system

Abstract

We provide the system. [Solution] User data management means, A content generation method using a generative model, Channel selection means, Distribution methods, User response analysis means, 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, including steps of receiving a user utterance, adding the user utterance to a prompt including an instruction sentence related to an explanation of a character of the chatbot, 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 a conventional customer messaging system, it is difficult to provide personalized information, and there is a problem that effective store visit promotion and information distribution according to various needs of users cannot be achieved. In particular, in a situation where information suitable for a wide range of age groups is required, there are many cases where uniform content is not effective for users. To solve this problem, it is desired to utilize user attributes and history to provide information optimized for individual users.

Means for Solving the Problems

[0005] The present invention solves the above problems by providing a system equipped with user data management means, content generation means using a generative model, channel selection means, distribution means, and user response analysis means. This system manages the user's customer history information and terminal usage history, and generates personalized message content based on user attributes using a generative model. Subsequently, it selects the optimal distribution channel and delivers the message, thereby achieving effective information provision to each user. Furthermore, by analyzing user responses and reflecting them in subsequent messaging, continuous improvement is achieved.

[0006] "User data management means" refers to means that have the function of collecting and managing customer history information and terminal usage history.

[0007] A "content generation method using a generative model" is a means of automatically generating personalized message content by utilizing user attribute information.

[0008] A "channel selection method" is a means of determining and selecting the optimal distribution channel according to the user's characteristics.

[0009] A "distribution method" is a means that has the function of delivering generated content to users through a selected channel.

[0010] A "user response analysis method" is a means of collecting and analyzing how users reacted to messages they received, and utilizing the results for future content creation. [Brief explanation of the drawing]

[0011] [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] This 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] This is a conceptual diagram showing an example of the configuration of a data processing system according to the fourth embodiment. [Figure 8] This 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] This shows an emotion map where multiple emotions are mapped. [Figure 10] This shows an emotion map where multiple emotions are mapped. [Figure 11] This is a sequence diagram showing the processing flow of the data processing system in Example 1. [Figure 12] This is a sequence diagram showing the processing flow of the data processing system in Application Example 1. [Figure 13] This is a sequence diagram showing the processing flow of the data processing system in Example 2, which incorporates an emotion engine. [Figure 14] This is a sequence diagram showing the processing flow of the data processing system in Application Example 2, which combines an emotion engine. [Modes for carrying out the invention]

[0012] Hereinafter, an example of an embodiment of the system relating to the technology of this disclosure will be described with reference to the attached drawings.

[0013] First, let's explain the terminology used in the following explanation.

[0014] In the following embodiments, the numbered 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.

[0015] In the following embodiments, the numbered RAM (Random Access Memory) is a memory in which information is temporarily stored and is used as a work memory by the processor.

[0016] In the following embodiments, the numbered 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, and the like.

[0017] In the following embodiments, the numbered communication I / F (Interface) is an interface including 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), and the like.

[0018] 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."

[0019] [First Embodiment]

[0020] Figure 1 shows an example of the configuration of the data processing system 10 according to the first embodiment.

[0021] 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.

[0022] 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).

[0023] 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.

[0024] 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.

[0025] 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.

[0026] 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.

[0027] Figure 2 shows an example of the main functions of the data processing device 12 and the smart device 14.

[0028] 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.

[0029] 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.

[0030] 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.

[0031] 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".

[0032] The system of the present invention is implemented as follows in order to provide personalized content to each user: A server controls the entire system, and a user data management means collects the user's customer history information and terminal usage history. This prepares the data necessary to generate content that is optimal for each user.

[0033] The server utilizes a generative model to automatically generate messages tailored to each user's individual needs and interests based on collected data. This generated content is specific to the user's attributes, enabling the provision of highly personalized information.

[0034] For the distribution of generated content, the channel selection mechanism determines the most effective distribution channel based on user characteristics. It selects the most accessible channel for each user from a variety of options, including email, messaging apps, and social media. Using the selected channel, the server sends the content to the user's device via the distribution mechanism.

[0035] After a user receives content, a user response analysis tool analyzes their reaction. For example, it analyzes whether the user clicked on a link in the message, what actions they took based on the information provided, and uses this information to improve future content generation.

[0036] For example, student users will automatically receive information on the latest educational applications and student discount plans, which will be distributed through popular social media platforms. Similarly, senior users will receive video tutorials on simple smartphone operation, delivered via their familiar email services. In this way, information can be provided to diverse user groups in a manner tailored to their individual needs.

[0037] The following describes the processing flow.

[0038] Step 1:

[0039] The server queries the user database to retrieve each user's customer history and device usage history. This collects the necessary basic data for generating personalized messages.

[0040] Step 2:

[0041] The server invokes a generative model and generates a personalized message using the user data obtained in step 1. This generated content includes information tailored to the user's interests and needs.

[0042] Step 3:

[0043] The server selects the channel best suited to the user's attributes from among numerous distribution channels. The selection criteria include the user's past behavioral data and device type.

[0044] Step 4:

[0045] The server prepares the content in the appropriate format and delivers it to the user's terminal via the selected channel. During this process, format conversion may occur depending on the channel and content type.

[0046] Step 5:

[0047] The user receives a message on their device and checks its contents. The user then takes action based on the received information (for example, visiting a store or completing an online procedure).

[0048] Step 6:

[0049] The server collects and analyzes user responses. Link click-through rates and response rates are analyzed and used as feedback data to generate future messages.

[0050] (Example 1)

[0051] 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."

[0052] Current information delivery systems struggle to efficiently deliver personalized information tailored to the diverse needs of users. Furthermore, there is a growing need to utilize user history data and attributes to select the optimal delivery channel and facilitate effective communication.

[0053] 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.

[0054] In this invention, the server includes means for accumulating user records, means for creating information using a generative AI model, and means for selecting communication means. This enables information distribution optimized for each user.

[0055] "User records" refer to data that collects information about a user's behavior history and attributes.

[0056] A "generative AI model" is an artificial intelligence system that automatically generates personalized content based on data.

[0057] "Communication methods" refer to the channels and platforms used to transmit information, such as email and social networking services (SNS).

[0058] "Means of creating information" refers to the process of generating user-oriented messages and content based on specific data and conditions.

[0059] "Means for analyzing user responses" refers to a function that collects and analyzes user behavior and reactions to information received as data.

[0060] In embodiments of this invention, the following hardware and software environment is used.

[0061] The server has the function of accumulating user records and uses a database system to efficiently collect and store information such as user purchase history and device usage history. Furthermore, the server incorporates a generative AI model, which operates on platforms such as Python and TENSORFLOW®. This makes it possible to generate personalized content based on user attribute information.

[0062] As a concrete example, the server can input the prompt text "Generate the latest application information for students" into a generating AI model, which can then automatically generate information on educational apps of interest to student users.

[0063] The terminal has the functionality to receive communications from the server and presents information through various communication channels so that users can easily access it. Various means are used, such as email services, messaging apps, and social media platforms. The terminal also has the functionality to feed back user responses to the server, which is done via HTTP requests, WebSockets, and other methods.

[0064] Users take action based on the content they receive, for example by clicking on links, and these responses are used to create future content for the user. This ensures that information is continuously provided in a way that is most suitable for each individual user.

[0065] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0066] Step 1:

[0067] The server uses a means of aggregating user records to collect user purchase history and device usage history from a database. The user ID is used as input, and this historical information is extracted via SQL queries. The output is data on the user's past behavior. This data forms the basis for personalization in subsequent processing steps.

[0068] Step 2:

[0069] The server takes the user data obtained in Step 1 as input and provides prompt messages to the generating AI model to generate personalized content. For example, it might use the prompt, "Generate the latest education-related information based on the user ID." The model then generates a personalized message in response to this prompt and provides it as output. This model operates using natural language processing techniques.

[0070] Step 3:

[0071] The server selects the communication method based on the generated content and user characteristics. Inputs include the user's past communication history and usage trends. For example, a user with a high open rate on social media in the past would be deemed best suited to social media. The output is information about the selected communication channel. At this stage, a condition-based algorithm is used.

[0072] Step 4:

[0073] The server sends personalized content to the terminal via the communication method selected in step 3. The input is the generated content and the selected communication channel, which may utilize the SMTP protocol or API requests. The output is a notification sent to the user terminal, making the user ready to receive the information.

[0074] Step 5:

[0075] The device collects user responses and sends feedback to the server. The input is user activity logs (e.g., link clicks), which are then organized as data for analysis. The resulting feedback data is added to the user's profile information as a reference for future content generation. Statistical processing and machine learning algorithms are used for the analysis.

[0076] (Application Example 1)

[0077] 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."

[0078] Traditional content delivery systems have struggled to provide optimal educational content based on each user's individual learning history and interests. As a result, they have provided users with uniform information, and effective learning support has not been adequately achieved.

[0079] 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.

[0080] In this invention, the server includes user data management means, content generation means using a generative model, and content recommendation means for personalizing educational content based on learning history. This enables the automatic generation and provision of educational content that corresponds to the user's learning history and interests.

[0081] "User data management means" refers to a device or program that collects and manages user history information and device usage data.

[0082] "Content generation means using a generative model" refers to a device or program for generating information according to user attributes based on collected data.

[0083] "Channel selection means" refers to a device or program that determines the optimal distribution route based on user characteristic information.

[0084] "Distribution means" refers to a device or program that transmits generated content to the user's terminal via a selected distribution route.

[0085] A "user response analysis tool" is a device or program that analyzes how a user reacted to the content they received.

[0086] A "content recommendation means for personalizing educational content based on learning history" refers to a device or program that personalizes and recommends education-related information based on the learning history of individual users.

[0087] The system in this invention is designed to provide users with personalized educational content. The server first collects and manages user history information and device usage data using user data management means. This information is processed by content generation means using a generative model to generate personalized educational content based on the user's learning history and interests. A generative AI model is used in this process.

[0088] Once appropriate content is generated based on user attributes and learning history, the channel selection mechanism determines the optimal delivery path based on the user's characteristic information. This selection is made from communication channels such as email, messaging apps, and social media.

[0089] The generated content is transmitted to the user's device via a communication path selected by the distribution method. The user's response to the received content is analyzed by a user response analysis tool and managed to feed back into the next content generation process. This loop enables the provision of increasingly accurate personalized information to the user.

[0090] As a concrete example, for student users interested in mathematics or science education, relevant learning content is automatically recommended. In this case, by utilizing a prompt such as "Generate recommended content for students looking for new mathematics learning materials," the system generates and provides content that matches the user's interests.

[0091] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0092] Step 1:

[0093] The server collects and manages user history information and device usage data using user data management means. This data includes user learning history and interests. This information is stored in a database for later processing.

[0094] Step 2:

[0095] The server inputs the collected data into a generating AI model to create personalized educational content based on the user's learning history and interests. The prompt used is "Generate recommended content for students looking for new math materials." The generated content is then output. This provides a high level of personalization based on user attributes.

[0096] Step 3:

[0097] The server uses the generated content to activate a channel selection mechanism, choosing the optimal delivery path based on user characteristics. Inputs include the user's communication history and preferred channel information, and the output is the determined optimal communication path. This allows for efficient and effective content delivery to the user.

[0098] Step 4:

[0099] The server uses a predetermined communication path to deliver content to the user's terminal. The inputs are the predetermined delivery path and the content, and the output is the user's terminal receiving the content. This allows the user to instantly receive personalized information.

[0100] Step 5:

[0101] Users respond to the received content. These responses are analyzed on the server using a user response analysis system. The input is user behavior data, and the output is analysis results showing changes in the user's interests and preferences. These analysis results are used as feedback in future content generation.

[0102] 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.

[0103] This invention provides a system comprising user data management means, content generation means using a generative model, channel selection means, distribution means, user response analysis means, and an emotion engine that recognizes user emotions. A server plays a central role, establishing the infrastructure for managing user data and collecting necessary information.

[0104] The server allows the user data management system to acquire and centrally manage customer history information and device usage history. This ensures that the data necessary for generating personalized content is prepared, and enables integration with the emotion engine using a generation model.

[0105] This sentiment engine is used to recognize sentiment patterns by comparing the user's past response data and interaction logs. Based on the sentiment recognized by the sentiment engine, the server adjusts the generated content. For example, if the sentiment engine determines that the user is unhappy, the server will generate a message that includes a special offer to alleviate that emotion.

[0106] After content generation, the server selects the most effective channel and determines the appropriate delivery timing based on the user's emotional state. For example, it might adjust the delivery of promotional information when the user is calm.

[0107] For example, if the server's sentiment engine detects that a user has left negative feedback on a product they frequently purchase, it will generate and deliver content that includes a message highlighting improvements to that product and offering a special discount. This can improve user satisfaction.

[0108] The following describes the processing flow.

[0109] Step 1:

[0110] The server accesses the user database and collects each user's customer history information, device usage history, and past interaction data. This establishes the dataset necessary for sentiment recognition.

[0111] Step 2:

[0112] The server analyzes data collected using an emotion engine to recognize the user's emotional state. For example, it can determine if a user is prone to dissatisfaction based on past negative feedback and interaction patterns.

[0113] Step 3:

[0114] The server invokes a generative model to generate message content based on the user's emotional state. Here, adjustments are made to mitigate the emotions identified by the emotion engine, and specific offers or information are incorporated.

[0115] Step 4:

[0116] The server uses a channel selection mechanism to determine the optimal delivery channel based on the user's characteristics and emotional state. It then formats the content appropriately and delivers it to the user's device.

[0117] Step 5:

[0118] The user receives the delivered content on their device and checks the message. Based on the information and offers presented, the user can, for example, make an online purchase or make an inquiry.

[0119] Step 6:

[0120] The server uses user response analysis tools to collect and analyze user reactions to delivered content. This feedback data is used to adjust future content and improve the accuracy of sentiment analysis.

[0121] (Example 2)

[0122] 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".

[0123] Existing digital marketing systems sometimes struggle to deliver flexible and personalized content that responds to user emotions. This can lead to decreased user engagement and satisfaction, which is a significant challenge.

[0124] 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.

[0125] In this invention, the server includes user data management means, content generation means using a generative model, and emotion recognition means. This enables the generation and delivery of optimal content tailored to the emotional state of each individual user.

[0126] "User data management means" refers to a function that collects and centrally manages customer history information and communication device usage history.

[0127] "Content generation methods using generative models" refer to functions that use pre-trained generative models to create customized messages and content based on user attributes and emotional patterns.

[0128] A "channel selection mechanism" is a function that selects the optimal communication path for delivering information to users.

[0129] "Distribution method" refers to the function of delivering generated content to users through selected channels.

[0130] "Emotion recognition means" refers to a function that analyzes the user's past responses and interaction data to recognize the user's emotional state.

[0131] The present invention is a system that generates personalized content for users and delivers it through the most suitable channel based on their emotions. This system operates with a server as the central component, and utilizes user data management means, content generation means using a generative model, channel selection means, delivery means, and emotion recognition means.

[0132] The server acquires customer history information and communication device usage history through user data management means and manages this information centrally. This data is efficiently managed using database software. Examples of specific software include database management systems such as MySQL® and MongoDB.

[0133] Next, the server uses a generative model to generate customized content based on the user's attributes and emotional state. This generation process utilizes machine learning algorithms. For example, frameworks such as TensorFlow and PyTorch are used to train and run the generative model. Natural language generation models are often used as the basis for these generative AI models.

[0134] Emotion recognition systems analyze past user responses and interaction data to recognize the user's emotional state. This process utilizes NLP (Natural Language Processing) technology, for example, by analyzing past text feedback and behavioral logs to detect the user's emotional trends.

[0135] The server selects the optimal channel based on emotions and delivers the generated content. The channel is chosen to best suit the user's situation, such as email, SMS, or push notifications. Messaging systems such as Apache® Kafka and RabbitMQ are used as the delivery infrastructure.

[0136] For example, if a server uses user sentiment recognition to detect that a user has left a negative review of a product in a specific category, it can generate a message highlighting improvements to that product and a special offer, which can then be delivered via email.

[0137] An example of a prompt message could be: "Analyze the user's sentiment about recently purchased items and generate a personalized message based on the user's sentiment."

[0138] This invention aims to improve user engagement through emotion-awareness, enabling the delivery of more satisfying digital experiences.

[0139] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0140] Step 1:

[0141] The server retrieves the user's activity history. The input includes the user's customer history and communication device usage history. The server extracts this data from the database and creates a user profile. The output is an activity history dataset corresponding to each individual user.

[0142] Step 2:

[0143] The server analyzes the user's emotional state using emotion recognition tools. The input consists of the user's past interaction data and feedback information. NLP techniques are used to analyze this data and recognize emotional patterns. Based on this analysis, the server outputs whether the user's emotional state is positive or negative.

[0144] Step 3:

[0145] The server uses a generative AI model to generate personalized content. The input consists of user attribute information and perceived emotional states. Based on this input data, the generative AI model generates personalized messages. The output is content optimized for the user.

[0146] Step 4:

[0147] The server determines the optimal delivery channel through a channel selection mechanism. Inputs include user usage history information and current emotional state. The server analyzes this data and selects the most effective channel, such as email or push notification. The output is the selected delivery channel information.

[0148] Step 5:

[0149] The server delivers the generated content to the user using the selected channel. The input is the generated message and channel information. The server delivers the content through the selected channel, and it reaches the user. The output is the content sent to the user's inbox or notification feed.

[0150] Through these steps, this system aims to provide users with a personalized experience and improve user engagement.

[0151] (Application Example 2)

[0152] 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 device 14 will be referred to as the "terminal."

[0153] In the field of personalized content delivery, the technology for accurately understanding a user's emotional state and delivering content tailored accordingly at the appropriate time is still immature. Therefore, there is a challenge in that the user experience is not sufficiently optimized.

[0154] 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.

[0155] In this invention, the server includes user data management means, content generation means using a generative model, and emotion recognition means. This makes it possible to analyze the user's emotion patterns and generate and deliver personalized content.

[0156] "User data management means" refers to technology for collecting, integrating, and managing users' past history information and device usage history.

[0157] "Content generation methods using generative models" refer to processes that use machine learning generative models to automatically generate content and messages tailored to the user.

[0158] A "channel selection method" is a method for selecting the optimal communication medium or route when distributing generated content.

[0159] A "delivery method" is a system for delivering personalized, sentiment-based content to users at the appropriate time.

[0160] "User response analysis means" refers to technologies that collect and analyze user reactions and feedback data to understand user emotions and needs.

[0161] An "emotion recognition method" is a process that uses algorithms to recognize and analyze emotional states based on user interaction and feedback.

[0162] This invention enables personalized content delivery based on the user's emotional state through a server-centered system. Specifically, the server employs the following means:

[0163] First, a SQL database, a means of managing user data, is used to centrally manage user history information and device usage history. Here, usage history data is collected and accessed along with individual identification information. Next, PyTorch and the natural language processing library transformers are used as content generation means that utilize generative AI models. This generates recommendation content and messages that are tailored to the user's emotional state.

[0164] Next, as a means of emotion recognition, the system analyzes emotion patterns based on interaction logs and response data. It utilizes PyTorch's emotion analysis algorithm to estimate emotions from user feedback and behavior. Based on the results of this emotion analysis, the server appropriately adjusts the content and delivers it to the user through the distribution method.

[0165] As a concrete example, if a user leaves negative feedback on a particular movie on a movie streaming service, the system will select highly-rated titles and create a promotion to recommend them to the user. This might involve a prompt such as, "If the user's sentiment is determined to be negative, select the most satisfying titles from their history and generate a message proposing a special campaign."

[0166] This invention improves the user experience and makes it possible to provide more personalized and engaging content viewing.

[0167] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0168] Step 1:

[0169] The server uses user data management tools to retrieve user history information and device usage history from an SQL database. This allows for the collection of individual users' past behavioral data and feedback. Input is user identification information, and output is historical data related to that user. Database queries are used to perform processing that aggregates device usage records and purchase history.

[0170] Step 2:

[0171] The server uses collected historical data and leverages PyTorch and natural language processing (NLP) libraries to analyze the user's emotional patterns using emotion recognition methods. The input is historical data, and the output is emotion labels and emotion scores. Specifically, the NLP model extracts emotional features from text data and quantifies emotions.

[0172] Step 3:

[0173] The server uses a generative AI model to generate personalized content based on the user's emotional state. The input is the result of the emotional analysis, and the output is the customized content. The server provides prompts to the model and performs a generation process to create content best suited to the user's preferences.

[0174] Step 4:

[0175] The server delivers the generated content to the user's device via a distribution method. The input is the generated content and information about the distribution channel, while the output is a notification message to the user. Here, the server considers the timing of delivery and selects the most appropriate method, such as push notification or email, for sending the message.

[0176] Step 5:

[0177] Users review the received content and provide feedback and reactions. Inputs include content ratings and comments, while output is this response data. This response data is then collected again by the server for use in future system improvements and content delivery.

[0178] 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.

[0179] 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.

[0180] 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.

[0181] [Second Embodiment]

[0182] Figure 3 shows an example of the configuration of the data processing system 210 according to the second embodiment.

[0183] 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.

[0184] 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).

[0185] 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.

[0186] 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.

[0187] 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).

[0188] 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.

[0189] 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.

[0190] 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.

[0191] 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.

[0192] 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.

[0193] 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".

[0194] The system of the present invention is implemented as follows in order to provide personalized content to each user: A server controls the entire system, and a user data management means collects the user's customer history information and terminal usage history. This prepares the data necessary to generate content that is optimal for each user.

[0195] The server utilizes a generative model to automatically generate messages tailored to each user's individual needs and interests based on collected data. This generated content is specific to the user's attributes, enabling the provision of highly personalized information.

[0196] For the distribution of generated content, the channel selection mechanism determines the most effective distribution channel based on user characteristics. It selects the most accessible channel for each user from a variety of options, including email, messaging apps, and social media. Using the selected channel, the server sends the content to the user's device via the distribution mechanism.

[0197] After a user receives content, a user response analysis tool analyzes their reaction. For example, it analyzes whether the user clicked on a link in the message, what actions they took based on the information provided, and uses this information to improve future content generation.

[0198] For example, student users will automatically receive information on the latest educational applications and student discount plans, which will be distributed through popular social media platforms. Similarly, senior users will receive video tutorials on simple smartphone operation, delivered via their familiar email services. In this way, information can be provided to diverse user groups in a manner tailored to their individual needs.

[0199] The following describes the processing flow.

[0200] Step 1:

[0201] The server queries the user database to retrieve each user's customer history and device usage history. This collects the necessary basic data for generating personalized messages.

[0202] Step 2:

[0203] The server invokes a generative model and generates a personalized message using the user data obtained in step 1. This generated content includes information tailored to the user's interests and needs.

[0204] Step 3:

[0205] The server selects the channel best suited to the user's attributes from among numerous distribution channels. The selection criteria include the user's past behavioral data and device type.

[0206] Step 4:

[0207] The server prepares the content in the appropriate format and delivers it to the user's terminal via the selected channel. During this process, format conversion may occur depending on the channel and content type.

[0208] Step 5:

[0209] The user receives a message on their device and checks its contents. The user then takes action based on the received information (for example, visiting a store or completing an online procedure).

[0210] Step 6:

[0211] The server collects and analyzes user responses. Link click-through rates and response rates are analyzed and used as feedback data to generate future messages.

[0212] (Example 1)

[0213] 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."

[0214] Current information delivery systems struggle to efficiently deliver personalized information tailored to the diverse needs of users. Furthermore, there is a growing need to utilize user history data and attributes to select the optimal delivery channel and facilitate effective communication.

[0215] 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.

[0216] In this invention, the server includes means for accumulating user records, means for creating information using a generative AI model, and means for selecting communication means. This enables information distribution optimized for each user.

[0217] "User records" refer to data that collects information about a user's behavior history and attributes.

[0218] A "generative AI model" is an artificial intelligence system that automatically generates personalized content based on data.

[0219] "Communication methods" refer to the channels and platforms used to transmit information, such as email and social networking services (SNS).

[0220] "Means of creating information" refers to the process of generating user-oriented messages and content based on specific data and conditions.

[0221] "Means for analyzing user responses" refers to a function that collects and analyzes user behavior and reactions to information received as data.

[0222] In embodiments of this invention, the following hardware and software environment is used.

[0223] The server has the functionality to collect user records and uses a database system to efficiently collect and store information such as user purchase history and device usage history. Furthermore, the server incorporates a generative AI model that runs on platforms such as Python and TensorFlow. This makes it possible to generate personalized content based on user attribute information.

[0224] As a concrete example, the server can input the prompt text "Generate the latest application information for students" into a generating AI model, which can then automatically generate information on educational apps of interest to student users.

[0225] The terminal has the functionality to receive communications from the server and presents information through various communication channels so that users can easily access it. Various means are used, such as email services, messaging apps, and social media platforms. The terminal also has the functionality to feed back user responses to the server, which is done via HTTP requests, WebSockets, and other methods.

[0226] Users take action based on the content they receive, for example by clicking on links, and these responses are used to create future content for the user. This ensures that information is continuously provided in a way that is most suitable for each individual user.

[0227] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0228] Step 1:

[0229] The server uses a means of aggregating user records to collect user purchase history and device usage history from a database. The user ID is used as input, and this historical information is extracted via SQL queries. The output is data on the user's past behavior. This data forms the basis for personalization in subsequent processing steps.

[0230] Step 2:

[0231] The server takes the user data obtained in Step 1 as input and provides prompt messages to the generating AI model to generate personalized content. For example, it might use the prompt, "Generate the latest education-related information based on the user ID." The model then generates a personalized message in response to this prompt and provides it as output. This model operates using natural language processing techniques.

[0232] Step 3:

[0233] The server selects the communication method based on the generated content and user characteristics. Inputs include the user's past communication history and usage trends. For example, a user with a high open rate on social media in the past would be deemed best suited to social media. The output is information about the selected communication channel. At this stage, a condition-based algorithm is used.

[0234] Step 4:

[0235] The server sends personalized content to the terminal via the communication method selected in step 3. The input is the generated content and the selected communication channel, which may utilize the SMTP protocol or API requests. The output is a notification sent to the user terminal, making the user ready to receive the information.

[0236] Step 5:

[0237] The device collects user responses and sends feedback to the server. The input is user activity logs (e.g., link clicks), which are then organized as data for analysis. The resulting feedback data is added to the user's profile information as a reference for future content generation. Statistical processing and machine learning algorithms are used for the analysis.

[0238] (Application Example 1)

[0239] 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."

[0240] Traditional content delivery systems have struggled to provide optimal educational content based on each user's individual learning history and interests. As a result, they have provided users with uniform information, and effective learning support has not been adequately achieved.

[0241] 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.

[0242] In this invention, the server includes user data management means, content generation means using a generative model, and content recommendation means for personalizing educational content based on learning history. This enables the automatic generation and provision of educational content that corresponds to the user's learning history and interests.

[0243] "User data management means" refers to a device or program that collects and manages user history information and device usage data.

[0244] "Content generation means using a generative model" refers to a device or program for generating information according to user attributes based on collected data.

[0245] "Channel selection means" refers to a device or program that determines the optimal distribution route based on user characteristic information.

[0246] "Distribution means" refers to a device or program that transmits generated content to the user's terminal via a selected distribution route.

[0247] A "user response analysis tool" is a device or program that analyzes how a user reacted to the content they received.

[0248] A "content recommendation means for personalizing educational content based on learning history" refers to a device or program that personalizes and recommends education-related information based on the learning history of individual users.

[0249] The system in this invention is designed to provide users with personalized educational content. The server first collects and manages user history information and device usage data using user data management means. This information is processed by content generation means using a generative model to generate personalized educational content based on the user's learning history and interests. A generative AI model is used in this process.

[0250] Once appropriate content is generated based on user attributes and learning history, the channel selection mechanism determines the optimal delivery path based on the user's characteristic information. This selection is made from communication channels such as email, messaging apps, and social media.

[0251] The generated content is transmitted to the user's device via a communication path selected by the distribution method. The user's response to the received content is analyzed by a user response analysis tool and managed to feed back into the next content generation process. This loop enables the provision of increasingly accurate personalized information to the user.

[0252] As a concrete example, for student users interested in mathematics or science education, relevant learning content is automatically recommended. In this case, by utilizing a prompt such as "Generate recommended content for students looking for new mathematics learning materials," the system generates and provides content that matches the user's interests.

[0253] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0254] Step 1:

[0255] The server collects and manages user history information and device usage data using user data management means. This data includes user learning history and interests. This information is stored in a database for later processing.

[0256] Step 2:

[0257] The server inputs the collected data into a generating AI model to create personalized educational content based on the user's learning history and interests. The prompt used is "Generate recommended content for students looking for new math materials." The generated content is then output. This provides a high level of personalization based on user attributes.

[0258] Step 3:

[0259] The server uses the generated content to activate a channel selection mechanism, choosing the optimal delivery path based on user characteristics. Inputs include the user's communication history and preferred channel information, and the output is the determined optimal communication path. This allows for efficient and effective content delivery to the user.

[0260] Step 4:

[0261] The server uses a predetermined communication path to deliver content to the user's terminal. The inputs are the predetermined delivery path and the content, and the output is the user's terminal receiving the content. This allows the user to instantly receive personalized information.

[0262] Step 5:

[0263] Users respond to the received content. These responses are analyzed on the server using a user response analysis system. The input is user behavior data, and the output is analysis results showing changes in the user's interests and preferences. These analysis results are used as feedback in future content generation.

[0264] 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.

[0265] This invention provides a system comprising user data management means, content generation means using a generative model, channel selection means, distribution means, user response analysis means, and an emotion engine that recognizes user emotions. A server plays a central role, establishing the infrastructure for managing user data and collecting necessary information.

[0266] The server allows the user data management system to acquire and centrally manage customer history information and device usage history. This ensures that the data necessary for generating personalized content is prepared, and enables integration with the emotion engine using a generation model.

[0267] This sentiment engine is used to recognize sentiment patterns by comparing the user's past response data and interaction logs. Based on the sentiment recognized by the sentiment engine, the server adjusts the generated content. For example, if the sentiment engine determines that the user is unhappy, the server will generate a message that includes a special offer to alleviate that emotion.

[0268] After content generation, the server selects the most effective channel and determines the appropriate delivery timing based on the user's emotional state. For example, it might adjust the delivery of promotional information when the user is calm.

[0269] For example, if the server's sentiment engine detects that a user has left negative feedback on a product they frequently purchase, it will generate and deliver content that includes a message highlighting improvements to that product and offering a special discount. This can improve user satisfaction.

[0270] The following describes the processing flow.

[0271] Step 1:

[0272] The server accesses the user database and collects each user's customer history information, device usage history, and past interaction data. This establishes the dataset necessary for sentiment recognition.

[0273] Step 2:

[0274] The server analyzes data collected using an emotion engine to recognize the user's emotional state. For example, it can determine if a user is prone to dissatisfaction based on past negative feedback and interaction patterns.

[0275] Step 3:

[0276] The server invokes a generative model to generate message content based on the user's emotional state. Here, adjustments are made to mitigate the emotions identified by the emotion engine, and specific offers or information are incorporated.

[0277] Step 4:

[0278] The server uses a channel selection mechanism to determine the optimal delivery channel based on the user's characteristics and emotional state. It then formats the content appropriately and delivers it to the user's device.

[0279] Step 5:

[0280] The user receives the content distributed by the terminal and checks the message. Based on the presented information and offers, the user makes, for example, an online purchase or an inquiry.

[0281] Step 6:

[0282] The server uses the user response analysis means to collect and analyze the user's reaction to the distributed content. The feedback data is utilized for content adjustment in subsequent times and improving the accuracy of sentiment analysis.

[0283] (Example 2)

[0284] Next, Example 2 will be described. In the following description, the data processing device 12 is referred to as the "server", and the smart glasses 214 are referred to as the "terminal".

[0285] In existing digital marketing systems, it may be difficult to distribute flexible and personalized content according to the user's sentiment. As a result, it is an issue that leads to a decrease in user engagement and satisfaction.

[0286] The specific processing by the specific processing unit 290 of the data processing device 12 in Example 2 is realized by the following respective means.

[0287] In this invention, the server includes user data management means, content generation means using a generation model, and sentiment recognition means. Thereby, it becomes possible to generate and distribute optimal content according to the emotional state of each user.

[0288] The "user data management means" is a function of collecting and centrally managing the customer's history information and the usage history of the communication device.

[0289] The "content generation means using a generation model" is a function of creating customized messages and content based on the user's attributes and emotional patterns using a pre-trained generation model.

[0290] A "channel selection mechanism" is a function that selects the optimal communication path for delivering information to users.

[0291] "Distribution method" refers to the function of delivering generated content to users through selected channels.

[0292] "Emotion recognition means" refers to a function that analyzes the user's past responses and interaction data to recognize the user's emotional state.

[0293] The present invention is a system that generates personalized content for users and delivers it through the most suitable channel based on their emotions. This system operates with a server as the central component, and utilizes user data management means, content generation means using a generative model, channel selection means, delivery means, and emotion recognition means.

[0294] The server acquires customer history information and communication device usage history through user data management means and manages this information centrally. This data is efficiently managed using database software. Examples of specific software include database management systems such as MySQL and MongoDB.

[0295] Next, the server uses a generative model to generate customized content based on the user's attributes and emotional state. This generation process utilizes machine learning algorithms. For example, frameworks such as TensorFlow and PyTorch are used to train and run the generative model. Natural language generation models are often used as the basis for these generative AI models.

[0296] Emotion recognition systems analyze past user responses and interaction data to recognize the user's emotional state. This process utilizes NLP (Natural Language Processing) technology, for example, by analyzing past text feedback and behavioral logs to detect the user's emotional trends.

[0297] The server selects the most suitable channel based on emotions and delivers the generated content. The channel is chosen to best suit the user's situation, such as email, SMS, or push notifications. Messaging systems such as Apache Kafka and RabbitMQ are used as the delivery infrastructure.

[0298] For example, if a server uses user sentiment recognition to detect that a user has left a negative review of a product in a specific category, it can generate a message highlighting improvements to that product and a special offer, which can then be delivered via email.

[0299] An example of a prompt message could be: "Analyze the user's sentiment about recently purchased items and generate a personalized message based on the user's sentiment."

[0300] This invention aims to improve user engagement through emotion-awareness, enabling the delivery of more satisfying digital experiences.

[0301] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0302] Step 1:

[0303] The server retrieves the user's activity history. The input includes the user's customer history and communication device usage history. The server extracts this data from the database and creates a user profile. The output is an activity history dataset corresponding to each individual user.

[0304] Step 2:

[0305] The server analyzes the user's emotional state using emotion recognition means. The input is the user's past interaction data and feedback information. This data is analyzed using NLP technology to recognize emotional patterns. Based on this analysis, an emotional state such as whether the user is positive or negative is output.

[0306] Step 3:

[0307] The server uses a generative AI model to generate personalized content. The input is the user's attribute information and the recognized emotional state. Based on these input data, the generative AI model generates individualized messages. The output is content optimized for the user.

[0308] Step 4:

[0309] The server determines the optimal delivery channel through channel selection means. The inputs are the user's usage history information and the current emotional state. The server analyzes this data and selects the most effective channel such as an email or a push notification. The output is the selected delivery channel information.

[0310] Step 5:

[0311] The server delivers the generated content to the user using the selected channel. The input is the generated message and the channel information. The server delivers the content through the selected channel and it reaches the user. The output is the content sent to the user's inbox or notification feed.

[0312] Through the above steps, this system aims to provide a personalized experience for the user and improve user engagement.

[0313] (Application Example 2)

[0314] 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."

[0315] In the field of personalized content delivery, the technology for accurately understanding a user's emotional state and delivering content tailored accordingly at the appropriate time is still immature. Therefore, there is a challenge in that the user experience is not sufficiently optimized.

[0316] 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.

[0317] In this invention, the server includes user data management means, content generation means using a generative model, and emotion recognition means. This makes it possible to analyze the user's emotion patterns and generate and deliver personalized content.

[0318] "User data management means" refers to technology for collecting, integrating, and managing users' past history information and device usage history.

[0319] "Content generation methods using generative models" refer to processes that use machine learning generative models to automatically generate content and messages tailored to the user.

[0320] A "channel selection method" is a method for selecting the optimal communication medium or route when distributing generated content.

[0321] A "delivery method" is a system for delivering personalized, sentiment-based content to users at the appropriate time.

[0322] "User response analysis means" refers to technologies that collect and analyze user reactions and feedback data to understand user emotions and needs.

[0323] An "emotion recognition method" is a process that uses algorithms to recognize and analyze emotional states based on user interaction and feedback.

[0324] This invention enables personalized content delivery based on the user's emotional state through a server-centered system. Specifically, the server employs the following means:

[0325] First, a SQL database, a means of managing user data, is used to centrally manage user history information and device usage history. Here, usage history data is collected and accessed along with individual identification information. Next, PyTorch and the natural language processing library transformers are used as content generation means that utilize generative AI models. This generates recommendation content and messages that are tailored to the user's emotional state.

[0326] Next, as a means of emotion recognition, the system analyzes emotion patterns based on interaction logs and response data. It utilizes PyTorch's emotion analysis algorithm to estimate emotions from user feedback and behavior. Based on the results of this emotion analysis, the server appropriately adjusts the content and delivers it to the user through the distribution method.

[0327] As a concrete example, if a user leaves negative feedback on a particular movie on a movie streaming service, the system will select highly-rated titles and create a promotion to recommend them to the user. This might involve a prompt such as, "If the user's sentiment is determined to be negative, select the most satisfying titles from their history and generate a message proposing a special campaign."

[0328] This invention improves the user experience and makes it possible to provide more personalized and engaging content viewing.

[0329] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0330] Step 1:

[0331] The server uses user data management tools to retrieve user history information and device usage history from an SQL database. This allows for the collection of individual users' past behavioral data and feedback. Input is user identification information, and output is historical data related to that user. Database queries are used to perform processing that aggregates device usage records and purchase history.

[0332] Step 2:

[0333] The server uses collected historical data and leverages PyTorch and natural language processing (NLP) libraries to analyze the user's emotional patterns using emotion recognition methods. The input is historical data, and the output is emotion labels and emotion scores. Specifically, the NLP model extracts emotional features from text data and quantifies emotions.

[0334] Step 3:

[0335] The server uses a generative AI model to generate personalized content based on the user's emotional state. The input is the result of the emotional analysis, and the output is the customized content. The server provides prompts to the model and performs a generation process to create content best suited to the user's preferences.

[0336] Step 4:

[0337] The server delivers the generated content to the user's device via a distribution method. The input is the generated content and information about the distribution channel, while the output is a notification message to the user. Here, the server considers the timing of delivery and selects the most appropriate method, such as push notification or email, for sending the message.

[0338] Step 5:

[0339] Users review the received content and provide feedback and reactions. Inputs include content ratings and comments, while output is this response data. This response data is then collected again by the server for use in future system improvements and content delivery.

[0340] 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.

[0341] 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.

[0342] 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.

[0343] [Third Embodiment]

[0344] Figure 5 shows an example of the configuration of the data processing system 310 according to the third embodiment.

[0345] 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.

[0346] 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).

[0347] 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.

[0348] 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.

[0349] 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).

[0350] 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.

[0351] 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.

[0352] 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.

[0353] 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.

[0354] 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.

[0355] 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".

[0356] The system of the present invention is implemented as follows in order to provide personalized content to each user: A server controls the entire system, and a user data management means collects the user's customer history information and terminal usage history. This prepares the data necessary to generate content that is optimal for each user.

[0357] The server utilizes a generative model to automatically generate messages tailored to each user's individual needs and interests based on collected data. This generated content is specific to the user's attributes, enabling the provision of highly personalized information.

[0358] For the distribution of generated content, the channel selection mechanism determines the most effective distribution channel based on user characteristics. It selects the most accessible channel for each user from a variety of options, including email, messaging apps, and social media. Using the selected channel, the server sends the content to the user's device via the distribution mechanism.

[0359] After a user receives content, a user response analysis tool analyzes their reaction. For example, it analyzes whether the user clicked on a link in the message, what actions they took based on the information provided, and uses this information to improve future content generation.

[0360] For example, student users will automatically receive information on the latest educational applications and student discount plans, which will be distributed through popular social media platforms. Similarly, senior users will receive video tutorials on simple smartphone operation, delivered via their familiar email services. In this way, information can be provided to diverse user groups in a manner tailored to their individual needs.

[0361] The following describes the processing flow.

[0362] Step 1:

[0363] The server queries the user database to retrieve each user's customer history and device usage history. This collects the necessary basic data for generating personalized messages.

[0364] Step 2:

[0365] The server invokes a generative model and generates a personalized message using the user data obtained in step 1. This generated content includes information tailored to the user's interests and needs.

[0366] Step 3:

[0367] The server selects the channel best suited to the user's attributes from among numerous distribution channels. The selection criteria include the user's past behavioral data and device type.

[0368] Step 4:

[0369] The server prepares the content in the appropriate format and delivers it to the user's terminal via the selected channel. During this process, format conversion may occur depending on the channel and content type.

[0370] Step 5:

[0371] The user receives a message on their device and checks its contents. The user then takes action based on the received information (for example, visiting a store or completing an online procedure).

[0372] Step 6:

[0373] The server collects and analyzes user responses. Link click-through rates and response rates are analyzed and used as feedback data to generate future messages.

[0374] (Example 1)

[0375] 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."

[0376] Current information delivery systems struggle to efficiently deliver personalized information tailored to the diverse needs of users. Furthermore, there is a growing need to utilize user history data and attributes to select the optimal delivery channel and facilitate effective communication.

[0377] 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.

[0378] In this invention, the server includes means for accumulating user records, means for creating information using a generative AI model, and means for selecting communication means. This enables information distribution optimized for each user.

[0379] "User records" refer to data that collects information about a user's behavior history and attributes.

[0380] A "generative AI model" is an artificial intelligence system that automatically generates personalized content based on data.

[0381] "Communication methods" refer to the channels and platforms used to transmit information, such as email and social networking services (SNS).

[0382] "Means of creating information" refers to the process of generating user-oriented messages and content based on specific data and conditions.

[0383] "Means for analyzing user responses" refers to a function that collects and analyzes user behavior and reactions to information received as data.

[0384] In embodiments of this invention, the following hardware and software environment is used.

[0385] The server has the functionality to collect user records and uses a database system to efficiently collect and store information such as user purchase history and device usage history. Furthermore, the server incorporates a generative AI model that runs on platforms such as Python and TensorFlow. This makes it possible to generate personalized content based on user attribute information.

[0386] As a concrete example, the server can input the prompt text "Generate the latest application information for students" into a generating AI model, which can then automatically generate information on educational apps of interest to student users.

[0387] The terminal has the functionality to receive communications from the server and presents information through various communication channels so that users can easily access it. Various means are used, such as email services, messaging apps, and social media platforms. The terminal also has the functionality to feed back user responses to the server, which is done via HTTP requests, WebSockets, and other methods.

[0388] Users take action based on the content they receive, for example by clicking on links, and these responses are used to create future content for the user. This ensures that information is continuously provided in a way that is most suitable for each individual user.

[0389] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0390] Step 1:

[0391] The server uses a means of aggregating user records to collect user purchase history and device usage history from a database. The user ID is used as input, and this historical information is extracted via SQL queries. The output is data on the user's past behavior. This data forms the basis for personalization in subsequent processing steps.

[0392] Step 2:

[0393] The server takes the user data obtained in Step 1 as input and provides prompt messages to the generating AI model to generate personalized content. For example, it might use the prompt, "Generate the latest education-related information based on the user ID." The model then generates a personalized message in response to this prompt and provides it as output. This model operates using natural language processing techniques.

[0394] Step 3:

[0395] The server selects the communication method based on the generated content and user characteristics. Inputs include the user's past communication history and usage trends. For example, a user with a high open rate on social media in the past would be deemed best suited to social media. The output is information about the selected communication channel. At this stage, a condition-based algorithm is used.

[0396] Step 4:

[0397] The server sends personalized content to the terminal via the communication method selected in step 3. The input is the generated content and the selected communication channel, which may utilize the SMTP protocol or API requests. The output is a notification sent to the user terminal, making the user ready to receive the information.

[0398] Step 5:

[0399] The device collects user responses and sends feedback to the server. The input is user activity logs (e.g., link clicks), which are then organized as data for analysis. The resulting feedback data is added to the user's profile information as a reference for future content generation. Statistical processing and machine learning algorithms are used for the analysis.

[0400] (Application Example 1)

[0401] 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."

[0402] Traditional content delivery systems have struggled to provide optimal educational content based on each user's individual learning history and interests. As a result, they have provided users with uniform information, and effective learning support has not been adequately achieved.

[0403] 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.

[0404] In this invention, the server includes user data management means, content generation means using a generative model, and content recommendation means for personalizing educational content based on learning history. This enables the automatic generation and provision of educational content that corresponds to the user's learning history and interests.

[0405] "User data management means" refers to a device or program that collects and manages user history information and device usage data.

[0406] "Content generation means using a generative model" refers to a device or program for generating information according to user attributes based on collected data.

[0407] "Channel selection means" refers to a device or program that determines the optimal distribution route based on user characteristic information.

[0408] "Distribution means" refers to a device or program that transmits generated content to the user's terminal via a selected distribution route.

[0409] A "user response analysis tool" is a device or program that analyzes how a user reacted to the content they received.

[0410] A "content recommendation means for personalizing educational content based on learning history" refers to a device or program that personalizes and recommends education-related information based on the learning history of individual users.

[0411] The system in this invention is designed to provide users with personalized educational content. The server first collects and manages user history information and device usage data using user data management means. This information is processed by content generation means using a generative model to generate personalized educational content based on the user's learning history and interests. A generative AI model is used in this process.

[0412] Once appropriate content is generated based on user attributes and learning history, the channel selection mechanism determines the optimal delivery path based on the user's characteristic information. This selection is made from communication channels such as email, messaging apps, and social media.

[0413] The generated content is transmitted to the user's device via a communication path selected by the distribution method. The user's response to the received content is analyzed by a user response analysis tool and managed to feed back into the next content generation process. This loop enables the provision of increasingly accurate personalized information to the user.

[0414] As a concrete example, for student users interested in mathematics or science education, relevant learning content is automatically recommended. In this case, by utilizing a prompt such as "Generate recommended content for students looking for new mathematics learning materials," the system generates and provides content that matches the user's interests.

[0415] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0416] Step 1:

[0417] The server collects and manages user history information and device usage data using user data management means. This data includes user learning history and interests. This information is stored in a database for later processing.

[0418] Step 2:

[0419] The server inputs the collected data into a generating AI model to create personalized educational content based on the user's learning history and interests. The prompt used is "Generate recommended content for students looking for new math materials." The generated content is then output. This provides a high level of personalization based on user attributes.

[0420] Step 3:

[0421] The server uses the generated content to activate a channel selection mechanism, choosing the optimal delivery path based on user characteristics. Inputs include the user's communication history and preferred channel information, and the output is the determined optimal communication path. This allows for efficient and effective content delivery to the user.

[0422] Step 4:

[0423] The server uses a predetermined communication path to deliver content to the user's terminal. The inputs are the predetermined delivery path and the content, and the output is the user's terminal receiving the content. This allows the user to instantly receive personalized information.

[0424] Step 5:

[0425] Users respond to the received content. These responses are analyzed on the server using a user response analysis system. The input is user behavior data, and the output is analysis results showing changes in the user's interests and preferences. These analysis results are used as feedback in future content generation.

[0426] 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.

[0427] This invention provides a system comprising user data management means, content generation means using a generative model, channel selection means, distribution means, user response analysis means, and an emotion engine that recognizes user emotions. A server plays a central role, establishing the infrastructure for managing user data and collecting necessary information.

[0428] The server allows the user data management system to acquire and centrally manage customer history information and device usage history. This ensures that the data necessary for generating personalized content is prepared, and enables integration with the emotion engine using a generation model.

[0429] This sentiment engine is used to recognize sentiment patterns by comparing the user's past response data and interaction logs. Based on the sentiment recognized by the sentiment engine, the server adjusts the generated content. For example, if the sentiment engine determines that the user is unhappy, the server will generate a message that includes a special offer to alleviate that emotion.

[0430] After content generation, the server selects the most effective channel and determines the appropriate delivery timing based on the user's emotional state. For example, it might adjust the delivery of promotional information when the user is calm.

[0431] For example, if the server's sentiment engine detects that a user has left negative feedback on a product they frequently purchase, it will generate and deliver content that includes a message highlighting improvements to that product and offering a special discount. This can improve user satisfaction.

[0432] The following describes the processing flow.

[0433] Step 1:

[0434] The server accesses the user database and collects each user's customer history information, device usage history, and past interaction data. This establishes the dataset necessary for sentiment recognition.

[0435] Step 2:

[0436] The server analyzes data collected using an emotion engine to recognize the user's emotional state. For example, it can determine if a user is prone to dissatisfaction based on past negative feedback and interaction patterns.

[0437] Step 3:

[0438] The server invokes a generative model to generate message content based on the user's emotional state. Here, adjustments are made to mitigate the emotions identified by the emotion engine, and specific offers or information are incorporated.

[0439] Step 4:

[0440] The server uses a channel selection mechanism to determine the optimal delivery channel based on the user's characteristics and emotional state. It then formats the content appropriately and delivers it to the user's device.

[0441] Step 5:

[0442] The user receives the delivered content on their device and checks the message. Based on the information and offers presented, the user can, for example, make an online purchase or make an inquiry.

[0443] Step 6:

[0444] The server uses user response analysis tools to collect and analyze user reactions to delivered content. This feedback data is used to adjust future content and improve the accuracy of sentiment analysis.

[0445] (Example 2)

[0446] 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."

[0447] Existing digital marketing systems sometimes struggle to deliver flexible and personalized content that responds to user emotions. This can lead to decreased user engagement and satisfaction, which is a significant challenge.

[0448] 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.

[0449] In this invention, the server includes user data management means, content generation means using a generative model, and emotion recognition means. This enables the generation and delivery of optimal content tailored to the emotional state of each individual user.

[0450] "User data management means" refers to a function that collects and centrally manages customer history information and communication device usage history.

[0451] "Content generation methods using generative models" refer to functions that use pre-trained generative models to create customized messages and content based on user attributes and emotional patterns.

[0452] A "channel selection mechanism" is a function that selects the optimal communication path for delivering information to users.

[0453] "Distribution method" refers to the function of delivering generated content to users through selected channels.

[0454] "Emotion recognition means" refers to a function that analyzes the user's past responses and interaction data to recognize the user's emotional state.

[0455] The present invention is a system that generates personalized content for users and delivers it through the most suitable channel based on their emotions. This system operates with a server as the central component, and utilizes user data management means, content generation means using a generative model, channel selection means, delivery means, and emotion recognition means.

[0456] The server acquires customer history information and communication device usage history through user data management means and manages this information centrally. This data is efficiently managed using database software. Examples of specific software include database management systems such as MySQL and MongoDB.

[0457] Next, the server uses a generative model to generate customized content based on the user's attributes and emotional state. This generation process utilizes machine learning algorithms. For example, frameworks such as TensorFlow and PyTorch are used to train and run the generative model. Natural language generation models are often used as the basis for these generative AI models.

[0458] Emotion recognition systems analyze past user responses and interaction data to recognize the user's emotional state. This process utilizes NLP (Natural Language Processing) technology, for example, by analyzing past text feedback and behavioral logs to detect the user's emotional trends.

[0459] The server selects the most suitable channel based on emotions and delivers the generated content. The channel is chosen to best suit the user's situation, such as email, SMS, or push notifications. Messaging systems such as Apache Kafka and RabbitMQ are used as the delivery infrastructure.

[0460] For example, if a server uses user sentiment recognition to detect that a user has left a negative review of a product in a specific category, it can generate a message highlighting improvements to that product and a special offer, which can then be delivered via email.

[0461] An example of a prompt message could be: "Analyze the user's sentiment about recently purchased items and generate a personalized message based on the user's sentiment."

[0462] This invention aims to improve user engagement through emotion-awareness, enabling the delivery of more satisfying digital experiences.

[0463] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0464] Step 1:

[0465] The server retrieves the user's activity history. The input includes the user's customer history and communication device usage history. The server extracts this data from the database and creates a user profile. The output is an activity history dataset corresponding to each individual user.

[0466] Step 2:

[0467] The server analyzes the user's emotional state using emotion recognition tools. The input consists of the user's past interaction data and feedback information. NLP techniques are used to analyze this data and recognize emotional patterns. Based on this analysis, the server outputs whether the user's emotional state is positive or negative.

[0468] Step 3:

[0469] The server uses a generative AI model to generate personalized content. The input consists of user attribute information and perceived emotional states. Based on this input data, the generative AI model generates personalized messages. The output is content optimized for the user.

[0470] Step 4:

[0471] The server determines the optimal delivery channel through a channel selection mechanism. Inputs include user usage history information and current emotional state. The server analyzes this data and selects the most effective channel, such as email or push notification. The output is the selected delivery channel information.

[0472] Step 5:

[0473] The server delivers the generated content to the user using the selected channel. The input is the generated message and channel information. The server delivers the content through the selected channel, and it reaches the user. The output is the content sent to the user's inbox or notification feed.

[0474] Through these steps, this system aims to provide users with a personalized experience and improve user engagement.

[0475] (Application Example 2)

[0476] 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."

[0477] In the field of personalized content delivery, the technology for accurately understanding a user's emotional state and delivering content tailored accordingly at the appropriate time is still immature. Therefore, there is a challenge in that the user experience is not sufficiently optimized.

[0478] 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.

[0479] In this invention, the server includes user data management means, content generation means using a generative model, and emotion recognition means. This makes it possible to analyze the user's emotion patterns and generate and deliver personalized content.

[0480] "User data management means" refers to technology for collecting, integrating, and managing users' past history information and device usage history.

[0481] "Content generation methods using generative models" refer to processes that use machine learning generative models to automatically generate content and messages tailored to the user.

[0482] A "channel selection method" is a method for selecting the optimal communication medium or route when distributing generated content.

[0483] A "delivery method" is a system for delivering personalized, sentiment-based content to users at the appropriate time.

[0484] "User response analysis means" refers to technologies that collect and analyze user reactions and feedback data to understand user emotions and needs.

[0485] An "emotion recognition method" is a process that uses algorithms to recognize and analyze emotional states based on user interaction and feedback.

[0486] This invention enables personalized content delivery based on the user's emotional state through a server-centered system. Specifically, the server employs the following means:

[0487] First, a SQL database, a means of managing user data, is used to centrally manage user history information and device usage history. Here, usage history data is collected and accessed along with individual identification information. Next, PyTorch and the natural language processing library transformers are used as content generation means that utilize generative AI models. This generates recommendation content and messages that are tailored to the user's emotional state.

[0488] Next, as a means of emotion recognition, the system analyzes emotion patterns based on interaction logs and response data. It utilizes PyTorch's emotion analysis algorithm to estimate emotions from user feedback and behavior. Based on the results of this emotion analysis, the server appropriately adjusts the content and delivers it to the user through the distribution method.

[0489] As a concrete example, if a user leaves negative feedback on a particular movie on a movie streaming service, the system will select highly-rated titles and create a promotion to recommend them to the user. This might involve a prompt such as, "If the user's sentiment is determined to be negative, select the most satisfying titles from their history and generate a message proposing a special campaign."

[0490] This invention improves the user experience and makes it possible to provide more personalized and engaging content viewing.

[0491] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0492] Step 1:

[0493] The server uses user data management tools to retrieve user history information and device usage history from an SQL database. This allows for the collection of individual users' past behavioral data and feedback. Input is user identification information, and output is historical data related to that user. Database queries are used to perform processing that aggregates device usage records and purchase history.

[0494] Step 2:

[0495] The server uses collected historical data and leverages PyTorch and natural language processing (NLP) libraries to analyze the user's emotional patterns using emotion recognition methods. The input is historical data, and the output is emotion labels and emotion scores. Specifically, the NLP model extracts emotional features from text data and quantifies emotions.

[0496] Step 3:

[0497] The server uses a generative AI model to generate personalized content based on the user's emotional state. The input is the result of the emotional analysis, and the output is the customized content. The server provides prompts to the model and performs a generation process to create content best suited to the user's preferences.

[0498] Step 4:

[0499] The server delivers the generated content to the user's device via a distribution method. The input is the generated content and information about the distribution channel, while the output is a notification message to the user. Here, the server considers the timing of delivery and selects the most appropriate method, such as push notification or email, for sending the message.

[0500] Step 5:

[0501] Users review the received content and provide feedback and reactions. Inputs include content ratings and comments, while output is this response data. This response data is then collected again by the server for use in future system improvements and content delivery.

[0502] 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.

[0503] 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.

[0504] 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.

[0505] [Fourth Embodiment]

[0506] Figure 7 shows an example of the configuration of the data processing system 410 according to the fourth embodiment.

[0507] 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.

[0508] 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).

[0509] 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.

[0510] 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.

[0511] 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).

[0512] 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.

[0513] 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.

[0514] 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.

[0515] 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.

[0516] 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.

[0517] 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.

[0518] 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".

[0519] The system of the present invention is implemented as follows in order to provide personalized content to each user: A server controls the entire system, and a user data management means collects the user's customer history information and terminal usage history. This prepares the data necessary to generate content that is optimal for each user.

[0520] The server utilizes a generative model to automatically generate messages tailored to each user's individual needs and interests based on collected data. This generated content is specific to the user's attributes, enabling the provision of highly personalized information.

[0521] For the distribution of generated content, the channel selection mechanism determines the most effective distribution channel based on user characteristics. It selects the most accessible channel for each user from a variety of options, including email, messaging apps, and social media. Using the selected channel, the server sends the content to the user's device via the distribution mechanism.

[0522] After a user receives content, a user response analysis tool analyzes their reaction. For example, it analyzes whether the user clicked on a link in the message, what actions they took based on the information provided, and uses this information to improve future content generation.

[0523] For example, student users will automatically receive information on the latest educational applications and student discount plans, which will be distributed through popular social media platforms. Similarly, senior users will receive video tutorials on simple smartphone operation, delivered via their familiar email services. In this way, information can be provided to diverse user groups in a manner tailored to their individual needs.

[0524] The following describes the processing flow.

[0525] Step 1:

[0526] The server queries the user database to retrieve each user's customer history and device usage history. This collects the necessary basic data for generating personalized messages.

[0527] Step 2:

[0528] The server invokes a generative model and generates a personalized message using the user data obtained in step 1. This generated content includes information tailored to the user's interests and needs.

[0529] Step 3:

[0530] The server selects the channel best suited to the user's attributes from among numerous distribution channels. The selection criteria include the user's past behavioral data and device type.

[0531] Step 4:

[0532] The server prepares the content in the appropriate format and delivers it to the user's terminal via the selected channel. During this process, format conversion may occur depending on the channel and content type.

[0533] Step 5:

[0534] The user receives a message on their device and checks its contents. The user then takes action based on the received information (for example, visiting a store or completing an online procedure).

[0535] Step 6:

[0536] The server collects and analyzes user responses. Link click-through rates and response rates are analyzed and used as feedback data to generate future messages.

[0537] (Example 1)

[0538] 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".

[0539] Current information delivery systems struggle to efficiently deliver personalized information tailored to the diverse needs of users. Furthermore, there is a growing need to utilize user history data and attributes to select the optimal delivery channel and facilitate effective communication.

[0540] 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.

[0541] In this invention, the server includes means for accumulating user records, means for creating information using a generative AI model, and means for selecting communication means. This enables information distribution optimized for each user.

[0542] "User records" refer to data that collects information about a user's behavior history and attributes.

[0543] A "generative AI model" is an artificial intelligence system that automatically generates personalized content based on data.

[0544] "Communication methods" refer to the channels and platforms used to transmit information, such as email and social networking services (SNS).

[0545] "Means of creating information" refers to the process of generating user-oriented messages and content based on specific data and conditions.

[0546] "Means for analyzing user responses" refers to a function that collects and analyzes user behavior and reactions to information received as data.

[0547] In embodiments of this invention, the following hardware and software environment is used.

[0548] The server has the functionality to collect user records and uses a database system to efficiently collect and store information such as user purchase history and device usage history. Furthermore, the server incorporates a generative AI model that runs on platforms such as Python and TensorFlow. This makes it possible to generate personalized content based on user attribute information.

[0549] As a concrete example, the server can input the prompt text "Generate the latest application information for students" into a generating AI model, which can then automatically generate information on educational apps of interest to student users.

[0550] The terminal has the functionality to receive communications from the server and presents information through various communication channels so that users can easily access it. Various means are used, such as email services, messaging apps, and social media platforms. The terminal also has the functionality to feed back user responses to the server, which is done via HTTP requests, WebSockets, and other methods.

[0551] Users take action based on the content they receive, for example by clicking on links, and these responses are used to create future content for the user. This ensures that information is continuously provided in a way that is most suitable for each individual user.

[0552] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0553] Step 1:

[0554] The server uses a means of aggregating user records to collect user purchase history and device usage history from a database. The user ID is used as input, and this historical information is extracted via SQL queries. The output is data on the user's past behavior. This data forms the basis for personalization in subsequent processing steps.

[0555] Step 2:

[0556] The server takes the user data obtained in Step 1 as input and provides prompt messages to the generating AI model to generate personalized content. For example, it might use the prompt, "Generate the latest education-related information based on the user ID." The model then generates a personalized message in response to this prompt and provides it as output. This model operates using natural language processing techniques.

[0557] Step 3:

[0558] The server selects the communication method based on the generated content and user characteristics. Inputs include the user's past communication history and usage trends. For example, a user with a high open rate on social media in the past would be deemed best suited to social media. The output is information about the selected communication channel. At this stage, a condition-based algorithm is used.

[0559] Step 4:

[0560] The server sends personalized content to the terminal via the communication method selected in step 3. The input is the generated content and the selected communication channel, which may utilize the SMTP protocol or API requests. The output is a notification sent to the user terminal, making the user ready to receive the information.

[0561] Step 5:

[0562] The device collects user responses and sends feedback to the server. The input is user activity logs (e.g., link clicks), which are then organized as data for analysis. The resulting feedback data is added to the user's profile information as a reference for future content generation. Statistical processing and machine learning algorithms are used for the analysis.

[0563] (Application Example 1)

[0564] 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".

[0565] Traditional content delivery systems have struggled to provide optimal educational content based on each user's individual learning history and interests. As a result, they have provided users with uniform information, and effective learning support has not been adequately achieved.

[0566] 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.

[0567] In this invention, the server includes user data management means, content generation means using a generative model, and content recommendation means for personalizing educational content based on learning history. This enables the automatic generation and provision of educational content that corresponds to the user's learning history and interests.

[0568] "User data management means" refers to a device or program that collects and manages user history information and device usage data.

[0569] "Content generation means using a generative model" refers to a device or program for generating information according to user attributes based on collected data.

[0570] "Channel selection means" refers to a device or program that determines the optimal distribution route based on user characteristic information.

[0571] "Distribution means" refers to a device or program that transmits generated content to the user's terminal via a selected distribution route.

[0572] A "user response analysis tool" is a device or program that analyzes how a user reacted to the content they received.

[0573] A "content recommendation means for personalizing educational content based on learning history" refers to a device or program that personalizes and recommends education-related information based on the learning history of individual users.

[0574] The system in this invention is designed to provide users with personalized educational content. The server first collects and manages user history information and device usage data using user data management means. This information is processed by content generation means using a generative model to generate personalized educational content based on the user's learning history and interests. A generative AI model is used in this process.

[0575] Once appropriate content is generated based on user attributes and learning history, the channel selection mechanism determines the optimal delivery path based on the user's characteristic information. This selection is made from communication channels such as email, messaging apps, and social media.

[0576] The generated content is transmitted to the user's device via a communication path selected by the distribution method. The user's response to the received content is analyzed by a user response analysis tool and managed to feed back into the next content generation process. This loop enables the provision of increasingly accurate personalized information to the user.

[0577] As a concrete example, for student users interested in mathematics or science education, relevant learning content is automatically recommended. In this case, by utilizing a prompt such as "Generate recommended content for students looking for new mathematics learning materials," the system generates and provides content that matches the user's interests.

[0578] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0579] Step 1:

[0580] The server collects and manages user history information and device usage data using user data management means. This data includes user learning history and interests. This information is stored in a database for later processing.

[0581] Step 2:

[0582] The server inputs the collected data into a generating AI model to create personalized educational content based on the user's learning history and interests. The prompt used is "Generate recommended content for students looking for new math materials." The generated content is then output. This provides a high level of personalization based on user attributes.

[0583] Step 3:

[0584] The server uses the generated content to activate a channel selection mechanism, choosing the optimal delivery path based on user characteristics. Inputs include the user's communication history and preferred channel information, and the output is the determined optimal communication path. This allows for efficient and effective content delivery to the user.

[0585] Step 4:

[0586] The server uses a predetermined communication path to deliver content to the user's terminal. The inputs are the predetermined delivery path and the content, and the output is the user's terminal receiving the content. This allows the user to instantly receive personalized information.

[0587] Step 5:

[0588] Users respond to the received content. These responses are analyzed on the server using a user response analysis system. The input is user behavior data, and the output is analysis results showing changes in the user's interests and preferences. These analysis results are used as feedback in future content generation.

[0589] 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.

[0590] This invention provides a system comprising user data management means, content generation means using a generative model, channel selection means, distribution means, user response analysis means, and an emotion engine that recognizes user emotions. A server plays a central role, establishing the infrastructure for managing user data and collecting necessary information.

[0591] The server allows the user data management system to acquire and centrally manage customer history information and device usage history. This ensures that the data necessary for generating personalized content is prepared, and enables integration with the emotion engine using a generation model.

[0592] This sentiment engine is used to recognize sentiment patterns by comparing the user's past response data and interaction logs. Based on the sentiment recognized by the sentiment engine, the server adjusts the generated content. For example, if the sentiment engine determines that the user is unhappy, the server will generate a message that includes a special offer to alleviate that emotion.

[0593] After content generation, the server selects the most effective channel and determines the appropriate delivery timing based on the user's emotional state. For example, it might adjust the delivery of promotional information when the user is calm.

[0594] For example, if the server's sentiment engine detects that a user has left negative feedback on a product they frequently purchase, it will generate and deliver content that includes a message highlighting improvements to that product and offering a special discount. This can improve user satisfaction.

[0595] The following describes the processing flow.

[0596] Step 1:

[0597] The server accesses the user database and collects each user's customer history information, device usage history, and past interaction data. This establishes the dataset necessary for sentiment recognition.

[0598] Step 2:

[0599] The server analyzes data collected using an emotion engine to recognize the user's emotional state. For example, it can determine if a user is prone to dissatisfaction based on past negative feedback and interaction patterns.

[0600] Step 3:

[0601] The server invokes a generative model to generate message content based on the user's emotional state. Here, adjustments are made to mitigate the emotions identified by the emotion engine, and specific offers or information are incorporated.

[0602] Step 4:

[0603] The server uses a channel selection mechanism to determine the optimal delivery channel based on the user's characteristics and emotional state. It then formats the content appropriately and delivers it to the user's device.

[0604] Step 5:

[0605] The user receives the delivered content on their device and checks the message. Based on the information and offers presented, the user can, for example, make an online purchase or make an inquiry.

[0606] Step 6:

[0607] The server uses user response analysis tools to collect and analyze user reactions to delivered content. This feedback data is used to adjust future content and improve the accuracy of sentiment analysis.

[0608] (Example 2)

[0609] 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".

[0610] Existing digital marketing systems sometimes struggle to deliver flexible and personalized content that responds to user emotions. This can lead to decreased user engagement and satisfaction, which is a significant challenge.

[0611] 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.

[0612] In this invention, the server includes user data management means, content generation means using a generative model, and emotion recognition means. This enables the generation and delivery of optimal content tailored to the emotional state of each individual user.

[0613] "User data management means" refers to a function that collects and centrally manages customer history information and communication device usage history.

[0614] "Content generation methods using generative models" refer to functions that use pre-trained generative models to create customized messages and content based on user attributes and emotional patterns.

[0615] A "channel selection mechanism" is a function that selects the optimal communication path for delivering information to users.

[0616] "Distribution method" refers to the function of delivering generated content to users through selected channels.

[0617] "Emotion recognition means" refers to a function that analyzes the user's past responses and interaction data to recognize the user's emotional state.

[0618] The present invention is a system that generates personalized content for users and delivers it through the most suitable channel based on their emotions. This system operates with a server as the central component, and utilizes user data management means, content generation means using a generative model, channel selection means, delivery means, and emotion recognition means.

[0619] The server acquires customer history information and communication device usage history through user data management means and manages this information centrally. This data is efficiently managed using database software. Examples of specific software include database management systems such as MySQL and MongoDB.

[0620] Next, the server uses a generative model to generate customized content based on the user's attributes and emotional state. This generation process utilizes machine learning algorithms. For example, frameworks such as TensorFlow and PyTorch are used to train and run the generative model. Natural language generation models are often used as the basis for these generative AI models.

[0621] Emotion recognition systems analyze past user responses and interaction data to recognize the user's emotional state. This process utilizes NLP (Natural Language Processing) technology, for example, by analyzing past text feedback and behavioral logs to detect the user's emotional trends.

[0622] The server selects the most suitable channel based on emotions and delivers the generated content. The channel is chosen to best suit the user's situation, such as email, SMS, or push notifications. Messaging systems such as Apache Kafka and RabbitMQ are used as the delivery infrastructure.

[0623] For example, if a server uses user sentiment recognition to detect that a user has left a negative review of a product in a specific category, it can generate a message highlighting improvements to that product and a special offer, which can then be delivered via email.

[0624] An example of a prompt message could be: "Analyze the user's sentiment about recently purchased items and generate a personalized message based on the user's sentiment."

[0625] This invention aims to improve user engagement through emotion-awareness, enabling the delivery of more satisfying digital experiences.

[0626] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0627] Step 1:

[0628] The server retrieves the user's activity history. The input includes the user's customer history and communication device usage history. The server extracts this data from the database and creates a user profile. The output is an activity history dataset corresponding to each individual user.

[0629] Step 2:

[0630] The server analyzes the user's emotional state using emotion recognition tools. The input consists of the user's past interaction data and feedback information. NLP techniques are used to analyze this data and recognize emotional patterns. Based on this analysis, the server outputs whether the user's emotional state is positive or negative.

[0631] Step 3:

[0632] The server uses a generative AI model to generate personalized content. The input consists of user attribute information and perceived emotional states. Based on this input data, the generative AI model generates personalized messages. The output is content optimized for the user.

[0633] Step 4:

[0634] The server determines the optimal delivery channel through a channel selection mechanism. Inputs include user usage history information and current emotional state. The server analyzes this data and selects the most effective channel, such as email or push notification. The output is the selected delivery channel information.

[0635] Step 5:

[0636] The server delivers the generated content to the user using the selected channel. The input is the generated message and channel information. The server delivers the content through the selected channel, and it reaches the user. The output is the content sent to the user's inbox or notification feed.

[0637] Through these steps, this system aims to provide users with a personalized experience and improve user engagement.

[0638] (Application Example 2)

[0639] 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".

[0640] In the field of personalized content delivery, the technology for accurately understanding a user's emotional state and delivering content tailored accordingly at the appropriate time is still immature. Therefore, there is a challenge in that the user experience is not sufficiently optimized.

[0641] 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.

[0642] In this invention, the server includes user data management means, content generation means using a generative model, and emotion recognition means. This makes it possible to analyze the user's emotion patterns and generate and deliver personalized content.

[0643] "User data management means" refers to technology for collecting, integrating, and managing users' past history information and device usage history.

[0644] "Content generation methods using generative models" refer to processes that use machine learning generative models to automatically generate content and messages tailored to the user.

[0645] A "channel selection method" is a method for selecting the optimal communication medium or route when distributing generated content.

[0646] A "delivery method" is a system for delivering personalized, sentiment-based content to users at the appropriate time.

[0647] "User response analysis means" refers to technologies that collect and analyze user reactions and feedback data to understand user emotions and needs.

[0648] An "emotion recognition method" is a process that uses algorithms to recognize and analyze emotional states based on user interaction and feedback.

[0649] This invention enables personalized content delivery based on the user's emotional state through a server-centered system. Specifically, the server employs the following means:

[0650] First, a SQL database, a means of managing user data, is used to centrally manage user history information and device usage history. Here, usage history data is collected and accessed along with individual identification information. Next, PyTorch and the natural language processing library transformers are used as content generation means that utilize generative AI models. This generates recommendation content and messages that are tailored to the user's emotional state.

[0651] Next, as a means of emotion recognition, the system analyzes emotion patterns based on interaction logs and response data. It utilizes PyTorch's emotion analysis algorithm to estimate emotions from user feedback and behavior. Based on the results of this emotion analysis, the server appropriately adjusts the content and delivers it to the user through the distribution method.

[0652] As a concrete example, if a user leaves negative feedback on a particular movie on a movie streaming service, the system will select highly-rated titles and create a promotion to recommend them to the user. This might involve a prompt such as, "If the user's sentiment is determined to be negative, select the most satisfying titles from their history and generate a message proposing a special campaign."

[0653] This invention improves the user experience and makes it possible to provide more personalized and engaging content viewing.

[0654] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0655] Step 1:

[0656] The server uses user data management tools to retrieve user history information and device usage history from an SQL database. This allows for the collection of individual users' past behavioral data and feedback. Input is user identification information, and output is historical data related to that user. Database queries are used to perform processing that aggregates device usage records and purchase history.

[0657] Step 2:

[0658] The server uses collected historical data and leverages PyTorch and natural language processing (NLP) libraries to analyze the user's emotional patterns using emotion recognition methods. The input is historical data, and the output is emotion labels and emotion scores. Specifically, the NLP model extracts emotional features from text data and quantifies emotions.

[0659] Step 3:

[0660] The server uses a generative AI model to generate personalized content based on the user's emotional state. The input is the result of the emotional analysis, and the output is the customized content. The server provides prompts to the model and performs a generation process to create content best suited to the user's preferences.

[0661] Step 4:

[0662] The server delivers the generated content to the user's device via a distribution method. The input is the generated content and information about the distribution channel, while the output is a notification message to the user. Here, the server considers the timing of delivery and selects the most appropriate method, such as push notification or email, for sending the message.

[0663] Step 5:

[0664] Users review the received content and provide feedback and reactions. Inputs include content ratings and comments, while output is this response data. This response data is then collected again by the server for use in future system improvements and content delivery.

[0665] 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.

[0666] 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.

[0667] 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 robot 414.

[0668] 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.

[0669] 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.

[0670] 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.

[0671] 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.

[0672] 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.

[0673] 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."

[0674] 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.

[0675] 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.

[0676] 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.

[0677] 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.

[0678] 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.

[0679] 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.

[0680] 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.

[0681] 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.

[0682] 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.

[0683] 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.

[0684] 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.

[0685] 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.

[0686] The following is further disclosed regarding the embodiments described above.

[0687] (Claim 1)

[0688] User data management means,

[0689] A content generation method using a generative model,

[0690] Channel selection means,

[0691] Distribution methods,

[0692] User response analysis means,

[0693] A system that includes this.

[0694] (Claim 2)

[0695] The system according to claim 1, characterized in that the user data management means manages customer history information and terminal usage history.

[0696] (Claim 3)

[0697] The system according to claim 1, characterized in that the content generation means using the generation model generates personalized message content based on user attributes.

[0698] "Example 1"

[0699] (Claim 1)

[0700] A means of accumulating user records,

[0701] A means of creating information using a generative AI model,

[0702] Means for selecting communication methods,

[0703] Means of providing information,

[0704] A means of analyzing user reactions,

[0705] A system that includes this.

[0706] (Claim 2)

[0707] The system according to claim 1, characterized in that the means for accumulating user records manages purchase history and equipment usage history.

[0708] (Claim 3)

[0709] The system according to claim 1, characterized in that the means for creating information using the aforementioned generation AI model generates personalized communication content based on user attributes.

[0710] "Application Example 1"

[0711] (Claim 1)

[0712] User data management means,

[0713] A content generation method using a generative model,

[0714] Channel selection means,

[0715] Distribution methods,

[0716] User response analysis means,

[0717] A content recommendation method that personalizes educational content based on learning history,

[0718] A system that includes this.

[0719] (Claim 2)

[0720] The system according to claim 1, characterized in that the user data management means manages historical information and device usage history.

[0721] (Claim 3)

[0722] The system according to claim 1, characterized in that the content generation means using the generation model generates information obtained based on user attributes.

[0723] "Example 2 of combining an emotion engine"

[0724] (Claim 1)

[0725] User data management means,

[0726] A content generation method using a generative model,

[0727] Channel selection means,

[0728] Distribution methods,

[0729] Means of recognizing emotions,

[0730] A system that includes this.

[0731] (Claim 2)

[0732] The system according to claim 1, characterized in that the user data management means manages customer history information and communication device usage history.

[0733] (Claim 3)

[0734] The system according to claim 1, characterized in that the content generation means using the generation model generates message content that is adjusted based on the user's emotional patterns.

[0735] "Application example 2 when combining with an emotional engine"

[0736] (Claim 1)

[0737] User data management means,

[0738] A content generation method using a generative model,

[0739] Channel selection means,

[0740] Distribution methods,

[0741] User response analysis means,

[0742] Means of recognizing emotions,

[0743] A means of generating personalized content based on sentiment analysis and delivering it at the appropriate time,

[0744] A system that includes this.

[0745] (Claim 2)

[0746] The system according to claim 1, characterized in that the user data management means manages user history information and terminal usage history.

[0747] (Claim 3)

[0748] The system according to claim 1, characterized in that the content generation means using the generation model generates personalized suggested content based on user attributes and emotional patterns. [Explanation of symbols]

[0749] 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

[Claim 1] A user data management means for managing customer history information and terminal usage history, A content generation means that generates personalized message content based on user attributes using a generative model, A channel selection method that determines and selects the optimal distribution channel according to the user's characteristics, A distribution method that delivers generated content to users through selected channels, A user response analysis tool that collects and analyzes how users reacted to messages they received, A system that includes this.

Images