system

Abstract

Provide a system. [Solution] an input means for inputting the child's name; a transmitting means for transmitting the child's name inputted via the input means to a server; a generation means for generating a story by using a generative artificial intelligence based on the child's name received by the server via the transmission means; a transmission means for transmitting the story generated by the generation means to a terminal; a display means for displaying the story received by the terminal via the transmission means; A system including:

Description

[Technical Field]

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

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

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

[0004] Conventional story generation and reading systems have difficulty reflecting the individuality of children, and it is particularly difficult to generate personalized stories that include children's names on a daily basis. Furthermore, reading aloud manually places a heavy burden on parents, and many systems lack a text-to-speech function. This makes it difficult for children to maintain their interest. [Means for solving the problem]

[0005] The present invention solves the above-mentioned problems by providing a system including an input means for inputting a child's name, a transmission means for transmitting the child's name input via the input means to a server, a generation means for the server to generate a story using generative artificial intelligence based on the child's name received via the transmission means, a transmission means for transmitting the story generated by the generation means to a terminal, and a display means for displaying the story received via the transmission means on the terminal. Furthermore, by including a voice synthesis means in the display means, the story can be read aloud, thereby reducing the burden on parents and maintaining the child's interest. Furthermore, by configuring the input means, transmission means, and display means as applications executed on a smartphone or tablet terminal, a system that is highly convenient for users can be provided.

[0006] "Input means" refers to a means by which a user inputs information such as the child's name.

[0007] The "transmission means" is a means for transmitting data acquired via the input means to the server.

[0008] The "generation means" is a means for generating a story using generative artificial intelligence based on the data received by the server via the transmission means.

[0009] The "display means" is a means for displaying the story generated by the generation means on the terminal.

[0010] The "voice synthesis means" is a means for reading out aloud the story displayed on the display means.

[0011] A "terminal" is a device (e.g., a smartphone or tablet) operated by a user, and is a platform for executing input means, transmission means, display means, and speech synthesis means.

[0012] A "server" is a computer system that performs back-end processing such as generative artificial intelligence, generates stories, and sends them to terminals.

[0013] "Generative AI" is an AI technology that uses algorithms to generate new stories based on input data. [Brief explanation of the drawings]

[0014] [Figure 1] 1 is a conceptual diagram showing an example of the configuration of a data processing system according to a first embodiment. [Figure 2] 1 is a conceptual diagram showing an example of main functions of a data processing device and a smart device according to a first embodiment. [Figure 3] FIG. 10 is a conceptual diagram showing an example of the configuration of a data processing system according to a second embodiment. [Figure 4] FIG. 10 is a conceptual diagram showing an example of main functions of a data processing device and smart glasses according to a second embodiment. [Figure 5] FIG. 10 is a conceptual diagram showing an example of the configuration of a data processing system according to a third embodiment. [Figure 6] FIG. 11 is a conceptual diagram showing an example of main functions of a data processing device and a headset-type terminal according to a third embodiment. [Figure 7] FIG. 10 is a conceptual diagram showing an example of the configuration of a data processing system according to a fourth embodiment. [Figure 8] FIG. 10 is a conceptual diagram showing an example of main functions of a data processing device and a robot according to a fourth embodiment. [Figure 9] 1 shows an emotion map onto which multiple emotions are mapped. [Figure 10] 1 shows an emotion map onto which multiple emotions are mapped. [Figure 11] FIG. 3 is a sequence diagram showing a processing flow of the data processing system according to the first embodiment. [Figure 12] FIG. 10 is a sequence diagram showing the flow of processing in the data processing system in Application Example 1. [Figure 13]FIG. 10 is a sequence diagram showing the flow of processing in the data processing system according to the second embodiment when an emotion engine is combined. [Figure 14] FIG. 10 is a sequence diagram showing the flow of processing in the data processing system in Application Example 2 when an emotion engine is combined. DETAILED DESCRIPTION OF THE INVENTION

[0015] An example of an embodiment of a system according to the technology of the present disclosure will be described below with reference to the accompanying drawings.

[0016] First, the terms used in the following description will be explained.

[0017] In the following embodiments, a coded processor (hereinafter simply referred to as a "processor") may be a single arithmetic device or a combination of multiple arithmetic devices. Furthermore, a processor may be a single type of arithmetic device or a combination of multiple types of arithmetic devices. Examples of arithmetic devices include a CPU (Central Processing Unit), a GPU (Graphics Processing Unit), a GPGPU (General-Purpose computing on Graphics Processing Units), and an APU (Accelerated Processing Unit).

[0018] In the following embodiments, a coded RAM (Random Access Memory) is a memory in which information is temporarily stored and is used as a working memory by a processor.

[0019] In the following embodiments, the coded storage is one or more non-volatile storage devices that store various programs, various parameters, etc. Examples of non-volatile storage devices include flash memory (SSD (Solid State Drive)), magnetic disks (e.g., hard disks), and magnetic tapes.

[0020] In the following embodiments, a communication I / F (Interface) with a symbol is an interface including a communication processor, an antenna, etc. The communication I / F controls communication between multiple computers. Examples of communication standards applied to the communication I / F include wireless communication standards including 5G (5th Generation Mobile Communication System), Wi-Fi (registered trademark), Bluetooth (registered trademark), etc.

[0021] In the following embodiments, "A and / or B" is synonymous with "at least one of A and B." In other words, "A and / or B" means that it may be only A, only B, or a combination of A and B. Furthermore, in this specification, the same concept as "A and / or B" is also applied when three or more things are expressed connected by "and / or."

[0022] [First embodiment]

[0023] FIG. 1 shows an example of the configuration of a data processing system 10 according to the first embodiment.

[0024] 1, a data processing system 10 includes a data processing device 12 and a smart device 14. An example of the data processing device 12 is a server.

[0025] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 is an example of a "computer" according to the technology of the present disclosure. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, the RAM 30, and the storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0026] The smart device 14 includes a computer 36, a reception device 38, an output device 40, a camera 42, and a communication I / F 44. The computer 36 includes a processor 46, a RAM 48, and a storage 50. The processor 46, the RAM 48, and the storage 50 are connected to a bus 52. The reception device 38, the output device 40, and the camera 42 are also connected to the bus 52.

[0027] The reception device 38 includes a touch panel 38A, a microphone 38B, and the like, and receives user input. The touch panel 38A detects contact with an indicator (for example, a pen or a finger) to receive user input by the touch of the indicator. The microphone 38B detects the user's voice to receive user input by voice. The control unit 46A transmits data indicating the user input received by the touch panel 38A and the microphone 38B to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the data indicating the user input.

[0028] The output device 40 includes a display 40A and a speaker 40B, and presents data to the user 20 by outputting the data in a form of expression that the user 20 can perceive (for example, audio and / or text). The display 40A displays visible information such as text and images in accordance with instructions from the processor 46. The speaker 40B outputs audio in accordance with instructions from the processor 46. The camera 42 is a compact digital camera equipped with an optical system including a lens, aperture, and shutter, and an imaging element such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor.

[0029] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 control the exchange of various information between the processor 46 and the processor 28 via the network 54.

[0030] FIG. 2 shows an example of the main functions of the data processing device 12 and the smart device 14.

[0031] 2, in the data processing device 12, a specific process is performed by the processor 28. A specific processing program 56 is stored in the storage 32. The specific processing program 56 is an example of a "program" according to the technology of the present disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific process is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[0032] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[0033] In the smart device 14, the processor 46 performs the reception output process. The storage 50 stores a reception output program 60. The reception output program 60 is used in conjunction with the specific processing program 56 by the data processing system 10. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output process is realized by the processor 46 operating as the control unit 46A in accordance with the reception output program 60 executed on the RAM 48.

[0034] Next, a description will be given of the specific processing performed by the specific processing unit 290 of the data processing device 12. In the following description, the data processing device 12 will be referred to as a "server" and the smart device 14 will be referred to as a "terminal."

[0035] This invention relates to a system in which a user inputs a child's name, and a server uses generative artificial intelligence to generate a story based on that information, and the story is then displayed and read aloud on the terminal. Below, we will explain the specific program processing in natural language, with examples.

[0036] 1. Enter your child's name

[0037] The user enters the child's name into an input field on the device, for example, "Taro" on the application screen of a smartphone or tablet.

[0038] 2. Sending input data

[0039] The device sends the entered data, including the name "Taro," to the server. Here, the data is sent securely using the HTTPS protocol.

[0040] 3. Receiving and Authenticating a Request

[0041] The server receives a request from the device. This request includes the child's name "Taro" and authentication information such as the user ID and session ID. The server authenticates the user based on this information and verifies that the request is legitimate.

[0042] 4. Story Generation

[0043] After authentication, the server instructs the generative AI to generate a story. The generative AI generates a personalized story with a protagonist named "Taro." This story is generated by combining unique templates and random elements.

[0044] 5. Formatting and sending the generated results

[0045] The server formats the generated story and sends it to the device in JSON or text format, and may also include the date and time of creation and other metadata along with the story.

[0046] 6. Viewing Stories

[0047] The device analyzes the story received from the server and displays it on the user interface (UI). The story may not only consist of text, but may also include illustrations and sound effects.

[0048] 7. Text-to-speech

[0049] The device will launch a text-to-speech tool to read the story aloud, making it easier for users to read stories to their children.

[0050] Specific examples

[0051] scenario:

[0052] Suppose a user wants to create a new story for a child named "Taro" and tell it to him.

[0053] 1. The user enters "Taro"

[0054] The user enters "Taro" in the application's input field and presses the generate button.

[0055] 2. Submitting a Request

[0056] The device sends data including the name "Taro" to the server using HTTPS.

[0057] 3. Processing on the Server

[0058] The server receives the request and authenticates the user. If authentication is successful, it instructs the generative AI to generate a story with "Taro" as the main character.

[0059] 4. Story Generation

[0060] Generative AI generates stories such as "Taro goes on an adventure in the forest," which are a combination of specific templates and random elements.

[0061] 5. Sending and displaying results

[0062] The server formats the generated story into JSON format and sends it to the device, which parses the story and displays it in the UI.

[0063] 6. Reading and User Interaction

[0064] The device uses a text-to-speech tool to read the story aloud, and the user can tap the screen to go to the next page or stop reading.

[0065] This invention allows users to create a different story every day using their child's name and easily read it to them, which can keep the child interested while reducing the burden on parents.

[0066] The processing flow will be explained below.

[0067] Step 1:

[0068] The user enters the child's name "Taro" into the input field on the device. The user presses the "Generate" button.

[0069] Step 2:

[0070] The device prepares request data including the input name "Taro." This request data also includes authentication information such as the user ID and session ID. The device sends a POST request to the server using the HTTPS protocol.

[0071] Step 3:

[0072] The server receives a POST request from the device, verifies the authentication information in the request, and verifies that the user has valid permissions.

[0073] Step 4:

[0074] After the server verifies it, it passes the received data, including the name "Taro," to the generative AI and requests it to generate a story.

[0075] Step 5:

[0076] Based on the data received, the generative AI generates a story with the name "Taro" as the main character. For example, it might generate a story about Taro's adventures in a magical forest. This story is created by combining random elements and predefined templates.

[0077] Step 6:

[0078] The generated story is temporarily stored on the server in text or JSON format, and the server formats this data in a format suitable for the user, adding images and audio data if necessary.

[0079] Step 7:

[0080] The server sends the formatted story to the device as response data, which includes the story text, the creation date and time, and other metadata.

[0081] Step 8:

[0082] The device analyzes the story received from the server and prepares it for display on the user interface (UI).

[0083] Step 9:

[0084] The device launches a speech synthesis tool to read the displayed story aloud. The device provides the user with the option to start reading the story aloud.

[0085] Step 10:

[0086] The user uses the device to read the generated story to the child, tapping the screen as needed to advance to the next page or stop reading.

[0087] Example 1

[0088] Next, a description will be given of Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the smart device 14 will be referred to as a "terminal."

[0089] In recent years, there has been a growing demand for systems with educational value that promote parent-child communication and foster children's creativity. However, existing systems have issues with difficulty in generating stories tailored to individual children's names and characteristics, and have complex operation and low usability. Furthermore, there is a lack of systems that allow users to enjoy the generated stories both visually and aurally. The purpose of this invention is to solve these issues and realize easy and personalized story generation and playback.

[0090] The specific processing by the specific processing unit 290 of the data processing device 12 in the first embodiment is realized by the following means.

[0091] In this invention, the server includes input means for inputting a child's name, transmission means for transmitting the child's name input via the input means to the server, authentication means for authenticating a user based on the child's name and authentication information received by the server via the transmission means, generation means for generating a story using generative artificial intelligence based on the information authenticated by the authentication means, transmission means for formatting the story generated by the generation means into JSON format or text format and transmitting it to a terminal, display means for the terminal to analyze the story received via the transmission means and display it on a user interface, and speech synthesis means for the terminal to read the story aloud. This makes it possible to generate personalized stories based on each child's name and easily display and read them aloud.

[0092] "Child Name" is the identifying name of a particular child that the user provides to the system via an input means.

[0093] "Input means" refers to the interface through which the user inputs the child's name, and includes a keyboard and a touch screen.

[0094] The "transmission means" is a communication interface for transmitting data input via the input means to a server, and includes a secure data transfer means such as the HTTPS protocol.

[0095] "Server" refers to a processing device that performs authentication and story generation based on received data.

[0096] The "authentication means" is a means for verifying the user based on authentication information such as the user ID and session ID received by the server, and authenticating the request as legitimate.

[0097] The "generation means" is a means for generating a personalized story based on a child's name using generative artificial intelligence.

[0098] "Generative AI" is an AI model that has the ability to generate new content based on prompts provided by users.

[0099] The "transmission means" is a communication interface for arranging the story generated by the generation means into an appropriate format and transmitting it to a terminal.

[0100] "Terminal" refers to a device operated by a user, including a smartphone or tablet.

[0101] The "display means" is a means for displaying the story received by the terminal from the server on a user interface.

[0102] "Analysis" refers to the process of interpreting received data based on a predetermined format and displaying it in a form that is easy for the user to understand.

[0103] The "voice synthesis means" is a processing device or software that converts the displayed story content into voice and reads it out loud.

[0104] "JSON format" is an abbreviation for JavaScript (registered trademark) Object Notation, and is a lightweight data format that is widely used as a data exchange format.

[0105] "Text format" refers to a format that refers to character-based data, and includes simple text files such as INI files.

[0106] This invention relates to a system in which a user inputs their child's name, and based on that, a server uses generative artificial intelligence (generative AI model) to generate a story, which is then displayed and read aloud on the terminal.

[0107] System configuration

[0108] The system includes the following components:

[0109] 1. An input method for entering a child's name

[0110] The user enters the child's name through the smartphone or tablet interface, for example, "Taro" using the touch keyboard.

[0111] 2. Transmission method for transmitting input data

[0112] The device sends the entered data, including the name "Taro," to the server using HTTPS, a secure communication protocol.

[0113] 3. Authentication method to receive and authenticate requests

[0114] The server receives the request from the terminal and verifies that the user is a valid user based on the user ID and session ID. If the user authentication is successful, it proceeds to the next step.

[0115] 4. A method for generating stories using generative artificial intelligence

[0116] After authentication, the server sends a prompt to the generative AI model. For example, it might say, "Please generate an adventure story with Taro as the main character." Based on this, the generative AI model generates a personalized story with the name "Taro" as the main character.

[0117] 5. A means of sending the generated stories in the appropriate format.

[0118] The server formats the generated story in JSON or text format and sends it to the device, sometimes with the creation date and time and other metadata.

[0119] 6. Display method for analyzing and displaying the story

[0120] The device analyzes the story received from the server and displays it on the user interface. The story may contain not only text but also illustrations and sound effects.

[0121] 7. A speech synthesis method to read a story aloud

[0122] The device will read the story aloud using a speech synthesis tool (such as Google® Text-to-Speech or Amazon Polly), making it easier for users to read stories to their children.

[0123] Specific examples

[0124] scenario

[0125] Suppose a user wants to create a new story for a child named "Taro" and play it. Here is a concrete example:

[0126] 1. The user enters "Taro"

[0127] The user enters "Taro" in the input field of the smartphone application and presses the generate button.

[0128] 2. Submitting a Request

[0129] The device sends data including the name "Taro" to the server using HTTPS.

[0130] 3. Processing on the Server

[0131] The server receives the request and authenticates the user. If authentication is successful, it instructs the generative AI to generate a story with "Taro" as the main character.

[0132] 4. Story Generation

[0133] A generative AI model generates stories such as "Taro goes on an adventure in the forest," which are a combination of specific templates and random elements.

[0134] 5. Sending and displaying results

[0135] The server formats the generated story into JSON format and sends it to the device, which parses the story and displays it in the user interface.

[0136] 6. Reading and User Interaction

[0137] The device uses a text-to-speech tool to read the story aloud, and the user can tap the screen to go to the next page or stop reading.

[0138] With the above configuration, it is possible to easily generate, display, and read out a personalized story based on the child's name.

[0139] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0140] Program processing flow

[0141] The processing flow of this system's program will be explained in the following steps. At each step, data processing and data calculation based on input and output will also be explained.

[0142] Step 1:

[0143] User enters child's name

[0144] Specific operation: The user enters a child's name into the input field on a smartphone or tablet. For example, they enter "Taro" and press the "Generate" button.

[0145] Input: The name "Taro" entered by the user.

[0146] Output: Request data including the input name "Taro".

[0147] Step 2:

[0148] The device sends the input data to the server

[0149] Specific operation: The device sends data containing "Taro" to the server using the HTTPS protocol.

[0150] Input: Request data (including the child's name "Taro").

[0151] Output: The request data sent to the server.

[0152] Step 3:

[0153] The server receives the request and authenticates the user

[0154] Specific operation: The server analyzes the request received from the terminal and authenticates the user ID and session ID by checking them against the database.

[0155] Input: Received request data (child's name "Taro", user ID, session ID).

[0156] Output: Authentication result (success / failure).

[0157] Step 4:

[0158] The server instructs the generative AI to generate a story.

[0159] Specific operation: After the server successfully authenticates, it sends a prompt to the generation AI model: "Please generate an adventure story with Taro as the main character."

[0160] Input: Request data and prompt for a successfully authenticated user.

[0161] Output: The story generated by the generative AI model.

[0162] Step 5:

[0163] The server formats the generated story and sends it to the device.

[0164] Specific operation: The server formats the generated story into JSON or text format, adds the creation date and time and metadata, and sends it to the device.

[0165] Input: The story returned by the generative AI model.

[0166] Output: Formatted story data (JSON or text format).

[0167] Step 6:

[0168] The device analyzes and displays the received story.

[0169] Specific behavior: The device analyzes the received story data and displays it on the user interface, which may include text, illustrations, sound effects, etc.

[0170] Input: Formatted story data received from the server.

[0171] Output: The story displayed in the user interface.

[0172] Step 7:

[0173] Your device will read the story aloud

[0174] What it does: The device uses a speech synthesis tool to read the story aloud, and the user can play, pause, and turn pages.

[0175] Input: Parsed story data.

[0176] Output: The story read aloud.

[0177] Example prompt

[0178] "Generate an adventure story with Taro as the main character."

[0179] (Application example 1)

[0180] Next, a description will be given of Application Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the smart device 14 will be referred to as a "terminal."

[0181] Previous story generation systems were limited to generating personalized stories based on the user's child's name, and lacked picture books and other reading materials that users could enjoy interactively with their children in a virtual environment. Furthermore, the reading function was often limited to simple audio reading, and was unable to provide a holistic, interactive experience.

[0182] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 1 is realized by the following means.

[0183] In this invention, the server includes an input means for inputting a child's name, a transmission means for transmitting the child's name input via the input means to the server, and a generation means for generating a story by using a generative artificial intelligence based on the child's name received by the server via the transmission means. This enables the user to provide an interactive picture book or reading material in a virtual environment using the child's name, allowing the user to share a sense of unity with the child.

[0184] "Child's name" refers to the unique name of a particular child that the user enters into the terminal.

[0185] "Input means" refers to the device or interface that the user uses to input the child's name.

[0186] "Transmission means" refers to the function or protocol used to transmit the entered child's name to the server.

[0187] "Generation means" refers to the function or algorithm that uses generative artificial intelligence to generate a story based on the received child's name.

[0188] "Device" refers to an electronic device used by a user, such as a smartphone or tablet device.

[0189] "Display means" refers to the function of visually displaying the generated story on the terminal screen.

[0190] "Audio output means" refers to a function or device for reading aloud the displayed story.

[0191] "Virtual environment" refers to a computer-generated space or scenario that a user can experience virtually through electronic devices.

[0192] "Interactive reading material" refers to stories or content that change dynamically in response to user actions.

[0193] "Implementation" refers to the software and hardware configuration for providing interactive storybooks and reading materials within a virtual environment.

[0194] "Generative artificial intelligence" refers to machine learning or deep learning models that generate new content based on provided input data.

[0195] This invention relates to a system that provides interactive reading material in a virtual environment based on a child's name. A user inputs the child's name using a terminal, and the information is sent to a server. The server uses generative artificial intelligence to generate a story incorporating the child's name and sends the generated story to the terminal. The terminal can display the story and read it aloud using audio output means.

[0196] Details of the hardware and software used

[0197] 1. User devices: Primarily smartphones and tablets are used. These devices run applications built using React Native.

[0198] 2. Server: Built using Node.js and the Express framework. The database uses MongoDB, and the generative AI uses OpenAI's GPT-4 API.

[0199] 3. Audio output method: The Google Cloud Text-to-Speech API is used to read the story aloud on the device.

[0200] Program processing and data calculation

[0201] The server receives the child's name sent from the user's device and uses it to instruct the generative AI to generate a story. The generated story is formatted in JSON format and sent back to the user's device. The user's device analyzes the story and displays it visually through a display device. The story is then read aloud using the Google Cloud Text-to-Speech API.

[0202] Examples and prompts

[0203] Examples:

[0204] When a user inputs "Sachiko" as the child's name, an "adventure story of Sachiko exploring a mysterious forest" is generated based on that name. The generated story is displayed in the virtual environment and read aloud using a voice output means.

[0205] Example prompt sentence:

[0206] "Generate a story in which the main character is Sachiko, who goes on an adventure in a mysterious forest where she encounters many different animals."

[0207] This invention allows users to create their own interactive stories in a virtual environment using their child's name, making the storytelling experience more immersive and helping to keep children engaged.

[0208] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0209] Step 1:

[0210] The user enters the child's name.

[0211] Specifically, the user launches the application on their smartphone or tablet and enters their child's name (e.g., "Sachiko") in the name input field. Input data (child's name) is generated.

[0212] Step 2:

[0213] The terminal sends the entered name to the server.

[0214] Specifically, the device securely sends data, including the child's name, to the server using the HTTPS protocol. The data also includes the user ID and session ID. Data to be sent is generated, including the input data (child's name).

[0215] Step 3:

[0216] The server receives the request and authenticates the user.

[0217] Specifically, the server receives a request from the terminal and performs authentication based on the user ID and session ID in the transmitted data. If authentication is successful, it proceeds to the next step. The input data is the user's authentication information, and the output data is the authentication result.

[0218] Step 4:

[0219] The server instructs the generative artificial intelligence to generate a story.

[0220] Specifically, the server creates a prompt and requests the generative artificial intelligence (GPT-4) to generate a story. An example of a prompt is, "Please generate a story in which the main character is Sachiko. Sachiko goes on an adventure in a mysterious forest, encountering many different animals." The input data is the prompt, and the output data is the generated story.

[0221] Step 5:

[0222] The server formats the generated story into JSON format and sends it to the device.

[0223] Specifically, the server converts the story obtained from the generative AI into an appropriate format (JSON format) and sends it to the terminal again via the HTTPS protocol. The input data is the generated story, and the output data is a story in JSON format.

[0224] Step 6:

[0225] The device analyzes the received story and displays it on the screen.

[0226] Specifically, the device parses the JSON-formatted story received from the server and displays the story on the screen. The input data is the JSON-formatted story, and the output data is the story displayed on the screen.

[0227] Step 7:

[0228] The device will read the story aloud.

[0229] Specifically, the device uses the Google Cloud Text-to-Speech API to convert the displayed story into audio and read it out through the speaker. The input data is the text story, and the output data is the audio story.

[0230] Furthermore, an emotion engine that estimates the user's emotion may be combined. That is, the identification processing unit 290 may estimate the user's emotion using the emotion identification model 59 and perform identification processing using the user's emotion.

[0231] This invention combines a system in which a user inputs their child's name, and a server uses generative artificial intelligence to generate a story based on that, and displays and reads it out loud on the terminal, with an emotion engine that recognizes the user's emotions. Below, we will explain the specific program processing in natural language, using concrete examples.

[0232] System configuration

[0233] 1. Enter your child's name

[0234] The user enters the child's name into an input field on the device, for example, "Taro" on the application screen of a smartphone or tablet.

[0235] 2. Sending input data

[0236] The device sends the entered data, including the name "Taro," to the server. Here, the data is sent securely using the HTTPS protocol.

[0237] 3. Receiving and Authenticating a Request

[0238] The server receives a request from the device. This request includes the child's name "Taro" and authentication information such as the user ID and session ID. The server authenticates the user based on this information and verifies that the request is legitimate.

[0239] 4. Story Generation

[0240] After authentication, the server instructs the generative AI to generate a story. The generative AI generates a personalized story with a protagonist named "Taro." This story is generated by combining unique templates and random elements.

[0241] 5. Recognizing and reflecting emotions

[0242] The emotion engine uses the device's camera and microphone to recognize the user's emotions in real time. The emotion recognition results are temporarily stored on the device and sent to a server, or used directly when reading out the text.

[0243] 6. Formatting and sending the generated results

[0244] The server formats the generated story and sends it to the device in JSON or text format, and may also include the date and time of creation and other metadata along with the story.

[0245] 7. Viewing Stories

[0246] The device analyzes the story received from the server and displays it on the user interface (UI). The story may not only consist of text, but may also include illustrations and sound effects.

[0247] 8. Voice reading and adjustment

[0248] The device activates a speech synthesis tool to read the story aloud, adjusting the reading speed and intonation based on the user's emotional information as recognized by the emotion engine.

[0249] Specific examples

[0250] scenario:

[0251] Suppose a user wants to create a new story for a child named "Taro" and tell it to him.

[0252] 1. The user enters "Taro"

[0253] The user enters "Taro" in the application's input field and presses the generate button.

[0254] 2. Submitting a Request

[0255] The device sends data including the name "Taro" to the server using HTTPS.

[0256] 3. Processing on the Server

[0257] The server receives the request and authenticates the user. If authentication is successful, it instructs the generative AI to generate a story with "Taro" as the main character.

[0258] 4. Story Generation

[0259] A generative AI generates a story, such as "Taro goes on an adventure in a magical forest," that combines specific templates and random elements.

[0260] 5. Recognizing and reflecting emotions

[0261] While the user is reading the story, the emotion engine analyzes the user's facial expressions and tone of voice through the device's camera and microphone, and recognizes the user's emotions in real time, such as whether they are enjoying themselves or excited. This information is sent to the server.

[0262] 6. Formatting and Displaying the Story

[0263] The server formats the generated story into JSON format and sends it to the device, which parses the story and displays it in the UI.

[0264] 7. Read aloud

[0265] The device uses a speech synthesis tool to read the story aloud, dynamically adjusting the reading speed and intonation based on the user's emotions as recognized by an emotion engine.

[0266] 8. User Operations

[0267] The user reads the generated story to the child using the device, and the emotion engine adjusts the story to make it more engaging and maintain the child's interest.

[0268] This invention allows users to create a different story each day using their child's name and utilizes emotion recognition to provide a more personalized reading experience, keeping children engaged and reducing the burden on parents.

[0269] The processing flow will be explained below.

[0270] Step 1:

[0271] The user enters the child's name "Taro" into the input field on the terminal and presses the "Generate" button. The terminal receives this input and proceeds to the next step.

[0272] Step 2:

[0273] The terminal prepares request data including the input name "Taro" and authentication information such as user ID and session ID. The terminal sends this data to the server as a POST request using the HTTPS protocol.

[0274] Step 3:

[0275] The server receives a POST request from the device, verifies the authentication information in the request, and verifies that the user has valid permissions.

[0276] Step 4:

[0277] After the server authenticates, it passes the received name "Taro" to the generative AI and requests a story to be generated.

[0278] Step 5:

[0279] A generative AI generates a story based on the name "Taro." For example, it generates a story about "Taro's adventure in a magical forest." This story is created by combining random elements and templates.

[0280] Step 6:

[0281] The emotion engine recognizes the user's emotions in real time using the device's camera and microphone. The device temporarily stores the emotion recognition results and sends them to the server as needed.

[0282] Step 7:

[0283] The server receives the generated stories and formats them appropriately. The formatted data includes the story text, the creation date and time, and other metadata.

[0284] Step 8:

[0285] The server sends the formatted story to the device, which receives the story as response data.

[0286] Step 9:

[0287] The device parses the received story and prepares it for display in the user interface (UI). The story may contain text, images, and sound effects.

[0288] Step 10:

[0289] The device activates a speech synthesis tool to read the story aloud, adjusting the reading speed and intonation based on the user's emotional information as recognized by the emotion engine.

[0290] Step 11:

[0291] The user reads the generated story to the child using the device, and the story is adjusted appropriately according to the user's emotions to keep the child interested.

[0292] Step 12:

[0293] Users can tap the device screen to advance to the next page or stop reading as needed.

[0294] In this way, users can utilize emotion recognition to generate personalized stories based on their child's name, providing a more interactive storytelling experience.

[0295] Example 2

[0296] Next, a description will be given of Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the smart device 14 will be referred to as a "terminal."

[0297] Conventional story generation systems can generate personalized stories simply by entering a user's name, but they lack the ability to reflect the user's emotions, meaning that the story cannot be read aloud in real time according to the user's emotions. This also reduces the quality of the user experience, making it difficult for children to maintain their interest in the story.

[0298] The identification process by the identification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means. In this invention, the server includes an input means for inputting the child's name, a transmission means for transmitting the child's name input via the input means to the server, a generation means for generating a story using a generative model based on the child's name received by the server via the transmission means, and a transmission means for shaping the story generated by the generation means into an appropriate format and transmitting it to the terminal. This makes it possible to adjust the reading speed and intonation of the generated story in real time according to the user's emotions.

[0299] An "input means for inputting a child's name" is a device or interface that a user uses to input a child's name.

[0300] The "transmission means" refers to a protocol or device for transmitting the child's name input via the input means to a server and performing data communication.

[0301] The "generation means for generating a story using a generative model" is a system or software for automatically generating a story using an artificial intelligence model based on the received child's name.

[0302] The "transmission means for converting the story into an appropriate format and transmitting it to the terminal" is a system or device for converting the generated story into a format that can be interpreted by the terminal and transmitting the content to the terminal.

[0303] The "display means" is a screen or display that visually displays the story received by the terminal to the user.

[0304] The "recognition means for recognizing a user's emotions using an emotion engine" is a system or software for analyzing and recognizing emotions from a user's facial expressions and tone of voice using devices such as a camera and a microphone.

[0305] An "adjustment means" is a system or software for dynamically changing the reading rate or intonation based on the recognized emotional information.

[0306] "A speech synthesis means for reading aloud" is a system or software for converting a displayed story from text to speech and reading it aloud.

[0307] A "personal digital assistant" is a portable computing device such as a smartphone or tablet.

[0308] An "application" refers to a software program that runs on the terminal and that the user operates to input data or view stories.

[0309] This invention combines a system in which a user inputs the name of their child, and a server uses generative artificial intelligence to generate a story based on that, and displays and reads it out loud on the terminal, with an emotion engine that recognizes the user's emotions. Specific embodiments for carrying out this invention are described below.

[0310] System configuration

[0311] Enter your child's name

[0312] The user enters the child's name into the application screen on the smartphone or tablet. The application provides an input field on the screen to receive the child's name. For example, the user enters "Taro."

[0313] Sending input data

[0314] The device sends the entered name "Taro" to the server using the HTTPS protocol. The sent data also includes the user ID and session ID, ensuring secure data transfer.

[0315] Receiving and authenticating requests

[0316] The server receives a request from the device. This request includes the child's name "Taro" and authentication information such as the user ID and session ID. The server authenticates the user based on this information and verifies that the request is valid.

[0317] Story Generation

[0318] After authentication, the server instructs a generative AI (e.g., GPT-3 (registered trademark)) to generate a story. The generative AI generates a personalized story with a protagonist named "Taro." This story is generated by combining unique templates and random elements.

[0319] Recognizing and reflecting emotions

[0320] The emotion engine uses the device's camera and microphone to recognize the user's emotions in real time. The emotion recognition results are temporarily stored on the device and sent to a server, or used directly when reading out the text.

[0321] Formatting and sending the generated results

[0322] The server formats the generated story and sends it to the device in JSON or text format, and may also include the date and time of creation and other metadata along with the story.

[0323] Viewing Stories

[0324] The device analyzes the story received from the server and displays it on the user interface (UI). The story may not only consist of text, but may also include illustrations and sound effects.

[0325] Speech reading and adjustments

[0326] The device launches a speech synthesis tool (e.g., Google Text-to-Speech) to read the story aloud, adjusting the reading speed and intonation based on the user's emotional information as recognized by the emotion engine.

[0327] Specific examples

[0328] scenario

[0329] Suppose a user wants to create a new story for a child named "Taro" and tell it to him.

[0330] 1. The user enters "Taro"

[0331] The user enters "Taro" in the application's input field and presses the generate button.

[0332] 2. Submitting a Request

[0333] The device sends data including the name "Taro" to the server using HTTPS.

[0334] 3. Processing on the Server

[0335] The server receives the request and authenticates the user. If authentication is successful, it instructs the generative AI to generate a story with "Taro" as the main character.

[0336] 4. Story Generation

[0337] A generative AI generates a story, such as "Taro goes on an adventure in a magical forest," that combines specific templates and random elements.

[0338] 5. Recognizing and reflecting emotions

[0339] While the user is reading the story, the emotion engine analyzes the user's facial expressions and tone of voice through the device's camera and microphone, and recognizes the user's emotions in real time, such as whether they are enjoying themselves or excited. This information is sent to the server.

[0340] 6. Formatting and Displaying the Story

[0341] The server formats the generated story into JSON format and sends it to the device, which parses the story and displays it in the UI.

[0342] 7. Read aloud

[0343] The device uses a speech synthesis tool to read the story aloud, dynamically adjusting the reading speed and intonation based on the user's emotions as recognized by an emotion engine.

[0344] Prompt Sentence Examples

[0345] "To generate an adventure story for children, please create a story that meets the following conditions: The main character's name should be 'Taro' and the story should include his adventures in a magical forest."

[0346] This invention allows users to create a different story each day using their child's name and utilizes emotion recognition to provide a more personalized reading experience, keeping children engaged and reducing the burden on parents.

[0347] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0348] Step 1:

[0349] User enters child's name

[0350] Specific behavior:

[0351] The user enters the child's name "Taro" into the application screen on their smartphone or tablet and presses the "Generate" button.

[0352] input:

[0353] Child's name: Taro

[0354] output:

[0355] Name "Taro" stored on the device

[0356] Step 2:

[0357] The device sends the input data to the server

[0358] Specific behavior:

[0359] The device uses the HTTPS protocol to send the child's name "Taro", the user ID, and the session ID to the server.

[0360] input:

[0361] Name "Taro", User ID, Session ID

[0362] output:

[0363] Request data sent to the server

[0364] Step 3:

[0365] The server receives the request and authenticates the user

[0366] Specific behavior:

[0367] The server analyzes the request data received and performs user authentication based on the user ID and session ID. It checks whether the authentication information is correct.

[0368] input:

[0369] Request data (name "Taro", user ID, session ID)

[0370] output:

[0371] Authentication success or failure flag

[0372] Step 4:

[0373] The server directs the creation of the story

[0374] Specific behavior:

[0375] If user authentication is successful, the server sends a prompt to the generative AI model (e.g., GPT-3) to instruct it to generate a story.

[0376] input:

[0377] Authentication successful, prompt: "To generate an adventure story for children, please create a story that meets the following conditions. The main character's name should be 'Taro' and include his adventures in a magical forest."

[0378] output:

[0379] Generated Stories

[0380] Step 5:

[0381] Emotion engine recognizes user emotions

[0382] Specific behavior:

[0383] The device uses the built-in camera and microphone to analyze the user's facial expressions and tone of voice, and the results are temporarily saved.

[0384] input:

[0385] User facial expression data, tone of voice data

[0386] output:

[0387] Recognized emotion data

[0388] Step 6:

[0389] The server sends the generated stories

[0390] Specific behavior:

[0391] The server formats the generated story into an appropriate format (such as JSON) and sends it to the device.

[0392] input:

[0393] Generated Stories

[0394] output:

[0395] Story in JSON data format sent to the device

[0396] Step 7:

[0397] Your device will display the story

[0398] Specific behavior:

[0399] The device parses the received JSON data and displays the story on the user's interface (UI).

[0400] input:

[0401] JSON data format story

[0402] output:

[0403] Story displayed in the UI

[0404] Step 8:

[0405] Your device will read the story aloud

[0406] Specific behavior:

[0407] The device uses a speech synthesis tool (e.g., Google Text-to-Speech) to read the story aloud, adjusting the reading speed and intonation based on the user's emotional information as recognized by the emotion engine.

[0408] input:

[0409] Displayed story, recognized emotion data

[0410] output:

[0411] Read-aloud stories

[0412] (Application example 2)

[0413] Next, a description will be given of Application Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the smart device 14 will be referred to as a "terminal."

[0414] Conventional story generation systems have difficulty sustaining children's interest because the generated stories are read aloud in the same tone and speed consistently. Additionally, they are unable to take the user's emotions into account when reading a story, making it difficult to provide a personalized experience.

[0415] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 2 is realized by the following means.

[0416] In this invention, the server includes input means for inputting the child's name, transmission means for transmitting the child's name input via the input means to the server, generation means for the server to generate a story using generative artificial intelligence based on the child's name received via the transmission means, transmission means for transmitting the story generated by the generation means to a terminal, display means for the terminal to display the story received via the transmission means, emotion recognition means for recognizing the user's emotion in real time using the camera and microphone of the terminal, and voice adjustment means for controlling the voice reading of the story based on the emotion recognized by the emotion recognition means. This allows for reading that is dynamically adjusted in response to the user's emotion, enabling a more interesting and personalized story experience.

[0417] An "input means" is a means by which a user inputs a child's name, including, for example, a keyboard or input field displayed on the screen of a mobile device.

[0418] The "transmission means" is a means for transmitting the child's name and other data entered via the input means to the server, using a secure communication protocol (e.g., HTTPS).

[0419] The "generation means" is a means for generating a story using generative artificial intelligence based on the child's name received by the server, and includes an algorithm for constructing a story by combining specific templates and random elements.

[0420] The "display means" is a means for displaying the story sent from the server to the user on the terminal, and provides an interface including text, graphics, and in some cases sound effects.

[0421] The "emotion recognition means" is a means for analyzing the user's facial expressions and tone of voice using the camera and microphone of the terminal, and recognizing the user's emotions in real time.

[0422] The "voice adjustment means" is a means for controlling the reading of the story aloud based on the user's emotional information recognized by the emotion recognition means, and includes an algorithm for adjusting the reading speed and intonation.

[0423] "Mobile device" refers to a device that can be carried by a user, including, for example, a smartphone or tablet terminal.

[0424] "Generative AI" is AI that has the ability to learn large amounts of data and generate new information and content, such as a type of text generation model.

[0425] This invention is a system that uses generative artificial intelligence to generate a story based on a child's name, and then displays and reads the story on a terminal. Furthermore, it adds functionality to recognize the user's emotions in real time and adjust the reading speed, intonation, etc. The specific configuration and operation of the system are described below.

[0426] Hardware and Software Configuration

[0427] This system mainly consists of the following hardware and software:

[0428] Mobile devices: Smartphones and tablets that users can carry around with them.

[0429] Server: Responsible for receiving and processing data and running generative artificial intelligence.

[0430] Camera and microphone: Built into the user device to collect data for emotion recognition.

[0431] Input method: On-screen keyboard or input field on the mobile device.

[0432] Transmission method: Data is sent to the server using the HTTPS protocol.

[0433] Generative AI: For example, OpenAI's GPT-3 has the ability to learn from large amounts of data and generate new information and content.

[0434] Emotion recognition means: For example, Microsoft® Azure® Emotion API, which analyzes facial expressions and tone of voice.

[0435] Speech synthesis and adaptation methods, including Google Cloud Text-to-Speech, which adjusts speaking rate and intonation based on user emotion.

[0436] System Operation

[0437] Personalized Story Generation

[0438] 1. User enters child's name

[0439] The user enters the child's name in the input field displayed on the mobile device, for example, "Taro," and taps the submit button.

[0440] 2. Data transmission

[0441] The mobile device sends the entered name "Taro" to the server using the HTTPS protocol.

[0442] 3. Processing on the Server

[0443] The server receives the request, authenticates the user, and then instructs the generative AI to generate a story based on the name "Taro." The generative AI generates a story such as "Taro goes on an adventure in a magical forest."

[0444] 4. Submitting and Viewing Stories

[0445] The server formats the generated story into JSON format and sends it to the mobile device, which receives the story and displays it in the UI.

[0446] Emotion recognition and speech-to-speech adjustment

[0447] 5. Emotional Recognition

[0448] Using the mobile device's built-in camera and microphone, the emotion recognition method analyzes the user's facial expressions and tone of voice, thereby recognizing the user's emotions (e.g., joy, excitement) in real time.

[0449] 6. Adjust reading

[0450] Based on the recognized emotional information, speech synthesis and adjustment methods adjust the reading speed and intonation to read the story aloud in a more personalized way.

[0451] Specific examples

[0452] The user launches the app, enters their child's name as "Taro," and submits.

[0453] The device sends data containing "Taro" to the server using HTTPS.

[0454] The server uses generative artificial intelligence to generate a story about Taro's adventures in a magical forest and sends it back to the device.

[0455] The device displays the story and uses the camera and microphone to recognize the user's emotions in real time.

[0456] Based on the recognized emotion, the speech synthesis tool adjusts the reading speed and intonation.

[0457] Example prompts to input to the generative AI model

[0458] "The child's name is Taro. Please generate a fun adventure story starring Taro. Specifically, please make it about Taro having a wonderful adventure in a magical forest."

[0459] As described above, this system enables dynamically adjusted reading based on the user's emotions, providing a personalized story experience.

[0460] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[0461] Step 1:

[0462] The user launches the application on their mobile device and enters their child's name into the input field. The input is exemplified as "Taro." The user taps the "Submit" button.

[0463] Input: Child's name (e.g. "Taro")

[0464] Output: Prepare input data for sending

[0465] Step 2:

[0466] The device sends the entered data, including the name "Taro," to the server using the HTTPS protocol, along with authentication information such as the user ID and session ID.

[0467] Input: Input data (child's name "Taro"), authentication information

[0468] Output: Request sent to server

[0469] Step 3:

[0470] The server receives the request from the device, verifies the authentication information, and if authentication is successful, instructs the generative AI to generate a story.

[0471] Input: Request data (child's name "Taro", authentication information)

[0472] Output: Story generation instructions for generative AI

[0473] Step 4:

[0474] The generative AI generates a story based on the input name "Taro." This story is constructed by combining specific templates and random elements. For example, it generates content such as "Taro goes on an adventure in a magical forest."

[0475] Input: Child's name ("Taro")

[0476] Output: The generated story (e.g. "Taro goes on an adventure in the magical forest")

[0477] Step 5:

[0478] The server formats the generated story into JSON format, adds the creation date and time and other metadata, and sends it to the device.

[0479] Input: Generated stories

[0480] Output: Formatted story (JSON format)

[0481] Step 6:

[0482] The device analyzes the story received from the server and displays it on the user interface (UI). The story may not only consist of text, but may also include illustrations and sound effects.

[0483] Input: JSON formatted story

[0484] Output: Generate data for display

[0485] Step 7:

[0486] The device's camera and microphone are used to recognize the user's emotions in real time. The emotion recognition means analyzes the user's facial expressions and tone of voice to determine whether the user is enjoying themselves or feeling excited.

[0487] Input: Camera video, microphone audio

[0488] Output: Recognized emotion data

[0489] Step 8:

[0490] The device uses a voice synthesis tool to read the story aloud, adjusting the reading speed and intonation based on the user's emotional information recognized by the emotion recognition means.

[0491] Input: Story text, recognized emotion data

[0492] Output: Emotionally adjusted speech

[0493] Through these steps, the system can dynamically adjust reading to respond to the user's emotions, providing a more engaging and personalized story experience.

[0494] The specific processing unit 290 transmits the result of the specific processing to the smart device 14. In the smart device 14, the control unit 46A causes the output device 40 to output the result of the specific processing. The microphone 38B acquires audio indicating a user input regarding the result of the specific processing. The control unit 46A transmits audio data indicating the user input acquired by the microphone 38B to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the audio data.

[0495] The data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of the data generation model 58 is ChatGPT (registered trademark) (Internet search engine).<URL: https: / / openai.com / blog / chatgpt> ), Gemini (registered trademark) (Internet search <url: https: gemini.google.com ?hl="ja">) and other generation AIs. The data generation model 58 is obtained by performing deep learning on a neural network. A prompt including an instruction is input to the data generation model 58, and inference data such as voice data indicating voice, text data indicating text, and image data indicating an image is also input. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt, and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[0496] In the above embodiment, an example in which the specific process is performed by the data processing device 12 has been given, but the technology of the present disclosure is not limited to this, and the specific process may be performed by the smart device 14.

[0497] [Second embodiment]

[0498] FIG. 3 shows an example of the configuration of a data processing system 210 according to the second embodiment.

[0499] 3, the data processing system 210 includes the data processing device 12 and smart glasses 214. An example of the data processing device 12 is a server.

[0500] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 is an example of a "computer" according to the technology of the present disclosure. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, the RAM 30, and the storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0501] The smart glasses 214 include a computer 36, a microphone 238, a speaker 240, a camera 42, and a communication I / F 44. The computer 36 includes a processor 46, a RAM 48, and a storage 50. The processor 46, the RAM 48, and the storage 50 are connected to a bus 52. The microphone 238, the speaker 240, and the camera 42 are also connected to the bus 52.

[0502] The microphone 238 receives instructions and the like from the user 20 by receiving voice uttered by the user 20. The microphone 238 captures the voice uttered by the user 20, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio in accordance with instructions from the processor 46.

[0503] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an imaging element such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the surroundings of user 20 (for example, an imaging range defined by an angle of view equivalent to the field of vision of a typical healthy person).

[0504] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 are responsible for the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is carried out in a secure state.

[0505] Fig. 4 shows an example of the main functions of the data processing device 12 and the smart glasses 214. As shown in Fig. 4, in the data processing device 12, a specific process is performed by the processor 28. A specific process program 56 is stored in the storage 32.

[0506] The specific processing program 56 is an example of a "program" according to the technology of the present disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[0507] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[0508] In the smart glasses 214, the reception output process is performed by the processor 46. A reception output program 60 is stored in the storage 50. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output process is realized by the processor 46 operating as the control unit 46A in accordance with the reception output program 60 executed on the RAM 48.

[0509] Next, a description will be given of the identification process performed by the identification processing unit 290 of the data processing device 12. In the following description, the data processing device 12 will be referred to as the "server" and the smart glasses 214 will be referred to as the "terminal."

[0510] This invention relates to a system in which a user inputs a child's name, and a server uses generative artificial intelligence to generate a story based on that information, and the story is then displayed and read aloud on the terminal. Below, we will explain the specific program processing in natural language, with examples.

[0511] 1. Enter your child's name

[0512] The user enters the child's name into an input field on the device, for example, "Taro" on the application screen of a smartphone or tablet.

[0513] 2. Sending input data

[0514] The device sends the entered data, including the name "Taro," to the server. Here, the data is sent securely using the HTTPS protocol.

[0515] 3. Receiving and Authenticating a Request

[0516] The server receives a request from the device. This request includes the child's name "Taro" and authentication information such as the user ID and session ID. The server authenticates the user based on this information and verifies that the request is legitimate.

[0517] 4. Story Generation

[0518] After authentication, the server instructs the generative AI to generate a story. The generative AI generates a personalized story with a protagonist named "Taro." This story is generated by combining unique templates and random elements.

[0519] 5. Formatting and sending the generated results

[0520] The server formats the generated story and sends it to the device in JSON or text format, and may also include the date and time of creation and other metadata along with the story.

[0521] 6. Viewing Stories

[0522] The device analyzes the story received from the server and displays it on the user interface (UI). The story may not only consist of text, but may also include illustrations and sound effects.

[0523] 7. Text-to-speech

[0524] The device will launch a text-to-speech tool to read the story aloud, making it easier for users to read stories to their children.

[0525] Specific examples

[0526] scenario:

[0527] Suppose a user wants to create a new story for a child named "Taro" and tell it to him.

[0528] 1. The user enters "Taro"

[0529] The user enters "Taro" in the application's input field and presses the generate button.

[0530] 2. Submitting a Request

[0531] The device sends data including the name "Taro" to the server using HTTPS.

[0532] 3. Processing on the Server

[0533] The server receives the request and authenticates the user. If authentication is successful, it instructs the generative AI to generate a story with "Taro" as the main character.

[0534] 4. Story Generation

[0535] Generative AI generates stories such as "Taro goes on an adventure in the forest," which are a combination of specific templates and random elements.

[0536] 5. Sending and displaying results

[0537] The server formats the generated story into JSON format and sends it to the device, which parses the story and displays it in the UI.

[0538] 6. Reading and User Interaction

[0539] The device uses a text-to-speech tool to read the story aloud, and the user can tap the screen to go to the next page or stop reading.

[0540] This invention allows users to create a different story every day using their child's name and easily read it to them, which can keep the child interested while reducing the burden on parents.

[0541] The processing flow will be explained below.

[0542] Step 1:

[0543] The user enters the child's name "Taro" into the input field on the device. The user presses the "Generate" button.

[0544] Step 2:

[0545] The device prepares request data including the input name "Taro." This request data also includes authentication information such as the user ID and session ID. The device sends a POST request to the server using the HTTPS protocol.

[0546] Step 3:

[0547] The server receives a POST request from the device, verifies the authentication information in the request, and verifies that the user has valid permissions.

[0548] Step 4:

[0549] After the server verifies it, it passes the received data, including the name "Taro," to the generative AI and requests it to generate a story.

[0550] Step 5:

[0551] Based on the data received, the generative AI generates a story with the name "Taro" as the main character. For example, it might generate a story about Taro's adventures in a magical forest. This story is created by combining random elements and predefined templates.

[0552] Step 6:

[0553] The generated story is temporarily stored on the server in text or JSON format, and the server formats this data in a format suitable for the user, adding images and audio data if necessary.

[0554] Step 7:

[0555] The server sends the formatted story to the device as response data, which includes the story text, the creation date and time, and other metadata.

[0556] Step 8:

[0557] The device analyzes the story received from the server and prepares it for display on the user interface (UI).

[0558] Step 9:

[0559] The device launches a speech synthesis tool to read the displayed story aloud. The device provides the user with the option to start reading the story aloud.

[0560] Step 10:

[0561] The user uses the device to read the generated story to the child, tapping the screen as needed to advance to the next page or stop reading.

[0562] Example 1

[0563] Next, a description will be given of Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the smart glasses 214 will be referred to as a "terminal."

[0564] In recent years, there has been a growing demand for systems with educational value that promote parent-child communication and foster children's creativity. However, existing systems have issues with difficulty in generating stories tailored to individual children's names and characteristics, and have complex operation and low usability. Furthermore, there is a lack of systems that allow users to enjoy the generated stories both visually and aurally. The purpose of this invention is to solve these issues and realize easy and personalized story generation and playback.

[0565] The specific processing by the specific processing unit 290 of the data processing device 12 in the first embodiment is realized by the following means.

[0566] In this invention, the server includes input means for inputting a child's name, transmission means for transmitting the child's name input via the input means to the server, authentication means for authenticating a user based on the child's name and authentication information received by the server via the transmission means, generation means for generating a story using generative artificial intelligence based on the information authenticated by the authentication means, transmission means for formatting the story generated by the generation means into JSON format or text format and transmitting it to a terminal, display means for the terminal to analyze the story received via the transmission means and display it on a user interface, and speech synthesis means for the terminal to read the story aloud. This makes it possible to generate personalized stories based on each child's name and easily display and read them aloud.

[0567] "Child Name" is the identifying name of a particular child that the user provides to the system via an input means.

[0568] "Input means" refers to the interface through which the user inputs the child's name, and includes a keyboard and a touch screen.

[0569] The "transmission means" is a communication interface for transmitting data input via the input means to a server, and includes a secure data transfer means such as the HTTPS protocol.

[0570] "Server" refers to a processing device that performs authentication and story generation based on received data.

[0571] The "authentication means" is a means for verifying the user based on authentication information such as the user ID and session ID received by the server, and authenticating the request as legitimate.

[0572] The "generation means" is a means for generating a personalized story based on a child's name using generative artificial intelligence.

[0573] "Generative AI" is an AI model that has the ability to generate new content based on prompts provided by users.

[0574] The "transmission means" is a communication interface for arranging the story generated by the generation means into an appropriate format and transmitting it to a terminal.

[0575] "Terminal" refers to a device operated by a user, including a smartphone or tablet.

[0576] The "display means" is a means for displaying the story received by the terminal from the server on a user interface.

[0577] "Analysis" refers to the process of interpreting received data based on a predetermined format and displaying it in a form that is easy for the user to understand.

[0578] The "voice synthesis means" is a processing device or software that converts the displayed story content into voice and reads it out loud.

[0579] "JSON format" is an abbreviation for JavaScript Object Notation, and is a lightweight data format widely used as a data exchange format.

[0580] "Text format" refers to a format that refers to character-based data, and includes simple text files such as INI files.

[0581] This invention relates to a system in which a user inputs their child's name, and based on that, a server uses generative artificial intelligence (generative AI model) to generate a story, which is then displayed and read aloud on the terminal.

[0582] System configuration

[0583] The system includes the following components:

[0584] 1. An input method for entering a child's name

[0585] The user enters the child's name through the smartphone or tablet interface, for example, "Taro" using the touch keyboard.

[0586] 2. Transmission method for transmitting input data

[0587] The device sends the entered data, including the name "Taro," to the server using HTTPS, a secure communication protocol.

[0588] 3. Authentication method to receive and authenticate requests

[0589] The server receives the request from the terminal and verifies that the user is a valid user based on the user ID and session ID. If the user authentication is successful, it proceeds to the next step.

[0590] 4. A method for generating stories using generative artificial intelligence

[0591] After authentication, the server sends a prompt to the generative AI model. For example, it might say, "Please generate an adventure story with Taro as the main character." Based on this, the generative AI model generates a personalized story with the name "Taro" as the main character.

[0592] 5. A means of sending the generated stories in the appropriate format.

[0593] The server formats the generated story in JSON or text format and sends it to the device, sometimes with the creation date and time and other metadata.

[0594] 6. Display method for analyzing and displaying the story

[0595] The device analyzes the story received from the server and displays it on the user interface. The story may contain not only text but also illustrations and sound effects.

[0596] 7. A speech synthesis method to read a story aloud

[0597] The device will read the story aloud using a speech synthesis tool (such as Google Text-to-Speech or Amazon Polly), making it easier for users to read stories to their children.

[0598] Specific examples

[0599] scenario

[0600] Suppose a user wants to create a new story for a child named "Taro" and play it. Here is a concrete example:

[0601] 1. The user enters "Taro"

[0602] The user enters "Taro" in the input field of the smartphone application and presses the generate button.

[0603] 2. Submitting a Request

[0604] The device sends data including the name "Taro" to the server using HTTPS.

[0605] 3. Processing on the Server

[0606] The server receives the request and authenticates the user. If authentication is successful, it instructs the generative AI to generate a story with "Taro" as the main character.

[0607] 4. Story Generation

[0608] A generative AI model generates stories such as "Taro goes on an adventure in the forest," which are a combination of specific templates and random elements.

[0609] 5. Sending and displaying results

[0610] The server formats the generated story into JSON format and sends it to the device, which parses the story and displays it in the user interface.

[0611] 6. Reading and User Interaction

[0612] The device uses a text-to-speech tool to read the story aloud, and the user can tap the screen to go to the next page or stop reading.

[0613] With the above configuration, it is possible to easily generate, display, and read out a personalized story based on the child's name.

[0614] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0615] Program processing flow

[0616] The processing flow of this system's program will be explained in the following steps. At each step, data processing and data calculation based on input and output will also be explained.

[0617] Step 1:

[0618] User enters child's name

[0619] Specific operation: The user enters a child's name into the input field on a smartphone or tablet. For example, they enter "Taro" and press the "Generate" button.

[0620] Input: The name "Taro" entered by the user.

[0621] Output: Request data including the input name "Taro".

[0622] Step 2:

[0623] The device sends the input data to the server

[0624] Specific operation: The device sends data containing "Taro" to the server using the HTTPS protocol.

[0625] Input: Request data (including the child's name "Taro").

[0626] Output: The request data sent to the server.

[0627] Step 3:

[0628] The server receives the request and authenticates the user

[0629] Specific operation: The server analyzes the request received from the terminal and authenticates the user ID and session ID by checking them against the database.

[0630] Input: Received request data (child's name "Taro", user ID, session ID).

[0631] Output: Authentication result (success / failure).

[0632] Step 4:

[0633] The server instructs the generative AI to generate a story.

[0634] Specific operation: After the server successfully authenticates, it sends a prompt to the generation AI model: "Please generate an adventure story with Taro as the main character."

[0635] Input: Request data and prompt for a successfully authenticated user.

[0636] Output: The story generated by the generative AI model.

[0637] Step 5:

[0638] The server formats the generated story and sends it to the device.

[0639] Specific operation: The server formats the generated story into JSON or text format, adds the creation date and time and metadata, and sends it to the device.

[0640] Input: The story returned by the generative AI model.

[0641] Output: Formatted story data (JSON or text format).

[0642] Step 6:

[0643] The device analyzes and displays the received story.

[0644] Specific behavior: The device analyzes the received story data and displays it on the user interface, which may include text, illustrations, sound effects, etc.

[0645] Input: Formatted story data received from the server.

[0646] Output: The story displayed in the user interface.

[0647] Step 7:

[0648] Your device will read the story aloud

[0649] What it does: The device uses a speech synthesis tool to read the story aloud, and the user can play, pause, and turn pages.

[0650] Input: Parsed story data.

[0651] Output: The story read aloud.

[0652] Example prompt

[0653] "Generate an adventure story with Taro as the main character."

[0654] (Application example 1)

[0655] Next, a description will be given of Application Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the smart glasses 214 will be referred to as a "terminal."

[0656] Previous story generation systems were limited to generating personalized stories based on the user's child's name, and lacked picture books and other reading materials that users could enjoy interactively with their children in a virtual environment. Furthermore, the reading function was often limited to simple audio reading, and was unable to provide a holistic, interactive experience.

[0657] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 1 is realized by the following means.

[0658] In this invention, the server includes an input means for inputting a child's name, a transmission means for transmitting the child's name input via the input means to the server, and a generation means for generating a story by using a generative artificial intelligence based on the child's name received by the server via the transmission means. This enables the user to provide an interactive picture book or reading material in a virtual environment using the child's name, allowing the user to share a sense of unity with the child.

[0659] "Child's name" refers to the unique name of a particular child that the user enters into the terminal.

[0660] "Input means" refers to the device or interface that the user uses to input the child's name.

[0661] "Transmission means" refers to the function or protocol used to transmit the entered child's name to the server.

[0662] "Generation means" refers to the function or algorithm that uses generative artificial intelligence to generate a story based on the received child's name.

[0663] "Device" refers to an electronic device used by a user, such as a smartphone or tablet device.

[0664] "Display means" refers to the function of visually displaying the generated story on the terminal screen.

[0665] "Audio output means" refers to a function or device for reading aloud the displayed story.

[0666] "Virtual environment" refers to a computer-generated space or scenario that a user can experience virtually through electronic devices.

[0667] "Interactive reading material" refers to stories or content that change dynamically in response to user actions.

[0668] "Implementation" refers to the software and hardware configuration for providing interactive storybooks and reading materials within a virtual environment.

[0669] "Generative artificial intelligence" refers to machine learning or deep learning models that generate new content based on provided input data.

[0670] This invention relates to a system that provides interactive reading material in a virtual environment based on a child's name. A user inputs the child's name using a terminal, and the information is sent to a server. The server uses generative artificial intelligence to generate a story incorporating the child's name and sends the generated story to the terminal. The terminal can display the story and read it aloud using audio output means.

[0671] Details of the hardware and software used

[0672] 1. User devices: Primarily smartphones and tablets are used. These devices run applications built using React Native.

[0673] 2. Server: Built using Node.js and the Express framework. The database uses MongoDB, and the generative AI uses OpenAI's GPT-4 API.

[0674] 3. Audio output method: The Google Cloud Text-to-Speech API is used to read the story aloud on the device.

[0675] Program processing and data calculation

[0676] The server receives the child's name sent from the user's device and uses it to instruct the generative AI to generate a story. The generated story is formatted in JSON format and sent back to the user's device. The user's device analyzes the story and displays it visually through a display device. The story is then read aloud using the Google Cloud Text-to-Speech API.

[0677] Examples and prompts

[0678] Examples:

[0679] When a user inputs "Sachiko" as the child's name, an "adventure story of Sachiko exploring a mysterious forest" is generated based on that name. The generated story is displayed in the virtual environment and read aloud using a voice output means.

[0680] Example prompt sentence:

[0681] "Generate a story in which the main character is Sachiko, who goes on an adventure in a mysterious forest where she encounters many different animals."

[0682] This invention allows users to create their own interactive stories in a virtual environment using their child's name, making the storytelling experience more immersive and helping to keep children engaged.

[0683] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0684] Step 1:

[0685] The user enters the child's name.

[0686] Specifically, the user launches the application on their smartphone or tablet and enters their child's name (e.g., "Sachiko") in the name input field. Input data (child's name) is generated.

[0687] Step 2:

[0688] The terminal sends the entered name to the server.

[0689] Specifically, the device securely sends data, including the child's name, to the server using the HTTPS protocol. The data also includes the user ID and session ID. Data to be sent is generated, including the input data (child's name).

[0690] Step 3:

[0691] The server receives the request and authenticates the user.

[0692] Specifically, the server receives a request from the terminal and performs authentication based on the user ID and session ID in the transmitted data. If authentication is successful, it proceeds to the next step. The input data is the user's authentication information, and the output data is the authentication result.

[0693] Step 4:

[0694] The server instructs the generative artificial intelligence to generate a story.

[0695] Specifically, the server creates a prompt and requests the generative artificial intelligence (GPT-4) to generate a story. An example of a prompt is, "Please generate a story in which the main character is Sachiko. Sachiko goes on an adventure in a mysterious forest, encountering many different animals." The input data is the prompt, and the output data is the generated story.

[0696] Step 5:

[0697] The server formats the generated story into JSON format and sends it to the device.

[0698] Specifically, the server converts the story obtained from the generative AI into an appropriate format (JSON format) and sends it to the terminal again via the HTTPS protocol. The input data is the generated story, and the output data is a story in JSON format.

[0699] Step 6:

[0700] The device analyzes the received story and displays it on the screen.

[0701] Specifically, the device parses the JSON-formatted story received from the server and displays the story on the screen. The input data is the JSON-formatted story, and the output data is the story displayed on the screen.

[0702] Step 7:

[0703] The device will read the story aloud.

[0704] Specifically, the device uses the Google Cloud Text-to-Speech API to convert the displayed story into audio and read it out through the speaker. The input data is the text story, and the output data is the audio story.

[0705] Furthermore, an emotion engine that estimates the user's emotion may be further combined. That is, the identification processing unit 290 may estimate the user's emotion using the emotion identification model 59, and perform identification processing using the user's emotion.

[0706] This invention combines a system in which a user inputs their child's name, and a server uses generative artificial intelligence to generate a story based on that, and displays and reads it out loud on the terminal, with an emotion engine that recognizes the user's emotions. Below, we will explain the specific program processing in natural language, using concrete examples.

[0707] System configuration

[0708] 1. Enter your child's name

[0709] The user enters the child's name into an input field on the device, for example, "Taro" on the application screen of a smartphone or tablet.

[0710] 2. Sending input data

[0711] The device sends the entered data, including the name "Taro," to the server. Here, the data is sent securely using the HTTPS protocol.

[0712] 3. Receiving and Authenticating a Request

[0713] The server receives a request from the device. This request includes the child's name "Taro" and authentication information such as the user ID and session ID. The server authenticates the user based on this information and verifies that the request is legitimate.

[0714] 4. Story Generation

[0715] After authentication, the server instructs the generative AI to generate a story. The generative AI generates a personalized story with a protagonist named "Taro." This story is generated by combining unique templates and random elements.

[0716] 5. Recognizing and reflecting emotions

[0717] The emotion engine uses the device's camera and microphone to recognize the user's emotions in real time. The emotion recognition results are temporarily stored on the device and sent to a server, or used directly when reading out the text.

[0718] 6. Formatting and sending the generated results

[0719] The server formats the generated story and sends it to the device in JSON or text format, and may also include the date and time of creation and other metadata along with the story.

[0720] 7. Viewing Stories

[0721] The device analyzes the story received from the server and displays it on the user interface (UI). The story may not only consist of text, but may also include illustrations and sound effects.

[0722] 8. Voice reading and adjustment

[0723] The device activates a speech synthesis tool to read the story aloud, adjusting the reading speed and intonation based on the user's emotional information as recognized by the emotion engine.

[0724] Specific examples

[0725] scenario:

[0726] Suppose a user wants to create a new story for a child named "Taro" and tell it to him.

[0727] 1. The user enters "Taro"

[0728] The user enters "Taro" in the application's input field and presses the generate button.

[0729] 2. Submitting a Request

[0730] The device sends data including the name "Taro" to the server using HTTPS.

[0731] 3. Processing on the Server

[0732] The server receives the request and authenticates the user. If authentication is successful, it instructs the generative AI to generate a story with "Taro" as the main character.

[0733] 4. Story Generation

[0734] A generative AI generates a story, such as "Taro goes on an adventure in a magical forest," that combines specific templates and random elements.

[0735] 5. Recognizing and reflecting emotions

[0736] While the user is reading the story, the emotion engine analyzes the user's facial expressions and tone of voice through the device's camera and microphone, and recognizes the user's emotions in real time, such as whether they are enjoying themselves or excited. This information is sent to the server.

[0737] 6. Formatting and Displaying the Story

[0738] The server formats the generated story into JSON format and sends it to the device, which parses the story and displays it in the UI.

[0739] 7. Read aloud

[0740] The device uses a speech synthesis tool to read the story aloud, dynamically adjusting the reading speed and intonation based on the user's emotions as recognized by an emotion engine.

[0741] 8. User Operations

[0742] The user reads the generated story to the child using the device, and the emotion engine adjusts the story to make it more engaging and maintain the child's interest.

[0743] This invention allows users to create a different story each day using their child's name and utilizes emotion recognition to provide a more personalized reading experience, keeping children engaged and reducing the burden on parents.

[0744] The processing flow will be explained below.

[0745] Step 1:

[0746] The user enters the child's name "Taro" into the input field on the terminal and presses the "Generate" button. The terminal receives this input and proceeds to the next step.

[0747] Step 2:

[0748] The terminal prepares request data including the input name "Taro" and authentication information such as user ID and session ID. The terminal sends this data to the server as a POST request using the HTTPS protocol.

[0749] Step 3:

[0750] The server receives a POST request from the device, verifies the authentication information in the request, and verifies that the user has valid permissions.

[0751] Step 4:

[0752] After the server authenticates, it passes the received name "Taro" to the generative AI and requests a story to be generated.

[0753] Step 5:

[0754] A generative AI generates a story based on the name "Taro." For example, it generates a story about "Taro's adventure in a magical forest." This story is created by combining random elements and templates.

[0755] Step 6:

[0756] The emotion engine recognizes the user's emotions in real time using the device's camera and microphone. The device temporarily stores the emotion recognition results and sends them to the server as needed.

[0757] Step 7:

[0758] The server receives the generated stories and formats them appropriately. The formatted data includes the story text, the creation date and time, and other metadata.

[0759] Step 8:

[0760] The server sends the formatted story to the device, which receives the story as response data.

[0761] Step 9:

[0762] The device parses the received story and prepares it for display in the user interface (UI). The story may contain text, images, and sound effects.

[0763] Step 10:

[0764] The device activates a speech synthesis tool to read the story aloud, adjusting the reading speed and intonation based on the user's emotional information as recognized by the emotion engine.

[0765] Step 11:

[0766] The user reads the generated story to the child using the device, and the story is adjusted appropriately according to the user's emotions to keep the child interested.

[0767] Step 12:

[0768] Users can tap the device screen to advance to the next page or stop reading as needed.

[0769] In this way, users can utilize emotion recognition to generate personalized stories based on their child's name, providing a more interactive storytelling experience.

[0770] Example 2

[0771] Next, a description will be given of Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the smart glasses 214 will be referred to as a "terminal."

[0772] Conventional story generation systems can generate personalized stories simply by entering a user's name, but they lack the ability to reflect the user's emotions, meaning that the story cannot be read aloud in real time according to the user's emotions. This also reduces the quality of the user experience, making it difficult for children to maintain their interest in the story.

[0773] The identification process by the identification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means. In this invention, the server includes an input means for inputting the child's name, a transmission means for transmitting the child's name input via the input means to the server, a generation means for generating a story using a generative model based on the child's name received by the server via the transmission means, and a transmission means for shaping the story generated by the generation means into an appropriate format and transmitting it to the terminal. This makes it possible to adjust the reading speed and intonation of the generated story in real time according to the user's emotions.

[0774] An "input means for inputting a child's name" is a device or interface that a user uses to input a child's name.

[0775] The "transmission means" refers to a protocol or device for transmitting the child's name input via the input means to a server and performing data communication.

[0776] The "generation means for generating a story using a generative model" is a system or software for automatically generating a story using an artificial intelligence model based on the received child's name.

[0777] The "transmission means for converting the story into an appropriate format and transmitting it to the terminal" is a system or device for converting the generated story into a format that can be interpreted by the terminal and transmitting the content to the terminal.

[0778] The "display means" is a screen or display that visually displays the story received by the terminal to the user.

[0779] The "recognition means for recognizing a user's emotions using an emotion engine" is a system or software for analyzing and recognizing emotions from a user's facial expressions and tone of voice using devices such as a camera and a microphone.

[0780] An "adjustment means" is a system or software for dynamically changing the reading rate or intonation based on the recognized emotional information.

[0781] "A speech synthesis means for reading aloud" is a system or software for converting a displayed story from text to speech and reading it aloud.

[0782] A "personal digital assistant" is a portable computing device such as a smartphone or tablet.

[0783] An "application" refers to a software program that runs on the terminal and that the user operates to input data or view stories.

[0784] This invention combines a system in which a user inputs the name of their child, and a server uses generative artificial intelligence to generate a story based on that, and displays and reads it out loud on the terminal, with an emotion engine that recognizes the user's emotions. Specific embodiments for carrying out this invention are described below.

[0785] System configuration

[0786] Enter your child's name

[0787] The user enters the child's name into the application screen on the smartphone or tablet. The application provides an input field on the screen to receive the child's name. For example, the user enters "Taro."

[0788] Sending input data

[0789] The device sends the entered name "Taro" to the server using the HTTPS protocol. The sent data also includes the user ID and session ID, ensuring secure data transfer.

[0790] Receiving and authenticating requests

[0791] The server receives a request from the device. This request includes the child's name "Taro" and authentication information such as the user ID and session ID. The server authenticates the user based on this information and verifies that the request is valid.

[0792] Story Generation

[0793] After authentication, the server instructs a generative AI (e.g., GPT-3) to generate a story. The generative AI generates a personalized story with a protagonist named "Taro." This story is generated by combining unique templates and random elements.

[0794] Recognizing and reflecting emotions

[0795] The emotion engine uses the device's camera and microphone to recognize the user's emotions in real time. The emotion recognition results are temporarily stored on the device and sent to a server, or used directly when reading out the text.

[0796] Formatting and sending the generated results

[0797] The server formats the generated story and sends it to the device in JSON or text format, and may also include the date and time of creation and other metadata along with the story.

[0798] Viewing Stories

[0799] The device analyzes the story received from the server and displays it on the user interface (UI). The story may not only consist of text, but may also include illustrations and sound effects.

[0800] Speech reading and adjustments

[0801] The device launches a speech synthesis tool (e.g., Google Text-to-Speech) to read the story aloud, adjusting the reading speed and intonation based on the user's emotional information as recognized by the emotion engine.

[0802] Specific examples

[0803] scenario

[0804] Suppose a user wants to create a new story for a child named "Taro" and tell it to him.

[0805] 1. The user enters "Taro"

[0806] The user enters "Taro" in the application's input field and presses the generate button.

[0807] 2. Submitting a Request

[0808] The device sends data including the name "Taro" to the server using HTTPS.

[0809] 3. Processing on the Server

[0810] The server receives the request and authenticates the user. If authentication is successful, it instructs the generative AI to generate a story with "Taro" as the main character.

[0811] 4. Story Generation

[0812] A generative AI generates a story, such as "Taro goes on an adventure in a magical forest," that combines specific templates and random elements.

[0813] 5. Recognizing and reflecting emotions

[0814] While the user is reading the story, the emotion engine analyzes the user's facial expressions and tone of voice through the device's camera and microphone, and recognizes the user's emotions in real time, such as whether they are enjoying themselves or excited. This information is sent to the server.

[0815] 6. Formatting and Displaying the Story

[0816] The server formats the generated story into JSON format and sends it to the device, which parses the story and displays it in the UI.

[0817] 7. Read aloud

[0818] The device uses a speech synthesis tool to read the story aloud, dynamically adjusting the reading speed and intonation based on the user's emotions as recognized by an emotion engine.

[0819] Prompt Sentence Examples

[0820] "To generate an adventure story for children, please create a story that meets the following conditions: The main character's name should be 'Taro' and the story should include his adventures in a magical forest."

[0821] This invention allows users to create a different story each day using their child's name and utilizes emotion recognition to provide a more personalized reading experience, keeping children engaged and reducing the burden on parents.

[0822] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0823] Step 1:

[0824] User enters child's name

[0825] Specific behavior:

[0826] The user enters the child's name "Taro" into the application screen on their smartphone or tablet and presses the "Generate" button.

[0827] input:

[0828] Child's name: Taro

[0829] output:

[0830] Name "Taro" stored on the device

[0831] Step 2:

[0832] The device sends the input data to the server

[0833] Specific behavior:

[0834] The device uses the HTTPS protocol to send the child's name "Taro", the user ID, and the session ID to the server.

[0835] input:

[0836] Name "Taro", User ID, Session ID

[0837] output:

[0838] Request data sent to the server

[0839] Step 3:

[0840] The server receives the request and authenticates the user

[0841] Specific behavior:

[0842] The server analyzes the request data received and performs user authentication based on the user ID and session ID. It checks whether the authentication information is correct.

[0843] input:

[0844] Request data (name "Taro", user ID, session ID)

[0845] output:

[0846] Authentication success or failure flag

[0847] Step 4:

[0848] The server directs the creation of the story

[0849] Specific behavior:

[0850] If user authentication is successful, the server sends a prompt to the generative AI model (e.g., GPT-3) to instruct it to generate a story.

[0851] input:

[0852] Authentication successful, prompt: "To generate an adventure story for children, please create a story that meets the following conditions. The main character's name should be 'Taro' and include his adventures in a magical forest."

[0853] output:

[0854] Generated Stories

[0855] Step 5:

[0856] Emotion engine recognizes user emotions

[0857] Specific behavior:

[0858] The device uses the built-in camera and microphone to analyze the user's facial expressions and tone of voice, and the results are temporarily saved.

[0859] input:

[0860] User facial expression data, tone of voice data

[0861] output:

[0862] Recognized emotion data

[0863] Step 6:

[0864] The server sends the generated stories

[0865] Specific behavior:

[0866] The server formats the generated story into an appropriate format (such as JSON) and sends it to the device.

[0867] input:

[0868] Generated Stories

[0869] output:

[0870] Story in JSON data format sent to the device

[0871] Step 7:

[0872] Your device will display the story

[0873] Specific behavior:

[0874] The device parses the received JSON data and displays the story on the user's interface (UI).

[0875] input:

[0876] JSON data format story

[0877] output:

[0878] Story displayed in the UI

[0879] Step 8:

[0880] Your device will read the story aloud

[0881] Specific behavior:

[0882] The device uses a speech synthesis tool (e.g., Google Text-to-Speech) to read the story aloud, adjusting the reading speed and intonation based on the user's emotional information as recognized by the emotion engine.

[0883] input:

[0884] Displayed story, recognized emotion data

[0885] output:

[0886] Read-aloud stories

[0887] (Application example 2)

[0888] Next, a description will be given of Application Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the smart glasses 214 will be referred to as a "terminal."

[0889] Conventional story generation systems have difficulty sustaining children's interest because the generated stories are read aloud in the same tone and speed consistently. Additionally, they are unable to take the user's emotions into account when reading a story, making it difficult to provide a personalized experience.

[0890] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 2 is realized by the following means.

[0891] In this invention, the server includes input means for inputting the child's name, transmission means for transmitting the child's name input via the input means to the server, generation means for the server to generate a story using generative artificial intelligence based on the child's name received via the transmission means, transmission means for transmitting the story generated by the generation means to a terminal, display means for the terminal to display the story received via the transmission means, emotion recognition means for recognizing the user's emotion in real time using the camera and microphone of the terminal, and voice adjustment means for controlling the voice reading of the story based on the emotion recognized by the emotion recognition means. This allows for reading that is dynamically adjusted in response to the user's emotion, enabling a more interesting and personalized story experience.

[0892] An "input means" is a means by which a user inputs a child's name, including, for example, a keyboard or input field displayed on the screen of a mobile device.

[0893] The "transmission means" is a means for transmitting the child's name and other data entered via the input means to the server, using a secure communication protocol (e.g., HTTPS).

[0894] The "generation means" is a means for generating a story using generative artificial intelligence based on the child's name received by the server, and includes an algorithm for constructing a story by combining specific templates and random elements.

[0895] The "display means" is a means for displaying the story sent from the server to the user on the terminal, and provides an interface including text, graphics, and in some cases sound effects.

[0896] The "emotion recognition means" is a means for analyzing the user's facial expressions and tone of voice using the camera and microphone of the terminal, and recognizing the user's emotions in real time.

[0897] The "voice adjustment means" is a means for controlling the reading of the story aloud based on the user's emotional information recognized by the emotion recognition means, and includes an algorithm for adjusting the reading speed and intonation.

[0898] "Mobile device" refers to a device that can be carried by a user, including, for example, a smartphone or tablet terminal.

[0899] "Generative AI" is AI that has the ability to learn large amounts of data and generate new information and content, such as a type of text generation model.

[0900] This invention is a system that uses generative artificial intelligence to generate a story based on a child's name, and then displays and reads the story on a terminal. Furthermore, it adds functionality to recognize the user's emotions in real time and adjust the reading speed, intonation, etc. The specific configuration and operation of the system are described below.

[0901] Hardware and Software Configuration

[0902] This system mainly consists of the following hardware and software:

[0903] Mobile devices: Smartphones and tablets that users can carry around with them.

[0904] Server: Responsible for receiving and processing data and running generative artificial intelligence.

[0905] Camera and microphone: Built into the user device to collect data for emotion recognition.

[0906] Input method: On-screen keyboard or input field on the mobile device.

[0907] Transmission method: Data is sent to the server using the HTTPS protocol.

[0908] Generative AI: For example, OpenAI's GPT-3 has the ability to learn from large amounts of data and generate new information and content.

[0909] Emotion recognition methods: For example, Microsoft Azure Emotion API, which analyzes facial expressions and tone of voice.

[0910] Speech synthesis and adaptation methods, including Google Cloud Text-to-Speech, which adjusts speaking rate and intonation based on user emotion.

[0911] System Operation

[0912] Personalized Story Generation

[0913] 1. User enters child's name

[0914] The user enters the child's name in the input field displayed on the mobile device, for example, "Taro," and taps the submit button.

[0915] 2. Data transmission

[0916] The mobile device sends the entered name "Taro" to the server using the HTTPS protocol.

[0917] 3. Processing on the Server

[0918] The server receives the request, authenticates the user, and then instructs the generative AI to generate a story based on the name "Taro." The generative AI generates a story such as "Taro goes on an adventure in a magical forest."

[0919] 4. Submitting and Viewing Stories

[0920] The server formats the generated story into JSON format and sends it to the mobile device, which receives the story and displays it in the UI.

[0921] Emotion recognition and speech-to-speech adjustment

[0922] 5. Emotional Recognition

[0923] Using the mobile device's built-in camera and microphone, the emotion recognition method analyzes the user's facial expressions and tone of voice, thereby recognizing the user's emotions (e.g., joy, excitement) in real time.

[0924] 6. Adjust reading

[0925] Based on the recognized emotional information, speech synthesis and adjustment methods adjust the reading speed and intonation to read the story aloud in a more personalized way.

[0926] Specific examples

[0927] The user launches the app, enters their child's name as "Taro," and submits.

[0928] The device sends data containing "Taro" to the server using HTTPS.

[0929] The server uses generative artificial intelligence to generate a story about Taro's adventures in a magical forest and sends it back to the device.

[0930] The device displays the story and uses the camera and microphone to recognize the user's emotions in real time.

[0931] Based on the recognized emotion, the speech synthesis tool adjusts the reading speed and intonation.

[0932] Example prompts to input to the generative AI model

[0933] "The child's name is Taro. Please generate a fun adventure story starring Taro. Specifically, please make it about Taro having a wonderful adventure in a magical forest."

[0934] As described above, this system enables dynamically adjusted reading based on the user's emotions, providing a personalized story experience.

[0935] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[0936] Step 1:

[0937] The user launches the application on their mobile device and enters their child's name into the input field. The input is exemplified as "Taro." The user taps the "Submit" button.

[0938] Input: Child's name (e.g. "Taro")

[0939] Output: Prepare input data for sending

[0940] Step 2:

[0941] The device sends the entered data, including the name "Taro," to the server using the HTTPS protocol, along with authentication information such as the user ID and session ID.

[0942] Input: Input data (child's name "Taro"), authentication information

[0943] Output: Request sent to server

[0944] Step 3:

[0945] The server receives the request from the device, verifies the authentication information, and if authentication is successful, instructs the generative AI to generate a story.

[0946] Input: Request data (child's name "Taro", authentication information)

[0947] Output: Story generation instructions for generative AI

[0948] Step 4:

[0949] The generative AI generates a story based on the input name "Taro." This story is constructed by combining specific templates and random elements. For example, it generates content such as "Taro goes on an adventure in a magical forest."

[0950] Input: Child's name ("Taro")

[0951] Output: The generated story (e.g. "Taro goes on an adventure in the magical forest")

[0952] Step 5:

[0953] The server formats the generated story into JSON format, adds the creation date and time and other metadata, and sends it to the device.

[0954] Input: Generated stories

[0955] Output: Formatted story (JSON format)

[0956] Step 6:

[0957] The device analyzes the story received from the server and displays it on the user interface (UI). The story may not only consist of text, but may also include illustrations and sound effects.

[0958] Input: JSON formatted story

[0959] Output: Generate data for display

[0960] Step 7:

[0961] The device's camera and microphone are used to recognize the user's emotions in real time. The emotion recognition means analyzes the user's facial expressions and tone of voice to determine whether the user is enjoying themselves or feeling excited.

[0962] Input: Camera video, microphone audio

[0963] Output: Recognized emotion data

[0964] Step 8:

[0965] The device uses a voice synthesis tool to read the story aloud, adjusting the reading speed and intonation based on the user's emotional information recognized by the emotion recognition means.

[0966] Input: Story text, recognized emotion data

[0967] Output: Emotionally adjusted speech

[0968] Through these steps, the system can dynamically adjust reading to respond to the user's emotions, providing a more engaging and personalized story experience.

[0969] The specific processing unit 290 transmits the result of the specific processing to the smart glasses 214. In the smart glasses 214, the control unit 46A causes the speaker 240 to output the result of the specific processing. The microphone 238 acquires audio indicating a user input regarding the result of the specific processing. The control unit 46A transmits audio data indicating the user input acquired by the microphone 238 to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the audio data.

[0970] The data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of the data generation model 58 is ChatGPT (Internet Search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search <url: https: gemini.google.com ?hl="ja">) and other generation AIs. The data generation model 58 is obtained by performing deep learning on a neural network. A prompt including an instruction is input to the data generation model 58, and inference data such as voice data indicating voice, text data indicating text, and image data indicating an image is also input. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt, and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[0971] In the above embodiment, an example in which the specific processing is performed by the data processing device 12 has been given, but the technology of the present disclosure is not limited to this, and the specific processing may be performed by the smart glasses 214.

[0972] [Third embodiment]

[0973] FIG. 5 shows an example of the configuration of a data processing system 310 according to the third embodiment.

[0974] 5, the data processing system 310 includes the data processing device 12 and a headset terminal 314. An example of the data processing device 12 is a server.

[0975] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 is an example of a "computer" according to the technology of the present disclosure. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, the RAM 30, and the storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0976] The headset type terminal 314 includes a computer 36, a microphone 238, a speaker 240, a camera 42, a communication I / F 44, and a display 343. The computer 36 includes a processor 46, a RAM 48, and a storage 50. The processor 46, the RAM 48, and the storage 50 are connected to a bus 52. The microphone 238, the speaker 240, the camera 42, and the display 343 are also connected to the bus 52.

[0977] The microphone 238 receives instructions and the like from the user 20 by receiving voice uttered by the user 20. The microphone 238 captures the voice uttered by the user 20, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio in accordance with instructions from the processor 46.

[0978] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an imaging element such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the surroundings of user 20 (for example, an imaging range defined by an angle of view equivalent to the field of vision of a typical healthy person).

[0979] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 are responsible for the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is carried out in a secure state.

[0980] Fig. 6 shows an example of the main functions of the data processing device 12 and the headset type terminal 314. As shown in Fig. 6, in the data processing device 12, a specific process is performed by the processor 28. A specific process program 56 is stored in the storage 32.

[0981] The specific processing program 56 is an example of a "program" according to the technology of the present disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[0982] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[0983] In the headset type terminal 314, a reception output process is performed by the processor 46. A reception output program 60 is stored in the storage 50. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output process is realized by the processor 46 operating as the control unit 46A in accordance with the reception output program 60 executed on the RAM 48.

[0984] Next, a description will be given of the identification process performed by the identification processing unit 290 of the data processing device 12. In the following description, the data processing device 12 will be referred to as the "server" and the headset type terminal 314 will be referred to as the "terminal."

[0985] This invention relates to a system in which a user inputs a child's name, and a server uses generative artificial intelligence to generate a story based on that information, and the story is then displayed and read aloud on the terminal. Below, we will explain the specific program processing in natural language, with examples.

[0986] 1. Enter your child's name

[0987] The user enters the child's name into an input field on the device, for example, "Taro" on the application screen of a smartphone or tablet.

[0988] 2. Sending input data

[0989] The device sends the entered data, including the name "Taro," to the server. Here, the data is sent securely using the HTTPS protocol.

[0990] 3. Receiving and Authenticating a Request

[0991] The server receives a request from the device. This request includes the child's name "Taro" and authentication information such as the user ID and session ID. The server authenticates the user based on this information and verifies that the request is legitimate.

[0992] 4. Story Generation

[0993] After authentication, the server instructs the generative AI to generate a story. The generative AI generates a personalized story with a protagonist named "Taro." This story is generated by combining unique templates and random elements.

[0994] 5. Formatting and sending the generated results

[0995] The server formats the generated story and sends it to the device in JSON or text format, and may also include the date and time of creation and other metadata along with the story.

[0996] 6. Viewing Stories

[0997] The device analyzes the story received from the server and displays it on the user interface (UI). The story may not only consist of text, but may also include illustrations and sound effects.

[0998] 7. Text-to-speech

[0999] The device will launch a text-to-speech tool to read the story aloud, making it easier for users to read stories to their children.

[1000] Specific examples

[1001] scenario:

[1002] Suppose a user wants to create a new story for a child named "Taro" and tell it to him.

[1003] 1. The user enters "Taro"

[1004] The user enters "Taro" in the application's input field and presses the generate button.

[1005] 2. Submitting a Request

[1006] The device sends data including the name "Taro" to the server using HTTPS.

[1007] 3. Processing on the Server

[1008] The server receives the request and authenticates the user. If authentication is successful, it instructs the generative AI to generate a story with "Taro" as the main character.

[1009] 4. Story Generation

[1010] Generative AI generates stories such as "Taro goes on an adventure in the forest," which are a combination of specific templates and random elements.

[1011] 5. Sending and displaying results

[1012] The server formats the generated story into JSON format and sends it to the device, which parses the story and displays it in the UI.

[1013] 6. Reading and User Interaction

[1014] The device uses a text-to-speech tool to read the story aloud, and the user can tap the screen to go to the next page or stop reading.

[1015] This invention allows users to create a different story every day using their child's name and easily read it to them, which can keep the child interested while reducing the burden on parents.

[1016] The processing flow will be explained below.

[1017] Step 1:

[1018] The user enters the child's name "Taro" into the input field on the device. The user presses the "Generate" button.

[1019] Step 2:

[1020] The device prepares request data including the input name "Taro." This request data also includes authentication information such as the user ID and session ID. The device sends a POST request to the server using the HTTPS protocol.

[1021] Step 3:

[1022] The server receives a POST request from the device, verifies the authentication information in the request, and verifies that the user has valid permissions.

[1023] Step 4:

[1024] After the server verifies it, it passes the received data, including the name "Taro," to the generative AI and requests it to generate a story.

[1025] Step 5:

[1026] Based on the data received, the generative AI generates a story with the name "Taro" as the main character. For example, it might generate a story about Taro's adventures in a magical forest. This story is created by combining random elements and predefined templates.

[1027] Step 6:

[1028] The generated story is temporarily stored on the server in text or JSON format, and the server formats this data in a format suitable for the user, adding images and audio data if necessary.

[1029] Step 7:

[1030] The server sends the formatted story to the device as response data, which includes the story text, the creation date and time, and other metadata.

[1031] Step 8:

[1032] The device analyzes the story received from the server and prepares it for display on the user interface (UI).

[1033] Step 9:

[1034] The device launches a speech synthesis tool to read the displayed story aloud. The device provides the user with the option to start reading the story aloud.

[1035] Step 10:

[1036] The user uses the device to read the generated story to the child, tapping the screen as needed to advance to the next page or stop reading.

[1037] Example 1

[1038] Next, a description will be given of Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the headset type terminal 314 will be referred to as a "terminal."

[1039] In recent years, there has been a growing demand for systems with educational value that promote parent-child communication and foster children's creativity. However, existing systems have issues with difficulty in generating stories tailored to individual children's names and characteristics, and have complex operation and low usability. Furthermore, there is a lack of systems that allow users to enjoy the generated stories both visually and aurally. The purpose of this invention is to solve these issues and realize easy and personalized story generation and playback.

[1040] The specific processing by the specific processing unit 290 of the data processing device 12 in the first embodiment is realized by the following means.

[1041] In this invention, the server includes input means for inputting a child's name, transmission means for transmitting the child's name input via the input means to the server, authentication means for authenticating a user based on the child's name and authentication information received by the server via the transmission means, generation means for generating a story using generative artificial intelligence based on the information authenticated by the authentication means, transmission means for formatting the story generated by the generation means into JSON format or text format and transmitting it to a terminal, display means for the terminal to analyze the story received via the transmission means and display it on a user interface, and speech synthesis means for the terminal to read the story aloud. This makes it possible to generate personalized stories based on each child's name and easily display and read them aloud.

[1042] "Child Name" is the identifying name of a particular child that the user provides to the system via an input means.

[1043] "Input means" refers to the interface through which the user inputs the child's name, and includes a keyboard and a touch screen.

[1044] The "transmission means" is a communication interface for transmitting data input via the input means to a server, and includes a secure data transfer means such as the HTTPS protocol.

[1045] "Server" refers to a processing device that performs authentication and story generation based on received data.

[1046] The "authentication means" is a means for verifying the user based on authentication information such as the user ID and session ID received by the server, and authenticating the request as legitimate.

[1047] The "generation means" is a means for generating a personalized story based on a child's name using generative artificial intelligence.

[1048] "Generative AI" is an AI model that has the ability to generate new content based on prompts provided by users.

[1049] The "transmission means" is a communication interface for arranging the story generated by the generation means into an appropriate format and transmitting it to a terminal.

[1050] "Terminal" refers to a device operated by a user, including a smartphone or tablet.

[1051] The "display means" is a means for displaying the story received by the terminal from the server on a user interface.

[1052] "Analysis" refers to the process of interpreting received data based on a predetermined format and displaying it in a form that is easy for the user to understand.

[1053] The "voice synthesis means" is a processing device or software that converts the displayed story content into voice and reads it out loud.

[1054] "JSON format" is an abbreviation for JavaScript Object Notation, and is a lightweight data format widely used as a data exchange format.

[1055] "Text format" refers to a format that refers to character-based data, and includes simple text files such as INI files.

[1056] This invention relates to a system in which a user inputs their child's name, and based on that, a server uses generative artificial intelligence (generative AI model) to generate a story, which is then displayed and read aloud on the terminal.

[1057] System configuration

[1058] The system includes the following components:

[1059] 1. An input method for entering a child's name

[1060] The user enters the child's name through the smartphone or tablet interface, for example, "Taro" using the touch keyboard.

[1061] 2. Transmission method for transmitting input data

[1062] The device sends the entered data, including the name "Taro," to the server using HTTPS, a secure communication protocol.

[1063] 3. Authentication method to receive and authenticate requests

[1064] The server receives the request from the terminal and verifies that the user is a valid user based on the user ID and session ID. If the user authentication is successful, it proceeds to the next step.

[1065] 4. A method for generating stories using generative artificial intelligence

[1066] After authentication, the server sends a prompt to the generative AI model. For example, it might say, "Please generate an adventure story with Taro as the main character." Based on this, the generative AI model generates a personalized story with the name "Taro" as the main character.

[1067] 5. A means of sending the generated stories in the appropriate format.

[1068] The server formats the generated story in JSON or text format and sends it to the device, sometimes with the creation date and time and other metadata.

[1069] 6. Display method for analyzing and displaying the story

[1070] The device analyzes the story received from the server and displays it on the user interface. The story may contain not only text but also illustrations and sound effects.

[1071] 7. A speech synthesis method to read a story aloud

[1072] The device will read the story aloud using a speech synthesis tool (such as Google Text-to-Speech or Amazon Polly), making it easier for users to read stories to their children.

[1073] Specific examples

[1074] scenario

[1075] Suppose a user wants to create a new story for a child named "Taro" and play it. Here is a concrete example:

[1076] 1. The user enters "Taro"

[1077] The user enters "Taro" in the input field of the smartphone application and presses the generate button.

[1078] 2. Submitting a Request

[1079] The device sends data including the name "Taro" to the server using HTTPS.

[1080] 3. Processing on the Server

[1081] The server receives the request and authenticates the user. If authentication is successful, it instructs the generative AI to generate a story with "Taro" as the main character.

[1082] 4. Story Generation

[1083] A generative AI model generates stories such as "Taro goes on an adventure in the forest," which are a combination of specific templates and random elements.

[1084] 5. Sending and displaying results

[1085] The server formats the generated story into JSON format and sends it to the device, which parses the story and displays it in the user interface.

[1086] 6. Reading and User Interaction

[1087] The device uses a text-to-speech tool to read the story aloud, and the user can tap the screen to go to the next page or stop reading.

[1088] With the above configuration, it is possible to easily generate, display, and read out a personalized story based on the child's name.

[1089] The flow of the identification process in the first embodiment will be described with reference to FIG.

[1090] Program processing flow

[1091] The processing flow of this system's program will be explained in the following steps. At each step, data processing and data calculation based on input and output will also be explained.

[1092] Step 1:

[1093] User enters child's name

[1094] Specific operation: The user enters a child's name into the input field on a smartphone or tablet. For example, they enter "Taro" and press the "Generate" button.

[1095] Input: The name "Taro" entered by the user.

[1096] Output: Request data including the input name "Taro".

[1097] Step 2:

[1098] The device sends the input data to the server

[1099] Specific operation: The device sends data containing "Taro" to the server using the HTTPS protocol.

[1100] Input: Request data (including the child's name "Taro").

[1101] Output: The request data sent to the server.

[1102] Step 3:

[1103] The server receives the request and authenticates the user

[1104] Specific operation: The server analyzes the request received from the terminal and authenticates the user ID and session ID by checking them against the database.

[1105] Input: Received request data (child's name "Taro", user ID, session ID).

[1106] Output: Authentication result (success / failure).

[1107] Step 4:

[1108] The server instructs the generative AI to generate a story.

[1109] Specific operation: After the server successfully authenticates, it sends a prompt to the generation AI model: "Please generate an adventure story with Taro as the main character."

[1110] Input: Request data and prompt for a successfully authenticated user.

[1111] Output: The story generated by the generative AI model.

[1112] Step 5:

[1113] The server formats the generated story and sends it to the device.

[1114] Specific operation: The server formats the generated story into JSON or text format, adds the creation date and time and metadata, and sends it to the device.

[1115] Input: The story returned by the generative AI model.

[1116] Output: Formatted story data (JSON or text format).

[1117] Step 6:

[1118] The device analyzes and displays the received story.

[1119] Specific behavior: The device analyzes the received story data and displays it on the user interface, which may include text, illustrations, sound effects, etc.

[1120] Input: Formatted story data received from the server.

[1121] Output: The story displayed in the user interface.

[1122] Step 7:

[1123] Your device will read the story aloud

[1124] What it does: The device uses a speech synthesis tool to read the story aloud, and the user can play, pause, and turn pages.

[1125] Input: Parsed story data.

[1126] Output: The story read aloud.

[1127] Example prompt

[1128] "Generate an adventure story with Taro as the main character."

[1129] (Application example 1)

[1130] Next, a description will be given of Application Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the headset type terminal 314 will be referred to as a "terminal."

[1131] Previous story generation systems were limited to generating personalized stories based on the user's child's name, and lacked picture books and other reading materials that users could enjoy interactively with their children in a virtual environment. Furthermore, the reading function was often limited to simple audio reading, and was unable to provide a holistic, interactive experience.

[1132] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 1 is realized by the following means.

[1133] In this invention, the server includes an input means for inputting a child's name, a transmission means for transmitting the child's name input via the input means to the server, and a generation means for generating a story by using a generative artificial intelligence based on the child's name received by the server via the transmission means. This enables the user to provide an interactive picture book or reading material in a virtual environment using the child's name, allowing the user to share a sense of unity with the child.

[1134] "Child's name" refers to the unique name of a particular child that the user enters into the terminal.

[1135] "Input means" refers to the device or interface that the user uses to input the child's name.

[1136] "Transmission means" refers to the function or protocol used to transmit the entered child's name to the server.

[1137] "Generation means" refers to the function or algorithm that uses generative artificial intelligence to generate a story based on the received child's name.

[1138] "Device" refers to an electronic device used by a user, such as a smartphone or tablet device.

[1139] "Display means" refers to the function of visually displaying the generated story on the terminal screen.

[1140] "Audio output means" refers to a function or device for reading aloud the displayed story.

[1141] "Virtual environment" refers to a computer-generated space or scenario that a user can experience virtually through electronic devices.

[1142] "Interactive reading material" refers to stories or content that change dynamically in response to user actions.

[1143] "Implementation" refers to the software and hardware configuration for providing interactive storybooks and reading materials within a virtual environment.

[1144] "Generative artificial intelligence" refers to machine learning or deep learning models that generate new content based on provided input data.

[1145] This invention relates to a system that provides interactive reading material in a virtual environment based on a child's name. A user inputs the child's name using a terminal, and the information is sent to a server. The server uses generative artificial intelligence to generate a story incorporating the child's name and sends the generated story to the terminal. The terminal can display the story and read it aloud using audio output means.

[1146] Details of the hardware and software used

[1147] 1. User devices: Primarily smartphones and tablets are used. These devices run applications built using React Native.

[1148] 2. Server: Built using Node.js and the Express framework. The database uses MongoDB, and the generative AI uses OpenAI's GPT-4 API.

[1149] 3. Audio output method: The Google Cloud Text-to-Speech API is used to read the story aloud on the device.

[1150] Program processing and data calculation

[1151] The server receives the child's name sent from the user's device and uses it to instruct the generative AI to generate a story. The generated story is formatted in JSON format and sent back to the user's device. The user's device analyzes the story and displays it visually through a display device. The story is then read aloud using the Google Cloud Text-to-Speech API.

[1152] Examples and prompts

[1153] Examples:

[1154] When a user inputs "Sachiko" as the child's name, an "adventure story of Sachiko exploring a mysterious forest" is generated based on that name. The generated story is displayed in the virtual environment and read aloud using a voice output means.

[1155] Example prompt sentence:

[1156] "Generate a story in which the main character is Sachiko, who goes on an adventure in a mysterious forest where she encounters many different animals."

[1157] This invention allows users to create their own interactive stories in a virtual environment using their child's name, making the storytelling experience more immersive and helping to keep children engaged.

[1158] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[1159] Step 1:

[1160] The user enters the child's name.

[1161] Specifically, the user launches the application on their smartphone or tablet and enters their child's name (e.g., "Sachiko") in the name input field. Input data (child's name) is generated.

[1162] Step 2:

[1163] The terminal sends the entered name to the server.

[1164] Specifically, the device securely sends data, including the child's name, to the server using the HTTPS protocol. The data also includes the user ID and session ID. Data to be sent is generated, including the input data (child's name).

[1165] Step 3:

[1166] The server receives the request and authenticates the user.

[1167] Specifically, the server receives a request from the terminal and performs authentication based on the user ID and session ID in the transmitted data. If authentication is successful, it proceeds to the next step. The input data is the user's authentication information, and the output data is the authentication result.

[1168] Step 4:

[1169] The server instructs the generative artificial intelligence to generate a story.

[1170] Specifically, the server creates a prompt and requests the generative artificial intelligence (GPT-4) to generate a story. An example of a prompt is, "Please generate a story in which the main character is Sachiko. Sachiko goes on an adventure in a mysterious forest, encountering many different animals." The input data is the prompt, and the output data is the generated story.

[1171] Step 5:

[1172] The server formats the generated story into JSON format and sends it to the device.

[1173] Specifically, the server converts the story obtained from the generative AI into an appropriate format (JSON format) and sends it to the terminal again via the HTTPS protocol. The input data is the generated story, and the output data is a story in JSON format.

[1174] Step 6:

[1175] The device analyzes the received story and displays it on the screen.

[1176] Specifically, the device parses the JSON-formatted story received from the server and displays the story on the screen. The input data is the JSON-formatted story, and the output data is the story displayed on the screen.

[1177] Step 7:

[1178] The device will read the story aloud.

[1179] Specifically, the device uses the Google Cloud Text-to-Speech API to convert the displayed story into audio and read it out through the speaker. The input data is the text story, and the output data is the audio story.

[1180] Furthermore, an emotion engine that estimates the user's emotion may be further combined. That is, the identification processing unit 290 may estimate the user's emotion using the emotion identification model 59, and perform identification processing using the user's emotion.

[1181] This invention combines a system in which a user inputs their child's name, and a server uses generative artificial intelligence to generate a story based on that, and displays and reads it out loud on the terminal, with an emotion engine that recognizes the user's emotions. Below, we will explain the specific program processing in natural language, using concrete examples.

[1182] System configuration

[1183] 1. Enter your child's name

[1184] The user enters the child's name into an input field on the device, for example, "Taro" on the application screen of a smartphone or tablet.

[1185] 2. Sending input data

[1186] The device sends the entered data, including the name "Taro," to the server. Here, the data is sent securely using the HTTPS protocol.

[1187] 3. Receiving and Authenticating a Request

[1188] The server receives a request from the device. This request includes the child's name "Taro" and authentication information such as the user ID and session ID. The server authenticates the user based on this information and verifies that the request is legitimate.

[1189] 4. Story Generation

[1190] After authentication, the server instructs the generative AI to generate a story. The generative AI generates a personalized story with a protagonist named "Taro." This story is generated by combining unique templates and random elements.

[1191] 5. Recognizing and reflecting emotions

[1192] The emotion engine uses the device's camera and microphone to recognize the user's emotions in real time. The emotion recognition results are temporarily stored on the device and sent to a server, or used directly when reading out the text.

[1193] 6. Formatting and sending the generated results

[1194] The server formats the generated story and sends it to the device in JSON or text format, and may also include the date and time of creation and other metadata along with the story.

[1195] 7. Viewing Stories

[1196] The device analyzes the story received from the server and displays it on the user interface (UI). The story may not only consist of text, but may also include illustrations and sound effects.

[1197] 8. Voice reading and adjustment

[1198] The device activates a speech synthesis tool to read the story aloud, adjusting the reading speed and intonation based on the user's emotional information as recognized by the emotion engine.

[1199] Specific examples

[1200] scenario:

[1201] Suppose a user wants to create a new story for a child named "Taro" and tell it to him.

[1202] 1. The user enters "Taro"

[1203] The user enters "Taro" in the application's input field and presses the generate button.

[1204] 2. Submitting a Request

[1205] The device sends data including the name "Taro" to the server using HTTPS.

[1206] 3. Processing on the Server

[1207] The server receives the request and authenticates the user. If authentication is successful, it instructs the generative AI to generate a story with "Taro" as the main character.

[1208] 4. Story Generation

[1209] A generative AI generates a story, such as "Taro goes on an adventure in a magical forest," that combines specific templates and random elements.

[1210] 5. Recognizing and reflecting emotions

[1211] While the user is reading the story, the emotion engine analyzes the user's facial expressions and tone of voice through the device's camera and microphone, and recognizes the user's emotions in real time, such as whether they are enjoying themselves or excited. This information is sent to the server.

[1212] 6. Formatting and Displaying the Story

[1213] The server formats the generated story into JSON format and sends it to the device, which parses the story and displays it in the UI.

[1214] 7. Read aloud

[1215] The device uses a speech synthesis tool to read the story aloud, dynamically adjusting the reading speed and intonation based on the user's emotions as recognized by an emotion engine.

[1216] 8. User Operations

[1217] The user reads the generated story to the child using the device, and the emotion engine adjusts the story to make it more engaging and maintain the child's interest.

[1218] This invention allows users to create a different story each day using their child's name and utilizes emotion recognition to provide a more personalized reading experience, keeping children engaged and reducing the burden on parents.

[1219] The processing flow will be explained below.

[1220] Step 1:

[1221] The user enters the child's name "Taro" into the input field on the terminal and presses the "Generate" button. The terminal receives this input and proceeds to the next step.

[1222] Step 2:

[1223] The terminal prepares request data including the input name "Taro" and authentication information such as user ID and session ID. The terminal sends this data to the server as a POST request using the HTTPS protocol.

[1224] Step 3:

[1225] The server receives a POST request from the device, verifies the authentication information in the request, and verifies that the user has valid permissions.

[1226] Step 4:

[1227] After the server authenticates, it passes the received name "Taro" to the generative AI and requests a story to be generated.

[1228] Step 5:

[1229] A generative AI generates a story based on the name "Taro." For example, it generates a story about "Taro's adventure in a magical forest." This story is created by combining random elements and templates.

[1230] Step 6:

[1231] The emotion engine recognizes the user's emotions in real time using the device's camera and microphone. The device temporarily stores the emotion recognition results and sends them to the server as needed.

[1232] Step 7:

[1233] The server receives the generated stories and formats them appropriately. The formatted data includes the story text, the creation date and time, and other metadata.

[1234] Step 8:

[1235] The server sends the formatted story to the device, which receives the story as response data.

[1236] Step 9:

[1237] The device parses the received story and prepares it for display in the user interface (UI). The story may contain text, images, and sound effects.

[1238] Step 10:

[1239] The device activates a speech synthesis tool to read the story aloud, adjusting the reading speed and intonation based on the user's emotional information as recognized by the emotion engine.

[1240] Step 11:

[1241] The user reads the generated story to the child using the device, and the story is adjusted appropriately according to the user's emotions to keep the child interested.

[1242] Step 12:

[1243] Users can tap the device screen to advance to the next page or stop reading as needed.

[1244] In this way, users can utilize emotion recognition to generate personalized stories based on their child's name, providing a more interactive storytelling experience.

[1245] Example 2

[1246] Next, a description will be given of Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the headset type terminal 314 will be referred to as a "terminal."

[1247] Conventional story generation systems can generate personalized stories simply by entering a user's name, but they lack the ability to reflect the user's emotions, meaning that the story cannot be read aloud in real time according to the user's emotions. This also reduces the quality of the user experience, making it difficult for children to maintain their interest in the story.

[1248] The identification process by the identification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means. In this invention, the server includes an input means for inputting the child's name, a transmission means for transmitting the child's name input via the input means to the server, a generation means for generating a story using a generative model based on the child's name received by the server via the transmission means, and a transmission means for shaping the story generated by the generation means into an appropriate format and transmitting it to the terminal. This makes it possible to adjust the reading speed and intonation of the generated story in real time according to the user's emotions.

[1249] An "input means for inputting a child's name" is a device or interface that a user uses to input a child's name.

[1250] The "transmission means" refers to a protocol or device for transmitting the child's name input via the input means to a server and performing data communication.

[1251] The "generation means for generating a story using a generative model" is a system or software for automatically generating a story using an artificial intelligence model based on the received child's name.

[1252] The "transmission means for converting the story into an appropriate format and transmitting it to the terminal" is a system or device for converting the generated story into a format that can be interpreted by the terminal and transmitting the content to the terminal.

[1253] The "display means" is a screen or display that visually displays the story received by the terminal to the user.

[1254] The "recognition means for recognizing a user's emotions using an emotion engine" is a system or software for analyzing and recognizing emotions from a user's facial expressions and tone of voice using devices such as a camera and a microphone.

[1255] An "adjustment means" is a system or software for dynamically changing the reading rate or intonation based on the recognized emotional information.

[1256] "A speech synthesis means for reading aloud" is a system or software for converting a displayed story from text to speech and reading it aloud.

[1257] A "personal digital assistant" is a portable computing device such as a smartphone or tablet.

[1258] An "application" refers to a software program that runs on the terminal and that the user operates to input data or view stories.

[1259] This invention combines a system in which a user inputs the name of their child, and a server uses generative artificial intelligence to generate a story based on that, and displays and reads it out loud on the terminal, with an emotion engine that recognizes the user's emotions. Specific embodiments for carrying out this invention are described below.

[1260] System configuration

[1261] Enter your child's name

[1262] The user enters the child's name into the application screen on the smartphone or tablet. The application provides an input field on the screen to receive the child's name. For example, the user enters "Taro."

[1263] Sending input data

[1264] The device sends the entered name "Taro" to the server using the HTTPS protocol. The sent data also includes the user ID and session ID, ensuring secure data transfer.

[1265] Receiving and authenticating requests

[1266] The server receives a request from the device. This request includes the child's name "Taro" and authentication information such as the user ID and session ID. The server authenticates the user based on this information and verifies that the request is valid.

[1267] Story Generation

[1268] After authentication, the server instructs a generative AI (e.g., GPT-3) to generate a story. The generative AI generates a personalized story with a protagonist named "Taro." This story is generated by combining unique templates and random elements.

[1269] Recognizing and reflecting emotions

[1270] The emotion engine uses the device's camera and microphone to recognize the user's emotions in real time. The emotion recognition results are temporarily stored on the device and sent to a server, or used directly when reading out the text.

[1271] Formatting and sending the generated results

[1272] The server formats the generated story and sends it to the device in JSON or text format, and may also include the date and time of creation and other metadata along with the story.

[1273] Viewing Stories

[1274] The device analyzes the story received from the server and displays it on the user interface (UI). The story may not only consist of text, but may also include illustrations and sound effects.

[1275] Speech reading and adjustments

[1276] The device launches a speech synthesis tool (e.g., Google Text-to-Speech) to read the story aloud, adjusting the reading speed and intonation based on the user's emotional information as recognized by the emotion engine.

[1277] Specific examples

[1278] scenario

[1279] Suppose a user wants to create a new story for a child named "Taro" and tell it to him.

[1280] 1. The user enters "Taro"

[1281] The user enters "Taro" in the application's input field and presses the generate button.

[1282] 2. Submitting a Request

[1283] The device sends data including the name "Taro" to the server using HTTPS.

[1284] 3. Processing on the Server

[1285] The server receives the request and authenticates the user. If authentication is successful, it instructs the generative AI to generate a story with "Taro" as the main character.

[1286] 4. Story Generation

[1287] A generative AI generates a story, such as "Taro goes on an adventure in a magical forest," that combines specific templates and random elements.

[1288] 5. Recognizing and reflecting emotions

[1289] While the user is reading the story, the emotion engine analyzes the user's facial expressions and tone of voice through the device's camera and microphone, and recognizes the user's emotions in real time, such as whether they are enjoying themselves or excited. This information is sent to the server.

[1290] 6. Formatting and Displaying the Story

[1291] The server formats the generated story into JSON format and sends it to the device, which parses the story and displays it in the UI.

[1292] 7. Read aloud

[1293] The device uses a speech synthesis tool to read the story aloud, dynamically adjusting the reading speed and intonation based on the user's emotions as recognized by an emotion engine.

[1294] Prompt Sentence Examples

[1295] "To generate an adventure story for children, please create a story that meets the following conditions: The main character's name should be 'Taro' and the story should include his adventures in a magical forest."

[1296] This invention allows users to create a different story each day using their child's name and utilizes emotion recognition to provide a more personalized reading experience, keeping children engaged and reducing the burden on parents.

[1297] The flow of the identification process in the second embodiment will be described with reference to FIG.

[1298] Step 1:

[1299] User enters child's name

[1300] Specific behavior:

[1301] The user enters the child's name "Taro" into the application screen on their smartphone or tablet and presses the "Generate" button.

[1302] input:

[1303] Child's name: Taro

[1304] output:

[1305] Name "Taro" stored on the device

[1306] Step 2:

[1307] The device sends the input data to the server

[1308] Specific behavior:

[1309] The device uses the HTTPS protocol to send the child's name "Taro", the user ID, and the session ID to the server.

[1310] input:

[1311] Name "Taro", User ID, Session ID

[1312] output:

[1313] Request data sent to the server

[1314] Step 3:

[1315] The server receives the request and authenticates the user

[1316] Specific behavior:

[1317] The server analyzes the request data received and performs user authentication based on the user ID and session ID. It checks whether the authentication information is correct.

[1318] input:

[1319] Request data (name "Taro", user ID, session ID)

[1320] output:

[1321] Authentication success or failure flag

[1322] Step 4:

[1323] The server directs the creation of the story

[1324] Specific behavior:

[1325] If user authentication is successful, the server sends a prompt to the generative AI model (e.g., GPT-3) to instruct it to generate a story.

[1326] input:

[1327] Authentication successful, prompt: "To generate an adventure story for children, please create a story that meets the following conditions. The main character's name should be 'Taro' and include his adventures in a magical forest."

[1328] output:

[1329] Generated Stories

[1330] Step 5:

[1331] Emotion engine recognizes user emotions

[1332] Specific behavior:

[1333] The device uses the built-in camera and microphone to analyze the user's facial expressions and tone of voice, and the results are temporarily saved.

[1334] input:

[1335] User facial expression data, tone of voice data

[1336] output:

[1337] Recognized emotion data

[1338] Step 6:

[1339] The server sends the generated stories

[1340] Specific behavior:

[1341] The server formats the generated story into an appropriate format (such as JSON) and sends it to the device.

[1342] input:

[1343] Generated Stories

[1344] output:

[1345] Story in JSON data format sent to the device

[1346] Step 7:

[1347] Your device will display the story

[1348] Specific behavior:

[1349] The device parses the received JSON data and displays the story on the user's interface (UI).

[1350] input:

[1351] JSON data format story

[1352] output:

[1353] Story displayed in the UI

[1354] Step 8:

[1355] Your device will read the story aloud

[1356] Specific behavior:

[1357] The device uses a speech synthesis tool (e.g., Google Text-to-Speech) to read the story aloud, adjusting the reading speed and intonation based on the user's emotional information as recognized by the emotion engine.

[1358] input:

[1359] Displayed story, recognized emotion data

[1360] output:

[1361] Read-aloud stories

[1362] (Application example 2)

[1363] Next, a description will be given of Application Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the headset type terminal 314 will be referred to as a "terminal."

[1364] Conventional story generation systems have difficulty sustaining children's interest because the generated stories are read aloud in the same tone and speed consistently. Additionally, they are unable to take the user's emotions into account when reading a story, making it difficult to provide a personalized experience.

[1365] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 2 is realized by the following means.

[1366] In this invention, the server includes input means for inputting the child's name, transmission means for transmitting the child's name input via the input means to the server, generation means for the server to generate a story using generative artificial intelligence based on the child's name received via the transmission means, transmission means for transmitting the story generated by the generation means to a terminal, display means for the terminal to display the story received via the transmission means, emotion recognition means for recognizing the user's emotion in real time using the camera and microphone of the terminal, and voice adjustment means for controlling the voice reading of the story based on the emotion recognized by the emotion recognition means. This allows for reading that is dynamically adjusted in response to the user's emotion, enabling a more interesting and personalized story experience.

[1367] An "input means" is a means by which a user inputs a child's name, including, for example, a keyboard or input field displayed on the screen of a mobile device.

[1368] The "transmission means" is a means for transmitting the child's name and other data entered via the input means to the server, using a secure communication protocol (e.g., HTTPS).

[1369] The "generation means" is a means for generating a story using generative artificial intelligence based on the child's name received by the server, and includes an algorithm for constructing a story by combining specific templates and random elements.

[1370] The "display means" is a means for displaying the story sent from the server to the user on the terminal, and provides an interface including text, graphics, and in some cases sound effects.

[1371] The "emotion recognition means" is a means for analyzing the user's facial expressions and tone of voice using the camera and microphone of the terminal, and recognizing the user's emotions in real time.

[1372] The "voice adjustment means" is a means for controlling the reading of the story aloud based on the user's emotional information recognized by the emotion recognition means, and includes an algorithm for adjusting the reading speed and intonation.

[1373] "Mobile device" refers to a device that can be carried by a user, including, for example, a smartphone or tablet terminal.

[1374] "Generative AI" is AI that has the ability to learn large amounts of data and generate new information and content, such as a type of text generation model.

[1375] This invention is a system that uses generative artificial intelligence to generate a story based on a child's name, and then displays and reads the story on a terminal. Furthermore, it adds functionality to recognize the user's emotions in real time and adjust the reading speed, intonation, etc. The specific configuration and operation of the system are described below.

[1376] Hardware and Software Configuration

[1377] This system mainly consists of the following hardware and software:

[1378] Mobile devices: Smartphones and tablets that users can carry around with them.

[1379] Server: Responsible for receiving and processing data and running generative artificial intelligence.

[1380] Camera and microphone: Built into the user device to collect data for emotion recognition.

[1381] Input method: On-screen keyboard or input field on the mobile device.

[1382] Transmission method: Data is sent to the server using the HTTPS protocol.

[1383] Generative AI: For example, OpenAI's GPT-3 has the ability to learn from large amounts of data and generate new information and content.

[1384] Emotion recognition methods: For example, Microsoft Azure Emotion API, which analyzes facial expressions and tone of voice.

[1385] Speech synthesis and adaptation methods, including Google Cloud Text-to-Speech, which adjusts speaking rate and intonation based on user emotion.

[1386] System Operation

[1387] Personalized Story Generation

[1388] 1. User enters child's name

[1389] The user enters the child's name in the input field displayed on the mobile device, for example, "Taro," and taps the submit button.

[1390] 2. Data transmission

[1391] The mobile device sends the entered name "Taro" to the server using the HTTPS protocol.

[1392] 3. Processing on the Server

[1393] The server receives the request, authenticates the user, and then instructs the generative AI to generate a story based on the name "Taro." The generative AI generates a story such as "Taro goes on an adventure in a magical forest."

[1394] 4. Submitting and Viewing Stories

[1395] The server formats the generated story into JSON format and sends it to the mobile device, which receives the story and displays it in the UI.

[1396] Emotion recognition and speech-to-speech adjustment

[1397] 5. Emotional Recognition

[1398] Using the mobile device's built-in camera and microphone, the emotion recognition method analyzes the user's facial expressions and tone of voice, thereby recognizing the user's emotions (e.g., joy, excitement) in real time.

[1399] 6. Adjust reading

[1400] Based on the recognized emotional information, speech synthesis and adjustment methods adjust the reading speed and intonation to read the story aloud in a more personalized way.

[1401] Specific examples

[1402] The user launches the app, enters their child's name as "Taro," and submits.

[1403] The device sends data containing "Taro" to the server using HTTPS.

[1404] The server uses generative artificial intelligence to generate a story about Taro's adventures in a magical forest and sends it back to the device.

[1405] The device displays the story and uses the camera and microphone to recognize the user's emotions in real time.

[1406] Based on the recognized emotion, the speech synthesis tool adjusts the reading speed and intonation.

[1407] Example prompts to input to the generative AI model

[1408] "The child's name is Taro. Please generate a fun adventure story starring Taro. Specifically, please make it about Taro having a wonderful adventure in a magical forest."

[1409] As described above, this system enables dynamically adjusted reading based on the user's emotions, providing a personalized story experience.

[1410] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[1411] Step 1:

[1412] The user launches the application on their mobile device and enters their child's name into the input field. The input is exemplified as "Taro." The user taps the "Submit" button.

[1413] Input: Child's name (e.g. "Taro")

[1414] Output: Prepare input data for sending

[1415] Step 2:

[1416] The device sends the entered data, including the name "Taro," to the server using the HTTPS protocol, along with authentication information such as the user ID and session ID.

[1417] Input: Input data (child's name "Taro"), authentication information

[1418] Output: Request sent to server

[1419] Step 3:

[1420] The server receives the request from the device, verifies the authentication information, and if authentication is successful, instructs the generative AI to generate a story.

[1421] Input: Request data (child's name "Taro", authentication information)

[1422] Output: Story generation instructions for generative AI

[1423] Step 4:

[1424] The generative AI generates a story based on the input name "Taro." This story is constructed by combining specific templates and random elements. For example, it generates content such as "Taro goes on an adventure in a magical forest."

[1425] Input: Child's name ("Taro")

[1426] Output: The generated story (e.g. "Taro goes on an adventure in the magical forest")

[1427] Step 5:

[1428] The server formats the generated story into JSON format, adds the creation date and time and other metadata, and sends it to the device.

[1429] Input: Generated stories

[1430] Output: Formatted story (JSON format)

[1431] Step 6:

[1432] The device analyzes the story received from the server and displays it on the user interface (UI). The story may not only consist of text, but may also include illustrations and sound effects.

[1433] Input: JSON formatted story

[1434] Output: Generate data for display

[1435] Step 7:

[1436] The device's camera and microphone are used to recognize the user's emotions in real time. The emotion recognition means analyzes the user's facial expressions and tone of voice to determine whether the user is enjoying themselves or feeling excited.

[1437] Input: Camera video, microphone audio

[1438] Output: Recognized emotion data

[1439] Step 8:

[1440] The device uses a voice synthesis tool to read the story aloud, adjusting the reading speed and intonation based on the user's emotional information recognized by the emotion recognition means.

[1441] Input: Story text, recognized emotion data

[1442] Output: Emotionally adjusted speech

[1443] Through these steps, the system can dynamically adjust reading to respond to the user's emotions, providing a more engaging and personalized story experience.

[1444] The specific processing unit 290 transmits the result of the specific processing to the headset type terminal 314. In the headset type terminal 314, the control unit 46A causes the speaker 240 and the display 343 to output the result of the specific processing. The microphone 238 acquires audio indicating a user input regarding the result of the specific processing. The control unit 46A transmits audio data indicating the user input acquired by the microphone 238 to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the audio data.

[1445] The data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of the data generation model 58 is ChatGPT (Internet Search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search <url: https: gemini.google.com ?hl="ja">) and other generation AIs. The data generation model 58 is obtained by performing deep learning on a neural network. A prompt including an instruction is input to the data generation model 58, and inference data such as voice data indicating voice, text data indicating text, and image data indicating an image is also input. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt, and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[1446] In the above embodiment, an example was given in which the specific processing is performed by the data processing device 12, but the technology of the present disclosure is not limited to this, and the specific processing may be performed by the headset type terminal 314.

[1447] [Fourth embodiment]

[1448] FIG. 7 shows an example of the configuration of a data processing system 410 according to the fourth embodiment.

[1449] 7, a data processing system 410 includes a data processing device 12 and a robot 414. An example of the data processing device 12 is a server.

[1450] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 is an example of a "computer" according to the technology of the present disclosure. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, the RAM 30, and the storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[1451] The robot 414 includes a computer 36, a microphone 238, a speaker 240, a camera 42, a communication I / F 44, and a control target 443. The computer 36 includes a processor 46, a RAM 48, and a storage 50. The processor 46, the RAM 48, and the storage 50 are connected to a bus 52. The microphone 238, the speaker 240, the camera 42, and the control target 443 are also connected to the bus 52.

[1452] The microphone 238 receives instructions and the like from the user 20 by receiving voice uttered by the user 20. The microphone 238 captures the voice uttered by the user 20, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio in accordance with instructions from the processor 46.

[1453] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an imaging element such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the surroundings of user 20 (for example, an imaging range defined by an angle of view equivalent to the field of vision of a typical healthy person).

[1454] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 are responsible for the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is carried out in a secure state.

[1455] The control object 443 includes a display device, LEDs in the eyes, and motors for driving the arms, hands, and feet. The posture and gestures of the robot 414 are controlled by controlling the motors of the arms, hands, and feet. Some of the emotions of the robot 414 can be expressed by controlling these motors. In addition, the facial expressions of the robot 414 can also be expressed by controlling the light emission state of the LEDs in the eyes of the robot 414.

[1456] Fig. 8 shows an example of the main functions of the data processing device 12 and the robot 414. As shown in Fig. 8, in the data processing device 12, a specific process is performed by the processor 28. A specific process program 56 is stored in the storage 32.

[1457] The specific processing program 56 is an example of a "program" according to the technology of the present disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[1458] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[1459] In the robot 414, the processor 46 performs the reception output process. A reception output program 60 is stored in the storage 50. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output process is realized by the processor 46 operating as the control unit 46A in accordance with the reception output program 60 executed on the RAM 48.

[1460] Next, a description will be given of the specific processing performed by the specific processing unit 290 of the data processing device 12. In the following description, the data processing device 12 will be referred to as a "server" and the robot 414 will be referred to as a "terminal."

[1461] This invention relates to a system in which a user inputs a child's name, and a server uses generative artificial intelligence to generate a story based on that information, and the story is then displayed and read aloud on the terminal. Below, we will explain the specific program processing in natural language, with examples.

[1462] 1. Enter your child's name

[1463] The user enters the child's name into an input field on the device, for example, "Taro" on the application screen of a smartphone or tablet.

[1464] 2. Sending input data

[1465] The device sends the entered data, including the name "Taro," to the server. Here, the data is sent securely using the HTTPS protocol.

[1466] 3. Receiving and Authenticating a Request

[1467] The server receives a request from the device. This request includes the child's name "Taro" and authentication information such as the user ID and session ID. The server authenticates the user based on this information and verifies that the request is legitimate.

[1468] 4. Story Generation

[1469] After authentication, the server instructs the generative AI to generate a story. The generative AI generates a personalized story with a protagonist named "Taro." This story is generated by combining unique templates and random elements.

[1470] 5. Formatting and sending the generated results

[1471] The server formats the generated story and sends it to the device in JSON or text format, and may also include the date and time of creation and other metadata along with the story.

[1472] 6. Viewing Stories

[1473] The device analyzes the story received from the server and displays it on the user interface (UI). The story may not only consist of text, but may also include illustrations and sound effects.

[1474] 7. Text-to-speech

[1475] The device will launch a text-to-speech tool to read the story aloud, making it easier for users to read stories to their children.

[1476] Specific examples

[1477] scenario:

[1478] Suppose a user wants to create a new story for a child named "Taro" and tell it to him.

[1479] 1. The user enters "Taro"

[1480] The user enters "Taro" in the application's input field and presses the generate button.

[1481] 2. Submitting a Request

[1482] The device sends data including the name "Taro" to the server using HTTPS.

[1483] 3. Processing on the Server

[1484] The server receives the request and authenticates the user. If authentication is successful, it instructs the generative AI to generate a story with "Taro" as the main character.

[1485] 4. Story Generation

[1486] Generative AI generates stories such as "Taro goes on an adventure in the forest," which are a combination of specific templates and random elements.

[1487] 5. Sending and displaying results

[1488] The server formats the generated story into JSON format and sends it to the device, which parses the story and displays it in the UI.

[1489] 6. Reading and User Interaction

[1490] The device uses a text-to-speech tool to read the story aloud, and the user can tap the screen to go to the next page or stop reading.

[1491] This invention allows users to create a different story every day using their child's name and easily read it to them, which can keep the child interested while reducing the burden on parents.

[1492] The processing flow will be explained below.

[1493] Step 1:

[1494] The user enters the child's name "Taro" into the input field on the device. The user presses the "Generate" button.

[1495] Step 2:

[1496] The device prepares request data including the input name "Taro." This request data also includes authentication information such as the user ID and session ID. The device sends a POST request to the server using the HTTPS protocol.

[1497] Step 3:

[1498] The server receives a POST request from the device, verifies the authentication information in the request, and verifies that the user has valid permissions.

[1499] Step 4:

[1500] After the server verifies it, it passes the received data, including the name "Taro," to the generative AI and requests it to generate a story.

[1501] Step 5:

[1502] Based on the data received, the generative AI generates a story with the name "Taro" as the main character. For example, it might generate a story about Taro's adventures in a magical forest. This story is created by combining random elements and predefined templates.

[1503] Step 6:

[1504] The generated story is temporarily stored on the server in text or JSON format, and the server formats this data in a format suitable for the user, adding images and audio data if necessary.

[1505] Step 7:

[1506] The server sends the formatted story to the device as response data, which includes the story text, the creation date and time, and other metadata.

[1507] Step 8:

[1508] The device analyzes the story received from the server and prepares it for display on the user interface (UI).

[1509] Step 9:

[1510] The device launches a speech synthesis tool to read the displayed story aloud. The device provides the user with the option to start reading the story aloud.

[1511] Step 10:

[1512] The user uses the device to read the generated story to the child, tapping the screen as needed to advance to the next page or stop reading.

[1513] Example 1

[1514] Next, a description will be given of Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the robot 414 will be referred to as a "terminal."

[1515] In recent years, there has been a growing demand for systems with educational value that promote parent-child communication and foster children's creativity. However, existing systems have issues with difficulty in generating stories tailored to individual children's names and characteristics, and have complex operation and low usability. Furthermore, there is a lack of systems that allow users to enjoy the generated stories both visually and aurally. The purpose of this invention is to solve these issues and realize easy and personalized story generation and playback.

[1516] The specific processing by the specific processing unit 290 of the data processing device 12 in the first embodiment is realized by the following means.

[1517] In this invention, the server includes input means for inputting a child's name, transmission means for transmitting the child's name input via the input means to the server, authentication means for authenticating a user based on the child's name and authentication information received by the server via the transmission means, generation means for generating a story using generative artificial intelligence based on the information authenticated by the authentication means, transmission means for formatting the story generated by the generation means into JSON format or text format and transmitting it to a terminal, display means for the terminal to analyze the story received via the transmission means and display it on a user interface, and speech synthesis means for the terminal to read the story aloud. This makes it possible to generate personalized stories based on each child's name and easily display and read them aloud.

[1518] "Child Name" is the identifying name of a particular child that the user provides to the system via an input means.

[1519] "Input means" refers to the interface through which the user inputs the child's name, and includes a keyboard and a touch screen.

[1520] The "transmission means" is a communication interface for transmitting data input via the input means to a server, and includes a secure data transfer means such as the HTTPS protocol.

[1521] "Server" refers to a processing device that performs authentication and story generation based on received data.

[1522] The "authentication means" is a means for verifying the user based on authentication information such as the user ID and session ID received by the server, and authenticating the request as legitimate.

[1523] The "generation means" is a means for generating a personalized story based on a child's name using generative artificial intelligence.

[1524] "Generative AI" is an AI model that has the ability to generate new content based on prompts provided by users.

[1525] The "transmission means" is a communication interface for arranging the story generated by the generation means into an appropriate format and transmitting it to a terminal.

[1526] "Terminal" refers to a device operated by a user, including a smartphone or tablet.

[1527] The "display means" is a means for displaying the story received by the terminal from the server on a user interface.

[1528] "Analysis" refers to the process of interpreting received data based on a predetermined format and displaying it in a form that is easy for the user to understand.

[1529] The "voice synthesis means" is a processing device or software that converts the displayed story content into voice and reads it out loud.

[1530] "JSON format" is an abbreviation for JavaScript Object Notation, and is a lightweight data format widely used as a data exchange format.

[1531] "Text format" refers to a format that refers to character-based data, and includes simple text files such as INI files.

[1532] This invention relates to a system in which a user inputs their child's name, and based on that, a server uses generative artificial intelligence (generative AI model) to generate a story, which is then displayed and read aloud on the terminal.

[1533] System configuration

[1534] The system includes the following components:

[1535] 1. An input method for entering a child's name

[1536] The user enters the child's name through the smartphone or tablet interface, for example, "Taro" using the touch keyboard.

[1537] 2. Transmission method for transmitting input data

[1538] The device sends the entered data, including the name "Taro," to the server using HTTPS, a secure communication protocol.

[1539] 3. Authentication method to receive and authenticate requests

[1540] The server receives the request from the terminal and verifies that the user is a valid user based on the user ID and session ID. If the user authentication is successful, it proceeds to the next step.

[1541] 4. A method for generating stories using generative artificial intelligence

[1542] After authentication, the server sends a prompt to the generative AI model. For example, it might say, "Please generate an adventure story with Taro as the main character." Based on this, the generative AI model generates a personalized story with the name "Taro" as the main character.

[1543] 5. A means of sending the generated stories in the appropriate format.

[1544] The server formats the generated story in JSON or text format and sends it to the device, sometimes with the creation date and time and other metadata.

[1545] 6. Display method for analyzing and displaying the story

[1546] The device analyzes the story received from the server and displays it on the user interface. The story may contain not only text but also illustrations and sound effects.

[1547] 7. A speech synthesis method to read a story aloud

[1548] The device will read the story aloud using a speech synthesis tool (such as Google Text-to-Speech or Amazon Polly), making it easier for users to read stories to their children.

[1549] Specific examples

[1550] scenario

[1551] Suppose a user wants to create a new story for a child named "Taro" and play it. Here is a concrete example:

[1552] 1. The user enters "Taro"

[1553] The user enters "Taro" in the input field of the smartphone application and presses the generate button.

[1554] 2. Submitting a Request

[1555] The device sends data including the name "Taro" to the server using HTTPS.

[1556] 3. Processing on the Server

[1557] The server receives the request and authenticates the user. If authentication is successful, it instructs the generative AI to generate a story with "Taro" as the main character.

[1558] 4. Story Generation

[1559] A generative AI model generates stories such as "Taro goes on an adventure in the forest," which are a combination of specific templates and random elements.

[1560] 5. Sending and displaying results

[1561] The server formats the generated story into JSON format and sends it to the device, which parses the story and displays it in the user interface.

[1562] 6. Reading and User Interaction

[1563] The device uses a text-to-speech tool to read the story aloud, and the user can tap the screen to go to the next page or stop reading.

[1564] With the above configuration, it is possible to easily generate, display, and read out a personalized story based on the child's name.

[1565] The flow of the identification process in the first embodiment will be described with reference to FIG.

[1566] Program processing flow

[1567] The processing flow of this system's program will be explained in the following steps. At each step, data processing and data calculation based on input and output will also be explained.

[1568] Step 1:

[1569] User enters child's name

[1570] Specific operation: The user enters a child's name into the input field on a smartphone or tablet. For example, they enter "Taro" and press the "Generate" button.

[1571] Input: The name "Taro" entered by the user.

[1572] Output: Request data including the input name "Taro".

[1573] Step 2:

[1574] The device sends the input data to the server

[1575] Specific operation: The device sends data containing "Taro" to the server using the HTTPS protocol.

[1576] Input: Request data (including the child's name "Taro").

[1577] Output: The request data sent to the server.

[1578] Step 3:

[1579] The server receives the request and authenticates the user

[1580] Specific operation: The server analyzes the request received from the terminal and authenticates the user ID and session ID by checking them against the database.

[1581] Input: Received request data (child's name "Taro", user ID, session ID).

[1582] Output: Authentication result (success / failure).

[1583] Step 4:

[1584] The server instructs the generative AI to generate a story.

[1585] Specific operation: After the server successfully authenticates, it sends a prompt to the generation AI model: "Please generate an adventure story with Taro as the main character."

[1586] Input: Request data and prompt for a successfully authenticated user.

[1587] Output: The story generated by the generative AI model.

[1588] Step 5:

[1589] The server formats the generated story and sends it to the device.

[1590] Specific operation: The server formats the generated story into JSON or text format, adds the creation date and time and metadata, and sends it to the device.

[1591] Input: The story returned by the generative AI model.

[1592] Output: Formatted story data (JSON or text format).

[1593] Step 6:

[1594] The device analyzes and displays the received story.

[1595] Specific behavior: The device analyzes the received story data and displays it on the user interface, which may include text, illustrations, sound effects, etc.

[1596] Input: Formatted story data received from the server.

[1597] Output: The story displayed in the user interface.

[1598] Step 7:

[1599] Your device will read the story aloud

[1600] What it does: The device uses a speech synthesis tool to read the story aloud, and the user can play, pause, and turn pages.

[1601] Input: Parsed story data.

[1602] Output: The story read aloud.

[1603] Example prompt

[1604] "Generate an adventure story with Taro as the main character."

[1605] (Application example 1)

[1606] Next, a description will be given of Application Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the robot 414 will be referred to as a "terminal."

[1607] Previous story generation systems were limited to generating personalized stories based on the user's child's name, and lacked picture books and other reading materials that users could enjoy interactively with their children in a virtual environment. Furthermore, the reading function was often limited to simple audio reading, and was unable to provide a holistic, interactive experience.

[1608] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 1 is realized by the following means.

[1609] In this invention, the server includes an input means for inputting a child's name, a transmission means for transmitting the child's name input via the input means to the server, and a generation means for generating a story by using a generative artificial intelligence based on the child's name received by the server via the transmission means. This enables the user to provide an interactive picture book or reading material in a virtual environment using the child's name, allowing the user to share a sense of unity with the child.

[1610] "Child's name" refers to the unique name of a particular child that the user enters into the terminal.

[1611] "Input means" refers to the device or interface that the user uses to input the child's name.

[1612] "Transmission means" refers to the function or protocol used to transmit the entered child's name to the server.

[1613] "Generation means" refers to the function or algorithm that uses generative artificial intelligence to generate a story based on the received child's name.

[1614] "Device" refers to an electronic device used by a user, such as a smartphone or tablet device.

[1615] "Display means" refers to the function of visually displaying the generated story on the terminal screen.

[1616] "Audio output means" refers to a function or device for reading aloud the displayed story.

[1617] "Virtual environment" refers to a computer-generated space or scenario that a user can experience virtually through electronic devices.

[1618] "Interactive reading material" refers to stories or content that change dynamically in response to user actions.

[1619] "Implementation" refers to the software and hardware configuration for providing interactive storybooks and reading materials within a virtual environment.

[1620] "Generative artificial intelligence" refers to machine learning or deep learning models that generate new content based on provided input data.

[1621] This invention relates to a system that provides interactive reading material in a virtual environment based on a child's name. A user inputs the child's name using a terminal, and the information is sent to a server. The server uses generative artificial intelligence to generate a story incorporating the child's name and sends the generated story to the terminal. The terminal can display the story and read it aloud using audio output means.

[1622] Details of the hardware and software used

[1623] 1. User devices: Primarily smartphones and tablets are used. These devices run applications built using React Native.

[1624] 2. Server: Built using Node.js and the Express framework. The database uses MongoDB, and the generative AI uses OpenAI's GPT-4 API.

[1625] 3. Audio output method: The Google Cloud Text-to-Speech API is used to read the story aloud on the device.

[1626] Program processing and data calculation

[1627] The server receives the child's name sent from the user's device and uses it to instruct the generative AI to generate a story. The generated story is formatted in JSON format and sent back to the user's device. The user's device analyzes the story and displays it visually through a display device. The story is then read aloud using the Google Cloud Text-to-Speech API.

[1628] Examples and prompts

[1629] Examples:

[1630] When a user inputs "Sachiko" as the child's name, an "adventure story of Sachiko exploring a mysterious forest" is generated based on that name. The generated story is displayed in the virtual environment and read aloud using a voice output means.

[1631] Example prompt sentence:

[1632] "Generate a story in which the main character is Sachiko, who goes on an adventure in a mysterious forest where she encounters many different animals."

[1633] This invention allows users to create their own interactive stories in a virtual environment using their child's name, making the storytelling experience more immersive and helping to keep children engaged.

[1634] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[1635] Step 1:

[1636] The user enters the child's name.

[1637] Specifically, the user launches the application on their smartphone or tablet and enters their child's name (e.g., "Sachiko") in the name input field. Input data (child's name) is generated.

[1638] Step 2:

[1639] The terminal sends the entered name to the server.

[1640] Specifically, the device securely sends data, including the child's name, to the server using the HTTPS protocol. The data also includes the user ID and session ID. Data to be sent is generated, including the input data (child's name).

[1641] Step 3:

[1642] The server receives the request and authenticates the user.

[1643] Specifically, the server receives a request from the terminal and performs authentication based on the user ID and session ID in the transmitted data. If authentication is successful, it proceeds to the next step. The input data is the user's authentication information, and the output data is the authentication result.

[1644] Step 4:

[1645] The server instructs the generative artificial intelligence to generate a story.

[1646] Specifically, the server creates a prompt and requests the generative artificial intelligence (GPT-4) to generate a story. An example of a prompt is, "Please generate a story in which the main character is Sachiko. Sachiko goes on an adventure in a mysterious forest, encountering many different animals." The input data is the prompt, and the output data is the generated story.

[1647] Step 5:

[1648] The server formats the generated story into JSON format and sends it to the device.

[1649] Specifically, the server converts the story obtained from the generative AI into an appropriate format (JSON format) and sends it to the terminal again via the HTTPS protocol. The input data is the generated story, and the output data is a story in JSON format.

[1650] Step 6:

[1651] The device analyzes the received story and displays it on the screen.

[1652] Specifically, the device parses the JSON-formatted story received from the server and displays the story on the screen. The input data is the JSON-formatted story, and the output data is the story displayed on the screen.

[1653] Step 7:

[1654] The device will read the story aloud.

[1655] Specifically, the device uses the Google Cloud Text-to-Speech API to convert the displayed story into audio and read it out through the speaker. The input data is the text story, and the output data is the audio story.

[1656] Furthermore, an emotion engine that estimates the user's emotion may be further combined. That is, the identification processing unit 290 may estimate the user's emotion using the emotion identification model 59, and perform identification processing using the user's emotion.

[1657] This invention combines a system in which a user inputs their child's name, and a server uses generative artificial intelligence to generate a story based on that, and displays and reads it out loud on the terminal, with an emotion engine that recognizes the user's emotions. Below, we will explain the specific program processing in natural language, using concrete examples.

[1658] System configuration

[1659] 1. Enter your child's name

[1660] The user enters the child's name into an input field on the device, for example, "Taro" on the application screen of a smartphone or tablet.

[1661] 2. Sending input data

[1662] The device sends the entered data, including the name "Taro," to the server. Here, the data is sent securely using the HTTPS protocol.

[1663] 3. Receiving and Authenticating a Request

[1664] The server receives a request from the device. This request includes the child's name "Taro" and authentication information such as the user ID and session ID. The server authenticates the user based on this information and verifies that the request is legitimate.

[1665] 4. Story Generation

[1666] After authentication, the server instructs the generative AI to generate a story. The generative AI generates a personalized story with a protagonist named "Taro." This story is generated by combining unique templates and random elements.

[1667] 5. Recognizing and reflecting emotions

[1668] The emotion engine uses the device's camera and microphone to recognize the user's emotions in real time. The emotion recognition results are temporarily stored on the device and sent to a server, or used directly when reading out the text.

[1669] 6. Formatting and sending the generated results

[1670] The server formats the generated story and sends it to the device in JSON or text format, and may also include the date and time of creation and other metadata along with the story.

[1671] 7. Viewing Stories

[1672] The device analyzes the story received from the server and displays it on the user interface (UI). The story may not only consist of text, but may also include illustrations and sound effects.

[1673] 8. Voice reading and adjustment

[1674] The device activates a speech synthesis tool to read the story aloud, adjusting the reading speed and intonation based on the user's emotional information as recognized by the emotion engine.

[1675] Specific examples

[1676] scenario:

[1677] Suppose a user wants to create a new story for a child named "Taro" and tell it to him.

[1678] 1. The user enters "Taro"

[1679] The user enters "Taro" in the application's input field and presses the generate button.

[1680] 2. Submitting a Request

[1681] The device sends data including the name "Taro" to the server using HTTPS.

[1682] 3. Processing on the Server

[1683] The server receives the request and authenticates the user. If authentication is successful, it instructs the generative AI to generate a story with "Taro" as the main character.

[1684] 4. Story Generation

[1685] A generative AI generates a story, such as "Taro goes on an adventure in a magical forest," that combines specific templates and random elements.

[1686] 5. Recognizing and reflecting emotions

[1687] While the user is reading the story, the emotion engine analyzes the user's facial expressions and tone of voice through the device's camera and microphone, and recognizes the user's emotions in real time, such as whether they are enjoying themselves or excited. This information is sent to the server.

[1688] 6. Formatting and Displaying the Story

[1689] The server formats the generated story into JSON format and sends it to the device, which parses the story and displays it in the UI.

[1690] 7. Read aloud

[1691] The device uses a speech synthesis tool to read the story aloud, dynamically adjusting the reading speed and intonation based on the user's emotions as recognized by an emotion engine.

[1692] 8. User Operations

[1693] The user reads the generated story to the child using the device, and the emotion engine adjusts the story to make it more engaging and maintain the child's interest.

[1694] This invention allows users to create a different story each day using their child's name and utilizes emotion recognition to provide a more personalized reading experience, keeping children engaged and reducing the burden on parents.

[1695] The processing flow will be explained below.

[1696] Step 1:

[1697] The user enters the child's name "Taro" into the input field on the terminal and presses the "Generate" button. The terminal receives this input and proceeds to the next step.

[1698] Step 2:

[1699] The terminal prepares request data including the input name "Taro" and authentication information such as user ID and session ID. The terminal sends this data to the server as a POST request using the HTTPS protocol.

[1700] Step 3:

[1701] The server receives a POST request from the device, verifies the authentication information in the request, and verifies that the user has valid permissions.

[1702] Step 4:

[1703] After the server authenticates, it passes the received name "Taro" to the generative AI and requests a story to be generated.

[1704] Step 5:

[1705] A generative AI generates a story based on the name "Taro." For example, it generates a story about "Taro's adventure in a magical forest." This story is created by combining random elements and templates.

[1706] Step 6:

[1707] The emotion engine recognizes the user's emotions in real time using the device's camera and microphone. The device temporarily stores the emotion recognition results and sends them to the server as needed.

[1708] Step 7:

[1709] The server receives the generated stories and formats them appropriately. The formatted data includes the story text, the creation date and time, and other metadata.

[1710] Step 8:

[1711] The server sends the formatted story to the device, which receives the story as response data.

[1712] Step 9:

[1713] The device parses the received story and prepares it for display in the user interface (UI). The story may contain text, images, and sound effects.

[1714] Step 10:

[1715] The device activates a speech synthesis tool to read the story aloud, adjusting the reading speed and intonation based on the user's emotional information as recognized by the emotion engine.

[1716] Step 11:

[1717] The user reads the generated story to the child using the device, and the story is adjusted appropriately according to the user's emotions to keep the child interested.

[1718] Step 12:

[1719] Users can tap the device screen to advance to the next page or stop reading as needed.

[1720] In this way, users can utilize emotion recognition to generate personalized stories based on their child's name, providing a more interactive storytelling experience.

[1721] Example 2

[1722] Next, a description will be given of Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the robot 414 will be referred to as a "terminal."

[1723] Conventional story generation systems can generate personalized stories simply by entering a user's name, but they lack the ability to reflect the user's emotions, meaning that the story cannot be read aloud in real time according to the user's emotions. This also reduces the quality of the user experience, making it difficult for children to maintain their interest in the story.

[1724] The identification process by the identification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means. In this invention, the server includes an input means for inputting the child's name, a transmission means for transmitting the child's name input via the input means to the server, a generation means for generating a story using a generative model based on the child's name received by the server via the transmission means, and a transmission means for shaping the story generated by the generation means into an appropriate format and transmitting it to the terminal. This makes it possible to adjust the reading speed and intonation of the generated story in real time according to the user's emotions.

[1725] An "input means for inputting a child's name" is a device or interface that a user uses to input a child's name.

[1726] The "transmission means" refers to a protocol or device for transmitting the child's name input via the input means to a server and performing data communication.

[1727] The "generation means for generating a story using a generative model" is a system or software for automatically generating a story using an artificial intelligence model based on the received child's name.

[1728] The "transmission means for converting the story into an appropriate format and transmitting it to the terminal" is a system or device for converting the generated story into a format that can be interpreted by the terminal and transmitting the content to the terminal.

[1729] The "display means" is a screen or display that visually displays the story received by the terminal to the user.

[1730] The "recognition means for recognizing a user's emotions using an emotion engine" is a system or software for analyzing and recognizing emotions from a user's facial expressions and tone of voice using devices such as a camera and a microphone.

[1731] An "adjustment means" is a system or software for dynamically changing the reading rate or intonation based on the recognized emotional information.

[1732] "A speech synthesis means for reading aloud" is a system or software for converting a displayed story from text to speech and reading it aloud.

[1733] A "personal digital assistant" is a portable computing device such as a smartphone or tablet.

[1734] An "application" refers to a software program that runs on the terminal and that the user operates to input data or view stories.

[1735] This invention combines a system in which a user inputs the name of their child, and a server uses generative artificial intelligence to generate a story based on that, and displays and reads it out loud on the terminal, with an emotion engine that recognizes the user's emotions. Specific embodiments for carrying out this invention are described below.

[1736] System configuration

[1737] Enter your child's name

[1738] The user enters the child's name into the application screen on the smartphone or tablet. The application provides an input field on the screen to receive the child's name. For example, the user enters "Taro."

[1739] Sending input data

[1740] The device sends the entered name "Taro" to the server using the HTTPS protocol. The sent data also includes the user ID and session ID, ensuring secure data transfer.

[1741] Receiving and authenticating requests

[1742] The server receives a request from the device. This request includes the child's name "Taro" and authentication information such as the user ID and session ID. The server authenticates the user based on this information and verifies that the request is valid.

[1743] Story Generation

[1744] After authentication, the server instructs a generative AI (e.g., GPT-3) to generate a story. The generative AI generates a personalized story with a protagonist named "Taro." This story is generated by combining unique templates and random elements.

[1745] Recognizing and reflecting emotions

[1746] The emotion engine uses the device's camera and microphone to recognize the user's emotions in real time. The emotion recognition results are temporarily stored on the device and sent to a server, or used directly when reading out the text.

[1747] Formatting and sending the generated results

[1748] The server formats the generated story and sends it to the device in JSON or text format, and may also include the date and time of creation and other metadata along with the story.

[1749] Viewing Stories

[1750] The device analyzes the story received from the server and displays it on the user interface (UI). The story may not only consist of text, but may also include illustrations and sound effects.

[1751] Speech reading and adjustments

[1752] The device launches a speech synthesis tool (e.g., Google Text-to-Speech) to read the story aloud, adjusting the reading speed and intonation based on the user's emotional information as recognized by the emotion engine.

[1753] Specific examples

[1754] scenario

[1755] Suppose a user wants to create a new story for a child named "Taro" and tell it to him.

[1756] 1. The user enters "Taro"

[1757] The user enters "Taro" in the application's input field and presses the generate button.

[1758] 2. Submitting a Request

[1759] The device sends data including the name "Taro" to the server using HTTPS.

[1760] 3. Processing on the Server

[1761] The server receives the request and authenticates the user. If authentication is successful, it instructs the generative AI to generate a story with "Taro" as the main character.

[1762] 4. Story Generation

[1763] A generative AI generates a story, such as "Taro goes on an adventure in a magical forest," that combines specific templates and random elements.

[1764] 5. Recognizing and reflecting emotions

[1765] While the user is reading the story, the emotion engine analyzes the user's facial expressions and tone of voice through the device's camera and microphone, and recognizes the user's emotions in real time, such as whether they are enjoying themselves or excited. This information is sent to the server.

[1766] 6. Formatting and Displaying the Story

[1767] The server formats the generated story into JSON format and sends it to the device, which parses the story and displays it in the UI.

[1768] 7. Read aloud

[1769] The device uses a speech synthesis tool to read the story aloud, dynamically adjusting the reading speed and intonation based on the user's emotions as recognized by an emotion engine.

[1770] Prompt Sentence Examples

[1771] "To generate an adventure story for children, please create a story that meets the following conditions: The main character's name should be 'Taro' and the story should include his adventures in a magical forest."

[1772] This invention allows users to create a different story each day using their child's name and utilizes emotion recognition to provide a more personalized reading experience, keeping children engaged and reducing the burden on parents.

[1773] The flow of the identification process in the second embodiment will be described with reference to FIG.

[1774] Step 1:

[1775] User enters child's name

[1776] Specific behavior:

[1777] The user enters the child's name "Taro" into the application screen on their smartphone or tablet and presses the "Generate" button.

[1778] input:

[1779] Child's name: Taro

[1780] output:

[1781] Name "Taro" stored on the device

[1782] Step 2:

[1783] The device sends the input data to the server

[1784] Specific behavior:

[1785] The device uses the HTTPS protocol to send the child's name "Taro", the user ID, and the session ID to the server.

[1786] input:

[1787] Name "Taro", User ID, Session ID

[1788] output:

[1789] Request data sent to the server

[1790] Step 3:

[1791] The server receives the request and authenticates the user

[1792] Specific behavior:

[1793] The server analyzes the request data received and performs user authentication based on the user ID and session ID. It checks whether the authentication information is correct.

[1794] input:

[1795] Request data (name "Taro", user ID, session ID)

[1796] output:

[1797] Authentication success or failure flag

[1798] Step 4:

[1799] The server directs the creation of the story

[1800] Specific behavior:

[1801] If user authentication is successful, the server sends a prompt to the generative AI model (e.g., GPT-3) to instruct it to generate a story.

[1802] input:

[1803] Authentication successful, prompt: "To generate an adventure story for children, please create a story that meets the following conditions. The main character's name should be 'Taro' and include his adventures in a magical forest."

[1804] output:

[1805] Generated Stories

[1806] Step 5:

[1807] Emotion engine recognizes user emotions

[1808] Specific behavior:

[1809] The device uses the built-in camera and microphone to analyze the user's facial expressions and tone of voice, and the results are temporarily saved.

[1810] input:

[1811] User facial expression data, tone of voice data

[1812] output:

[1813] Recognized emotion data

[1814] Step 6:

[1815] The server sends the generated stories

[1816] Specific behavior:

[1817] The server formats the generated story into an appropriate format (such as JSON) and sends it to the device.

[1818] input:

[1819] Generated Stories

[1820] output:

[1821] Story in JSON data format sent to the device

[1822] Step 7:

[1823] Your device will display the story

[1824] Specific behavior:

[1825] The device parses the received JSON data and displays the story on the user's interface (UI).

[1826] input:

[1827] JSON data format story

[1828] output:

[1829] Story displayed in the UI

[1830] Step 8:

[1831] Your device will read the story aloud

[1832] Specific behavior:

[1833] The device uses a speech synthesis tool (e.g., Google Text-to-Speech) to read the story aloud, adjusting the reading speed and intonation based on the user's emotional information as recognized by the emotion engine.

[1834] input:

[1835] Displayed story, recognized emotion data

[1836] output:

[1837] Read-aloud stories

[1838] (Application example 2)

[1839] Next, a description will be given of Application Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the robot 414 will be referred to as a "terminal."

[1840] Conventional story generation systems have difficulty sustaining children's interest because the generated stories are read aloud in the same tone and speed consistently. Additionally, they are unable to take the user's emotions into account when reading a story, making it difficult to provide a personalized experience.

[1841] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 2 is realized by the following means.

[1842] In this invention, the server includes input means for inputting the child's name, transmission means for transmitting the child's name input via the input means to the server, generation means for the server to generate a story using generative artificial intelligence based on the child's name received via the transmission means, transmission means for transmitting the story generated by the generation means to a terminal, display means for the terminal to display the story received via the transmission means, emotion recognition means for recognizing the user's emotion in real time using the camera and microphone of the terminal, and voice adjustment means for controlling the voice reading of the story based on the emotion recognized by the emotion recognition means. This allows for reading that is dynamically adjusted in response to the user's emotion, enabling a more interesting and personalized story experience.

[1843] An "input means" is a means by which a user inputs a child's name, including, for example, a keyboard or input field displayed on the screen of a mobile device.

[1844] The "transmission means" is a means for transmitting the child's name and other data entered via the input means to the server, using a secure communication protocol (e.g., HTTPS).

[1845] The "generation means" is a means for generating a story using generative artificial intelligence based on the child's name received by the server, and includes an algorithm for constructing a story by combining specific templates and random elements.

[1846] The "display means" is a means for displaying the story sent from the server to the user on the terminal, and provides an interface including text, graphics, and in some cases sound effects.

[1847] The "emotion recognition means" is a means for analyzing the user's facial expressions and tone of voice using the camera and microphone of the terminal, and recognizing the user's emotions in real time.

[1848] The "voice adjustment means" is a means for controlling the reading of the story aloud based on the user's emotional information recognized by the emotion recognition means, and includes an algorithm for adjusting the reading speed and intonation.

[1849] "Mobile device" refers to a device that can be carried by a user, including, for example, a smartphone or tablet terminal.

[1850] "Generative AI" is AI that has the ability to learn large amounts of data and generate new information and content, such as a type of text generation model.

[1851] This invention is a system that uses generative artificial intelligence to generate a story based on a child's name, and then displays and reads the story on a terminal. Furthermore, it adds functionality to recognize the user's emotions in real time and adjust the reading speed, intonation, etc. The specific configuration and operation of the system are described below.

[1852] Hardware and Software Configuration

[1853] This system mainly consists of the following hardware and software:

[1854] Mobile devices: Smartphones and tablets that users can carry around with them.

[1855] Server: Responsible for receiving and processing data and running generative artificial intelligence.

[1856] Camera and microphone: Built into the user device to collect data for emotion recognition.

[1857] Input method: On-screen keyboard or input field on the mobile device.

[1858] Transmission method: Data is sent to the server using the HTTPS protocol.

[1859] Generative AI: For example, OpenAI's GPT-3 has the ability to learn from large amounts of data and generate new information and content.

[1860] Emotion recognition methods: For example, Microsoft Azure Emotion API, which analyzes facial expressions and tone of voice.

[1861] Speech synthesis and adaptation methods, including Google Cloud Text-to-Speech, which adjusts speaking rate and intonation based on user emotion.

[1862] System Operation

[1863] Personalized Story Generation

[1864] 1. User enters child's name

[1865] The user enters the child's name in the input field displayed on the mobile device, for example, "Taro," and taps the submit button.

[1866] 2. Data transmission

[1867] The mobile device sends the entered name "Taro" to the server using the HTTPS protocol.

[1868] 3. Processing on the Server

[1869] The server receives the request, authenticates the user, and then instructs the generative AI to generate a story based on the name "Taro." The generative AI generates a story such as "Taro goes on an adventure in a magical forest."

[1870] 4. Submitting and Viewing Stories

[1871] The server formats the generated story into JSON format and sends it to the mobile device, which receives the story and displays it in the UI.

[1872] Emotion recognition and speech-to-speech adjustment

[1873] 5. Emotional Recognition

[1874] Using the mobile device's built-in camera and microphone, the emotion recognition method analyzes the user's facial expressions and tone of voice, thereby recognizing the user's emotions (e.g., joy, excitement) in real time.

[1875] 6. Adjust reading

[1876] Based on the recognized emotional information, speech synthesis and adjustment methods adjust the reading speed and intonation to read the story aloud in a more personalized way.

[1877] Specific examples

[1878] The user launches the app, enters their child's name as "Taro," and submits.

[1879] The device sends data containing "Taro" to the server using HTTPS.

[1880] The server uses generative artificial intelligence to generate a story about Taro's adventures in a magical forest and sends it back to the device.

[1881] The device displays the story and uses the camera and microphone to recognize the user's emotions in real time.

[1882] Based on the recognized emotion, the speech synthesis tool adjusts the reading speed and intonation.

[1883] Example prompts to input to the generative AI model

[1884] "The child's name is Taro. Please generate a fun adventure story starring Taro. Specifically, please make it about Taro having a wonderful adventure in a magical forest."

[1885] As described above, this system enables dynamically adjusted reading based on the user's emotions, providing a personalized story experience.

[1886] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[1887] Step 1:

[1888] The user launches the application on their mobile device and enters their child's name into the input field. The input is exemplified as "Taro." The user taps the "Submit" button.

[1889] Input: Child's name (e.g. "Taro")

[1890] Output: Prepare input data for sending

[1891] Step 2:

[1892] The device sends the entered data, including the name "Taro," to the server using the HTTPS protocol, along with authentication information such as the user ID and session ID.

[1893] Input: Input data (child's name "Taro"), authentication information

[1894] Output: Request sent to server

[1895] Step 3:

[1896] The server receives the request from the device, verifies the authentication information, and if authentication is successful, instructs the generative AI to generate a story.

[1897] Input: Request data (child's name "Taro", authentication information)

[1898] Output: Story generation instructions for generative AI

[1899] Step 4:

[1900] The generative AI generates a story based on the input name "Taro." This story is constructed by combining specific templates and random elements. For example, it generates content such as "Taro goes on an adventure in a magical forest."

[1901] Input: Child's name ("Taro")

[1902] Output: The generated story (e.g. "Taro goes on an adventure in the magical forest")

[1903] Step 5:

[1904] The server formats the generated story into JSON format, adds the creation date and time and other metadata, and sends it to the device.

[1905] Input: Generated stories

[1906] Output: Formatted story (JSON format)

[1907] Step 6:

[1908] The device analyzes the story received from the server and displays it on the user interface (UI). The story may not only consist of text, but may also include illustrations and sound effects.

[1909] Input: JSON formatted story

[1910] Output: Generate data for display

[1911] Step 7:

[1912] The device's camera and microphone are used to recognize the user's emotions in real time. The emotion recognition means analyzes the user's facial expressions and tone of voice to determine whether the user is enjoying themselves or feeling excited.

[1913] Input: Camera video, microphone audio

[1914] Output: Recognized emotion data

[1915] Step 8:

[1916] The device uses a voice synthesis tool to read the story aloud, adjusting the reading speed and intonation based on the user's emotional information recognized by the emotion recognition means.

[1917] Input: Story text, recognized emotion data

[1918] Output: Emotionally adjusted speech

[1919] Through these steps, the system can dynamically adjust reading to respond to the user's emotions, providing a more engaging and personalized story experience.

[1920] The specific processing unit 290 transmits the result of the specific processing to the robot 414. In the robot 414, the control unit 46A causes the speaker 240 and the control target 443 to output the result of the specific processing. The microphone 238 acquires voice indicating a user input regarding the result of the specific processing. The control unit 46A transmits voice data indicating the user input acquired by the microphone 238 to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the voice data.

[1921] The data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of the data generation model 58 is ChatGPT (Internet Search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search <url: https: gemini.google.com ?hl="ja">) and other generation AIs. The data generation model 58 is obtained by performing deep learning on a neural network. A prompt including an instruction is input to the data generation model 58, and inference data such as voice data indicating voice, text data indicating text, and image data indicating an image is also input. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt, and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[1922] In the above embodiment, an example was given in which the specific processing is performed by the data processing device 12, but the technology of the present disclosure is not limited to this, and the specific processing may be performed by the robot 414.

[1923] The emotion identification model 59 as an emotion engine may determine the user's emotion according to a specific mapping. Specifically, the emotion identification model 59 may determine the user's emotion according to an emotion map (see FIG. 9), which is a specific mapping. Similarly, the emotion identification model 59 may determine the robot's emotion, and the identification processing unit 290 may perform identification processing using the robot's emotion.

[1924] FIG. 9 is a diagram illustrating an emotion map 400 on which multiple emotions are mapped. In the emotion map 400, emotions are arranged in concentric circles radiating from the center. Emotions closer to the center of the concentric circles are more primitive. Emotions representing states and actions arising from a state of mind are arranged on the outer edges of the concentric circles. The concept of emotion includes both affect and mental states. Emotions generally generated from reactions occurring in the brain are arranged on the left side of the concentric circles. Emotions generally induced by situational judgment are arranged on the right side of the concentric circles. Emotions generally generated from reactions occurring in the brain and induced by situational judgment are arranged on the upper and lower sides of the concentric circles. Furthermore, the emotion of "pleasure" is arranged on the upper side of the concentric circles, and the emotion of "discomfort" is arranged on the lower side. In this way, in the emotion map 400, multiple emotions are mapped based on the structure by which emotions are generated, and emotions that tend to occur simultaneously are mapped close to each other.

[1925] These emotions are distributed in the 3 o'clock direction on emotion map 400, and typically fluctuate between relief and anxiety. In the right half of emotion map 400, situational awareness dominates over internal sensations, resulting in a sense of calm.

[1926] The inside of emotion map 400 represents what is going on in the mind, and the outside of emotion map 400 represents behavior, so the further you go outside emotion map 400, the more visible the emotions become (the more they are expressed in behavior).

[1927] Human emotions are based on various balances, such as posture and blood sugar levels. When these balances deviate from the ideal, a state of discomfort is indicated, and when they approach the ideal, a state of pleasure is indicated. Emotions can also be created for robots, automobiles, and motorcycles, based on various balances, such as posture and remaining battery life. When these balances deviate from the ideal, a state of discomfort is indicated, and when they approach the ideal, a state of pleasure is indicated. An emotion map can be generated, for example, based on Dr. Mitsuyoshi's emotion map (Research on Voice Emotion Recognition and Emotional Brain Physiological Signal Analysis Systems, Tokushima University, Doctoral Dissertation: https: / / ci.nii.ac.jp / naid / 500000375379). The left half of the emotion map lists emotions belonging to the "reaction" domain, where sensation is dominant. The right half of the emotion map lists emotions belonging to the "situation" domain, where situational awareness is dominant.

[1928] The emotion map defines two emotions that promote learning. One is a negative emotion on the situation side, around the middle of "repentance" or "reflection." In other words, this occurs when the robot experiences negative emotions such as "I never want to feel this way again" or "I don't want to be scolded again." The other is a positive emotion on the response side, around "desire." In other words, this occurs when the robot experiences positive feelings such as "I want more" or "I want to know more."

[1929] The emotion identification model 59 inputs user input into a pre-trained neural network, obtains emotion values ​​indicating each emotion shown in the emotion map 400, and determines the user's emotion. This neural network is pre-trained based on multiple pieces of training data that are combinations of user input and emotion values ​​indicating each emotion shown in the emotion map 400. Furthermore, this neural network is trained so that emotions that are located close to each other have similar values, as in the emotion map 900 shown in FIG. 10. FIG. 10 shows an example in which multiple emotions, "relieved," "calm," and "reassuring," have similar emotion values.

[1930] The system according to the present disclosure has been described above mainly with respect to the functions of the data processing device 12, but the system according to the present disclosure is not necessarily implemented on a server. The system according to the present disclosure may be implemented as a general information processing system. The present disclosure may be implemented, for example, as a software program running on a personal computer or an application running on a smartphone, etc. The method according to the present disclosure may be provided to users in the form of SaaS (Software as a Service).

[1931] In the above embodiment, an example was given in which the specific processing is performed by one computer 22, but the technology of the present disclosure is not limited to this, and the specific processing may be distributed and performed by a plurality of computers including the computer 22. For example, the data generation model 58 may be provided in an external device of the data processing device 12, and data may be generated in the external device in accordance with input data.

[1932] In the above embodiment, an example in which the specific processing program 56 is stored in the storage 32 has been described, but the technology of the present disclosure is not limited to this. For example, the specific processing program 56 may be stored in a portable, computer-readable, non-transitory storage medium such as a USB (Universal Serial Bus) memory. The specific processing program 56 stored in the non-transitory storage medium is installed in the computer 22 of the data processing device 12. The processor 28 executes the specific processing in accordance with the specific processing program 56.

[1933] 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.

[1934] It is not necessary to store all of the specific processing program 56 in a storage device such as a server connected to the data processing device 12 via the network 54, or to store all of the specific processing program 56 in the storage 32; only a portion of the specific processing program 56 may be stored.

[1935] The hardware resource for executing a specific process can be any of the following processors: An example of a processor is a CPU, which is a general-purpose processor that functions as a hardware resource for executing a specific process by executing software, i.e., a program. Another example of a processor is a dedicated electrical circuit, such as an FPGA (Field-Programmable Gate Array), a PLD (Programmable Logic Device), or an ASIC (Application Specific Integrated Circuit), which is a processor with a circuit configuration designed specifically for executing a specific process. Each processor has built-in or connected memory, and each processor uses the memory to execute the specific process.

[1936] The hardware resource that executes the specific processing may be configured with one of these various processors, or may be configured with a combination of two or more processors of the same or different types (for example, a combination of multiple FPGAs, or a combination of a CPU and an FPGA). Also, the hardware resource that executes the specific processing may be a single processor.

[1937] As an example of a system configured with a single processor, first, one processor is configured by combining one or more CPUs and software, and this processor functions as a hardware resource that executes a specific process. Second, there is a system that uses a processor that realizes the functions of an entire system including multiple hardware resources that execute a specific process on a single IC chip, as typified by SoC (System-on-a-chip). In this way, a specific process is realized using one or more of the above-mentioned various processors as hardware resources.

[1938] Furthermore, the hardware structure of these various processors can be, more specifically, an electric circuit that combines circuit elements such as semiconductor devices. The specific processing described above is merely an example. Therefore, it goes without saying that unnecessary steps may be deleted, new steps may be added, or the processing order may be rearranged, without departing from the spirit of the invention.

[1939] The above-described description and illustrations are a detailed explanation of the parts related to the technology of the present disclosure and are merely an example of the technology of the present disclosure. For example, the above description of the configuration, functions, actions, and effects is an explanation of an example of the configuration, functions, actions, and effects of the parts related to the technology of the present disclosure. Therefore, it goes without saying that unnecessary parts may be deleted, new elements may be added, or replacements may be made to the above-described description and illustrations within the scope of the gist of the technology of the present disclosure. Furthermore, to avoid confusion and facilitate understanding of the parts related to the technology of the present disclosure, the above-described description and illustrations omit explanations of common technical knowledge that do not require particular explanation to enable the implementation of the technology of the present disclosure.

[1940] All publications, patent applications, and technical standards mentioned in this specification are herein incorporated by reference to the same extent as if each individual publication, patent application, or technical standard was specifically and individually indicated to be incorporated by reference.

[1941] The following is further disclosed regarding the above embodiment.

[1942] (Claim 1)

[1943] an input means for inputting the child's name;

[1944] a transmitting means for transmitting the child's name inputted via the input means to a server;

[1945] a generation means for generating a story by using a generative artificial intelligence based on the child's name received by the server via the transmission means;

[1946] a transmission means for transmitting the story generated by the generation means to a terminal;

[1947] a display means for displaying the story received by the terminal via the transmission means;

[1948] A system including:

[1949] (Claim 2)

[1950] 2. The system of claim 1, wherein said display means includes a voice synthesis means for reading said story aloud.

[1951] (Claim 3)

[1952] 2. The system according to claim 1, wherein the input means, transmission means, and display means are configured from an application executed on a smartphone or tablet terminal.

[1953] "Example 1"

[1954] (Claim 1)

[1955] an input means for inputting the child's name;

[1956] a transmitting means for transmitting the child's name inputted via the input means to a server;

[1957] an authentication means for authenticating a user based on the child's name and authentication information received by the server via the transmission means;

[1958] a generation means for generating a story using a generative artificial intelligence based on the information authenticated by the authentication means;

[1959] a transmission means for formatting the story generated by the generation means into a JSON format or a text format and transmitting the formatted story to a terminal;

[1960] a display means for analyzing the story received by the terminal via the transmission means and displaying the story on a user interface;

[1961] The system includes a voice synthesis means for the terminal to read the story aloud.

[1962] (Claim 2)

[1963] 2. The system according to claim 1, wherein the input means, transmission means, and display means are configured from an application executed on a smartphone or tablet terminal.

[1964] (Claim 3)

[1965] 10. The system of claim 1, wherein the story generation means includes a generative artificial intelligence for generating a personalized story based on an inputted child's name.

[1966] "Application Example 1"

[1967] (Claim 1)

[1968] an input means for inputting the child's name;

[1969] a transmitting means for transmitting the child's name inputted via the input means to a server;

[1970] a generation means for generating a story by using a generative artificial intelligence based on the child's name received by the server via the transmission means;

[1971] a transmission means for transmitting the story generated by the generation means to a terminal;

[1972] a display means for displaying the story received by the terminal via the transmission means;

[1973] a voice output means for reading out the story displayed on the display means;

[1974] Implementation means provided as interactive reading material within a virtual environment;

[1975] A system including:

[1976] (Claim 2)

[1977] 2. The system of claim 1, wherein said display means includes an audio output means for reading said story aloud.

[1978] (Claim 3)

[1979] 2. The system according to claim 1, wherein the input means, the transmission means, and the display means are configured by a program executed on an electronic device.

[1980] "Example 2: Combining Emotion Engines"

[1981] (Claim 1)

[1982] an input means for inputting the child's name;

[1983] a transmitting means for transmitting the child's name inputted via the input means to a server;

[1984] a generation means for generating a story by using a generative model based on the child's name received by the server via the transmission means;

[1985] a transmission means for arranging the story generated by the generation means into an appropriate format and transmitting the formatted story to a terminal;

[1986] a display means for displaying the story received by the terminal via the transmission means;

[1987] a recognition means for recognizing a user's emotion using an emotion engine built into the terminal;

[1988] an adjustment means for adjusting the reading rate and intonation based on the recognized emotion;

[1989] A system including:

[1990] (Claim 2)

[1991] 2. The system of claim 1, wherein said display means includes a voice synthesis means for reading said story aloud.

[1992] (Claim 3)

[1993] 2. The system according to claim 1, wherein the input means, the transmission means, and the display means are configured by an application executed on a portable information terminal.

[1994] "Application example 2 when combining emotion engines"

[1995] (Claim 1)

[1996] an input means for inputting the child's name;

[1997] a transmitting means for transmitting the child's name inputted via the input means to a server;

[1998] a generation means for generating a story by using a generative artificial intelligence based on the child's name received by the server via the transmission means;

[1999] a transmission means for transmitting the story generated by the generation means to a terminal;

[2000] a display means for displaying the story received by the terminal via the transmission means;

[2001] emotion recognition means for recognizing the user's emotion in real time using a camera and a microphone of the terminal;

[2002] a voice adjusting means for controlling the voice reading of the story based on the emotion recognized by the emotion recognition means;

[2003] A system including:

[2004] (Claim 2)

[2005] 2. The system of claim 1, wherein said display means includes a voice synthesis means for reading said story aloud and for adjusting the reading aloud based on the emotion recognized by said emotion recognition means.

[2006] (Claim 3)

[2007] 10. The system of claim 1, wherein the input means, transmission means, display means, emotion recognition means, and voice adjustment means are comprised of applications running on a mobile device. [Explanation of symbols]

[2008] 10, 210, 310, 410 Data Processing Systems 12 Data Processing Device 14 Smart Devices 214 Smart Glasses 314 Headset-type terminal 414 Robot< / url:> < / url:> < / url:> < / url:>

Claims

1. an input means for inputting the child's name; a transmitting means for transmitting the child's name inputted via the input means to a server; a generation means for generating a story by using a generative artificial intelligence based on the child's name received by the server via the transmission means; a transmission means for transmitting the story generated by the generation means to a terminal; a display means for displaying the story received by the terminal via the transmission means; A system including:

2. 2. The system of claim 1, wherein said display means includes a voice synthesis means for reading said story aloud.

3. The system according to claim 1 , wherein the input means, the transmission means, and the display means are configured by an application executed on a smartphone or a tablet terminal.

Images