile data as input, and sends advertising requests to the server as output. In this process, the device plays the role of establishing a connection with the server via the internet.

[0588] Step 2:

[0589] The server processes ad requests received from the device and selects appropriate ad content based on the user's profile data and past browsing history. This selection uses a recommendation algorithm based on database queries and generative AI models. It receives profile data and ad requests from the device as input, and identifies and sends appropriate ad content to the device as output.

[0590] Step 3:

[0591] The device receives advertising content sent from the server and displays it to the user as visual content. Simultaneously, the device uses its camera and microphone to acquire data on the user's facial expressions and voice in real time. This data is used as input for emotion analysis, and the analysis results are generated as output. Specifically, the emotion engine identifies the user's emotional state by analyzing changes in the user's facial expressions and tone of voice.

[0592] Step 4:

[0593] The server receives sentiment analysis data sent from the terminal and dynamically adjusts the advertisement content. In this process, the user's sentiment data is taken as input, and the adjusted advertisement content is generated as output. Based on this data, the server updates the dialogue and visual content of the virtual character and resends it to the user.

[0594] Step 5:

[0595] When a user completes an interaction with an advertisement, the server determines a reward based on the user's past emotional data and notifies the user via their device. The server uses past emotional data and interaction completion information as input, and provides the user with information about rewards or points as output. This step improves the user experience and encourages repeat use.

[0596] (Application Example 2)

[0597] Next, we will explain application example 2. In the following explanation, 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."

[0598] Conventional advertising systems have struggled to provide personalized advertisements that take into account the emotions of users. As a result, they have suffered from insufficient appeal to viewers and insufficient advertising effectiveness. The present invention aims to solve the above problem by dynamically adjusting the content of advertisements based on the emotions of users and providing an interactive advertising experience that captures the interest of viewers.

[0599] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means.

[0600] In this invention, the server includes an emotion analysis means for analyzing the user's emotions, a means for dynamically generating advertising information based on the emotion data acquired by the emotion analysis means, and a means for presenting the advertising information to the user through a virtual character. This makes it possible to personalize advertisements according to the user's emotions and provide an engaging advertising experience through a virtual character.

[0601] An "information processing device" is a device that receives input from users and processes the data.

[0602] A "computational device" is a device that executes a specified process and generates and controls responses.

[0603] "Visual content" refers to dynamic video information displayed to the user.

[0604] A "control mechanism" is a function for overseeing and controlling the entire system.

[0605] "Means of providing rewards" refers to functions that offer benefits or incentives to users.

[0606] "Emotional analysis means" refers to a function that analyzes the user's emotions and acquires that information.

[0607] "Means for dynamically generating advertising information based on emotional data" refers to a function that changes and generates advertising content based on analyzed emotional data.

[0608] A "virtual character" is a computer-generated character that behaves like a human.

[0609] The system for implementing this invention includes an information processing device, a computing device, and emotion analysis means. A terminal receives user input, and this data is processed by the information processing device. The user's emotions are analyzed by the emotion analysis means installed in the information processing device, and this emotion data is transmitted to a server. The server dynamically generates advertising content in response using the computing device. This process utilizes computer vision technology and voice analysis software. Specifically, smart glasses equipped with a camera and microphone are used to analyze facial expressions and voice using software such as OpenCV or Praat. The server generates visual content based on this data and presents it to the user through a virtual person.

[0610] As a concrete example, when a user is walking in a city, smart glasses display information about nearby stores and analyze the user's emotions. If the user shows interest, a virtual character introduces special offers from those stores.

[0611] An example of a prompt message is: "When the user walks past the cafe through their smart glasses, perform real-time sentiment analysis, and if they show interest, have a virtual character recommend the day's menu."

[0612] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0613] Step 1:

[0614] The device receives input from the user. This input is captured by the camera and microphone and includes video and audio of the user's face. The device collects this data and transmits it to an emotion analysis system.

[0615] Step 2:

[0616] The sentiment analysis system installed in the device analyzes the collected input data. In this step, OpenCV is used to recognize facial expressions and Praat is used to analyze voice tone. The sentiment analysis system then identifies the user's emotions and generates the results as data.

[0617] Step 3:

[0618] Emotional data obtained through emotion analysis is sent to the server. The server receives this input data and performs data processing and calculations to generate advertising content optimized for the user. Specifically, it uses a generative AI model to design advertising content based on the user's emotions.

[0619] Step 4:

[0620] The server generates advertising content, which is then sent to the device. The device uses a virtual character to interactively present advertising information to the user. At this time, the advertisement is designed to combine visual and auditory elements to better capture the user's interest.

[0621] Step 5:

[0622] When a user responds to an ad, the device receives that input again and analyzes the data. Based on the analysis results, the server further adjusts the ad content and generates and presents a new interaction.

[0623] The specific processing unit 290 transmits the result of the specific processing to the headset terminal 314. In the headset terminal 314, the control unit 46A causes the speaker 240 and display 343 to output the result of the specific processing. The microphone 238 acquires audio indicating user input for the result of the specific processing. The control unit 46A transmits the audio data indicating user input acquired by the microphone 238 to the data processing unit 12. In the data processing unit 12, the specific processing unit 290 acquires the audio data.

[0624] Data generation model 58 is a type of so-called generative AI (Artificial Intelligence). One example of data generation model 58 is ChatGPT (Internet search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search) <url: https: gemini.google.com ?hl="ja">Examples of generative AI include the following. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 is input with prompts containing instructions, and with inference data such as audio data representing speech, text data representing text, and image data representing images. The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference results in data formats such as audio data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[0625] In the above embodiment, an example was given in which specific processing is performed by the data processing device 12, but the technology of this disclosure is not limited thereto, and specific processing may also be performed by the headset terminal 314.

[0626] [Fourth Embodiment]

[0627] Figure 7 shows an example of the configuration of the data processing system 410 according to the fourth embodiment.

[0628] As shown in Figure 7, the 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.

[0629] The data processing device 12 comprises a computer 22, a database 24, and a communication interface 26. The computer 22 is an example of a "computer" related to the technology of this disclosure. The computer 22 comprises a processor 28, RAM 30, and storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication interface 26 are also connected to the bus 34. The communication interface 26 is connected to a network 54. An example of the network 54 is a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0630] The robot 414 includes a computer 36, a microphone 238, a speaker 240, a camera 42, a communication interface 44, and a controlled object 443. The computer 36 includes a processor 46, RAM 48, and storage 50. The processor 46, RAM 48, and storage 50 are connected to a bus 52. The microphone 238, speaker 240, camera 42, and controlled object 443 are also connected to the bus 52.

[0631] The microphone 238 receives voice signals from the user 20 and receives instructions from the user 20. The microphone 238 captures the voice signals from the user 20, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to the instructions from the processor 46.

[0632] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an image sensor such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the area around the user 20 (for example, an imaging range defined by a field of view equivalent to the width of a typical healthy person's field of vision).

[0633] Communication interface 44 is connected to network 54. Communication interfaces 44 and 26 are responsible for the exchange of various information between processor 46 and processor 28 via network 54. The exchange of various information between processor 46 and processor 28 using communication interfaces 44 and 26 is performed in a secure manner.

[0634] The controlled object 443 includes a display device, LEDs in the eyes, and motors that drive 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 robot 414's emotions can be expressed by controlling these motors. Furthermore, the robot 414's facial expressions can also be expressed by controlling the illumination state of the LEDs in its eyes.

[0635] Figure 8 shows an example of the main functions of the data processing device 12 and the robot 414. As shown in Figure 8, the data processing device 12 performs specific processing using the processor 28. The storage 32 stores the specific processing program 56.

[0636] The specific processing program 56 is an example of a "program" relating to the technology of this 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.

[0637] The storage 32 stores the data generation model 58 and the emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[0638] In robot 414, the processor 46 performs the reception output processing. The storage 50 stores the reception output program 60. 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 processing is realized by the processor 46 operating as a control unit 46A according to the reception output program 60 executed on the RAM 48.

[0639] Next, the specific processing performed by the specific processing unit 290 of the data processing device 12 will be described. In the following description, the data processing device 12 will be referred to as the "server" and the robot 414 as the "terminal".

[0640] The present invention provides an interactive advertising system that can communicate with users, and a specific embodiment thereof is shown below.

[0641] The system consists of a terminal that accepts input via user voice or button presses, and a server.

[0642] First, the device connects to the server via the internet and requests an advertisement video. The server selects optimized advertisement content based on the user's profile information and browsing history, and sends that information to the device. The device then plays the advertisement video based on the received information.

[0643] The advertising videos include virtual humans, who have the ability to ask questions to the user. Users can respond using voice commands or on-screen options via their device. For example, in a cosmetics advertisement, the virtual human might ask, "What is your skin type?"

[0644] The device sends the user's response to the server in real time. The server analyzes the received response using natural language processing and regenerates corresponding advertisement content. If the user answers "dry skin," the next advertisement video for the most suitable moisturizing cream will be played.

[0645] It also features a function that provides rewards in response to user interactions. Once an interaction is complete, the server sends information about the reward or benefit to the device, which the user can then view on their device.

[0646] This system configuration allows advertising agencies to directly approach users' interests and provides viewers with a new advertising experience where they can enjoy ads tailored to their preferences.

[0647] The following describes the processing flow.

[0648] Step 1:

[0649] The device connects to the server via the internet and sends a request for an advertising video along with the user's information to the server.

[0650] Step 2:

[0651] Based on the user information received by the server, it selects an advertising video optimized for that user. The selection takes into account the user's profile and past viewing history.

[0652] Step 3:

[0653] The server sends the data and URL of the selected advertisement video to the device.

[0654] Step 4:

[0655] The device uses the data received from the server to start playing the advertisement video.

[0656] Step 5:

[0657] A virtual human appears in the video, posing specific questions to the user and requesting a response.

[0658] Step 6:

[0659] The user responds to the virtual human's questions with voice or selects options on the screen.

[0660] Step 7:

[0661] The terminal sends user response data to the server in real time.

[0662] Step 8:

[0663] The server analyzes the response data it receives and uses natural language processing to understand the user's intent.

[0664] Step 9:

[0665] The server selects the next appropriate video ad sequence based on the user's response and sends that information to the device.

[0666] Step 10:

[0667] The device plays a new advertisement video sent from the server.

[0668] Step 11:

[0669] Once the interaction with the user is complete, the server generates reward information and sends it to the device.

[0670] Step 12:

[0671] The device displays information on the screen to the user regarding the receipt of rewards and how to use them.

[0672] (Example 1)

[0673] Next, we will describe Example 1. In the following description, the data processing device 12 will be referred to as the "server" and the robot 414 as the "terminal".

[0674] Traditional advertising systems could only deliver advertisements to users in a one-way manner, making it difficult to provide dynamic and personalized advertising experiences based on users' interests and attributes. Furthermore, there were limitations to methods for improving viewership and increasing user engagement, creating a need for an interactive and flexible system to maximize advertising effectiveness.

[0675] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 1 is realized by the following means.

[0676] In this invention, the server includes means for selecting optimized video information based on the user's attribute information and past history information, means for dynamically adjusting the video content in response to the generated response, and means for utilizing a generative AI model that provides new video content based on the generated response. This enables personalized advertising experiences based on the user's interests and attributes.

[0677] "Users" refer to individual individuals who operate and access the system, and who receive advertising content through their interactions.

[0678] "Input" refers to the information and operations that users provide through their devices, and includes various forms such as voice and touch input.

[0679] A "terminal" is a device used by users for interactive operations, and includes mobile computing devices such as smartphones and tablets.

[0680] An "information processing device" refers to a device that performs necessary calculations and data processing based on received input and generates a response.

[0681] "Attribute information" refers to characteristics and profile information about users, including data such as age, gender, and preferences.

[0682] "History information" refers to records of users' past actions and interactions, and is data that enables the provision of more relevant content based on this information.

[0683] "Visual information" refers to the video and image data that make up advertisements and content, and is presented to users visually.

[0684] A "generative AI model" refers to a computational model that uses artificial intelligence to dynamically generate new content and responses based on input data.

[0685] A "virtual character" refers to a computer-generated person or character that appears in video content for the purpose of interactive dialogue.

[0686] "Rewards" refer to the benefits or incentives that users can receive when they complete an interaction within the system.

[0687] This invention provides an interactive advertising platform that can communicate with users. This system consists of a terminal that receives user input and a server that processes the information.

[0688] First, users request advertising videos by connecting to a server via the internet using a device such as a smartphone or tablet. The device accepts the user's voice input and touch input and sends this input to the server.

[0689] The server analyzes the user's attribute and history information received. This includes, for example, the types of advertisements the user has viewed in the past and the preferences registered in their user profile. An AI algorithm is used to select the most suitable video information. This selection process utilizes software that converts speech input into text using natural language processing technology.

[0690] The advertising video features a virtual human character who asks the user specific questions and facilitates interaction through dialogue. The user can respond using voice or on-screen options. The server then analyzes the response and generates a new advertising video optimized for that response using a new generative AI model. This new video is sent to the device, and the user watches it. For example, in a cosmetics advertisement, the user might be asked, "What is your skin type?" and if they answer that they have dry skin, an advertisement for moisturizing products will then be displayed.

[0691] Furthermore, once the user interaction is complete, the server calculates the reward and sends that information to the device. This reward is provided as points or coupons, which the user can use at a later date.

[0692] Examples of prompts include, "Generate an ad for the best moisturizing cream for people with dry skin," or "Generate an ad for a health food that can be recommended to a user who is aiming to lose weight."

[0693] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0694] Step 1:

[0695] The user requests an advertisement video via their device. The device accepts the user's voice input and button presses. It receives user input (e.g., a voice command such as "Please start the advertisement") and sends this information to the server via the internet in the form of a request. The output is request data sent to the server based on the user's advertisement viewing request.

[0696] Step 2:

[0697] Based on the requests received by the server, the system analyzes the user's profile and history information. It takes request data sent from the device as input. It then searches the database for user attribute information (e.g., past ad viewing history, registered profile) and selects the most suitable ad. The selected ad content is then returned as output.

[0698] Step 3:

[0699] The device receives advertising data sent from the server and plays the advertising video on the screen. The input is advertising content information sent from the server. Specifically, the video data is displayed on the device's screen, presenting it visually to the user. The output is an advertising video that the user can view.

[0700] Step 4:

[0701] The user responds to a question posed by a virtual character in the advertisement. The device accepts the user's voice and on-screen selections as input. For example, when the virtual character asks, "What is your skin type?", the user might answer "Dry skin" by voice. The output is the user's response data.

[0702] Step 5:

[0703] The terminal sends user responses to the server in real time. It receives dialogue data between the user and a virtual character as input. In the case of voice input, speech recognition software is used to convert it to text, and the data is sent to the server. The output is user response data for analysis.

[0704] Step 6:

[0705] Based on the response received by the server, analysis is performed using natural language processing. A generative AI model is used to generate new advertising content that is optimal for the response. The input is response data from the user. The server analyzes the response content using natural language processing and creates a new advertising video using a generative AI model. The output is the newly generated advertising content.

[0706] Step 7:

[0707] The device receives and plays a new advertising video. It receives new advertising content data from the server as input. Specifically, it displays the newly generated video on the device screen and offers the user the next advertisement. The output is the next viewable advertising video.

[0708] Step 8:

[0709] Once the user interaction is complete, the server calculates the reward and sends that information to the device. The input is the user's interaction history, which is used to calculate the reward and prepare the data. The reward information is then sent to the device for the user to review. The output is the reward information that the user can view on their device.

[0710] (Application Example 1)

[0711] Next, we will explain Application Example 1. In the following explanation, the data processing device 12 will be referred to as the "server" and the robot 414 as the "terminal".

[0712] The present invention aims to improve the user experience in advertising by providing technology that dynamically updates advertising content through interactive communication while delivering optimal advertisements based on user characteristics and interests. Conventional advertising systems have the problem of only providing content unilaterally, making it difficult to update content immediately in response to user reactions, and thus failing to provide information that is useful to users. Therefore, there is a need to develop a new system that solves these problems and has functions to further enhance user engagement.

[0713] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 1 is realized by the following means.

[0714] In this invention, the server includes an information processing device that receives user input, a computing device that controls the response generated based on the input, control means that dynamically switches video information according to the generated response, and means that uses a virtual character to ask questions to the user and dynamically update the advertising content based on the questions. This makes it possible to improve the user experience by providing advertisements that match the user's interests and characteristics, while also providing real-time content updates and rewards.

[0715] An "information processing device that accepts user input" is a device that allows users to input data through voice, button operations, etc., and has the role of transmitting that input information to a server.

[0716] A "computer that controls the generated response" is a device that performs calculations to generate the optimal response based on the user's input information.

[0717] A "dynamic video information switching control method" is a control method that has the function of changing the displayed advertisements and content in real time based on user responses.

[0718] "Methods for questioning users using virtual characters" refer to methods in which virtual character models that operate on a screen ask questions or engage in dialogue with users.

[0719] "Means for dynamically updating ad content" refers to a means of providing a function that changes and optimizes the displayed ad content in real time, reflecting information obtained from users.

[0720] This invention employs a system configuration combining terminals and servers to realize an interactive advertising system that can converse with users. This system primarily utilizes speech recognition and natural language processing technologies to provide advertising content optimized for the user.

[0721] The terminal functions as an information processing device, such as a smartphone equipped with a microphone, and accepts input via the user's voice or button presses. This input information is transmitted to a server via the internet. The server uses computing power to select the most suitable advertising content based on the user's profile information and past behavioral history. To do this, the server uses a database and machine learning models to perform data analysis and recommend advertisements relevant to the user.

[0722] The advertising content selected by the server is sent to the device as video information and played. A virtual character is displayed in the video and asks questions to the user. For example, in an advertisement for a beauty product, interaction such as "What is your skin type?" is possible. The device sends the user's response back to the server in real time, and the server analyzes this using natural language processing, updates the advertising content, and sends it again.

[0723] Furthermore, based on user interaction, the server sets rewards and benefits and sends reward information to the device. This configuration allows users to view ads tailored to their preferences, improving their engagement with advertisements.

[0724] A concrete example is a scenario where, when a user uses an application, a virtual human asks, "How are you feeling today?", and fashion-related advertisements are customized based on the user's response. An example of a prompt for a generative AI model would be, "Ask the user 'How are you feeling today?' and customize fashion-related advertisements based on their response."

[0725] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0726] Step 1:

[0727] The device accepts voice input and button presses from the user. This input data is collected through the smartphone's microphone and touchscreen and recorded as audio data. This provides basic data to understand what kind of information the user is seeking.

[0728] Step 2:

[0729] The device uses speech recognition software to convert voice input into text. Here, a speech recognition library (e.g., Google Speech Recognition API) is used to analyze the voice data and generate corresponding text data. At this stage, voice data is received as input, and text data is generated as output.

[0730] Step 3:

[0731] The terminal sends the generated text data to the server over the internet. This transmission uses the standard HTTP protocol, and the user's text response is sent for further analysis on the server side. The input includes text data converted from speech, and the output is the transfer of that text data to the server.

[0732] Step 4:

[0733] The server generates a response using natural language processing techniques based on the received text data. Here, a generative AI model is used to select the advertising content that best suits the user's statements. In this process, the user's text data is used as input, and advertising content to be presented to the user is generated as output.

[0734] Step 5:

[0735] The server sends the selected advertising content back to the device. In this communication, advertising information is sent to the device as digital data. The data must be in a format suitable for the device's interface. The input includes optimized advertising content, and the output is the information displayed on the device.

[0736] Step 6:

[0737] The device displays the received advertising content on its screen and maintains interaction with the user using a virtual character. This ensures that the user receives the most relevant advertising message directly. For example, if the virtual character asks, "What is your skin type?" and the user answers, "Dry skin," an advertisement for a suitable moisturizing cream will be displayed. At this stage, the input is advertising information sent from the server, and the output is an updated advertising screen based on the user's actions.

[0738] Furthermore, an emotion engine that estimates the user's emotions may be incorporated. That is, the identification processing unit 290 may use the emotion identification model 59 to estimate the user's emotions and perform identification processing using the user's emotions.

[0739] This invention is an interactive advertising system that uses an emotion engine to recognize user emotions, and consists of a terminal that receives user input and a server. It also includes a virtual human for interacting with the user and control means for dynamically switching video content in response to the generated response.

[0740] First, the device connects to the server via the internet and requests an advertisement video. The server selects appropriate advertisement content based on the user's profile information and past interaction history, and delivers that information to the device. The device receives this information and plays the advertisement video.

[0741] As a user watches a video, the emotion engine analyzes the user's facial expressions and tone of voice, and evaluates their emotions in real time. For example, if the user shows curiosity, the emotion engine sends that information to the server.

[0742] The server can dynamically adjust ad content based on data from the emotion engine and instruct the virtual human to respond in a way that matches the user's emotions. For example, if the user shows interest in a product description, the virtual human will provide more detailed information.

[0743] Furthermore, when a user completes an interaction, the content and method of rewards are also adjusted based on their emotions. For example, if a user expresses positive emotions, they may be offered special offers or additional points.

[0744] In this way, incorporating an emotion engine makes advertisements more personalized and effective. By interacting with users based on their emotions, advertising agencies can achieve higher viewer satisfaction and more effective messaging.

[0745] The following describes the processing flow.

[0746] Step 1:

[0747] The device connects to the server via the internet and sends a request for an advertising video to the server. This request includes the user's profile information.

[0748] Step 2:

[0749] The server selects the most suitable advertising content based on the user's profile information. The selected advertising data is then sent to the device.

[0750] Step 3:

[0751] The device uses data received from the server to begin playing an advertisement video. This video contains a virtual human.

[0752] Step 4:

[0753] An emotion engine operates on the device, analyzing the user's facial expressions and voice tone in real time to generate emotion data.

[0754] Step 5:

[0755] The device sends the generated emotion data to the server.

[0756] Step 6:

[0757] The server analyzes emotional data and adjusts the currently playing advertisement content accordingly. This includes selecting video sequences based on emotions and modifying the virtual human's responses.

[0758] Step 7:

[0759] Users interact with a virtual human, responding to questions verbally and selecting options on the screen.

[0760] Step 8:

[0761] The terminal sends the user's response data back to the server.

[0762] Step 9:

[0763] The server analyzes user responses and sentiment data to determine what advertisement to play next and what compensation to offer.

[0764] Step 10:

[0765] Once the user completes the interaction, the server generates reward information and sends it to the device, including any perks or coupons.

[0766] Step 11:

[0767] The device displays reward information to the user and prompts them to check how to use the rewards and confirm their points.

[0768] (Example 2)

[0769] Next, we will describe Example 2. In the following description, the data processing device 12 will be referred to as the "server" and the robot 414 as the "terminal".

[0770] Modern advertising faces challenges in effectively appealing to users because it fails to adequately address their individual emotions and preferences. In particular, advertising is often one-way and does not fully utilize user interaction, resulting in low viewer satisfaction. Furthermore, there is a problem with the inappropriate provision of rewards and benefits based on user emotions.

[0771] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means.

[0772] In this invention, the server includes an information processing device that receives user input, a computing means that controls the response generated based on the input, and a conversion means that dynamically switches visual content according to the generated response. This makes it possible to provide advertising content that is in line with the user's emotions and to improve viewer satisfaction.

[0773] An "information processing device" is a device that receives input from a user and performs a specified function.

[0774] "Computation means" refers to electronic equipment or software that generates a response based on user input and controls the content of that response.

[0775] "Conversion means" refers to a processing device or software for dynamically switching visual content in response to the generated response.

[0776] "Means of providing compensation" refers to a process or system for providing benefits or rewards to users through visual content.

[0777] "Analysis means" refers to technology or software used to analyze a user's facial expressions and voice to identify their emotions.

[0778] "Improvement measures" refer to processes or systems for adjusting visual content based on analyzed sentiment data.

[0779] "Natural language understanding means" refers to technology or software that processes a user's voice input and generates a response that a computer can understand.

[0780] A "virtual character" is a digitally generated character placed within visual content to interact with the user.

[0781] This invention is a system that recognizes user emotions and dynamically adjusts advertising content. This system has two main components: a terminal that receives user input and a server that processes information.

[0782] The terminal acquires user input via camera and microphone and sends the necessary data for emotion analysis to the server. The terminal has dedicated emotion recognition software installed, which analyzes facial expressions and voice tone in real time. The results of this analysis are quickly transmitted to the server.

[0783] The server evaluates the user's emotional state based on the received data and selects appropriate advertising content. The server has a recommendation system implemented that uses machine learning algorithms to determine the optimal content, taking into account user profile information and past interaction history.

[0784] The selected advertising content interacts with the user using a virtual character, and the advertising content is adjusted to match the user's emotions. For example, if a user shows interest in a product, the server can instruct the virtual character to provide further product information.

[0785] As a concrete example, suppose a user is viewing travel-related advertisements on their device, and the emotion engine detects the user's curiosity. Based on this information, the server dynamically adjusts the virtual character to provide content including detailed information and perks for the travel destination.

[0786] To enhance the effectiveness of this system, prompts generated using AI models are extremely helpful. An example of a prompt would be: "Please suggest a scenario for providing detailed information when a user expresses interest in a product. This information would be provided by a virtual character."

[0787] Thus, the system of the present invention is designed to realize an emotion-based, personalized advertising experience, thereby increasing user engagement and satisfaction.

[0788] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0789] Step 1:

[0790] The device receives advertising requests from users and sends them to the server as data packets along with profile information. It receives the user's selected advertising categories and profile data as input, and sends advertising requests to the server as output. In this process, the device plays the role of establishing a connection with the server via the internet.

[0791] Step 2:

[0792] The server processes ad requests received from the device and selects appropriate ad content based on the user's profile data and past browsing history. This selection uses a recommendation algorithm based on database queries and generative AI models. It receives profile data and ad requests from the device as input, and identifies and sends appropriate ad content to the device as output.

[0793] Step 3:

[0794] The device receives advertising content sent from the server and displays it to the user as visual content. Simultaneously, the device uses its camera and microphone to acquire data on the user's facial expressions and voice in real time. This data is used as input for emotion analysis, and the analysis results are generated as output. Specifically, the emotion engine identifies the user's emotional state by analyzing changes in the user's facial expressions and tone of voice.

[0795] Step 4:

[0796] The server receives sentiment analysis data sent from the terminal and dynamically adjusts the advertisement content. In this process, the user's sentiment data is taken as input, and the adjusted advertisement content is generated as output. Based on this data, the server updates the dialogue and visual content of the virtual character and resends it to the user.

[0797] Step 5:

[0798] When a user completes an interaction with an advertisement, the server determines a reward based on the user's past emotional data and notifies the user via their device. The server uses past emotional data and interaction completion information as input, and provides the user with information about rewards or points as output. This step improves the user experience and encourages repeat use.

[0799] (Application Example 2)

[0800] Next, we will explain application example 2. In the following explanation, the data processing device 12 will be referred to as the "server" and the robot 414 as the "terminal".

[0801] Conventional advertising systems have struggled to provide personalized advertisements that take into account the emotions of users. As a result, they have suffered from insufficient appeal to viewers and insufficient advertising effectiveness. The present invention aims to solve the above problem by dynamically adjusting the content of advertisements based on the emotions of users and providing an interactive advertising experience that captures the interest of viewers.

[0802] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means.

[0803] In this invention, the server includes an emotion analysis means for analyzing the user's emotions, a means for dynamically generating advertising information based on the emotion data acquired by the emotion analysis means, and a means for presenting the advertising information to the user through a virtual character. This makes it possible to personalize advertisements according to the user's emotions and provide an engaging advertising experience through a virtual character.

[0804] An "information processing device" is a device that receives input from users and processes the data.

[0805] A "computational device" is a device that executes a specified process and generates and controls responses.

[0806] "Visual content" refers to dynamic video information displayed to the user.

[0807] A "control mechanism" is a function for overseeing and controlling the entire system.

[0808] "Means of providing rewards" refers to functions that offer benefits or incentives to users.

[0809] "Emotional analysis means" refers to a function that analyzes the user's emotions and acquires that information.

[0810] "Means for dynamically generating advertising information based on emotional data" refers to a function that changes and generates advertising content based on analyzed emotional data.

[0811] A "virtual character" is a computer-generated character that behaves like a human.

[0812] The system for implementing this invention includes an information processing device, a computing device, and emotion analysis means. A terminal receives user input, and this data is processed by the information processing device. The user's emotions are analyzed by the emotion analysis means installed in the information processing device, and this emotion data is transmitted to a server. The server dynamically generates advertising content in response using the computing device. This process utilizes computer vision technology and voice analysis software. Specifically, smart glasses equipped with a camera and microphone are used to analyze facial expressions and voice using software such as OpenCV or Praat. The server generates visual content based on this data and presents it to the user through a virtual person.

[0813] As a concrete example, when a user is walking in a city, smart glasses display information about nearby stores and analyze the user's emotions. If the user shows interest, a virtual character introduces special offers from those stores.

[0814] An example of a prompt message is: "When the user walks past the cafe through their smart glasses, perform real-time sentiment analysis, and if they show interest, have a virtual character recommend the day's menu."

[0815] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0816] Step 1:

[0817] The device receives input from the user. This input is captured by the camera and microphone and includes video and audio of the user's face. The device collects this data and transmits it to an emotion analysis system.

[0818] Step 2:

[0819] The sentiment analysis system installed in the device analyzes the collected input data. In this step, OpenCV is used to recognize facial expressions and Praat is used to analyze voice tone. The sentiment analysis system then identifies the user's emotions and generates the results as data.

[0820] Step 3:

[0821] Emotional data obtained through emotion analysis is sent to the server. The server receives this input data and performs data processing and calculations to generate advertising content optimized for the user. Specifically, it uses a generative AI model to design advertising content based on the user's emotions.

[0822] Step 4:

[0823] The server generates advertising content, which is then sent to the device. The device uses a virtual character to interactively present advertising information to the user. At this time, the advertisement is designed to combine visual and auditory elements to better capture the user's interest.

[0824] Step 5:

[0825] When a user responds to an ad, the device receives that input again and analyzes the data. Based on the analysis results, the server further adjusts the ad content and generates and presents a new interaction.

[0826] 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 controlled object 443 to output the result of the specific processing. The microphone 238 acquires audio indicating user input for the result of the specific processing. The control unit 46A transmits the audio data indicating user input acquired by the microphone 238 to the data processing unit 12. In the data processing unit 12, the specific processing unit 290 acquires the audio data.

[0827] Data generation model 58 is a type of so-called generative AI (Artificial Intelligence). One example of data generation model 58 is ChatGPT (Internet search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search) <url: https: gemini.google.com ?hl="ja">Examples of generative AI include the following. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 is input with prompts containing instructions, and with inference data such as audio data representing speech, text data representing text, and image data representing images. The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference results in data formats such as audio data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[0828] 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 this disclosure is not limited thereto, and the specific processing may also be performed by the robot 414.

[0829] Furthermore, the emotion identification model 59, acting 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 a specific mapping, which is an emotion map (see Figure 9). Similarly, the emotion identification model 59 may also determine the robot's emotion, and the identification processing unit 290 may perform identification processing using the robot's emotion.

[0830] Figure 9 shows an emotion map 400 in which multiple emotions are mapped. In the emotion map 400, emotions are arranged in concentric circles radiating from the center. The closer to the center of the concentric circles, the more primitive the emotions are located. Further out of the concentric circles, emotions representing states and actions arising from mental states are located. Emotion is a concept that includes feelings and mental states. On the left side of the concentric circles, emotions that are generally generated from reactions occurring in the brain are located. On the right side of the concentric circles, emotions that are generally induced by situational judgment are located. Above and below the concentric circles, emotions that are generally generated from reactions occurring in the brain and induced by situational judgment are located. In addition, the emotion of "pleasure" is located on the upper side of the concentric circles, and the emotion of "displeasure" is located on the lower side. Thus, in the emotion map 400, multiple emotions are mapped based on the structure in which emotions arise, and emotions that are likely to occur simultaneously are mapped close together.

[0831] These emotions are distributed at the 3 o'clock position on the Emotion Map 400, and usually fluctuate between feelings of security and anxiety. In the right half of the Emotion Map 400, situational awareness takes precedence over internal feelings, resulting in a calm impression.

[0832] The inside of the Emotion Map 400 represents inner thoughts, while the outside represents actions. Therefore, the further you go from the outside of the Emotion Map 400, the more visible (expressed in actions) your emotions become.

[0833] Here, human emotions are based on various balances, such as posture and blood sugar levels. When these balances deviate from the ideal, it results in discomfort, and when they approach the ideal, it results in pleasure. Similarly, in robots, cars, motorcycles, etc., emotions can be created based on various balances, such as posture and battery level. When these balances deviate from the ideal, it results in discomfort, and when they approach the ideal, it results in pleasure. The emotion map can be generated, for example, based on Dr. Mitsuyoshi's emotion map (Research on a system for analyzing brain physiological signals of speech emotion recognition and emotion, Tokushima University, doctoral dissertation: https: / / ci.nii.ac.jp / naid / 500000375379). The left half of the emotion map contains emotions belonging to a region called "response," where sensation is dominant. The right half of the emotion map contains emotions belonging to a region called "situation," where situational awareness is dominant.

[0834] The emotion map defines two emotions that promote learning. One is the emotion around the middle of the negative "repentance" and "reflection" on the situation side. In other words, it is 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 the emotion around the positive "desire" on the reaction side. In other words, it is when the robot has positive feelings such as "I want more" or "I want to know more."

[0835] The emotion identification model 59 inputs user input into a pre-trained neural network, obtains emotion values ​​representing each emotion shown in the emotion map 400, and determines the user's emotion. This neural network is pre-trained based on multiple training data sets, which are combinations of user input and emotion values ​​representing each emotion shown in the emotion map 400. Furthermore, this neural network is trained so that emotions located close together have similar values, as shown in the emotion map 900 in Figure 10. Figure 10 shows an example where multiple emotions such as "reassured," "calm," and "confident" have similar emotion values.

[0836] The above description primarily focuses on the functions of the data processing device 12 in relation to this disclosure. However, the system related to this disclosure is not necessarily implemented on a server. The system related to this disclosure may be implemented as a general information processing system. This disclosure may be implemented, for example, as a software program that runs on a personal computer or as an application that runs on a smartphone. The method related to this disclosure may be provided to users in SaaS (Software as a Service) format.

[0837] In the above embodiment, an example was given in which a specific process is performed by a single computer 22. However, the technology of this disclosure is not limited thereto, and a distributed processing of the specific process may be performed by multiple computers, including computer 22. For example, a data generation model 58 may be provided in an external device of the data processing device 12, and the external device may generate data according to the input data.

[0838] In the above embodiment, an example was given in which the specific processing program 56 is stored in the storage 32, but the technology of this disclosure is not limited thereto. For example, the specific processing program 56 may be stored in a portable, computer-readable, non-temporary storage medium such as a USB (Universal Serial Bus) memory. The specific processing program 56 stored in the non-temporary storage medium is installed in the computer 22 of the data processing device 12. The processor 28 executes specific processing according to the specific processing program 56.

[0839] 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.

[0840] Furthermore, it is not necessary to store the entirety 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 the entirety of the specific processing program 56 in the storage 32; it is acceptable to store only a portion of the specific processing program 56.

[0841] The following types of processors can be used as hardware resources to perform specific processing. Examples of processors include a CPU, a general-purpose processor that functions as a hardware resource to perform specific processing by executing software, i.e., a program. Other examples of processors include dedicated electrical circuits, such as FPGAs (Field-Programmable Gate Arrays), PLDs (Programmable Logic Devices), or ASICs (Application Specific Integrated Circuits), which have circuit configurations specifically designed to perform specific processing. All of these processors have built-in or connected memory, and all of them perform specific processing by using memory.

[0842] The hardware resource that performs a specific process may consist of one of these various processors, or it may consist of 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). Alternatively, the hardware resource that performs a specific process may consist of a single processor.

[0843] Examples of configurations using a single processor include, firstly, a configuration in which one or more CPUs and software are combined to form a single processor, and this processor functions as a hardware resource that performs a specific process. Secondly, there is a configuration using a processor that realizes the functions of the entire system, including multiple hardware resources that perform a specific process, on a single IC chip, as exemplified by SoCs (System-on-a-chip). In this way, a specific process is realized using one or more of the above types of processors as hardware resources.

[0844] Furthermore, the hardware structure of these various processors can more specifically utilize electrical circuits that combine circuit elements such as semiconductor devices. Also, the specific processing described above is merely an example. Therefore, it goes without saying that unnecessary steps can be deleted, new steps added, or the processing order rearranged, as long as it does not deviate from the main purpose.

[0845] The descriptions and illustrations presented above are detailed explanations of the technical aspects of this disclosure and are merely examples of the technical aspects. For example, the above descriptions of the structure, function, operation, and effect are examples of the structure, function, operation, and effect of the technical aspects of this disclosure. Therefore, it goes without saying that you may delete unnecessary parts, add new elements, or replace elements in the descriptions and illustrations presented above, as long as you do not deviate from the essence of the technical aspects of this disclosure. Furthermore, in order to avoid confusion and facilitate understanding of the technical aspects of this disclosure, explanations of common technical knowledge and the like that do not require special explanation to enable the implementation of the technical aspects of this disclosure have been omitted from the descriptions and illustrations presented above.

[0846] All documents, patent applications, and technical standards described herein are incorporated by reference to the same extent as if each individual document, patent application, and technical standard were specifically and individually noted to be incorporated by reference.

[0847] The following is further disclosed regarding the embodiments described above.

[0848] (Claim 1)

[0849] A terminal that accepts user input,

[0850] A computing device that controls the response generated based on the input,

[0851] A control means that dynamically switches video content in response to the generated response,

[0852] A means of providing compensation to users through the video content,

[0853] A system that includes this.

[0854] (Claim 2)

[0855] The system according to claim 1, comprising natural language processing means for processing a user's voice input and generating a response.

[0856] (Claim 3)

[0857] The system according to claim 1, comprising means for placing a virtual character within video content and for interacting with the user through the virtual character.

[0858] "Example 1"

[0859] (Claim 1)

[0860] A terminal that accepts user input,

[0861] An information processing device that controls the response generated based on the input,

[0862] A means for selecting optimized video information based on user attribute information and past history information,

[0863] A control means that dynamically adjusts the video content in accordance with the generated response,

[0864] A means of interacting with the user through a virtual character in conjunction with the video content,

[0865] A means of providing compensation after the completion of the dialogue with the user,

[0866] A system that includes this.

[0867] (Claim 2)

[0868] The system according to claim 1, comprising a natural language processing means for analyzing a user's voice input and generating a response.

[0869] (Claim 3)

[0870] The system according to claim 1, comprising means for utilizing a generative AI model that provides new video content based on the generated response.

[0871] "Application Example 1"

[0872] (Claim 1)

[0873] An information processing device that accepts user input,

[0874] A computing device that controls the response generated based on the input,

[0875] A control means that dynamically switches video information in response to the generated response,

[0876] A means of providing compensation to the user through the video information,

[0877] A means of using a virtual character to ask questions to the user and dynamically updating the advertising content based on those questions,

[0878] A system that includes this.

[0879] (Claim 2)

[0880] The system according to claim 1, comprising natural language processing means for processing a user's voice input and generating a response.

[0881] (Claim 3)

[0882] The system according to claim 1, comprising means for placing a virtual person within video information, for interacting with the user through the virtual person, and further comprising means for providing advertisements based on the user's interests.

[0883] "Example 2 of combining an emotion engine"

[0884] (Claim 1)

[0885] An information processing device that accepts user input,

[0886] Computation means for controlling the response generated based on the input,

[0887] A transformation means that dynamically switches visual content in response to the generated response,

[0888] A means of providing compensation to users through the visual content,

[0889] An analytical means for identifying emotions by analyzing the user's facial expressions and voice,

[0890] Improvement means for adjusting the visual content based on the emotion,

[0891] A system that includes this.

[0892] (Claim 2)

[0893] The system according to claim 1, comprising a natural language understanding means for processing user voice input and generating a response.

[0894] (Claim 3)

[0895] The system according to claim 1, comprising means for placing a virtual character within visual content and for interacting with the user through the virtual character.

[0896] "Application example 2 when combining with an emotional engine"

[0897] (Claim 1)

[0898] An information processing device that accepts user input,

[0899] A computing device that controls the response generated based on the input,

[0900] Control means for dynamically switching visual content in response to the generated response,

[0901] A means of providing rewards to users through the visual content,

[0902] A means of analyzing the emotions of users,

[0903] A means for dynamically generating advertising information based on emotional data acquired by the emotion analysis means,

[0904] A means of presenting advertising information to users through a virtual persona,

[0905] A system that includes this.

[0906] (Claim 2)

[0907] The system according to claim 1, comprising natural language processing means for processing a user's voice input and generating a response.

[0908] (Claim 3)

[0909] The system according to claim 1, comprising means for placing a virtual character within visual content and for interacting with the user through the virtual character. [Explanation of symbols]

[0910] 10, 210, 310, 410 Data Processing Systems 12 Data Processing Devices 14 Smart Devices 214 Smart Glasses 314 Headset-type terminal 414 Robots< / url:> < / url:> < / url:> < / url:>

Claims

1. A terminal that accepts user input, A computing device that controls the response generated based on the input, A control means that dynamically switches video content in response to the generated response, A means of providing compensation to users through the video content, A system that includes this.

2. The system according to claim 1, comprising a natural language processing means for processing a user's voice input and generating a response.

3. The system according to claim 1, comprising means for placing a virtual character within video content and for interacting with the user through the virtual character.

Images