System

Abstract

A system is provided.SOLUTION: The system includes a means for receiving basic child information input by a user, a generation means for generating a story on the basis of the received basic information, a display means for displaying the generated story on a user interface, and a reading means for reading the generated story by speech synthesis.SELECTED DRAWING: Figure 1

Description

[Technical Field]

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

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

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

[0004] In today's busy lifestyles, parents often find it difficult to spend enough time with their children. In particular, they often lack time to read to and play with their children, which can have a negative impact on their children's educational and emotional development. Another challenge is providing an environment where children can enjoy playing on their own. [Means for solving the problem]

[0005] This invention provides a means for accepting basic information about a child (such as name, age, and favorite things) entered by a user, and a generation means for generating a story in which the child is the protagonist based on the accepted basic information. Furthermore, by including a display means for displaying the generated story on a user interface and a reading means for reading the generated story aloud using voice synthesis, a system is provided that can be enjoyed by children on their own. This system allows parents to provide their children with an educational and enjoyable experience, even when they are busy.

[0006] The "means for accepting basic information about the child entered by the user" is an interface through which the user can enter basic information about the child, such as the child's name, age, and favorite things, and receive that information.

[0007] The "means for generating a story based on the received basic information" is an algorithm or program for creating a personalized story with the child as the main character based on the basic information about the child received from the user.

[0008] "Display means for displaying the generated story on a user interface" refers to a screen or device for visually presenting the generated story to a user or child.

[0009] The "reading means for reading the generated story by voice synthesis" refers to a voice synthesis technology for converting the generated story into voice and reading it aloud, as well as a device or program for that purpose. [Brief explanation of the drawings]

[0010] [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

[0011] 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.

[0012] First, the terms used in the following description will be explained.

[0013] 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).

[0014] 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.

[0015] 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.

[0016] 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.

[0017] 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."

[0018] [First embodiment]

[0019] FIG. 1 shows an example of the configuration of a data processing system 10 according to the first embodiment.

[0020] 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.

[0021] 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).

[0022] 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.

[0023] 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.

[0024] 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.

[0025] 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.

[0026] FIG. 2 shows an example of the main functions of the data processing device 12 and the smart device 14.

[0027] 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.

[0028] 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.

[0029] 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.

[0030] 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."

[0031] The following describes the mode for carrying out this invention. The system accepts basic information about a child entered by a user, generates a personalized story based on that information, and displays or reads it aloud. This system consists of three main components: a terminal, a server, and a user.

[0032] User Input

[0033] First, the user enters basic information about their child using the terminal. The terminal provides an interface for the user to enter information. For example, they can enter their child's name, age, favorite things, etc. through a form. This basic information is converted into JSON format and sent to the server.

[0034] Receiving and storing data

[0035] The server receives the basic information sent from the device and checks for errors. The received information is then stored in a database. For example, a NoSQL database such as MongoDB can be used for the database.

[0036] Narrative Generation

[0037] The server generates a story based on the stored basic information. It uses a generative algorithm that uses natural language processing (NLP) technology to create a personalized story with the child as the protagonist. Specifically, a generative AI model such as GPT-3 (registered trademark) is used. The story is generated with appropriate context and content based on the information entered by the user.

[0038] Providing Choices

[0039] The generated story data is sent back to the terminal and displayed on the terminal. The terminal presents the user and the child with the choice of print mode and reading mode. The user can select from these modes.

[0040] Showing the story

[0041] If the user selects print mode, the device will display the generated story on the screen, allowing the child to read the story themselves.

[0042] Story reading

[0043] If the user selects the reading mode, the device will read the generated story using speech synthesis technology, such as a speech synthesis API (Amazon Polly or Google® Text-to-Speech). This allows parents to use the system as an alternative to reading aloud to their children.

[0044] Specific examples

[0045] For example, if a user enters their child's name as "Taro," their age as "5 years old," and their favorite thing as "dinosaurs," the server will generate the following story based on this information:

[0046] "Taro is a five-year-old boy. His favorite thing is dinosaurs. One day, while Taro was playing in the park, a huge dinosaur suddenly appeared! Taro was startled and stepped back a little, but the dinosaur had kind eyes."

[0047] When the user selects print mode, the story is displayed on the device screen. When the user selects read-aloud mode, the story is read aloud using text-to-speech technology. This way, children can have fun on their own and parents can have an educational experience even when they're busy.

[0048] The processing flow will be explained below.

[0049] Step 1:

[0050] User: Enter basic information such as the child's name, age, and favorite things into the input form on the device. For example, enter the child's name "Taro," age "5 years old," and favorite thing "dinosaurs."

[0051] Step 2:

[0052] Device: Convert the entered basic information into JSON format. The converted data is {"name": "Taro", "age": "5 years old", "likes": "dinosaur"}.

[0053] Step 3:

[0054] Terminal: The converted JSON data is sent to the server as an HTTP POST request.

[0055] Step 4:

[0056] Server: Receives the transmitted data and checks whether the format of the received data is correct.

[0057] Step 5:

[0058] Server: Store the received data in a database. For example, store it in a NoSQL database as {"name": "Taro", "age": "5 years old", "likes": "Dinosaur"}.

[0059] Step 6:

[0060] Server: Activates the generation method based on the stored data. Specifically, it generates a story using a natural language processing algorithm (e.g., GPT-3).

[0061] Step 7:

[0062] Server: Generates a story from an AI model. For example, it generates a story like, "Taro is a 5-year-old boy. His favorite thing is dinosaurs. One day, while Taro was playing in the park, a huge dinosaur suddenly appeared! Taro was startled and stepped back a little, but the dinosaur had kind eyes."

[0063] Step 8:

[0064] Server: Sends the generated story data to the terminal.

[0065] Step 9:

[0066] Terminal: Prepares an interface for displaying received story data. Presents the user with the choice between print mode and reading mode.

[0067] Step 10:

[0068] User: Select print mode or speech mode.

[0069] Step 11:

[0070] Device: If the user selects print mode, the story is displayed on the screen. If the user selects reading mode, the story is read aloud using a speech synthesis API.

[0071] Step 12:

[0072] Terminal: Based on the selection, presents the story to the user: in print mode, it displays the text; in read-aloud mode, it plays the story aloud.

[0073] The above are specific processing steps including the roles of the user, terminal, and server.

[0074] Example 1

[0075] 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."

[0076] Conventional story generation systems have limited functionality for generating personalized stories based on individual child information, resulting in issues with not being able to provide content optimized for a child's interests and comprehension level. Additionally, parents have had to spend time and effort reading the displayed stories aloud, which hinders the provision of a meaningful educational experience. Given these issues, there is a demand for a story generation system that offers an improved user experience and high educational effectiveness.

[0077] 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.

[0078] In this invention, the server includes means for accepting basic information about a child entered by a user, means for converting the accepted basic information into JSON format and sending it to the server, means for checking the received basic information for errors and storing it in a database, means for generating a personalized story based on the stored basic information, means for displaying the generated story on a user interface, means for reading the generated story using voice synthesis, and means for presenting the user with a choice between a print mode and a reading mode. This makes it possible to generate a personalized story with high accuracy based on individual information, allowing children to enjoy stories themselves and providing an educational experience that reduces the burden on parents.

[0079] "User" refers to a user who uses the system to input basic information about their child and enjoys the generated story in viewing or reading mode.

[0080] "Basic child information" refers to data needed to personalize the story, such as the child's name, age, and likes.

[0081] A "terminal" is a device through which a user enters basic information about their child, and includes a PC, smartphone, tablet, etc.

[0082] "Server" refers to a central computer system that receives and processes data sent from the terminals and provides the generated story.

[0083] "JSON format" is an abbreviation for JavaScript (registered trademark) Object Notation, and refers to a lightweight text-based data format used for exchanging and storing data.

[0084] A "database" is a digital storehouse that stores information in an organized manner and makes it easy to search and retrieve; an example of a NoSQL database is MongoDB.

[0085] "Personalization" refers to personalizing content based on specific information provided by the user to provide the best possible experience for the target child.

[0086] "Generation means" refers to a mechanism that automatically creates a story based on stored information using natural language processing technology.

[0087] "Natural language processing technology" refers to the field of technology for processing, understanding, and generating human language using computers.

[0088] A "generative AI model" is a type of artificial intelligence that generates human language based on large amounts of data, and examples include GPT-3.

[0089] "Display means" refers to a mechanism for visually presenting the generated story in a user interface.

[0090] "Reading means" refers to a mechanism for playing back the generated story aloud using speech synthesis technology.

[0091] "Speech synthesis technology" refers to technology that generates speech that resembles a human voice based on text information, and examples include text-to-speech technology.

[0092] "User interface" refers to the interface through which a user interacts with a system, including screen displays and audio outputs.

[0093] This invention is a system that generates a personalized story based on basic information about a child entered by the user, and displays or reads the story. This system consists of three main components: the user, the terminal, and the server.

[0094] User Input

[0095] The user uses the device to enter basic information about their child. The device provides an interface for the user to enter information, such as the child's name, age, and favorite things, through a form. This basic information is converted into JSON format and sent to the server.

[0096] Receiving and storing data

[0097] The server receives the basic information sent by the device and checks for errors, specifically whether required fields are empty and whether the format is correct. The received information is then stored in a NoSQL database such as MongoDB.

[0098] Narrative Generation

[0099] The server generates a story based on the stored basic information. It uses a generation algorithm that uses natural language processing (NLP) technology to create a personalized story with the child as the protagonist. Specifically, a generative AI model (e.g., GPT-3) is used. The following prompt is used:

[0100] Prompt Sentence Examples

[0101] "Name: Taro, Age: 5, Favorite thing: Dinosaurs"

[0102] Based on this prompt, the generative AI model will generate a story. The generated story will look something like this:

[0103] Taro is a five-year-old boy. His favorite thing is dinosaurs. One day, while Taro was playing in the park, a huge dinosaur suddenly appeared! Taro was startled and stepped back a little, but the dinosaur had kind eyes.

[0104] Providing Choices

[0105] The generated story data is sent back to the terminal and displayed on the terminal. The terminal presents the user with the choice of print mode or reading mode. The user can select from these modes.

[0106] Showing the story

[0107] If the user selects print mode, the device will display the generated story on the screen, allowing the child to read the story themselves.

[0108] Story reading

[0109] If the user selects the reading mode, the device will read the generated story using speech synthesis technology, such as a speech synthesis API (e.g., Amazon Polly or Google Text-to-Speech). This allows parents to use the system as an alternative to reading aloud.

[0110] In this way, the system generates, displays, and recites personalized stories based on basic information about the child entered by the user, providing an educational experience while reducing the burden on parents.

[0111] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0112] Step 1:

[0113] The user enters information on the device

[0114] The user uses the device interface to enter basic information about the child (name, age, favorite things). This information becomes input data. The device converts the entered information into JSON format. Here, the input is the child's basic information, and the output is JSON format data.

[0115] What happens: A user fills out a web form or app and clicks the "Submit" button.

[0116] Step 2:

[0117] The device sends information to the server

[0118] The terminal sends the converted JSON formatted data to the server via an HTTP POST request. The input is the basic information of the child in JSON format, and the output is an HTTP request.

[0119] Specific operation: The device sends an HTTP POST request to the API endpoint.

[0120] Step 3:

[0121] The server receives the information

[0122] The server receives the JSON data sent from the terminal. It analyzes the received data and performs validation such as checking whether required fields are empty and whether the format is correct. The input is the JSON data included in the HTTP request, and the output is the validated JSON data.

[0123] Specific operation: A data validation script runs on the server side to check for invalid data.

[0124] Step 4:

[0125] The server stores the information in a database

[0126] The server stores the verified basic information in a NoSQL database such as MongoDB, where the input is the validated JSON data and the output is the entry stored in the database.

[0127] What happens: The server performs a database insert operation, for example, storing the data as a document in a MongoDB collection.

[0128] db.childrenInfo.insert({"Name": "Taro", "Age": "5 years old", "Favorite things": "Dinosaurs"})

[0129] Step 5:

[0130] The server generates the story

[0131] The server generates a personalized story using a generative AI model (e.g., GPT-3) based on the stored basic information. The input is the JSON data stored in the database, and the output is the text of the generated story. Specifically, the following prompt sentence is provided to the AI ​​model:

[0132] {

[0133] "Name": "Taro",

[0134] "age": "5 years old",

[0135] "Favorite things": "Dinosaurs"

[0136] }

[0137] The generative AI model generates the following story:

[0138] Taro is a five-year-old boy. His favorite thing is dinosaurs. One day, while Taro was playing in the park, a huge dinosaur suddenly appeared! Taro was startled and stepped back a little, but the dinosaur had kind eyes.

[0139] Step 6:

[0140] The server sends the story to the device.

[0141] The generated story data is again sent to the terminal as an HTTP response. The input is the generated story text, and the output is the HTTP response.

[0142] Specific operation: The server sends the generated story text in the HTTP response body.

[0143] Step 7:

[0144] The device presents the user with a choice of display modes

[0145] The terminal presents the user with the options of "print mode" and "reading mode" on the screen. The input is the story data included in the HTTP response, and the output is a user interface displaying the options.

[0146] Specific operation: The device generates a UI including a selection button and displays it to the user.

[0147] Step 8:

[0148] If the user selects type mode

[0149] If the user selects print mode, the terminal displays the generated story on the screen: the input is the user's selections, and the output is the story text displayed on the screen.

[0150] Specific action: The user clicks the "print mode" button and the device displays the text on the screen.

[0151] Step 9:

[0152] When the user selects read aloud mode

[0153] If the user selects read-aloud mode, the device reads the story aloud using speech synthesis technology (e.g., Amazon Polly or Google Text-to-Speech). The input is the user's selection, and the output is the story played as audio.

[0154] Specific operation: The device calls the speech synthesis API and plays the generated voice data.

[0155] (Application example 1)

[0156] 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."

[0157] With conventional story provision systems, it was difficult to provide personalized stories for specific children, and the lack of a choice between print and reading modes meant that children's interest could not be fully stimulated.Furthermore, there was a lack of experiential educational applications that could be immediately used in stores, which led to low customer satisfaction in stores.

[0158] 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.

[0159] In this invention, the server includes means for accepting basic information input by a user, means for generating a story based on the accepted basic information, means for displaying the generated story on a user interface, means for reading the generated story by voice synthesis, and means for providing a choice between a print mode and a read-aloud mode through the user interface. This makes it possible to instantly provide a story personalized to a specific child and to pique the child's interest by offering a choice between the print mode and the read-aloud mode, thereby increasing customer satisfaction in the store.

[0160] "Basic information entered by the user" is data that the user enters about the child, such as name, age, and favorite things.

[0161] "Generation means" refers to a device or program that has the function of creating a story based on input basic information.

[0162] "Display means" refers to a device or program for visually presenting the generated story on a user interface.

[0163] The "reading means" is a device or program for reproducing the generated story aloud using voice synthesis technology.

[0164] A "user interface" is a device or program that allows a user to interact with a system, input information, view or listen to a story.

[0165] "Print mode" is a function that displays the generated story in text format.

[0166] "Reading mode" is a function that plays the generated story as audio.

[0167] A "database" is a structured collection of data for storing basic information received from users.

[0168] "Natural language processing" is a technology for understanding and generating human language, and is used here to generate stories.

[0169] A "generative AI model" is an algorithm that uses artificial intelligence to generate personalized stories.

[0170] A "prompt sentence" is a sentence that serves as the starting point for the generative AI model to generate a story, and is constructed based on basic information entered by the user.

[0171] The system of this invention uses a generative AI model to generate personalized stories based on basic information entered by the user, and provides the functionality to display or read them aloud. The system consists of three main components: a terminal, a server, and a user.

[0172] User Input

[0173] The user enters basic information using a device, such as the child's name, age, and favorite things, through a form. For example, a tablet or smartphone can be used. The entered basic information is converted into JSON format and sent to the server.

[0174] Receiving and storing data

[0175] The server receives the basic information sent from the device and performs error checking. The received information is then stored in a database, typically a NoSQL database such as MongoDB.

[0176] Narrative Generation

[0177] The server generates a story based on the stored basic information. For example, GPT-3 is used as a generative AI model. This model uses natural language processing technology to generate a story with appropriate context and content based on the information entered by the user. For example, if a user enters the following basic information:

[0178] Name: "Rina"

[0179] Age: 6

[0180] Likes: Princesses

[0181] With this information, the server generates a prompt like this:

[0182] Lina is a 6-year-old girl. Her favorite thing is princesses. One day, while Lina was playing in the garden, a huge castle suddenly appeared!

[0183] The prompt sentence is then used as input to generate a story using a GPT-3 model.

[0184] Providing Choices

[0185] The generated story data is sent to the terminal and displayed on the terminal. The terminal presents the user or child with the choice of print mode or reading mode. The user can select from these modes.

[0186] Showing the story

[0187] If the user selects the print mode, the device will display the generated story on the screen, allowing the child to read the story themselves.

[0188] Story reading

[0189] When the user selects the reading mode, the device will read the generated story using speech synthesis technology, specifically using speech synthesis APIs such as Amazon Polly and Google Text-to-Speech.

[0190] For example, the following story appears on the terminal screen:

[0191] Lina is a 6-year-old girl. Her favorite thing is princesses. One day, while Lina was playing in the garden, a huge castle suddenly appeared!

[0192] Lina stared in amazement at the sight before her. The castle door opened, and the kind-looking king stepped out. "Hello, Lina. Welcome to your adventure to become a princess," the king smiled.

[0193] If the user selects the read aloud mode, the story will be read aloud for the child's listening pleasure.

[0194] This system allows for personalized stories to be delivered to specific children in-store, resulting in higher customer satisfaction.

[0195] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0196] Step 1:

[0197] The user uses the device to enter basic information about their child, such as the child's name, age, and favorite things, into the form displayed on the device screen, and then presses the submit button. The entered basic information is converted into JSON format and sent to the server.

[0198] Input: Basic information such as your child's name, age, and favorite things.

[0199] Output: Basic information converted to JSON format.

[0200] Step 2:

[0201] The server receives the basic information in JSON format sent from the device and performs error checks. Information that passes the check is saved in a database. Specifically, the information is stored in a NoSQL database such as MongoDB.

[0202] Input: Basic information in JSON format.

[0203] Output: Basic information stored in the database.

[0204] Step 3:

[0205] The server generates a story based on the basic information stored in the database. First, it creates a prompt sentence using the basic information, and then inputs the prompt sentence into a generative AI model (e.g., GPT-3). This model uses natural language processing technology to generate a story based on the input prompt sentence.

[0206] Input: Basic information retrieved from the database.

[0207] Data processing: Convert basic information into prompt sentences.

[0208] Data Computation: Generate stories using generative AI models.

[0209] Output: The generated narrative text.

[0210] Step 4:

[0211] The generated story data is sent from the server to the terminal. On the terminal, before the generated story is displayed to the user, the user is presented with the choice of print mode or reading mode. The user selects the desired mode.

[0212] Input: The text data of the generated story.

[0213] Output: The choices presented to the user (print mode, spoken mode).

[0214] Step 5:

[0215] If the user selects print mode, the terminal displays the generated story on the screen.

[0216] Input: User selection of type mode.

[0217] Output: The generated narrative text that is displayed on the screen.

[0218] Step 6:

[0219] When the user selects the reading mode, the device reads the generated story aloud using speech synthesis technology, specifically, using speech synthesis APIs such as Amazon Polly and Google Text-to-Speech to play the story aloud.

[0220] Input: User selection of reading mode.

[0221] Output: The generated story played as audio.

[0222] 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.

[0223] We will now explain the mode for implementing this invention. The system accepts basic information about a child entered by a user, generates a personalized story based on that information, and has the function of recognizing the user's emotions and adjusting the content of the story. This system consists of four main elements: a terminal, a server, a user, and an emotion engine.

[0224] User Input

[0225] First, the user enters basic information about their child using the device. The device provides an interface for the user to enter information. For example, they can enter their child's name, age, favorite things, etc. through a form. This basic information is converted into JSON format and sent to the server.

[0226] Receiving and storing data

[0227] The server receives the basic information sent from the device and checks whether it is correct. The received information is stored in a database. For example, a NoSQL database can be used for the database.

[0228] Narrative Generation

[0229] The server then activates a generation mechanism based on the stored basic information. Specifically, a generation algorithm is used to create a personalized story with a child as the main character, using a natural language processing algorithm (e.g., GPT-3). The story is generated with appropriate context and content based on the information entered by the user.

[0230] Use of emotion engine

[0231] When the generation means operates, the emotion engine recognizes the user's emotion. The emotion engine analyzes the user's voice input and facial expressions to recognize the emotion and sends the information to the server. The emotion engine can use a speech recognition API or facial expression recognition API (e.g., Google Cloud Speech-to-Text or Microsoft® Azure® Face API).

[0232] Emotion-based narrative adjustment

[0233] The server adjusts the content of the generated story based on information from the emotion engine. For example, if the user expresses happy emotions, it adjusts the tone of the story to be lighter.

[0234] Providing Choices

[0235] The generated story data is sent back to the terminal and displayed on the terminal. The terminal presents the user and the child with the choice of print mode and reading mode. The user can select from these modes.

[0236] Showing the story

[0237] If the user selects print mode, the device will display the generated story on the screen, allowing the child to read the story themselves.

[0238] Story reading

[0239] If the user selects the reading mode, the device will read the generated story using speech synthesis technology, for example, using a speech synthesis API (such as Amazon Polly or Google Text-to-Speech), allowing parents to use the system as an alternative to reading aloud.

[0240] Specific examples

[0241] For example, if a user enters their child's name as "Taro," their age as "5 years old," and their favorite thing as "dinosaurs," the server will generate the following story based on this information:

[0242] "Taro is a five-year-old boy. His favorite thing is dinosaurs. One day, while Taro was playing in the park, a huge dinosaur suddenly appeared! Taro was startled and stepped back a little, but the dinosaur had kind eyes."

[0243] If the emotion engine recognizes the user's emotion of joy, it can adjust the tone of the story to be even brighter.

[0244] "Taro is a five-year-old boy. His favorite thing is dinosaurs. One day, while Taro was having fun playing in the park, a big, smiling dinosaur suddenly appeared! Taro was startled and stepped back a little, but the dinosaur's eyes were kind, and the two quickly became friends."

[0245] When the user selects print mode, the story is displayed on the device screen. When the user selects read-aloud mode, the story is read aloud using text-to-speech technology. This way, children can have fun on their own and parents can have an educational experience even when they're busy.

[0246] The processing flow will be explained below.

[0247] Step 1:

[0248] User: Enter basic information such as the child's name, age, and favorite things into the input form on the device. For example, enter the child's name "Taro," age "5 years old," and favorite thing "dinosaurs."

[0249] Step 2:

[0250] Device: Convert the entered basic information into JSON format. The converted data is {"name": "Taro", "age": "5 years old", "likes": "dinosaur"}.

[0251] Step 3:

[0252] Terminal: The converted JSON data is sent to the server as an HTTP POST request.

[0253] Step 4:

[0254] Server: Receives the transmitted data and checks whether the format of the received data is correct.

[0255] Step 5:

[0256] Server: Store the received data in a database. For example, store it in a NoSQL database as {"name": "Taro", "age": "5 years old", "likes": "Dinosaur"}.

[0257] Step 6:

[0258] Server: Activates the generation method based on the stored data. Specifically, it generates a story using a natural language processing algorithm (e.g., GPT-3).

[0259] Step 7:

[0260] Server: Generates a story from an AI model. For example, it generates a story like, "Taro is a 5-year-old boy. His favorite thing is dinosaurs. One day, while Taro was playing in the park, a huge dinosaur suddenly appeared! Taro was startled and stepped back a little, but the dinosaur had kind eyes."

[0261] Step 8:

[0262] Terminal: Receives the generated story and activates the emotion engine, which is a function for analyzing the user's voice and facial expressions.

[0263] Step 9:

[0264] Terminal: The emotion engine analyzes the user's voice input and generates the user's emotion data. For example, if a happy voice pattern is detected, the emotion data for "joy" is generated.

[0265] Step 10:

[0266] Device: The emotion engine analyzes the user's facial expressions and complements the user's emotional data. For example, if a smiling expression is detected, the "joy" emotion data is strengthened.

[0267] Step 11:

[0268] Terminal: Sends the generated emotion data to the server.

[0269] Step 12:

[0270] Server: Analyzes the received emotional data and adjusts the tone and content of the generated story. For example, if it receives emotional data of "joy," it brightens the tone of the story. It adjusts the story to something like, "Taro was having fun playing in the park when suddenly, a big, smiling dinosaur appeared!"

[0271] Step 13:

[0272] Server: Sends the adjusted story data to the device.

[0273] Step 14:

[0274] Terminal: Prepares an interface for displaying received story data. Presents the user with the choice between print mode and reading mode.

[0275] Step 15:

[0276] User: Select print mode or speech mode.

[0277] Step 16:

[0278] Device: If the user selects print mode, the story is displayed on the screen. If the user selects reading mode, the story is read aloud using a speech synthesis API.

[0279] Step 17:

[0280] Terminal: Based on the selection, presents the story to the user: in print mode, it displays the text; in read-aloud mode, it plays the story aloud.

[0281] The above are specific processing steps including the roles of the user, terminal, server, and emotion engine.

[0282] Example 2

[0283] 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."

[0284] Conventional personalized story generation systems lack the ability to dynamically adjust the content of a story based on the user's emotions. This makes it difficult to provide stories that reflect the user's emotions and children's preferences. Furthermore, since users have limited options for listening to stories through audio, there is a need to provide a more interactive and richer experience.

[0285] The specific processing by the specific processing unit 290 of the data processing device 12 in the second embodiment is realized by the following means.

[0286] In this invention, the server includes means for accepting basic information about the child entered by the user, means for converting the accepted basic information into JSON format and transmitting it to the server, means for storing the accepted basic information in a database, means for generating a story using a generative AI model based on the stored basic information, means for adjusting the content of the generated story using an emotion recognition engine that analyzes the user's emotions, means for displaying the generated story on a user interface, and means for reciting the generated story using speech synthesis. This enables the provision of a personalized story that reflects the user's emotions and the child's preferences. Furthermore, by providing the user with the option of reading the story as text or listening to it audibly, a more interactive and richer experience can be provided.

[0287] "User" refers to the person who operates the system and enters basic information about the child.

[0288] "Basic information" refers to personally identifiable information such as the child's name, age, and likes.

[0289] "Terminal" refers to an electronic device that a user uses to input information.

[0290] "JSON format" refers to a standard data format that represents data in text.

[0291] "Server" refers to a remote computer for processing and storing received data.

[0292] "Database" means a data management system for storing received Basic Information.

[0293] A "generative AI model" refers to artificial intelligence technology that generates stories using natural language processing technology.

[0294] An "emotion recognition engine" refers to technology that recognizes emotions by analyzing a user's voice and facial expressions.

[0295] "User interface" refers to the screen or display device through which a user can view the generated story.

[0296] "Speech synthesis" refers to the technology of reading text data aloud.

[0297] "Interactive" refers to a dynamic experience that involves interaction with the user.

[0298] MODE FOR CARRYING OUT THE INVENTION

[0299] This section describes an embodiment of the present invention. This system accepts basic information about a child entered by a user, generates a personalized story based on that information, and also has the ability to adjust the content of the story by recognizing the user's emotions. This system consists of four main components: a terminal, a server, a user, and an emotion recognition engine.

[0300] User Input

[0301] The user uses the device to enter basic information about the child. The device provides an interface for the user to enter information. For example, the user can enter the child's name, age, favorite things, etc. through a form. This basic information is converted into JSON format and sent to the server.

[0302] Examples:

[0303] The user enters the child's name as "Taro," their age as "5 years old," and their favorite thing as "dinosaurs" through a form on the device.

[0304] Receiving and storing data

[0305] The server receives the basic information sent from the device and checks for errors. The received information is stored in a database. A NoSQL database (e.g., MongoDB) can be used for the database.

[0306] Examples:

[0307] The server receives basic information such as "Taro," "5 years old," and "dinosaur," and stores this in MongoDB.

[0308] Narrative Generation

[0309] The server then activates a generation mechanism based on the stored basic information. Specifically, it uses a generative AI model (e.g., GPT-3 natural language processing technology) to create a personalized story with the child as the protagonist. The story is generated with appropriate context and content based on the information entered by the user.

[0310] Examples:

[0311] The server uses GPT-3 to generate a story with Taro as the main character.

[0312] Example prompt sentence:

[0313] "I have a 5-year-old boy named Taro who loves dinosaurs. Please create a fun story with Taro as the main character, where he meets a big dinosaur in the park."

[0314] Use of emotion engine

[0315] When the generation means operates, the emotion recognition engine recognizes the user's emotions. The emotion engine analyzes the user's voice input and facial expressions to recognize emotions and sends that information to the server. Specifically, it can use a speech recognition API (e.g., Google Cloud Speech-to-Text) or a facial expression recognition API (e.g., Microsoft Azure Face API).

[0316] Examples:

[0317] The emotion engine uses Google Cloud Speech-to-Text to recognize the emotion of joy from the user's voice and send that information to the server.

[0318] Emotion-based narrative adjustment

[0319] The server adjusts the content of the generated story based on information from the emotion engine. For example, if the user expresses happy emotions, it adjusts the tone of the story to be lighter.

[0320] Examples:

[0321] The server recognizes the user's emotions of joy and lightens the tone of the story.

[0322] Providing a Generative Story

[0323] The generated story data is sent back to the terminal and displayed on the terminal. The terminal provides the user and the child with the choice of a print mode or a reading mode. The user can select from these modes.

[0324] Examples:

[0325] The device offers a choice between print mode and read-aloud mode below the displayed story, and the user can choose one.

[0326] Display or read the mode

[0327] If the user selects print mode, the device displays the generated story on the screen, allowing the child to read the story by themselves. If the user selects read-aloud mode, the device uses speech synthesis technology (e.g., Amazon Polly) to read the story aloud, allowing parents to use the system as an alternative to reading aloud to their children.

[0328] Examples:

[0329] If the user selects print mode, Tarou begins reading the story displayed on the device. If the user selects read-aloud mode, Tarou listens to the story read aloud by Amazon Polly.

[0330] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0331] Step 1: Enter your user information

[0332] The user uses the terminal to enter basic information about the child. The terminal provides an interface for the user to enter information. The entered information includes the child's name, age, favorite things, etc. This basic information is converted into JSON format and sent to the server.

[0333] Specific behavior:

[0334] The user enters information such as "Taro," "5 years old," and "dinosaur" into a form on the device.

[0335] Input: Basic information such as your child's name, age, and favorite things

[0336] Output: JSON format data

[0337] Step 2: Sending and receiving basic information

[0338] The device sends basic information converted to JSON format to the server, which then receives the JSON data and checks for errors.

[0339] Specific behavior:

[0340] The device converts the information into JSON format and sends it to the server, which then analyzes the received JSON data and checks for errors.

[0341] Input: Basic information in JSON format

[0342] Output: Parsed basic information

[0343] Step 3: Save your basic information

[0344] The server stores the parsed basic information in a database, which can be a NoSQL database (e.g., MongoDB).

[0345] Specific behavior:

[0346] The server stores the parsed basic information in MongoDB.

[0347] Input: Parsed basic information

[0348] Output: Basic information stored in the database

[0349] Step 4: Narrative generation

[0350] The server then uses the stored basic information to launch a generative AI model (e.g., GPT-3) to generate a personalized story with the child as the protagonist. The story is generated with appropriate context and content according to the prompt text entered by the user.

[0351] Specific behavior:

[0352] The server inputs the prompt "Taro is the main character, and his favorite thing is dinosaurs" into GPT-3 and generates a story.

[0353] Input: Basic information, prompt

[0354] Output: The generated story

[0355] Step 5: Recognize emotions

[0356] When the generator is running, the emotion recognition engine recognizes the user's emotions. The emotion engine uses a speech recognition API (e.g., Google Cloud Speech-to-Text) or a facial expression recognition API (e.g., Microsoft Azure Face API) to analyze the user's voice input and facial expressions and recognize the emotions. This information is sent to the server.

[0357] Specific behavior:

[0358] The emotion engine uses Google Cloud Speech-to-Text to recognize the emotion of joy from the user's voice and send that information to the server.

[0359] Input: User's voice or facial expression

[0360] Output: Recognized user emotion information

[0361] Step 6: Adjust the story

[0362] The server adjusts the content of the generated story based on the user's emotional information received from the emotion engine. For example, if the user expresses a happy emotion, the server adjusts the tone of the story to be brighter.

[0363] Specific behavior:

[0364] The server recognizes that the user is happy and adjusts the tone of the story to be even lighter.

[0365] Input: User's emotion information, generated story

[0366] Output: Adjusted narrative

[0367] Step 7: Submit and view your story

[0368] The generated story data is sent back to the terminal from the server and displayed on the terminal, which provides the user and the child with the choice of a print mode or a reading mode.

[0369] Specific behavior:

[0370] The server sends the generated story data to the terminal, which displays it on the screen, and the user can choose between print mode and reading mode.

[0371] Input: Adjusted Narrative

[0372] Output: The story displayed on the terminal

[0373] Step 8: Select a Mode

[0374] The user selects one of the options displayed on the terminal: print mode or reading mode.

[0375] Specific behavior:

[0376] The user selects print mode or speech mode from the options displayed on the device screen.

[0377] Input: Mode selection

[0378] Output: Selected mode

[0379] Step 9: Show or read the story

[0380] If the user selects print mode, the device displays the generated story on the screen. If the user selects read-aloud mode, the device uses speech synthesis technology (e.g., Amazon Polly) to read the story aloud.

[0381] Specific behavior:

[0382] When the user selects print mode, the device displays the story on the screen for the user to read, and when the user selects read aloud mode, the story is played aloud using Amazon Polly.

[0383] Input: Selected mode

[0384] Output: A story displayed on a screen or read aloud

[0385] (Application example 2)

[0386] 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."

[0387] Conventional story generation systems are unable to dynamically adjust story content to match the user's emotions, making it difficult to provide children with a more engaging and personalized educational experience. Furthermore, they lack comprehensive methods for easily storing, viewing, and reciting stories.

[0388] 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.

[0389] In this invention, the server includes means for accepting basic information about the child input by the user, means for generating a story based on the accepted basic information, means for recognizing the user's emotions and adjusting the content of the story, means for displaying the generated story on a user interface, and means for reciting the generated story by voice synthesis. This enables the generation of a personalized story according to the user's emotions, providing a more engaging and educational experience for the child.

[0390] "User-entered basic information about the child" is information the user enters to personalize the story, such as the child's name, age, and favorite things.

[0391] The "generation means" is a mechanism for generating a story based on the received basic information, and primarily uses natural language processing technology.

[0392] "Display means" is a mechanism for displaying the generated story on the user interface of the terminal.

[0393] The "reading means" is a mechanism for reading aloud a story generated using speech synthesis technology.

[0394] The "means for recognizing emotions and adjusting the content of the story" is a mechanism for analyzing the user's voice input and facial expressions, and dynamically changing the content and tone of the story based on the results.

[0395] The "storage means" is a mechanism for storing basic information received from a user in a database.

[0396] "Natural language processing" is a technology that enables computers to understand and generate human language.

[0397] "Speech synthesis" is a technology that converts text data into speech.

[0398] Specific embodiments for carrying out the present invention will be described below.

[0399] 1. System Program

[0400] This invention is a system consisting of four main elements: a server, a terminal, a user, and an emotion engine. The terminal provides an interface for inputting basic information about the child, the server generates a story based on that information, and the emotion engine recognizes the user's emotions and adjusts the content of the story. The terminal is equipped with a means for displaying the story and a means for reading it aloud.

[0401] 1.1 Enter your child's basic information

[0402] The user uses a terminal to enter basic information about their child, such as their name, age, and interests. This information is converted into JSON format and sent to the server.

[0403] 1.2 Receipt and storage of data

[0404] The server receives the basic information sent from the device, checks that the information is correct, and then stores it in a database, which may be a NoSQL database, for example.

[0405] 1.3 Narrative Generation

[0406] The server uses the stored basic information to generate a personalized story using a generative AI model (e.g., OpenAI's GPT-3), which generates a story with appropriate context and content based on the information entered by the user.

[0407] 1.4 Using the Emotion Engine

[0408] When the generator is running, the emotion engine analyzes the user's voice input and facial expressions to recognize emotions. The emotion engine uses the Google Cloud Speech API and Microsoft Azure Face API. This information is sent to the server in real time, and the content of the story is adjusted according to the user's emotions.

[0409] 1.5 Displaying and Reading Stories

[0410] The generated story is sent to the device, which presents the user with the choice of print mode or reading mode. If print mode is selected, the device displays the story on the screen. If reading mode is selected, the device reads the story aloud using speech synthesis technology (e.g., Google Text-to-Speech or Amazon Polly).

[0411] 2. Hardware and Software Details

[0412] To realize this system, the following hardware and software are used:

[0413] Hardware: Devices such as smartphones, tablets, and computers.

[0414] Software: Natural language processing algorithms (e.g., GPT-3), speech recognition APIs (e.g., Google Cloud Speech-to-Text), facial expression recognition APIs (e.g., Microsoft Azure Face API), and speech synthesis APIs (e.g., Google Text-to-Speech, Amazon Polly).

[0415] 3. Specific Examples

[0416] For example, suppose a user inputs their child's name as "Taro," their age as "5 years old," and their favorite thing as "dinosaurs." Based on this information, the following story will be generated:

[0417] Example prompt sentence:

[0418] Taro is a 5-year-old boy. His favorite thing is dinosaurs. One day, while he was playing in the park, a huge dinosaur suddenly appeared!

[0419] Examples of generated narrative contributions:

[0420] Taro is a five-year-old boy. His favorite thing is dinosaurs. One day, while Taro was playing in the park, a huge dinosaur suddenly appeared! Taro was startled and stepped back a little, but the dinosaur had kind eyes.

[0421] If the emotion engine recognizes the user's emotion of joy, the story content is adjusted as follows:

[0422] Taro is a five-year-old boy. His favorite thing is dinosaurs. One day, while Taro was having fun playing in the park, a big, smiling dinosaur suddenly appeared! Taro was surprised and stepped back a little, but the dinosaur's eyes were kind, and the two quickly became friends.

[0423] In this way, the present invention provides a system that provides a personalized story for children and dynamically adjusts the content based on the user's emotions, providing a more engaging and educational experience.

[0424] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[0425] Step 1:

[0426] The user uses the terminal to enter basic information about their child (such as name, age, and favorite things). The terminal converts this information into JSON format and sends it to the server. This process prepares the terminal to send the entered information to the server in the appropriate format. The input data is the child's basic information entered by the user into the interface, and the output is the data converted to JSON format.

[0427] Step 2:

[0428] The server receives the child's basic information in JSON format sent from the device and verifies that the information is correct. During the verification process, the data format and content are checked to ensure they are correct. Once the data is confirmed to be correct, it is stored in a NoSQL database. The input data is the child's basic information in JSON format, and the output is the information stored in the database.

[0429] Step 3:

[0430] The server runs a generative AI model (e.g., OpenAI's GPT-3) based on the stored basic information to generate a story. In the generation process, the basic information entered by the user is converted into a prompt sentence and sent to the AI ​​model. The AI ​​model generates a story based on the prompt sentence and returns the result to the server. The input data is the basic information stored in the database, and the output is the generated story.

[0431] Step 4:

[0432] After the generated story is returned to the server, the server launches an emotion engine to analyze the user's emotions. The user's emotions are analyzed in real time using voice input and facial expression recognition APIs (such as Google Cloud Speech-to-Text or Microsoft Azure Face API). Once the emotion data is analyzed, the server uses that information to adjust the tone and content of the generated story. The input data are the generated story and emotion data, and the output is the adjusted story.

[0433] Step 5:

[0434] The server sends the adapted story to the terminal, which displays it on its user interface. The terminal then offers the user a choice between a print mode and a reading mode. When the user selects one of the modes, the terminal displays or reads the story based on the user's selection. The input data is the adapted story and the user's mode selection, and the output is a visual display or audio reading of the story.

[0435] Step 6:

[0436] If the device displays a story based on the user's selection, the story will be displayed on the screen. The user can read the story themselves. If read-aloud mode is selected, the device will read the story using a speech synthesis API (such as Google Text-to-Speech or Amazon Polly). The speech synthesis API converts text data into speech and plays it through the speaker. The input data is the story text, and the output is synthesized speech.

[0437] 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.

[0438] 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.

[0439] 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.

[0440] [Second embodiment]

[0441] FIG. 3 shows an example of the configuration of a data processing system 210 according to the second embodiment.

[0442] 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.

[0443] 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).

[0444] 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.

[0445] 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.

[0446] 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).

[0447] 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.

[0448] 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.

[0449] 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.

[0450] 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.

[0451] In the smart glasses 214, 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.

[0452] 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."

[0453] The following describes the mode for carrying out this invention. The system accepts basic information about a child entered by a user, generates a personalized story based on that information, and displays or reads it aloud. This system consists of three main components: a terminal, a server, and a user.

[0454] User Input

[0455] First, the user enters basic information about their child using the terminal. The terminal provides an interface for the user to enter information. For example, they can enter their child's name, age, favorite things, etc. through a form. This basic information is converted into JSON format and sent to the server.

[0456] Receiving and storing data

[0457] The server receives the basic information sent from the device and checks for errors. The received information is then stored in a database. For example, a NoSQL database such as MongoDB can be used for the database.

[0458] Narrative Generation

[0459] The server generates a story based on the stored basic information. It uses a generative algorithm that uses natural language processing (NLP) technology to create a personalized story with the child as the protagonist. Specifically, a generative AI model such as GPT-3 is used. The story is generated with appropriate context and content based on the information entered by the user.

[0460] Providing Choices

[0461] The generated story data is sent back to the terminal and displayed on the terminal. The terminal presents the user and the child with the choice of print mode and reading mode. The user can select from these modes.

[0462] Showing the story

[0463] If the user selects print mode, the device will display the generated story on the screen, allowing the child to read the story themselves.

[0464] Story reading

[0465] If the user selects the reading mode, the device will read the generated story using speech synthesis technology, for example, using a speech synthesis API (such as Amazon Polly or Google Text-to-Speech), allowing parents to use the system as an alternative to reading aloud.

[0466] Specific examples

[0467] For example, if a user enters their child's name as "Taro," their age as "5 years old," and their favorite thing as "dinosaurs," the server will generate the following story based on this information:

[0468] "Taro is a five-year-old boy. His favorite thing is dinosaurs. One day, while Taro was playing in the park, a huge dinosaur suddenly appeared! Taro was startled and stepped back a little, but the dinosaur had kind eyes."

[0469] When the user selects print mode, the story is displayed on the device screen. When the user selects read-aloud mode, the story is read aloud using text-to-speech technology. This way, children can have fun on their own and parents can have an educational experience even when they're busy.

[0470] The processing flow will be explained below.

[0471] Step 1:

[0472] User: Enter basic information such as the child's name, age, and favorite things into the input form on the device. For example, enter the child's name "Taro," age "5 years old," and favorite thing "dinosaurs."

[0473] Step 2:

[0474] Device: Convert the entered basic information into JSON format. The converted data is {"name": "Taro", "age": "5 years old", "likes": "dinosaur"}.

[0475] Step 3:

[0476] Terminal: The converted JSON data is sent to the server as an HTTP POST request.

[0477] Step 4:

[0478] Server: Receives the transmitted data and checks whether the format of the received data is correct.

[0479] Step 5:

[0480] Server: Store the received data in a database. For example, store it in a NoSQL database as {"name": "Taro", "age": "5 years old", "likes": "Dinosaur"}.

[0481] Step 6:

[0482] Server: Activates the generation method based on the stored data. Specifically, it generates a story using a natural language processing algorithm (e.g., GPT-3).

[0483] Step 7:

[0484] Server: Generates a story from an AI model. For example, it generates a story like, "Taro is a 5-year-old boy. His favorite thing is dinosaurs. One day, while Taro was playing in the park, a huge dinosaur suddenly appeared! Taro was startled and stepped back a little, but the dinosaur had kind eyes."

[0485] Step 8:

[0486] Server: Sends the generated story data to the terminal.

[0487] Step 9:

[0488] Terminal: Prepares an interface for displaying received story data. Presents the user with the choice between print mode and reading mode.

[0489] Step 10:

[0490] User: Select print mode or speech mode.

[0491] Step 11:

[0492] Device: If the user selects print mode, the story is displayed on the screen. If the user selects reading mode, the story is read aloud using a speech synthesis API.

[0493] Step 12:

[0494] Terminal: Based on the selection, presents the story to the user: in print mode, it displays the text; in read-aloud mode, it plays the story aloud.

[0495] The above are specific processing steps including the roles of the user, terminal, and server.

[0496] Example 1

[0497] 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."

[0498] Conventional story generation systems have limited functionality for generating personalized stories based on individual child information, resulting in issues with not being able to provide content optimized for a child's interests and comprehension level. Additionally, parents have had to spend time and effort reading the displayed stories aloud, which hinders the provision of a meaningful educational experience. Given these issues, there is a demand for a story generation system that offers an improved user experience and high educational effectiveness.

[0499] 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.

[0500] In this invention, the server includes means for accepting basic information about a child entered by a user, means for converting the accepted basic information into JSON format and sending it to the server, means for checking the received basic information for errors and storing it in a database, means for generating a personalized story based on the stored basic information, means for displaying the generated story on a user interface, means for reading the generated story using voice synthesis, and means for presenting the user with a choice between a print mode and a reading mode. This makes it possible to generate a personalized story with high accuracy based on individual information, allowing children to enjoy stories themselves and providing an educational experience that reduces the burden on parents.

[0501] "User" refers to a user who uses the system to input basic information about their child and enjoys the generated story in viewing or reading mode.

[0502] "Basic child information" refers to data needed to personalize the story, such as the child's name, age, and likes.

[0503] A "terminal" is a device through which a user enters basic information about their child, and includes a PC, smartphone, tablet, etc.

[0504] "Server" refers to a central computer system that receives and processes data sent from the terminals and provides the generated story.

[0505] "JSON format" stands for JavaScript Object Notation and refers to a lightweight text-based data format used for exchanging and storing data.

[0506] A "database" is a digital storehouse that stores information in an organized manner and makes it easy to search and retrieve; an example of a NoSQL database is MongoDB.

[0507] "Personalization" refers to personalizing content based on specific information provided by the user to provide the best possible experience for the target child.

[0508] "Generation means" refers to a mechanism that automatically creates a story based on stored information using natural language processing technology.

[0509] "Natural language processing technology" refers to the field of technology for processing, understanding, and generating human language using computers.

[0510] A "generative AI model" is a type of artificial intelligence that generates human language based on large amounts of data, and examples include GPT-3.

[0511] "Display means" refers to a mechanism for visually presenting the generated story in a user interface.

[0512] "Reading means" refers to a mechanism for playing back the generated story aloud using speech synthesis technology.

[0513] "Speech synthesis technology" refers to technology that generates speech that resembles a human voice based on text information, and examples include text-to-speech technology.

[0514] "User interface" refers to the interface through which a user interacts with a system, including screen displays and audio outputs.

[0515] This invention is a system that generates a personalized story based on basic information about a child entered by the user, and displays or reads the story. This system consists of three main components: the user, the terminal, and the server.

[0516] User Input

[0517] The user uses the device to enter basic information about their child. The device provides an interface for the user to enter information, such as the child's name, age, and favorite things, through a form. This basic information is converted into JSON format and sent to the server.

[0518] Receiving and storing data

[0519] The server receives the basic information sent by the device and checks for errors, specifically whether required fields are empty and whether the format is correct. The received information is then stored in a NoSQL database such as MongoDB.

[0520] Narrative Generation

[0521] The server generates a story based on the stored basic information. It uses a generation algorithm that uses natural language processing (NLP) technology to create a personalized story with the child as the protagonist. Specifically, a generative AI model (e.g., GPT-3) is used. The following prompt is used:

[0522] Prompt Sentence Examples

[0523] "Name: Taro, Age: 5, Favorite thing: Dinosaurs"

[0524] Based on this prompt, the generative AI model will generate a story. The generated story will look something like this:

[0525] Taro is a five-year-old boy. His favorite thing is dinosaurs. One day, while Taro was playing in the park, a huge dinosaur suddenly appeared! Taro was startled and stepped back a little, but the dinosaur had kind eyes.

[0526] Providing Choices

[0527] The generated story data is sent back to the terminal and displayed on the terminal. The terminal presents the user with the choice of print mode or reading mode. The user can select from these modes.

[0528] Showing the story

[0529] If the user selects print mode, the device will display the generated story on the screen, allowing the child to read the story themselves.

[0530] Story reading

[0531] If the user selects the reading mode, the device will read the generated story using speech synthesis technology, such as a speech synthesis API (e.g., Amazon Polly or Google Text-to-Speech). This allows parents to use the system as an alternative to reading aloud.

[0532] In this way, the system generates, displays, and recites personalized stories based on basic information about the child entered by the user, providing an educational experience while reducing the burden on parents.

[0533] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0534] Step 1:

[0535] The user enters information on the device

[0536] The user uses the device interface to enter basic information about the child (name, age, favorite things). This information becomes input data. The device converts the entered information into JSON format. Here, the input is the child's basic information, and the output is JSON format data.

[0537] What happens: A user fills out a web form or app and clicks the "Submit" button.

[0538] Step 2:

[0539] The device sends information to the server

[0540] The terminal sends the converted JSON formatted data to the server via an HTTP POST request. The input is the basic information of the child in JSON format, and the output is an HTTP request.

[0541] Specific operation: The device sends an HTTP POST request to the API endpoint.

[0542] Step 3:

[0543] The server receives the information

[0544] The server receives the JSON data sent from the terminal. It analyzes the received data and performs validation such as checking whether required fields are empty and whether the format is correct. The input is the JSON data included in the HTTP request, and the output is the validated JSON data.

[0545] Specific operation: A data validation script runs on the server side to check for invalid data.

[0546] Step 4:

[0547] The server stores the information in a database

[0548] The server stores the verified basic information in a NoSQL database such as MongoDB, where the input is the validated JSON data and the output is the entry stored in the database.

[0549] What happens: The server performs a database insert operation, for example, storing the data as a document in a MongoDB collection.

[0550] db.childrenInfo.insert({"Name": "Taro", "Age": "5 years old", "Favorite things": "Dinosaurs"})

[0551] Step 5:

[0552] The server generates the story

[0553] The server generates a personalized story using a generative AI model (e.g., GPT-3) based on the stored basic information. The input is the JSON data stored in the database, and the output is the text of the generated story. Specifically, the following prompt sentence is provided to the AI ​​model:

[0554] {

[0555] "Name": "Taro",

[0556] "age": "5 years old",

[0557] "Favorite things": "Dinosaurs"

[0558] }

[0559] The generative AI model generates the following story:

[0560] Taro is a five-year-old boy. His favorite thing is dinosaurs. One day, while Taro was playing in the park, a huge dinosaur suddenly appeared! Taro was startled and stepped back a little, but the dinosaur had kind eyes.

[0561] Step 6:

[0562] The server sends the story to the device.

[0563] The generated story data is again sent to the terminal as an HTTP response. The input is the generated story text, and the output is the HTTP response.

[0564] Specific operation: The server sends the generated story text in the HTTP response body.

[0565] Step 7:

[0566] The device presents the user with a choice of display modes

[0567] The terminal presents the user with the options of "print mode" and "reading mode" on the screen. The input is the story data included in the HTTP response, and the output is a user interface displaying the options.

[0568] Specific operation: The device generates a UI including a selection button and displays it to the user.

[0569] Step 8:

[0570] If the user selects type mode

[0571] If the user selects print mode, the terminal displays the generated story on the screen: the input is the user's selections, and the output is the story text displayed on the screen.

[0572] Specific action: The user clicks the "print mode" button and the device displays the text on the screen.

[0573] Step 9:

[0574] When the user selects read aloud mode

[0575] If the user selects read-aloud mode, the device reads the story aloud using speech synthesis technology (e.g., Amazon Polly or Google Text-to-Speech). The input is the user's selection, and the output is the story played as audio.

[0576] Specific operation: The device calls the speech synthesis API and plays the generated voice data.

[0577] (Application example 1)

[0578] 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."

[0579] With conventional story provision systems, it was difficult to provide personalized stories for specific children, and the lack of a choice between print and reading modes meant that children's interest could not be fully stimulated.Furthermore, there was a lack of experiential educational applications that could be immediately used in stores, which led to low customer satisfaction in stores.

[0580] 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.

[0581] In this invention, the server includes means for accepting basic information input by a user, means for generating a story based on the accepted basic information, means for displaying the generated story on a user interface, means for reading the generated story by voice synthesis, and means for providing a choice between a print mode and a read-aloud mode through the user interface. This makes it possible to instantly provide a story personalized to a specific child and to pique the child's interest by offering a choice between the print mode and the read-aloud mode, thereby increasing customer satisfaction in the store.

[0582] "Basic information entered by the user" is data that the user enters about the child, such as name, age, and favorite things.

[0583] "Generation means" refers to a device or program that has the function of creating a story based on input basic information.

[0584] "Display means" refers to a device or program for visually presenting the generated story on a user interface.

[0585] The "reading means" is a device or program for reproducing the generated story aloud using voice synthesis technology.

[0586] A "user interface" is a device or program that allows a user to interact with a system, input information, view or listen to a story.

[0587] "Print mode" is a function that displays the generated story in text format.

[0588] "Reading mode" is a function that plays the generated story as audio.

[0589] A "database" is a structured collection of data for storing basic information received from users.

[0590] "Natural language processing" is a technology for understanding and generating human language, and is used here to generate stories.

[0591] A "generative AI model" is an algorithm that uses artificial intelligence to generate personalized stories.

[0592] A "prompt sentence" is a sentence that serves as the starting point for the generative AI model to generate a story, and is constructed based on basic information entered by the user.

[0593] The system of this invention uses a generative AI model to generate personalized stories based on basic information entered by the user, and provides the functionality to display or read them aloud. The system consists of three main components: a terminal, a server, and a user.

[0594] User Input

[0595] The user enters basic information using a device, such as the child's name, age, and favorite things, through a form. For example, a tablet or smartphone can be used. The entered basic information is converted into JSON format and sent to the server.

[0596] Receiving and storing data

[0597] The server receives the basic information sent from the device and performs error checking. The received information is then stored in a database, typically a NoSQL database such as MongoDB.

[0598] Narrative Generation

[0599] The server generates a story based on the stored basic information. For example, GPT-3 is used as a generative AI model. This model uses natural language processing technology to generate a story with appropriate context and content based on the information entered by the user. For example, if a user enters the following basic information:

[0600] Name: "Rina"

[0601] Age: 6

[0602] Likes: Princesses

[0603] With this information, the server generates a prompt like this:

[0604] Lina is a 6-year-old girl. Her favorite thing is princesses. One day, while Lina was playing in the garden, a huge castle suddenly appeared!

[0605] The prompt sentence is then used as input to generate a story using a GPT-3 model.

[0606] Providing Choices

[0607] The generated story data is sent to the terminal and displayed on the terminal. The terminal presents the user or child with the choice of print mode or reading mode. The user can select from these modes.

[0608] Showing the story

[0609] If the user selects the print mode, the device will display the generated story on the screen, allowing the child to read the story themselves.

[0610] Story reading

[0611] When the user selects the reading mode, the device will read the generated story using speech synthesis technology, specifically using speech synthesis APIs such as Amazon Polly and Google Text-to-Speech.

[0612] For example, the following story appears on the terminal screen:

[0613] Lina is a 6-year-old girl. Her favorite thing is princesses. One day, while Lina was playing in the garden, a huge castle suddenly appeared!

[0614] Lina stared in amazement at the sight before her. The castle door opened, and the kind-looking king stepped out. "Hello, Lina. Welcome to your adventure to become a princess," the king smiled.

[0615] If the user selects the read aloud mode, the story will be read aloud for the child's listening pleasure.

[0616] This system allows for personalized stories to be delivered to specific children in-store, resulting in higher customer satisfaction.

[0617] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0618] Step 1:

[0619] The user uses the device to enter basic information about their child, such as the child's name, age, and favorite things, into the form displayed on the device screen, and then presses the submit button. The entered basic information is converted into JSON format and sent to the server.

[0620] Input: Basic information such as your child's name, age, and favorite things.

[0621] Output: Basic information converted to JSON format.

[0622] Step 2:

[0623] The server receives the basic information in JSON format sent from the device and performs error checks. Information that passes the check is saved in a database. Specifically, the information is stored in a NoSQL database such as MongoDB.

[0624] Input: Basic information in JSON format.

[0625] Output: Basic information stored in the database.

[0626] Step 3:

[0627] The server generates a story based on the basic information stored in the database. First, it creates a prompt sentence using the basic information, and then inputs the prompt sentence into a generative AI model (e.g., GPT-3). This model uses natural language processing technology to generate a story based on the input prompt sentence.

[0628] Input: Basic information retrieved from the database.

[0629] Data processing: Convert basic information into prompt sentences.

[0630] Data Computation: Generate stories using generative AI models.

[0631] Output: The generated narrative text.

[0632] Step 4:

[0633] The generated story data is sent from the server to the terminal. On the terminal, before the generated story is displayed to the user, the user is presented with the choice of print mode or reading mode. The user selects the desired mode.

[0634] Input: The text data of the generated story.

[0635] Output: The choices presented to the user (print mode, spoken mode).

[0636] Step 5:

[0637] If the user selects print mode, the terminal displays the generated story on the screen.

[0638] Input: User selection of type mode.

[0639] Output: The generated narrative text that is displayed on the screen.

[0640] Step 6:

[0641] When the user selects the reading mode, the device reads the generated story aloud using speech synthesis technology, specifically, using speech synthesis APIs such as Amazon Polly and Google Text-to-Speech to play the story aloud.

[0642] Input: User selection of reading mode.

[0643] Output: The generated story played as audio.

[0644] 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.

[0645] We will now explain the mode for implementing this invention. The system accepts basic information about a child entered by a user, generates a personalized story based on that information, and has the function of recognizing the user's emotions and adjusting the content of the story. This system consists of four main elements: a terminal, a server, a user, and an emotion engine.

[0646] User Input

[0647] First, the user enters basic information about their child using the device. The device provides an interface for the user to enter information. For example, they can enter their child's name, age, favorite things, etc. through a form. This basic information is converted into JSON format and sent to the server.

[0648] Receiving and storing data

[0649] The server receives the basic information sent from the device and checks whether it is correct. The received information is stored in a database. For example, a NoSQL database can be used for the database.

[0650] Narrative Generation

[0651] The server then activates a generation mechanism based on the stored basic information. Specifically, a generation algorithm is used to create a personalized story with a child as the main character, using a natural language processing algorithm (e.g., GPT-3). The story is generated with appropriate context and content based on the information entered by the user.

[0652] Use of emotion engine

[0653] When the generation means operates, the emotion engine recognizes the user's emotion. The emotion engine analyzes the user's voice input and facial expressions to recognize the emotion and sends the information to the server. The emotion engine can use a speech recognition API or facial expression recognition API (e.g., Google Cloud Speech-to-Text or Microsoft Azure Face API).

[0654] Emotion-based narrative adjustment

[0655] The server adjusts the content of the generated story based on information from the emotion engine. For example, if the user expresses happy emotions, it adjusts the tone of the story to be lighter.

[0656] Providing Choices

[0657] The generated story data is sent back to the terminal and displayed on the terminal. The terminal presents the user and the child with the choice of print mode and reading mode. The user can select from these modes.

[0658] Showing the story

[0659] If the user selects print mode, the device will display the generated story on the screen, allowing the child to read the story themselves.

[0660] Story reading

[0661] If the user selects the reading mode, the device will read the generated story using speech synthesis technology, for example, using a speech synthesis API (such as Amazon Polly or Google Text-to-Speech), allowing parents to use the system as an alternative to reading aloud.

[0662] Specific examples

[0663] For example, if a user enters their child's name as "Taro," their age as "5 years old," and their favorite thing as "dinosaurs," the server will generate the following story based on this information:

[0664] "Taro is a five-year-old boy. His favorite thing is dinosaurs. One day, while Taro was playing in the park, a huge dinosaur suddenly appeared! Taro was startled and stepped back a little, but the dinosaur had kind eyes."

[0665] If the emotion engine recognizes the user's emotion of joy, it can adjust the tone of the story to be even brighter.

[0666] "Taro is a five-year-old boy. His favorite thing is dinosaurs. One day, while Taro was having fun playing in the park, a big, smiling dinosaur suddenly appeared! Taro was startled and stepped back a little, but the dinosaur's eyes were kind, and the two quickly became friends."

[0667] When the user selects print mode, the story is displayed on the device screen. When the user selects read-aloud mode, the story is read aloud using text-to-speech technology. This way, children can have fun on their own and parents can have an educational experience even when they're busy.

[0668] The processing flow will be explained below.

[0669] Step 1:

[0670] User: Enter basic information such as the child's name, age, and favorite things into the input form on the device. For example, enter the child's name "Taro," age "5 years old," and favorite thing "dinosaurs."

[0671] Step 2:

[0672] Device: Convert the entered basic information into JSON format. The converted data is {"name": "Taro", "age": "5 years old", "likes": "dinosaur"}.

[0673] Step 3:

[0674] Terminal: The converted JSON data is sent to the server as an HTTP POST request.

[0675] Step 4:

[0676] Server: Receives the transmitted data and checks whether the format of the received data is correct.

[0677] Step 5:

[0678] Server: Store the received data in a database. For example, store it in a NoSQL database as {"name": "Taro", "age": "5 years old", "likes": "Dinosaur"}.

[0679] Step 6:

[0680] Server: Activates the generation method based on the stored data. Specifically, it generates a story using a natural language processing algorithm (e.g., GPT-3).

[0681] Step 7:

[0682] Server: Generates a story from an AI model. For example, it generates a story like, "Taro is a 5-year-old boy. His favorite thing is dinosaurs. One day, while Taro was playing in the park, a huge dinosaur suddenly appeared! Taro was startled and stepped back a little, but the dinosaur had kind eyes."

[0683] Step 8:

[0684] Terminal: Receives the generated story and activates the emotion engine, which is a function for analyzing the user's voice and facial expressions.

[0685] Step 9:

[0686] Terminal: The emotion engine analyzes the user's voice input and generates the user's emotion data. For example, if a happy voice pattern is detected, the emotion data for "joy" is generated.

[0687] Step 10:

[0688] Device: The emotion engine analyzes the user's facial expressions and complements the user's emotional data. For example, if a smiling expression is detected, the "joy" emotion data is strengthened.

[0689] Step 11:

[0690] Terminal: Sends the generated emotion data to the server.

[0691] Step 12:

[0692] Server: Analyzes the received emotional data and adjusts the tone and content of the generated story. For example, if it receives emotional data of "joy," it brightens the tone of the story. It adjusts the story to something like, "Taro was having fun playing in the park when suddenly, a big, smiling dinosaur appeared!"

[0693] Step 13:

[0694] Server: Sends the adjusted story data to the device.

[0695] Step 14:

[0696] Terminal: Prepares an interface for displaying received story data. Presents the user with the choice between print mode and reading mode.

[0697] Step 15:

[0698] User: Select print mode or speech mode.

[0699] Step 16:

[0700] Device: If the user selects print mode, the story is displayed on the screen. If the user selects reading mode, the story is read aloud using a speech synthesis API.

[0701] Step 17:

[0702] Terminal: Based on the selection, presents the story to the user: in print mode, it displays the text; in read-aloud mode, it plays the story aloud.

[0703] The above are specific processing steps including the roles of the user, terminal, server, and emotion engine.

[0704] Example 2

[0705] 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."

[0706] Conventional personalized story generation systems lack the ability to dynamically adjust the content of a story based on the user's emotions. This makes it difficult to provide stories that reflect the user's emotions and children's preferences. Furthermore, since users have limited options for listening to stories through audio, there is a need to provide a more interactive and richer experience.

[0707] The specific processing by the specific processing unit 290 of the data processing device 12 in the second embodiment is realized by the following means.

[0708] In this invention, the server includes means for accepting basic information about the child entered by the user, means for converting the accepted basic information into JSON format and transmitting it to the server, means for storing the accepted basic information in a database, means for generating a story using a generative AI model based on the stored basic information, means for adjusting the content of the generated story using an emotion recognition engine that analyzes the user's emotions, means for displaying the generated story on a user interface, and means for reciting the generated story using speech synthesis. This enables the provision of a personalized story that reflects the user's emotions and the child's preferences. Furthermore, by providing the user with the option of reading the story as text or listening to it audibly, a more interactive and richer experience can be provided.

[0709] "User" refers to the person who operates the system and enters basic information about the child.

[0710] "Basic information" refers to personally identifiable information such as the child's name, age, and likes.

[0711] "Terminal" refers to an electronic device that a user uses to input information.

[0712] "JSON format" refers to a standard data format that represents data in text.

[0713] "Server" refers to a remote computer for processing and storing received data.

[0714] "Database" means a data management system for storing received Basic Information.

[0715] A "generative AI model" refers to artificial intelligence technology that generates stories using natural language processing technology.

[0716] An "emotion recognition engine" refers to technology that recognizes emotions by analyzing a user's voice and facial expressions.

[0717] "User interface" refers to the screen or display device through which a user can view the generated story.

[0718] "Speech synthesis" refers to the technology of reading text data aloud.

[0719] "Interactive" refers to a dynamic experience that involves interaction with the user.

[0720] MODE FOR CARRYING OUT THE INVENTION

[0721] This section describes an embodiment of the present invention. This system accepts basic information about a child entered by a user, generates a personalized story based on that information, and also has the ability to adjust the content of the story by recognizing the user's emotions. This system consists of four main components: a terminal, a server, a user, and an emotion recognition engine.

[0722] User Input

[0723] The user uses the device to enter basic information about the child. The device provides an interface for the user to enter information. For example, the user can enter the child's name, age, favorite things, etc. through a form. This basic information is converted into JSON format and sent to the server.

[0724] Examples:

[0725] The user enters the child's name as "Taro," their age as "5 years old," and their favorite thing as "dinosaurs" through a form on the device.

[0726] Receiving and storing data

[0727] The server receives the basic information sent from the device and checks for errors. The received information is stored in a database. A NoSQL database (e.g., MongoDB) can be used for the database.

[0728] Examples:

[0729] The server receives basic information such as "Taro," "5 years old," and "dinosaur," and stores this in MongoDB.

[0730] Narrative Generation

[0731] The server then activates a generation mechanism based on the stored basic information. Specifically, it uses a generative AI model (e.g., GPT-3 natural language processing technology) to create a personalized story with the child as the protagonist. The story is generated with appropriate context and content based on the information entered by the user.

[0732] Examples:

[0733] The server uses GPT-3 to generate a story with Taro as the main character.

[0734] Example prompt sentence:

[0735] "I have a 5-year-old boy named Taro who loves dinosaurs. Please create a fun story with Taro as the main character, where he meets a big dinosaur in the park."

[0736] Use of emotion engine

[0737] When the generation means operates, the emotion recognition engine recognizes the user's emotions. The emotion engine analyzes the user's voice input and facial expressions to recognize emotions and sends that information to the server. Specifically, it can use a speech recognition API (e.g., Google Cloud Speech-to-Text) or a facial expression recognition API (e.g., Microsoft Azure Face API).

[0738] Examples:

[0739] The emotion engine uses Google Cloud Speech-to-Text to recognize the emotion of joy from the user's voice and send that information to the server.

[0740] Emotion-based narrative adjustment

[0741] The server adjusts the content of the generated story based on information from the emotion engine. For example, if the user expresses happy emotions, it adjusts the tone of the story to be lighter.

[0742] Examples:

[0743] The server recognizes the user's emotions of joy and lightens the tone of the story.

[0744] Providing a Generative Story

[0745] The generated story data is sent back to the terminal and displayed on the terminal. The terminal provides the user and the child with the choice of a print mode or a reading mode. The user can select from these modes.

[0746] Examples:

[0747] The device offers a choice between print mode and read-aloud mode below the displayed story, and the user can choose one.

[0748] Display or read the mode

[0749] If the user selects print mode, the device displays the generated story on the screen, allowing the child to read the story by themselves. If the user selects read-aloud mode, the device uses speech synthesis technology (e.g., Amazon Polly) to read the story aloud, allowing parents to use the system as an alternative to reading aloud to their children.

[0750] Examples:

[0751] If the user selects print mode, Tarou begins reading the story displayed on the device. If the user selects read-aloud mode, Tarou listens to the story read aloud by Amazon Polly.

[0752] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0753] Step 1: Enter your user information

[0754] The user uses the terminal to enter basic information about the child. The terminal provides an interface for the user to enter information. The entered information includes the child's name, age, favorite things, etc. This basic information is converted into JSON format and sent to the server.

[0755] Specific behavior:

[0756] The user enters information such as "Taro," "5 years old," and "dinosaur" into a form on the device.

[0757] Input: Basic information such as your child's name, age, and favorite things

[0758] Output: JSON format data

[0759] Step 2: Sending and receiving basic information

[0760] The device sends basic information converted to JSON format to the server, which then receives the JSON data and checks for errors.

[0761] Specific behavior:

[0762] The device converts the information into JSON format and sends it to the server, which then analyzes the received JSON data and checks for errors.

[0763] Input: Basic information in JSON format

[0764] Output: Parsed basic information

[0765] Step 3: Save your basic information

[0766] The server stores the parsed basic information in a database, which can be a NoSQL database (e.g., MongoDB).

[0767] Specific behavior:

[0768] The server stores the parsed basic information in MongoDB.

[0769] Input: Parsed basic information

[0770] Output: Basic information stored in the database

[0771] Step 4: Narrative generation

[0772] The server then uses the stored basic information to launch a generative AI model (e.g., GPT-3) to generate a personalized story with the child as the protagonist. The story is generated with appropriate context and content according to the prompt text entered by the user.

[0773] Specific behavior:

[0774] The server inputs the prompt "Taro is the main character, and his favorite thing is dinosaurs" into GPT-3 and generates a story.

[0775] Input: Basic information, prompt

[0776] Output: The generated story

[0777] Step 5: Recognize emotions

[0778] When the generator is running, the emotion recognition engine recognizes the user's emotions. The emotion engine uses a speech recognition API (e.g., Google Cloud Speech-to-Text) or a facial expression recognition API (e.g., Microsoft Azure Face API) to analyze the user's voice input and facial expressions and recognize the emotions. This information is sent to the server.

[0779] Specific behavior:

[0780] The emotion engine uses Google Cloud Speech-to-Text to recognize the emotion of joy from the user's voice and send that information to the server.

[0781] Input: User's voice or facial expression

[0782] Output: Recognized user emotion information

[0783] Step 6: Adjust the story

[0784] The server adjusts the content of the generated story based on the user's emotional information received from the emotion engine. For example, if the user expresses a happy emotion, the server adjusts the tone of the story to be brighter.

[0785] Specific behavior:

[0786] The server recognizes that the user is happy and adjusts the tone of the story to be even lighter.

[0787] Input: User's emotion information, generated story

[0788] Output: Adjusted narrative

[0789] Step 7: Submit and view your story

[0790] The generated story data is sent back to the terminal from the server and displayed on the terminal, which provides the user and the child with the choice of a print mode or a reading mode.

[0791] Specific behavior:

[0792] The server sends the generated story data to the terminal, which displays it on the screen, and the user can choose between print mode and reading mode.

[0793] Input: Adjusted Narrative

[0794] Output: The story displayed on the terminal

[0795] Step 8: Select a Mode

[0796] The user selects one of the options displayed on the terminal: print mode or reading mode.

[0797] Specific behavior:

[0798] The user selects print mode or speech mode from the options displayed on the device screen.

[0799] Input: Mode selection

[0800] Output: Selected mode

[0801] Step 9: Show or read the story

[0802] If the user selects print mode, the device displays the generated story on the screen. If the user selects read-aloud mode, the device uses speech synthesis technology (e.g., Amazon Polly) to read the story aloud.

[0803] Specific behavior:

[0804] When the user selects print mode, the device displays the story on the screen for the user to read, and when the user selects read aloud mode, the story is played aloud using Amazon Polly.

[0805] Input: Selected mode

[0806] Output: A story displayed on a screen or read aloud

[0807] (Application example 2)

[0808] 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."

[0809] Conventional story generation systems are unable to dynamically adjust story content to match the user's emotions, making it difficult to provide children with a more engaging and personalized educational experience. Furthermore, they lack comprehensive methods for easily storing, viewing, and reciting stories.

[0810] 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.

[0811] In this invention, the server includes means for accepting basic information about the child input by the user, means for generating a story based on the accepted basic information, means for recognizing the user's emotions and adjusting the content of the story, means for displaying the generated story on a user interface, and means for reciting the generated story by voice synthesis. This enables the generation of a personalized story according to the user's emotions, providing a more engaging and educational experience for the child.

[0812] "User-entered basic information about the child" is information the user enters to personalize the story, such as the child's name, age, and favorite things.

[0813] The "generation means" is a mechanism for generating a story based on the received basic information, and primarily uses natural language processing technology.

[0814] "Display means" is a mechanism for displaying the generated story on the user interface of the terminal.

[0815] The "reading means" is a mechanism for reading aloud a story generated using speech synthesis technology.

[0816] The "means for recognizing emotions and adjusting the content of the story" is a mechanism for analyzing the user's voice input and facial expressions, and dynamically changing the content and tone of the story based on the results.

[0817] The "storage means" is a mechanism for storing basic information received from a user in a database.

[0818] "Natural language processing" is a technology that enables computers to understand and generate human language.

[0819] "Speech synthesis" is a technology that converts text data into speech.

[0820] Specific embodiments for carrying out the present invention will be described below.

[0821] 1. System Program

[0822] This invention is a system consisting of four main elements: a server, a terminal, a user, and an emotion engine. The terminal provides an interface for inputting basic information about the child, the server generates a story based on that information, and the emotion engine recognizes the user's emotions and adjusts the content of the story. The terminal is equipped with a means for displaying the story and a means for reading it aloud.

[0823] 1.1 Enter your child's basic information

[0824] The user uses a terminal to enter basic information about their child, such as their name, age, and interests. This information is converted into JSON format and sent to the server.

[0825] 1.2 Receipt and storage of data

[0826] The server receives the basic information sent from the device, checks that the information is correct, and then stores it in a database, which may be a NoSQL database, for example.

[0827] 1.3 Narrative Generation

[0828] The server uses the stored basic information to generate a personalized story using a generative AI model (e.g., OpenAI's GPT-3), which generates a story with appropriate context and content based on the information entered by the user.

[0829] 1.4 Using the Emotion Engine

[0830] When the generator is running, the emotion engine analyzes the user's voice input and facial expressions to recognize emotions. The emotion engine uses the Google Cloud Speech API and Microsoft Azure Face API. This information is sent to the server in real time, and the content of the story is adjusted according to the user's emotions.

[0831] 1.5 Displaying and Reading Stories

[0832] The generated story is sent to the device, which presents the user with the choice of print mode or reading mode. If print mode is selected, the device displays the story on the screen. If reading mode is selected, the device reads the story aloud using speech synthesis technology (e.g., Google Text-to-Speech or Amazon Polly).

[0833] 2. Hardware and Software Details

[0834] To realize this system, the following hardware and software are used:

[0835] Hardware: Devices such as smartphones, tablets, and computers.

[0836] Software: Natural language processing algorithms (e.g., GPT-3), speech recognition APIs (e.g., Google Cloud Speech-to-Text), facial expression recognition APIs (e.g., Microsoft Azure Face API), and speech synthesis APIs (e.g., Google Text-to-Speech, Amazon Polly).

[0837] 3. Specific Examples

[0838] For example, suppose a user inputs their child's name as "Taro," their age as "5 years old," and their favorite thing as "dinosaurs." Based on this information, the following story will be generated:

[0839] Example prompt sentence:

[0840] Taro is a 5-year-old boy. His favorite thing is dinosaurs. One day, while he was playing in the park, a huge dinosaur suddenly appeared!

[0841] Examples of generated narrative contributions:

[0842] Taro is a five-year-old boy. His favorite thing is dinosaurs. One day, while Taro was playing in the park, a huge dinosaur suddenly appeared! Taro was startled and stepped back a little, but the dinosaur had kind eyes.

[0843] If the emotion engine recognizes the user's emotion of joy, the story content is adjusted as follows:

[0844] Taro is a five-year-old boy. His favorite thing is dinosaurs. One day, while Taro was having fun playing in the park, a big, smiling dinosaur suddenly appeared! Taro was surprised and stepped back a little, but the dinosaur's eyes were kind, and the two quickly became friends.

[0845] In this way, the present invention provides a system that provides a personalized story for children and dynamically adjusts the content based on the user's emotions, providing a more engaging and educational experience.

[0846] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[0847] Step 1:

[0848] The user uses the terminal to enter basic information about their child (such as name, age, and favorite things). The terminal converts this information into JSON format and sends it to the server. This process prepares the terminal to send the entered information to the server in the appropriate format. The input data is the child's basic information entered by the user into the interface, and the output is the data converted to JSON format.

[0849] Step 2:

[0850] The server receives the child's basic information in JSON format sent from the device and verifies that the information is correct. During the verification process, the data format and content are checked to ensure they are correct. Once the data is confirmed to be correct, it is stored in a NoSQL database. The input data is the child's basic information in JSON format, and the output is the information stored in the database.

[0851] Step 3:

[0852] The server runs a generative AI model (e.g., OpenAI's GPT-3) based on the stored basic information to generate a story. In the generation process, the basic information entered by the user is converted into a prompt sentence and sent to the AI ​​model. The AI ​​model generates a story based on the prompt sentence and returns the result to the server. The input data is the basic information stored in the database, and the output is the generated story.

[0853] Step 4:

[0854] After the generated story is returned to the server, the server launches an emotion engine to analyze the user's emotions. The user's emotions are analyzed in real time using voice input and facial expression recognition APIs (such as Google Cloud Speech-to-Text or Microsoft Azure Face API). Once the emotion data is analyzed, the server uses that information to adjust the tone and content of the generated story. The input data are the generated story and emotion data, and the output is the adjusted story.

[0855] Step 5:

[0856] The server sends the adapted story to the terminal, which displays it on its user interface. The terminal then offers the user a choice between a print mode and a reading mode. When the user selects one of the modes, the terminal displays or reads the story based on the user's selection. The input data is the adapted story and the user's mode selection, and the output is a visual display or audio reading of the story.

[0857] Step 6:

[0858] If the device displays a story based on the user's selection, the story will be displayed on the screen. The user can read the story themselves. If read-aloud mode is selected, the device will read the story using a speech synthesis API (such as Google Text-to-Speech or Amazon Polly). The speech synthesis API converts text data into speech and plays it through the speaker. The input data is the story text, and the output is synthesized speech.

[0859] 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.

[0860] 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.

[0861] 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.

[0862] [Third embodiment]

[0863] FIG. 5 shows an example of the configuration of a data processing system 310 according to the third embodiment.

[0864] 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.

[0865] 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).

[0866] 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.

[0867] 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.

[0868] 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).

[0869] 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.

[0870] 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.

[0871] 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.

[0872] 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.

[0873] 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.

[0874] 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."

[0875] The following describes the mode for carrying out this invention. The system accepts basic information about a child entered by a user, generates a personalized story based on that information, and displays or reads it aloud. This system consists of three main components: a terminal, a server, and a user.

[0876] User Input

[0877] First, the user enters basic information about their child using the terminal. The terminal provides an interface for the user to enter information. For example, they can enter their child's name, age, favorite things, etc. through a form. This basic information is converted into JSON format and sent to the server.

[0878] Receiving and storing data

[0879] The server receives the basic information sent from the device and checks for errors. The received information is then stored in a database. For example, a NoSQL database such as MongoDB can be used for the database.

[0880] Narrative Generation

[0881] The server generates a story based on the stored basic information. It uses a generative algorithm that uses natural language processing (NLP) technology to create a personalized story with the child as the protagonist. Specifically, a generative AI model such as GPT-3 is used. The story is generated with appropriate context and content based on the information entered by the user.

[0882] Providing Choices

[0883] The generated story data is sent back to the terminal and displayed on the terminal. The terminal presents the user and the child with the choice of print mode and reading mode. The user can select from these modes.

[0884] Showing the story

[0885] If the user selects print mode, the device will display the generated story on the screen, allowing the child to read the story themselves.

[0886] Story reading

[0887] If the user selects the reading mode, the device will read the generated story using speech synthesis technology, for example, using a speech synthesis API (such as Amazon Polly or Google Text-to-Speech), allowing parents to use the system as an alternative to reading aloud.

[0888] Specific examples

[0889] For example, if a user enters their child's name as "Taro," their age as "5 years old," and their favorite thing as "dinosaurs," the server will generate the following story based on this information:

[0890] "Taro is a five-year-old boy. His favorite thing is dinosaurs. One day, while Taro was playing in the park, a huge dinosaur suddenly appeared! Taro was startled and stepped back a little, but the dinosaur had kind eyes."

[0891] When the user selects print mode, the story is displayed on the device screen. When the user selects read-aloud mode, the story is read aloud using text-to-speech technology. This way, children can have fun on their own and parents can have an educational experience even when they're busy.

[0892] The processing flow will be explained below.

[0893] Step 1:

[0894] User: Enter basic information such as the child's name, age, and favorite things into the input form on the device. For example, enter the child's name "Taro," age "5 years old," and favorite thing "dinosaurs."

[0895] Step 2:

[0896] Device: Convert the entered basic information into JSON format. The converted data is {"name": "Taro", "age": "5 years old", "likes": "dinosaur"}.

[0897] Step 3:

[0898] Terminal: The converted JSON data is sent to the server as an HTTP POST request.

[0899] Step 4:

[0900] Server: Receives the transmitted data and checks whether the format of the received data is correct.

[0901] Step 5:

[0902] Server: Store the received data in a database. For example, store it in a NoSQL database as {"name": "Taro", "age": "5 years old", "likes": "Dinosaur"}.

[0903] Step 6:

[0904] Server: Activates the generation method based on the stored data. Specifically, it generates a story using a natural language processing algorithm (e.g., GPT-3).

[0905] Step 7:

[0906] Server: Generates a story from an AI model. For example, it generates a story like, "Taro is a 5-year-old boy. His favorite thing is dinosaurs. One day, while Taro was playing in the park, a huge dinosaur suddenly appeared! Taro was startled and stepped back a little, but the dinosaur had kind eyes."

[0907] Step 8:

[0908] Server: Sends the generated story data to the terminal.

[0909] Step 9:

[0910] Terminal: Prepares an interface for displaying received story data. Presents the user with the choice between print mode and reading mode.

[0911] Step 10:

[0912] User: Select print mode or speech mode.

[0913] Step 11:

[0914] Device: If the user selects print mode, the story is displayed on the screen. If the user selects reading mode, the story is read aloud using a speech synthesis API.

[0915] Step 12:

[0916] Terminal: Based on the selection, presents the story to the user: in print mode, it displays the text; in read-aloud mode, it plays the story aloud.

[0917] The above are specific processing steps including the roles of the user, terminal, and server.

[0918] Example 1

[0919] 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."

[0920] Conventional story generation systems have limited functionality for generating personalized stories based on individual child information, resulting in issues with not being able to provide content optimized for a child's interests and comprehension level. Additionally, parents have had to spend time and effort reading the displayed stories aloud, which hinders the provision of a meaningful educational experience. Given these issues, there is a demand for a story generation system that offers an improved user experience and high educational effectiveness.

[0921] 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.

[0922] In this invention, the server includes means for accepting basic information about a child entered by a user, means for converting the accepted basic information into JSON format and sending it to the server, means for checking the received basic information for errors and storing it in a database, means for generating a personalized story based on the stored basic information, means for displaying the generated story on a user interface, means for reading the generated story using voice synthesis, and means for presenting the user with a choice between a print mode and a reading mode. This makes it possible to generate a personalized story with high accuracy based on individual information, allowing children to enjoy stories themselves and providing an educational experience that reduces the burden on parents.

[0923] "User" refers to a user who uses the system to input basic information about their child and enjoys the generated story in viewing or reading mode.

[0924] "Basic child information" refers to data needed to personalize the story, such as the child's name, age, and likes.

[0925] A "terminal" is a device through which a user enters basic information about their child, and includes a PC, smartphone, tablet, etc.

[0926] "Server" refers to a central computer system that receives and processes data sent from the terminals and provides the generated story.

[0927] "JSON format" stands for JavaScript Object Notation and refers to a lightweight text-based data format used for exchanging and storing data.

[0928] A "database" is a digital storehouse that stores information in an organized manner and makes it easy to search and retrieve; an example of a NoSQL database is MongoDB.

[0929] "Personalization" refers to personalizing content based on specific information provided by the user to provide the best possible experience for the target child.

[0930] "Generation means" refers to a mechanism that automatically creates a story based on stored information using natural language processing technology.

[0931] "Natural language processing technology" refers to the field of technology for processing, understanding, and generating human language using computers.

[0932] A "generative AI model" is a type of artificial intelligence that generates human language based on large amounts of data, and examples include GPT-3.

[0933] "Display means" refers to a mechanism for visually presenting the generated story in a user interface.

[0934] "Reading means" refers to a mechanism for playing back the generated story aloud using speech synthesis technology.

[0935] "Speech synthesis technology" refers to technology that generates speech that resembles a human voice based on text information, and examples include text-to-speech technology.

[0936] "User interface" refers to the interface through which a user interacts with a system, including screen displays and audio outputs.

[0937] This invention is a system that generates a personalized story based on basic information about a child entered by the user, and displays or reads the story. This system consists of three main components: the user, the terminal, and the server.

[0938] User Input

[0939] The user uses the device to enter basic information about their child. The device provides an interface for the user to enter information, such as the child's name, age, and favorite things, through a form. This basic information is converted into JSON format and sent to the server.

[0940] Receiving and storing data

[0941] The server receives the basic information sent by the device and checks for errors, specifically whether required fields are empty and whether the format is correct. The received information is then stored in a NoSQL database such as MongoDB.

[0942] Narrative Generation

[0943] The server generates a story based on the stored basic information. It uses a generation algorithm that uses natural language processing (NLP) technology to create a personalized story with the child as the protagonist. Specifically, a generative AI model (e.g., GPT-3) is used. The following prompt is used:

[0944] Prompt Sentence Examples

[0945] "Name: Taro, Age: 5, Favorite thing: Dinosaurs"

[0946] Based on this prompt, the generative AI model will generate a story. The generated story will look something like this:

[0947] Taro is a five-year-old boy. His favorite thing is dinosaurs. One day, while Taro was playing in the park, a huge dinosaur suddenly appeared! Taro was startled and stepped back a little, but the dinosaur had kind eyes.

[0948] Providing Choices

[0949] The generated story data is sent back to the terminal and displayed on the terminal. The terminal presents the user with the choice of print mode or reading mode. The user can select from these modes.

[0950] Showing the story

[0951] If the user selects print mode, the device will display the generated story on the screen, allowing the child to read the story themselves.

[0952] Story reading

[0953] If the user selects the reading mode, the device will read the generated story using speech synthesis technology, such as a speech synthesis API (e.g., Amazon Polly or Google Text-to-Speech). This allows parents to use the system as an alternative to reading aloud.

[0954] In this way, the system generates, displays, and recites personalized stories based on basic information about the child entered by the user, providing an educational experience while reducing the burden on parents.

[0955] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0956] Step 1:

[0957] The user enters information on the device

[0958] The user uses the device interface to enter basic information about the child (name, age, favorite things). This information becomes input data. The device converts the entered information into JSON format. Here, the input is the child's basic information, and the output is JSON format data.

[0959] What happens: A user fills out a web form or app and clicks the "Submit" button.

[0960] Step 2:

[0961] The device sends information to the server

[0962] The terminal sends the converted JSON formatted data to the server via an HTTP POST request. The input is the basic information of the child in JSON format, and the output is an HTTP request.

[0963] Specific operation: The device sends an HTTP POST request to the API endpoint.

[0964] Step 3:

[0965] The server receives the information

[0966] The server receives the JSON data sent from the terminal. It analyzes the received data and performs validation such as checking whether required fields are empty and whether the format is correct. The input is the JSON data included in the HTTP request, and the output is the validated JSON data.

[0967] Specific operation: A data validation script runs on the server side to check for invalid data.

[0968] Step 4:

[0969] The server stores the information in a database

[0970] The server stores the verified basic information in a NoSQL database such as MongoDB, where the input is the validated JSON data and the output is the entry stored in the database.

[0971] What happens: The server performs a database insert operation, for example, storing the data as a document in a MongoDB collection.

[0972] db.childrenInfo.insert({"Name": "Taro", "Age": "5 years old", "Favorite things": "Dinosaurs"})

[0973] Step 5:

[0974] The server generates the story

[0975] The server generates a personalized story using a generative AI model (e.g., GPT-3) based on the stored basic information. The input is the JSON data stored in the database, and the output is the text of the generated story. Specifically, the following prompt sentence is provided to the AI ​​model:

[0976] {

[0977] "Name": "Taro",

[0978] "age": "5 years old",

[0979] "Favorite things": "Dinosaurs"

[0980] }

[0981] The generative AI model generates the following story:

[0982] Taro is a five-year-old boy. His favorite thing is dinosaurs. One day, while Taro was playing in the park, a huge dinosaur suddenly appeared! Taro was startled and stepped back a little, but the dinosaur had kind eyes.

[0983] Step 6:

[0984] The server sends the story to the device.

[0985] The generated story data is again sent to the terminal as an HTTP response. The input is the generated story text, and the output is the HTTP response.

[0986] Specific operation: The server sends the generated story text in the HTTP response body.

[0987] Step 7:

[0988] The device presents the user with a choice of display modes

[0989] The terminal presents the user with the options of "print mode" and "reading mode" on the screen. The input is the story data included in the HTTP response, and the output is a user interface displaying the options.

[0990] Specific operation: The device generates a UI including a selection button and displays it to the user.

[0991] Step 8:

[0992] If the user selects type mode

[0993] If the user selects print mode, the terminal displays the generated story on the screen: the input is the user's selections, and the output is the story text displayed on the screen.

[0994] Specific action: The user clicks the "print mode" button and the device displays the text on the screen.

[0995] Step 9:

[0996] When the user selects read aloud mode

[0997] If the user selects read-aloud mode, the device reads the story aloud using speech synthesis technology (e.g., Amazon Polly or Google Text-to-Speech). The input is the user's selection, and the output is the story played as audio.

[0998] Specific operation: The device calls the speech synthesis API and plays the generated voice data.

[0999] (Application example 1)

[1000] 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."

[1001] With conventional story provision systems, it was difficult to provide personalized stories for specific children, and the lack of a choice between print and reading modes meant that children's interest could not be fully stimulated.Furthermore, there was a lack of experiential educational applications that could be immediately used in stores, which led to low customer satisfaction in stores.

[1002] 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.

[1003] In this invention, the server includes means for accepting basic information input by a user, means for generating a story based on the accepted basic information, means for displaying the generated story on a user interface, means for reading the generated story by voice synthesis, and means for providing a choice between a print mode and a read-aloud mode through the user interface. This makes it possible to instantly provide a story personalized to a specific child and to pique the child's interest by offering a choice between the print mode and the read-aloud mode, thereby increasing customer satisfaction in the store.

[1004] "Basic information entered by the user" is data that the user enters about the child, such as name, age, and favorite things.

[1005] "Generation means" refers to a device or program that has the function of creating a story based on input basic information.

[1006] "Display means" refers to a device or program for visually presenting the generated story on a user interface.

[1007] The "reading means" is a device or program for reproducing the generated story aloud using voice synthesis technology.

[1008] A "user interface" is a device or program that allows a user to interact with a system, input information, view or listen to a story.

[1009] "Print mode" is a function that displays the generated story in text format.

[1010] "Reading mode" is a function that plays the generated story as audio.

[1011] A "database" is a structured collection of data for storing basic information received from users.

[1012] "Natural language processing" is a technology for understanding and generating human language, and is used here to generate stories.

[1013] A "generative AI model" is an algorithm that uses artificial intelligence to generate personalized stories.

[1014] A "prompt sentence" is a sentence that serves as the starting point for the generative AI model to generate a story, and is constructed based on basic information entered by the user.

[1015] The system of this invention uses a generative AI model to generate personalized stories based on basic information entered by the user, and provides the functionality to display or read them aloud. The system consists of three main components: a terminal, a server, and a user.

[1016] User Input

[1017] The user enters basic information using a device, such as the child's name, age, and favorite things, through a form. For example, a tablet or smartphone can be used. The entered basic information is converted into JSON format and sent to the server.

[1018] Receiving and storing data

[1019] The server receives the basic information sent from the device and performs error checking. The received information is then stored in a database, typically a NoSQL database such as MongoDB.

[1020] Narrative Generation

[1021] The server generates a story based on the stored basic information. For example, GPT-3 is used as a generative AI model. This model uses natural language processing technology to generate a story with appropriate context and content based on the information entered by the user. For example, if a user enters the following basic information:

[1022] Name: "Rina"

[1023] Age: 6

[1024] Likes: Princesses

[1025] With this information, the server generates a prompt like this:

[1026] Lina is a 6-year-old girl. Her favorite thing is princesses. One day, while Lina was playing in the garden, a huge castle suddenly appeared!

[1027] The prompt sentence is then used as input to generate a story using a GPT-3 model.

[1028] Providing Choices

[1029] The generated story data is sent to the terminal and displayed on the terminal. The terminal presents the user or child with the choice of print mode or reading mode. The user can select from these modes.

[1030] Showing the story

[1031] If the user selects the print mode, the device will display the generated story on the screen, allowing the child to read the story themselves.

[1032] Story reading

[1033] When the user selects the reading mode, the device will read the generated story using speech synthesis technology, specifically using speech synthesis APIs such as Amazon Polly and Google Text-to-Speech.

[1034] For example, the following story appears on the terminal screen:

[1035] Lina is a 6-year-old girl. Her favorite thing is princesses. One day, while Lina was playing in the garden, a huge castle suddenly appeared!

[1036] Lina stared in amazement at the sight before her. The castle door opened, and the kind-looking king stepped out. "Hello, Lina. Welcome to your adventure to become a princess," the king smiled.

[1037] If the user selects the read aloud mode, the story will be read aloud for the child's listening pleasure.

[1038] This system allows for personalized stories to be delivered to specific children in-store, resulting in higher customer satisfaction.

[1039] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[1040] Step 1:

[1041] The user uses the device to enter basic information about their child, such as the child's name, age, and favorite things, into the form displayed on the device screen, and then presses the submit button. The entered basic information is converted into JSON format and sent to the server.

[1042] Input: Basic information such as your child's name, age, and favorite things.

[1043] Output: Basic information converted to JSON format.

[1044] Step 2:

[1045] The server receives the basic information in JSON format sent from the device and performs error checks. Information that passes the check is saved in a database. Specifically, the information is stored in a NoSQL database such as MongoDB.

[1046] Input: Basic information in JSON format.

[1047] Output: Basic information stored in the database.

[1048] Step 3:

[1049] The server generates a story based on the basic information stored in the database. First, it creates a prompt sentence using the basic information, and then inputs the prompt sentence into a generative AI model (e.g., GPT-3). This model uses natural language processing technology to generate a story based on the input prompt sentence.

[1050] Input: Basic information retrieved from the database.

[1051] Data processing: Convert basic information into prompt sentences.

[1052] Data Computation: Generate stories using generative AI models.

[1053] Output: The generated narrative text.

[1054] Step 4:

[1055] The generated story data is sent from the server to the terminal. On the terminal, before the generated story is displayed to the user, the user is presented with the choice of print mode or reading mode. The user selects the desired mode.

[1056] Input: The text data of the generated story.

[1057] Output: The choices presented to the user (print mode, spoken mode).

[1058] Step 5:

[1059] If the user selects print mode, the terminal displays the generated story on the screen.

[1060] Input: User selection of type mode.

[1061] Output: The generated narrative text that is displayed on the screen.

[1062] Step 6:

[1063] When the user selects the reading mode, the device reads the generated story aloud using speech synthesis technology, specifically, using speech synthesis APIs such as Amazon Polly and Google Text-to-Speech to play the story aloud.

[1064] Input: User selection of reading mode.

[1065] Output: The generated story played as audio.

[1066] 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.

[1067] We will now explain the mode for implementing this invention. The system accepts basic information about a child entered by a user, generates a personalized story based on that information, and has the function of recognizing the user's emotions and adjusting the content of the story. This system consists of four main elements: a terminal, a server, a user, and an emotion engine.

[1068] User Input

[1069] First, the user enters basic information about their child using the device. The device provides an interface for the user to enter information. For example, they can enter their child's name, age, favorite things, etc. through a form. This basic information is converted into JSON format and sent to the server.

[1070] Receiving and storing data

[1071] The server receives the basic information sent from the device and checks whether it is correct. The received information is stored in a database. For example, a NoSQL database can be used for the database.

[1072] Narrative Generation

[1073] The server then activates a generation mechanism based on the stored basic information. Specifically, a generation algorithm is used to create a personalized story with a child as the main character, using a natural language processing algorithm (e.g., GPT-3). The story is generated with appropriate context and content based on the information entered by the user.

[1074] Use of emotion engine

[1075] When the generation means operates, the emotion engine recognizes the user's emotion. The emotion engine analyzes the user's voice input and facial expressions to recognize the emotion and sends the information to the server. The emotion engine can use a speech recognition API or facial expression recognition API (e.g., Google Cloud Speech-to-Text or Microsoft Azure Face API).

[1076] Emotion-based narrative adjustment

[1077] The server adjusts the content of the generated story based on information from the emotion engine. For example, if the user expresses happy emotions, it adjusts the tone of the story to be lighter.

[1078] Providing Choices

[1079] The generated story data is sent back to the terminal and displayed on the terminal. The terminal presents the user and the child with the choice of print mode and reading mode. The user can select from these modes.

[1080] Showing the story

[1081] If the user selects print mode, the device will display the generated story on the screen, allowing the child to read the story themselves.

[1082] Story reading

[1083] If the user selects the reading mode, the device will read the generated story using speech synthesis technology, for example, using a speech synthesis API (such as Amazon Polly or Google Text-to-Speech), allowing parents to use the system as an alternative to reading aloud.

[1084] Specific examples

[1085] For example, if a user enters their child's name as "Taro," their age as "5 years old," and their favorite thing as "dinosaurs," the server will generate the following story based on this information:

[1086] "Taro is a five-year-old boy. His favorite thing is dinosaurs. One day, while Taro was playing in the park, a huge dinosaur suddenly appeared! Taro was startled and stepped back a little, but the dinosaur had kind eyes."

[1087] If the emotion engine recognizes the user's emotion of joy, it can adjust the tone of the story to be even brighter.

[1088] "Taro is a five-year-old boy. His favorite thing is dinosaurs. One day, while Taro was having fun playing in the park, a big, smiling dinosaur suddenly appeared! Taro was startled and stepped back a little, but the dinosaur's eyes were kind, and the two quickly became friends."

[1089] When the user selects print mode, the story is displayed on the device screen. When the user selects read-aloud mode, the story is read aloud using text-to-speech technology. This way, children can have fun on their own and parents can have an educational experience even when they're busy.

[1090] The processing flow will be explained below.

[1091] Step 1:

[1092] User: Enter basic information such as the child's name, age, and favorite things into the input form on the device. For example, enter the child's name "Taro," age "5 years old," and favorite thing "dinosaurs."

[1093] Step 2:

[1094] Device: Convert the entered basic information into JSON format. The converted data is {"name": "Taro", "age": "5 years old", "likes": "dinosaur"}.

[1095] Step 3:

[1096] Terminal: The converted JSON data is sent to the server as an HTTP POST request.

[1097] Step 4:

[1098] Server: Receives the transmitted data and checks whether the format of the received data is correct.

[1099] Step 5:

[1100] Server: Store the received data in a database. For example, store it in a NoSQL database as {"name": "Taro", "age": "5 years old", "likes": "Dinosaur"}.

[1101] Step 6:

[1102] Server: Activates the generation method based on the stored data. Specifically, it generates a story using a natural language processing algorithm (e.g., GPT-3).

[1103] Step 7:

[1104] Server: Generates a story from an AI model. For example, it generates a story like, "Taro is a 5-year-old boy. His favorite thing is dinosaurs. One day, while Taro was playing in the park, a huge dinosaur suddenly appeared! Taro was startled and stepped back a little, but the dinosaur had kind eyes."

[1105] Step 8:

[1106] Terminal: Receives the generated story and activates the emotion engine, which is a function for analyzing the user's voice and facial expressions.

[1107] Step 9:

[1108] Terminal: The emotion engine analyzes the user's voice input and generates the user's emotion data. For example, if a happy voice pattern is detected, the emotion data for "joy" is generated.

[1109] Step 10:

[1110] Device: The emotion engine analyzes the user's facial expressions and complements the user's emotional data. For example, if a smiling expression is detected, the "joy" emotion data is strengthened.

[1111] Step 11:

[1112] Terminal: Sends the generated emotion data to the server.

[1113] Step 12:

[1114] Server: Analyzes the received emotional data and adjusts the tone and content of the generated story. For example, if it receives emotional data of "joy," it brightens the tone of the story. It adjusts the story to something like, "Taro was having fun playing in the park when suddenly, a big, smiling dinosaur appeared!"

[1115] Step 13:

[1116] Server: Sends the adjusted story data to the device.

[1117] Step 14:

[1118] Terminal: Prepares an interface for displaying received story data. Presents the user with the choice between print mode and reading mode.

[1119] Step 15:

[1120] User: Select print mode or speech mode.

[1121] Step 16:

[1122] Device: If the user selects print mode, the story is displayed on the screen. If the user selects reading mode, the story is read aloud using a speech synthesis API.

[1123] Step 17:

[1124] Terminal: Based on the selection, presents the story to the user: in print mode, it displays the text; in read-aloud mode, it plays the story aloud.

[1125] The above are specific processing steps including the roles of the user, terminal, server, and emotion engine.

[1126] Example 2

[1127] 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."

[1128] Conventional personalized story generation systems lack the ability to dynamically adjust the content of a story based on the user's emotions. This makes it difficult to provide stories that reflect the user's emotions and children's preferences. Furthermore, since users have limited options for listening to stories through audio, there is a need to provide a more interactive and richer experience.

[1129] The specific processing by the specific processing unit 290 of the data processing device 12 in the second embodiment is realized by the following means.

[1130] In this invention, the server includes means for accepting basic information about the child entered by the user, means for converting the accepted basic information into JSON format and transmitting it to the server, means for storing the accepted basic information in a database, means for generating a story using a generative AI model based on the stored basic information, means for adjusting the content of the generated story using an emotion recognition engine that analyzes the user's emotions, means for displaying the generated story on a user interface, and means for reciting the generated story using speech synthesis. This enables the provision of a personalized story that reflects the user's emotions and the child's preferences. Furthermore, by providing the user with the option of reading the story as text or listening to it audibly, a more interactive and richer experience can be provided.

[1131] "User" refers to the person who operates the system and enters basic information about the child.

[1132] "Basic information" refers to personally identifiable information such as the child's name, age, and likes.

[1133] "Terminal" refers to an electronic device that a user uses to input information.

[1134] "JSON format" refers to a standard data format that represents data in text.

[1135] "Server" refers to a remote computer for processing and storing received data.

[1136] "Database" means a data management system for storing received Basic Information.

[1137] A "generative AI model" refers to artificial intelligence technology that generates stories using natural language processing technology.

[1138] An "emotion recognition engine" refers to technology that recognizes emotions by analyzing a user's voice and facial expressions.

[1139] "User interface" refers to the screen or display device through which a user can view the generated story.

[1140] "Speech synthesis" refers to the technology of reading text data aloud.

[1141] "Interactive" refers to a dynamic experience that involves interaction with the user.

[1142] MODE FOR CARRYING OUT THE INVENTION

[1143] This section describes an embodiment of the present invention. This system accepts basic information about a child entered by a user, generates a personalized story based on that information, and also has the ability to adjust the content of the story by recognizing the user's emotions. This system consists of four main components: a terminal, a server, a user, and an emotion recognition engine.

[1144] User Input

[1145] The user uses the device to enter basic information about the child. The device provides an interface for the user to enter information. For example, the user can enter the child's name, age, favorite things, etc. through a form. This basic information is converted into JSON format and sent to the server.

[1146] Examples:

[1147] The user enters the child's name as "Taro," their age as "5 years old," and their favorite thing as "dinosaurs" through a form on the device.

[1148] Receiving and storing data

[1149] The server receives the basic information sent from the device and checks for errors. The received information is stored in a database. A NoSQL database (e.g., MongoDB) can be used for the database.

[1150] Examples:

[1151] The server receives basic information such as "Taro," "5 years old," and "dinosaur," and stores this in MongoDB.

[1152] Narrative Generation

[1153] The server then activates a generation mechanism based on the stored basic information. Specifically, it uses a generative AI model (e.g., GPT-3 natural language processing technology) to create a personalized story with the child as the protagonist. The story is generated with appropriate context and content based on the information entered by the user.

[1154] Examples:

[1155] The server uses GPT-3 to generate a story with Taro as the main character.

[1156] Example prompt sentence:

[1157] "I have a 5-year-old boy named Taro who loves dinosaurs. Please create a fun story with Taro as the main character, where he meets a big dinosaur in the park."

[1158] Use of emotion engine

[1159] When the generation means operates, the emotion recognition engine recognizes the user's emotions. The emotion engine analyzes the user's voice input and facial expressions to recognize emotions and sends that information to the server. Specifically, it can use a speech recognition API (e.g., Google Cloud Speech-to-Text) or a facial expression recognition API (e.g., Microsoft Azure Face API).

[1160] Examples:

[1161] The emotion engine uses Google Cloud Speech-to-Text to recognize the emotion of joy from the user's voice and send that information to the server.

[1162] Emotion-based narrative adjustment

[1163] The server adjusts the content of the generated story based on information from the emotion engine. For example, if the user expresses happy emotions, it adjusts the tone of the story to be lighter.

[1164] Examples:

[1165] The server recognizes the user's emotions of joy and lightens the tone of the story.

[1166] Providing a Generative Story

[1167] The generated story data is sent back to the terminal and displayed on the terminal. The terminal provides the user and the child with the choice of a print mode or a reading mode. The user can select from these modes.

[1168] Examples:

[1169] The device offers a choice between print mode and read-aloud mode below the displayed story, and the user can choose one.

[1170] Display or read the mode

[1171] If the user selects print mode, the device displays the generated story on the screen, allowing the child to read the story by themselves. If the user selects read-aloud mode, the device uses speech synthesis technology (e.g., Amazon Polly) to read the story aloud, allowing parents to use the system as an alternative to reading aloud to their children.

[1172] Examples:

[1173] If the user selects print mode, Tarou begins reading the story displayed on the device. If the user selects read-aloud mode, Tarou listens to the story read aloud by Amazon Polly.

[1174] The flow of the identification process in the second embodiment will be described with reference to FIG.

[1175] Step 1: Enter your user information

[1176] The user uses the terminal to enter basic information about the child. The terminal provides an interface for the user to enter information. The entered information includes the child's name, age, favorite things, etc. This basic information is converted into JSON format and sent to the server.

[1177] Specific behavior:

[1178] The user enters information such as "Taro," "5 years old," and "dinosaur" into a form on the device.

[1179] Input: Basic information such as your child's name, age, and favorite things

[1180] Output: JSON format data

[1181] Step 2: Sending and receiving basic information

[1182] The device sends basic information converted to JSON format to the server, which then receives the JSON data and checks for errors.

[1183] Specific behavior:

[1184] The device converts the information into JSON format and sends it to the server, which then analyzes the received JSON data and checks for errors.

[1185] Input: Basic information in JSON format

[1186] Output: Parsed basic information

[1187] Step 3: Save your basic information

[1188] The server stores the parsed basic information in a database, which can be a NoSQL database (e.g., MongoDB).

[1189] Specific behavior:

[1190] The server stores the parsed basic information in MongoDB.

[1191] Input: Parsed basic information

[1192] Output: Basic information stored in the database

[1193] Step 4: Narrative generation

[1194] The server then uses the stored basic information to launch a generative AI model (e.g., GPT-3) to generate a personalized story with the child as the protagonist. The story is generated with appropriate context and content according to the prompt text entered by the user.

[1195] Specific behavior:

[1196] The server inputs the prompt "Taro is the main character, and his favorite thing is dinosaurs" into GPT-3 and generates a story.

[1197] Input: Basic information, prompt

[1198] Output: The generated story

[1199] Step 5: Recognize emotions

[1200] When the generator is running, the emotion recognition engine recognizes the user's emotions. The emotion engine uses a speech recognition API (e.g., Google Cloud Speech-to-Text) or a facial expression recognition API (e.g., Microsoft Azure Face API) to analyze the user's voice input and facial expressions and recognize the emotions. This information is sent to the server.

[1201] Specific behavior:

[1202] The emotion engine uses Google Cloud Speech-to-Text to recognize the emotion of joy from the user's voice and send that information to the server.

[1203] Input: User's voice or facial expression

[1204] Output: Recognized user emotion information

[1205] Step 6: Adjust the story

[1206] The server adjusts the content of the generated story based on the user's emotional information received from the emotion engine. For example, if the user expresses a happy emotion, the server adjusts the tone of the story to be brighter.

[1207] Specific behavior:

[1208] The server recognizes that the user is happy and adjusts the tone of the story to be even lighter.

[1209] Input: User's emotion information, generated story

[1210] Output: Adjusted narrative

[1211] Step 7: Submit and view your story

[1212] The generated story data is sent back to the terminal from the server and displayed on the terminal, which provides the user and the child with the choice of a print mode or a reading mode.

[1213] Specific behavior:

[1214] The server sends the generated story data to the terminal, which displays it on the screen, and the user can choose between print mode and reading mode.

[1215] Input: Adjusted Narrative

[1216] Output: The story displayed on the terminal

[1217] Step 8: Select a Mode

[1218] The user selects one of the options displayed on the terminal: print mode or reading mode.

[1219] Specific behavior:

[1220] The user selects print mode or speech mode from the options displayed on the device screen.

[1221] Input: Mode selection

[1222] Output: Selected mode

[1223] Step 9: Show or read the story

[1224] If the user selects print mode, the device displays the generated story on the screen. If the user selects read-aloud mode, the device uses speech synthesis technology (e.g., Amazon Polly) to read the story aloud.

[1225] Specific behavior:

[1226] When the user selects print mode, the device displays the story on the screen for the user to read, and when the user selects read aloud mode, the story is played aloud using Amazon Polly.

[1227] Input: Selected mode

[1228] Output: A story displayed on a screen or read aloud

[1229] (Application example 2)

[1230] 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."

[1231] Conventional story generation systems are unable to dynamically adjust story content to match the user's emotions, making it difficult to provide children with a more engaging and personalized educational experience. Furthermore, they lack comprehensive methods for easily storing, viewing, and reciting stories.

[1232] 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.

[1233] In this invention, the server includes means for accepting basic information about the child input by the user, means for generating a story based on the accepted basic information, means for recognizing the user's emotions and adjusting the content of the story, means for displaying the generated story on a user interface, and means for reciting the generated story by voice synthesis. This enables the generation of a personalized story according to the user's emotions, providing a more engaging and educational experience for the child.

[1234] "User-entered basic information about the child" is information the user enters to personalize the story, such as the child's name, age, and favorite things.

[1235] The "generation means" is a mechanism for generating a story based on the received basic information, and primarily uses natural language processing technology.

[1236] "Display means" is a mechanism for displaying the generated story on the user interface of the terminal.

[1237] The "reading means" is a mechanism for reading aloud a story generated using speech synthesis technology.

[1238] The "means for recognizing emotions and adjusting the content of the story" is a mechanism for analyzing the user's voice input and facial expressions, and dynamically changing the content and tone of the story based on the results.

[1239] The "storage means" is a mechanism for storing basic information received from a user in a database.

[1240] "Natural language processing" is a technology that enables computers to understand and generate human language.

[1241] "Speech synthesis" is a technology that converts text data into speech.

[1242] Specific embodiments for carrying out the present invention will be described below.

[1243] 1. System Program

[1244] This invention is a system consisting of four main elements: a server, a terminal, a user, and an emotion engine. The terminal provides an interface for inputting basic information about the child, the server generates a story based on that information, and the emotion engine recognizes the user's emotions and adjusts the content of the story. The terminal is equipped with a means for displaying the story and a means for reading it aloud.

[1245] 1.1 Enter your child's basic information

[1246] The user uses a terminal to enter basic information about their child, such as their name, age, and interests. This information is converted into JSON format and sent to the server.

[1247] 1.2 Receipt and storage of data

[1248] The server receives the basic information sent from the device, checks that the information is correct, and then stores it in a database, which may be a NoSQL database, for example.

[1249] 1.3 Narrative Generation

[1250] The server uses the stored basic information to generate a personalized story using a generative AI model (e.g., OpenAI's GPT-3), which generates a story with appropriate context and content based on the information entered by the user.

[1251] 1.4 Using the Emotion Engine

[1252] When the generator is running, the emotion engine analyzes the user's voice input and facial expressions to recognize emotions. The emotion engine uses the Google Cloud Speech API and Microsoft Azure Face API. This information is sent to the server in real time, and the content of the story is adjusted according to the user's emotions.

[1253] 1.5 Displaying and Reading Stories

[1254] The generated story is sent to the device, which presents the user with the choice of print mode or reading mode. If print mode is selected, the device displays the story on the screen. If reading mode is selected, the device reads the story aloud using speech synthesis technology (e.g., Google Text-to-Speech or Amazon Polly).

[1255] 2. Hardware and Software Details

[1256] To realize this system, the following hardware and software are used:

[1257] Hardware: Devices such as smartphones, tablets, and computers.

[1258] Software: Natural language processing algorithms (e.g., GPT-3), speech recognition APIs (e.g., Google Cloud Speech-to-Text), facial expression recognition APIs (e.g., Microsoft Azure Face API), and speech synthesis APIs (e.g., Google Text-to-Speech, Amazon Polly).

[1259] 3. Specific Examples

[1260] For example, suppose a user inputs their child's name as "Taro," their age as "5 years old," and their favorite thing as "dinosaurs." Based on this information, the following story will be generated:

[1261] Example prompt sentence:

[1262] Taro is a 5-year-old boy. His favorite thing is dinosaurs. One day, while he was playing in the park, a huge dinosaur suddenly appeared!

[1263] Examples of generated narrative contributions:

[1264] Taro is a five-year-old boy. His favorite thing is dinosaurs. One day, while Taro was playing in the park, a huge dinosaur suddenly appeared! Taro was startled and stepped back a little, but the dinosaur had kind eyes.

[1265] If the emotion engine recognizes the user's emotion of joy, the story content is adjusted as follows:

[1266] Taro is a five-year-old boy. His favorite thing is dinosaurs. One day, while Taro was having fun playing in the park, a big, smiling dinosaur suddenly appeared! Taro was surprised and stepped back a little, but the dinosaur's eyes were kind, and the two quickly became friends.

[1267] In this way, the present invention provides a system that provides a personalized story for children and dynamically adjusts the content based on the user's emotions, providing a more engaging and educational experience.

[1268] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[1269] Step 1:

[1270] The user uses the terminal to enter basic information about their child (such as name, age, and favorite things). The terminal converts this information into JSON format and sends it to the server. This process prepares the terminal to send the entered information to the server in the appropriate format. The input data is the child's basic information entered by the user into the interface, and the output is the data converted to JSON format.

[1271] Step 2:

[1272] The server receives the child's basic information in JSON format sent from the device and verifies that the information is correct. During the verification process, the data format and content are checked to ensure they are correct. Once the data is confirmed to be correct, it is stored in a NoSQL database. The input data is the child's basic information in JSON format, and the output is the information stored in the database.

[1273] Step 3:

[1274] The server runs a generative AI model (e.g., OpenAI's GPT-3) based on the stored basic information to generate a story. In the generation process, the basic information entered by the user is converted into a prompt sentence and sent to the AI ​​model. The AI ​​model generates a story based on the prompt sentence and returns the result to the server. The input data is the basic information stored in the database, and the output is the generated story.

[1275] Step 4:

[1276] After the generated story is returned to the server, the server launches an emotion engine to analyze the user's emotions. The user's emotions are analyzed in real time using voice input and facial expression recognition APIs (such as Google Cloud Speech-to-Text or Microsoft Azure Face API). Once the emotion data is analyzed, the server uses that information to adjust the tone and content of the generated story. The input data are the generated story and emotion data, and the output is the adjusted story.

[1277] Step 5:

[1278] The server sends the adapted story to the terminal, which displays it on its user interface. The terminal then offers the user a choice between a print mode and a reading mode. When the user selects one of the modes, the terminal displays or reads the story based on the user's selection. The input data is the adapted story and the user's mode selection, and the output is a visual display or audio reading of the story.

[1279] Step 6:

[1280] If the device displays a story based on the user's selection, the story will be displayed on the screen. The user can read the story themselves. If read-aloud mode is selected, the device will read the story using a speech synthesis API (such as Google Text-to-Speech or Amazon Polly). The speech synthesis API converts text data into speech and plays it through the speaker. The input data is the story text, and the output is synthesized speech.

[1281] 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.

[1282] 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.

[1283] 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.

[1284] [Fourth embodiment]

[1285] FIG. 7 shows an example of the configuration of a data processing system 410 according to the fourth embodiment.

[1286] 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.

[1287] 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).

[1288] 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.

[1289] 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.

[1290] 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).

[1291] 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.

[1292] 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.

[1293] 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.

[1294] 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.

[1295] 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.

[1296] 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.

[1297] 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."

[1298] The following describes the mode for carrying out this invention. The system accepts basic information about a child entered by a user, generates a personalized story based on that information, and displays or reads it aloud. This system consists of three main components: a terminal, a server, and a user.

[1299] User Input

[1300] First, the user enters basic information about their child using the terminal. The terminal provides an interface for the user to enter information. For example, they can enter their child's name, age, favorite things, etc. through a form. This basic information is converted into JSON format and sent to the server.

[1301] Receiving and storing data

[1302] The server receives the basic information sent from the device and checks for errors. The received information is then stored in a database. For example, a NoSQL database such as MongoDB can be used for the database.

[1303] Narrative Generation

[1304] The server generates a story based on the stored basic information. It uses a generative algorithm that uses natural language processing (NLP) technology to create a personalized story with the child as the protagonist. Specifically, a generative AI model such as GPT-3 is used. The story is generated with appropriate context and content based on the information entered by the user.

[1305] Providing Choices

[1306] The generated story data is sent back to the terminal and displayed on the terminal. The terminal presents the user and the child with the choice of print mode and reading mode. The user can select from these modes.

[1307] Showing the story

[1308] If the user selects print mode, the device will display the generated story on the screen, allowing the child to read the story themselves.

[1309] Story reading

[1310] If the user selects the reading mode, the device will read the generated story using speech synthesis technology, for example, using a speech synthesis API (such as Amazon Polly or Google Text-to-Speech), allowing parents to use the system as an alternative to reading aloud.

[1311] Specific examples

[1312] For example, if a user enters their child's name as "Taro," their age as "5 years old," and their favorite thing as "dinosaurs," the server will generate the following story based on this information:

[1313] "Taro is a five-year-old boy. His favorite thing is dinosaurs. One day, while Taro was playing in the park, a huge dinosaur suddenly appeared! Taro was startled and stepped back a little, but the dinosaur had kind eyes."

[1314] When the user selects print mode, the story is displayed on the device screen. When the user selects read-aloud mode, the story is read aloud using text-to-speech technology. This way, children can have fun on their own and parents can have an educational experience even when they're busy.

[1315] The processing flow will be explained below.

[1316] Step 1:

[1317] User: Enter basic information such as the child's name, age, and favorite things into the input form on the device. For example, enter the child's name "Taro," age "5 years old," and favorite thing "dinosaurs."

[1318] Step 2:

[1319] Device: Convert the entered basic information into JSON format. The converted data is {"name": "Taro", "age": "5 years old", "likes": "dinosaur"}.

[1320] Step 3:

[1321] Terminal: The converted JSON data is sent to the server as an HTTP POST request.

[1322] Step 4:

[1323] Server: Receives the transmitted data and checks whether the format of the received data is correct.

[1324] Step 5:

[1325] Server: Store the received data in a database. For example, store it in a NoSQL database as {"name": "Taro", "age": "5 years old", "likes": "Dinosaur"}.

[1326] Step 6:

[1327] Server: Activates the generation method based on the stored data. Specifically, it generates a story using a natural language processing algorithm (e.g., GPT-3).

[1328] Step 7:

[1329] Server: Generates a story from an AI model. For example, it generates a story like, "Taro is a 5-year-old boy. His favorite thing is dinosaurs. One day, while Taro was playing in the park, a huge dinosaur suddenly appeared! Taro was startled and stepped back a little, but the dinosaur had kind eyes."

[1330] Step 8:

[1331] Server: Sends the generated story data to the terminal.

[1332] Step 9:

[1333] Terminal: Prepares an interface for displaying received story data. Presents the user with the choice between print mode and reading mode.

[1334] Step 10:

[1335] User: Select print mode or speech mode.

[1336] Step 11:

[1337] Device: If the user selects print mode, the story is displayed on the screen. If the user selects reading mode, the story is read aloud using a speech synthesis API.

[1338] Step 12:

[1339] Terminal: Based on the selection, presents the story to the user: in print mode, it displays the text; in read-aloud mode, it plays the story aloud.

[1340] The above are specific processing steps including the roles of the user, terminal, and server.

[1341] Example 1

[1342] 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."

[1343] Conventional story generation systems have limited functionality for generating personalized stories based on individual child information, resulting in issues with not being able to provide content optimized for a child's interests and comprehension level. Additionally, parents have had to spend time and effort reading the displayed stories aloud, which hinders the provision of a meaningful educational experience. Given these issues, there is a demand for a story generation system that offers an improved user experience and high educational effectiveness.

[1344] 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.

[1345] In this invention, the server includes means for accepting basic information about a child entered by a user, means for converting the accepted basic information into JSON format and sending it to the server, means for checking the received basic information for errors and storing it in a database, means for generating a personalized story based on the stored basic information, means for displaying the generated story on a user interface, means for reading the generated story using voice synthesis, and means for presenting the user with a choice between a print mode and a reading mode. This makes it possible to generate a personalized story with high accuracy based on individual information, allowing children to enjoy stories themselves and providing an educational experience that reduces the burden on parents.

[1346] "User" refers to a user who uses the system to input basic information about their child and enjoys the generated story in viewing or reading mode.

[1347] "Basic child information" refers to data needed to personalize the story, such as the child's name, age, and likes.

[1348] A "terminal" is a device through which a user enters basic information about their child, and includes a PC, smartphone, tablet, etc.

[1349] "Server" refers to a central computer system that receives and processes data sent from the terminals and provides the generated story.

[1350] "JSON format" stands for JavaScript Object Notation and refers to a lightweight text-based data format used for exchanging and storing data.

[1351] A "database" is a digital storehouse that stores information in an organized manner and makes it easy to search and retrieve; an example of a NoSQL database is MongoDB.

[1352] "Personalization" refers to personalizing content based on specific information provided by the user to provide the best possible experience for the target child.

[1353] "Generation means" refers to a mechanism that automatically creates a story based on stored information using natural language processing technology.

[1354] "Natural language processing technology" refers to the field of technology for processing, understanding, and generating human language using computers.

[1355] A "generative AI model" is a type of artificial intelligence that generates human language based on large amounts of data, and examples include GPT-3.

[1356] "Display means" refers to a mechanism for visually presenting the generated story in a user interface.

[1357] "Reading means" refers to a mechanism for playing back the generated story aloud using speech synthesis technology.

[1358] "Speech synthesis technology" refers to technology that generates speech that resembles a human voice based on text information, and examples include text-to-speech technology.

[1359] "User interface" refers to the interface through which a user interacts with a system, including screen displays and audio outputs.

[1360] This invention is a system that generates a personalized story based on basic information about a child entered by the user, and displays or reads the story. This system consists of three main components: the user, the terminal, and the server.

[1361] User Input

[1362] The user uses the device to enter basic information about their child. The device provides an interface for the user to enter information, such as the child's name, age, and favorite things, through a form. This basic information is converted into JSON format and sent to the server.

[1363] Receiving and storing data

[1364] The server receives the basic information sent by the device and checks for errors, specifically whether required fields are empty and whether the format is correct. The received information is then stored in a NoSQL database such as MongoDB.

[1365] Narrative Generation

[1366] The server generates a story based on the stored basic information. It uses a generation algorithm that uses natural language processing (NLP) technology to create a personalized story with the child as the protagonist. Specifically, a generative AI model (e.g., GPT-3) is used. The following prompt is used:

[1367] Prompt Sentence Examples

[1368] "Name: Taro, Age: 5, Favorite thing: Dinosaurs"

[1369] Based on this prompt, the generative AI model will generate a story. The generated story will look something like this:

[1370] Taro is a five-year-old boy. His favorite thing is dinosaurs. One day, while Taro was playing in the park, a huge dinosaur suddenly appeared! Taro was startled and stepped back a little, but the dinosaur had kind eyes.

[1371] Providing Choices

[1372] The generated story data is sent back to the terminal and displayed on the terminal. The terminal presents the user with the choice of print mode or reading mode. The user can select from these modes.

[1373] Showing the story

[1374] If the user selects print mode, the device will display the generated story on the screen, allowing the child to read the story themselves.

[1375] Story reading

[1376] If the user selects the reading mode, the device will read the generated story using speech synthesis technology, such as a speech synthesis API (e.g., Amazon Polly or Google Text-to-Speech). This allows parents to use the system as an alternative to reading aloud.

[1377] In this way, the system generates, displays, and recites personalized stories based on basic information about the child entered by the user, providing an educational experience while reducing the burden on parents.

[1378] The flow of the identification process in the first embodiment will be described with reference to FIG.

[1379] Step 1:

[1380] The user enters information on the device

[1381] The user uses the device interface to enter basic information about the child (name, age, favorite things). This information becomes input data. The device converts the entered information into JSON format. Here, the input is the child's basic information, and the output is JSON format data.

[1382] What happens: A user fills out a web form or app and clicks the "Submit" button.

[1383] Step 2:

[1384] The device sends information to the server

[1385] The terminal sends the converted JSON formatted data to the server via an HTTP POST request. The input is the basic information of the child in JSON format, and the output is an HTTP request.

[1386] Specific operation: The device sends an HTTP POST request to the API endpoint.

[1387] Step 3:

[1388] The server receives the information

[1389] The server receives the JSON data sent from the terminal. It analyzes the received data and performs validation such as checking whether required fields are empty and whether the format is correct. The input is the JSON data included in the HTTP request, and the output is the validated JSON data.

[1390] Specific operation: A data validation script runs on the server side to check for invalid data.

[1391] Step 4:

[1392] The server stores the information in a database

[1393] The server stores the verified basic information in a NoSQL database such as MongoDB, where the input is the validated JSON data and the output is the entry stored in the database.

[1394] What happens: The server performs a database insert operation, for example, storing the data as a document in a MongoDB collection.

[1395] db.childrenInfo.insert({"Name": "Taro", "Age": "5 years old", "Favorite things": "Dinosaurs"})

[1396] Step 5:

[1397] The server generates the story

[1398] The server generates a personalized story using a generative AI model (e.g., GPT-3) based on the stored basic information. The input is the JSON data stored in the database, and the output is the text of the generated story. Specifically, the following prompt sentence is provided to the AI ​​model:

[1399] {

[1400] "Name": "Taro",

[1401] "age": "5 years old",

[1402] "Favorite things": "Dinosaurs"

[1403] }

[1404] The generative AI model generates the following story:

[1405] Taro is a five-year-old boy. His favorite thing is dinosaurs. One day, while Taro was playing in the park, a huge dinosaur suddenly appeared! Taro was startled and stepped back a little, but the dinosaur had kind eyes.

[1406] Step 6:

[1407] The server sends the story to the device.

[1408] The generated story data is again sent to the terminal as an HTTP response. The input is the generated story text, and the output is the HTTP response.

[1409] Specific operation: The server sends the generated story text in the HTTP response body.

[1410] Step 7:

[1411] The device presents the user with a choice of display modes

[1412] The terminal presents the user with the options of "print mode" and "reading mode" on the screen. The input is the story data included in the HTTP response, and the output is a user interface displaying the options.

[1413] Specific operation: The device generates a UI including a selection button and displays it to the user.

[1414] Step 8:

[1415] If the user selects type mode

[1416] If the user selects print mode, the terminal displays the generated story on the screen: the input is the user's selections, and the output is the story text displayed on the screen.

[1417] Specific action: The user clicks the "print mode" button and the device displays the text on the screen.

[1418] Step 9:

[1419] When the user selects read aloud mode

[1420] If the user selects read-aloud mode, the device reads the story aloud using speech synthesis technology (e.g., Amazon Polly or Google Text-to-Speech). The input is the user's selection, and the output is the story played as audio.

[1421] Specific operation: The device calls the speech synthesis API and plays the generated voice data.

[1422] (Application example 1)

[1423] 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."

[1424] With conventional story provision systems, it was difficult to provide personalized stories for specific children, and the lack of a choice between print and reading modes meant that children's interest could not be fully stimulated.Furthermore, there was a lack of experiential educational applications that could be immediately used in stores, which led to low customer satisfaction in stores.

[1425] 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.

[1426] In this invention, the server includes means for accepting basic information input by a user, means for generating a story based on the accepted basic information, means for displaying the generated story on a user interface, means for reading the generated story by voice synthesis, and means for providing a choice between a print mode and a read-aloud mode through the user interface. This makes it possible to instantly provide a story personalized to a specific child and to pique the child's interest by offering a choice between the print mode and the read-aloud mode, thereby increasing customer satisfaction in the store.

[1427] "Basic information entered by the user" is data that the user enters about the child, such as name, age, and favorite things.

[1428] "Generation means" refers to a device or program that has the function of creating a story based on input basic information.

[1429] "Display means" refers to a device or program for visually presenting the generated story on a user interface.

[1430] The "reading means" is a device or program for reproducing the generated story aloud using voice synthesis technology.

[1431] A "user interface" is a device or program that allows a user to interact with a system, input information, view or listen to a story.

[1432] "Print mode" is a function that displays the generated story in text format.

[1433] "Reading mode" is a function that plays the generated story as audio.

[1434] A "database" is a structured collection of data for storing basic information received from users.

[1435] "Natural language processing" is a technology for understanding and generating human language, and is used here to generate stories.

[1436] A "generative AI model" is an algorithm that uses artificial intelligence to generate personalized stories.

[1437] A "prompt sentence" is a sentence that serves as the starting point for the generative AI model to generate a story, and is constructed based on basic information entered by the user.

[1438] The system of this invention uses a generative AI model to generate personalized stories based on basic information entered by the user, and provides the functionality to display or read them aloud. The system consists of three main components: a terminal, a server, and a user.

[1439] User Input

[1440] The user enters basic information using a device, such as the child's name, age, and favorite things, through a form. For example, a tablet or smartphone can be used. The entered basic information is converted into JSON format and sent to the server.

[1441] Receiving and storing data

[1442] The server receives the basic information sent from the device and performs error checking. The received information is then stored in a database, typically a NoSQL database such as MongoDB.

[1443] Narrative Generation

[1444] The server generates a story based on the stored basic information. For example, GPT-3 is used as a generative AI model. This model uses natural language processing technology to generate a story with appropriate context and content based on the information entered by the user. For example, if a user enters the following basic information:

[1445] Name: "Rina"

[1446] Age: 6

[1447] Likes: Princesses

[1448] With this information, the server generates a prompt like this:

[1449] Lina is a 6-year-old girl. Her favorite thing is princesses. One day, while Lina was playing in the garden, a huge castle suddenly appeared!

[1450] The prompt sentence is then used as input to generate a story using a GPT-3 model.

[1451] Providing Choices

[1452] The generated story data is sent to the terminal and displayed on the terminal. The terminal presents the user or child with the choice of print mode or reading mode. The user can select from these modes.

[1453] Showing the story

[1454] If the user selects the print mode, the device will display the generated story on the screen, allowing the child to read the story themselves.

[1455] Story reading

[1456] When the user selects the reading mode, the device will read the generated story using speech synthesis technology, specifically using speech synthesis APIs such as Amazon Polly and Google Text-to-Speech.

[1457] For example, the following story appears on the terminal screen:

[1458] Lina is a 6-year-old girl. Her favorite thing is princesses. One day, while Lina was playing in the garden, a huge castle suddenly appeared!

[1459] Lina stared in amazement at the sight before her. The castle door opened, and the kind-looking king stepped out. "Hello, Lina. Welcome to your adventure to become a princess," the king smiled.

[1460] If the user selects the read aloud mode, the story will be read aloud for the child's listening pleasure.

[1461] This system allows for personalized stories to be delivered to specific children in-store, resulting in higher customer satisfaction.

[1462] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[1463] Step 1:

[1464] The user uses the device to enter basic information about their child, such as the child's name, age, and favorite things, into the form displayed on the device screen, and then presses the submit button. The entered basic information is converted into JSON format and sent to the server.

[1465] Input: Basic information such as your child's name, age, and favorite things.

[1466] Output: Basic information converted to JSON format.

[1467] Step 2:

[1468] The server receives the basic information in JSON format sent from the device and performs error checks. Information that passes the check is saved in a database. Specifically, the information is stored in a NoSQL database such as MongoDB.

[1469] Input: Basic information in JSON format.

[1470] Output: Basic information stored in the database.

[1471] Step 3:

[1472] The server generates a story based on the basic information stored in the database. First, it creates a prompt sentence using the basic information, and then inputs the prompt sentence into a generative AI model (e.g., GPT-3). This model uses natural language processing technology to generate a story based on the input prompt sentence.

[1473] Input: Basic information retrieved from the database.

[1474] Data processing: Convert basic information into prompt sentences.

[1475] Data Computation: Generate stories using generative AI models.

[1476] Output: The generated narrative text.

[1477] Step 4:

[1478] The generated story data is sent from the server to the terminal. On the terminal, before the generated story is displayed to the user, the user is presented with the choice of print mode or reading mode. The user selects the desired mode.

[1479] Input: The text data of the generated story.

[1480] Output: The choices presented to the user (print mode, spoken mode).

[1481] Step 5:

[1482] If the user selects print mode, the terminal displays the generated story on the screen.

[1483] Input: User selection of type mode.

[1484] Output: The generated narrative text that is displayed on the screen.

[1485] Step 6:

[1486] When the user selects the reading mode, the device reads the generated story aloud using speech synthesis technology, specifically, using speech synthesis APIs such as Amazon Polly and Google Text-to-Speech to play the story aloud.

[1487] Input: User selection of reading mode.

[1488] Output: The generated story played as audio.

[1489] 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.

[1490] We will now explain the mode for implementing this invention. The system accepts basic information about a child entered by a user, generates a personalized story based on that information, and has the function of recognizing the user's emotions and adjusting the content of the story. This system consists of four main elements: a terminal, a server, a user, and an emotion engine.

[1491] User Input

[1492] First, the user enters basic information about their child using the device. The device provides an interface for the user to enter information. For example, they can enter their child's name, age, favorite things, etc. through a form. This basic information is converted into JSON format and sent to the server.

[1493] Receiving and storing data

[1494] The server receives the basic information sent from the device and checks whether it is correct. The received information is stored in a database. For example, a NoSQL database can be used for the database.

[1495] Narrative Generation

[1496] The server then activates a generation mechanism based on the stored basic information. Specifically, a generation algorithm is used to create a personalized story with a child as the main character, using a natural language processing algorithm (e.g., GPT-3). The story is generated with appropriate context and content based on the information entered by the user.

[1497] Use of emotion engine

[1498] When the generation means operates, the emotion engine recognizes the user's emotion. The emotion engine analyzes the user's voice input and facial expressions to recognize the emotion and sends the information to the server. The emotion engine can use a speech recognition API or facial expression recognition API (e.g., Google Cloud Speech-to-Text or Microsoft Azure Face API).

[1499] Emotion-based narrative adjustment

[1500] The server adjusts the content of the generated story based on information from the emotion engine. For example, if the user expresses happy emotions, it adjusts the tone of the story to be lighter.

[1501] Providing Choices

[1502] The generated story data is sent back to the terminal and displayed on the terminal. The terminal presents the user and the child with the choice of print mode and reading mode. The user can select from these modes.

[1503] Showing the story

[1504] If the user selects print mode, the device will display the generated story on the screen, allowing the child to read the story themselves.

[1505] Story reading

[1506] If the user selects the reading mode, the device will read the generated story using speech synthesis technology, for example, using a speech synthesis API (such as Amazon Polly or Google Text-to-Speech), allowing parents to use the system as an alternative to reading aloud.

[1507] Specific examples

[1508] For example, if a user enters their child's name as "Taro," their age as "5 years old," and their favorite thing as "dinosaurs," the server will generate the following story based on this information:

[1509] "Taro is a five-year-old boy. His favorite thing is dinosaurs. One day, while Taro was playing in the park, a huge dinosaur suddenly appeared! Taro was startled and stepped back a little, but the dinosaur had kind eyes."

[1510] If the emotion engine recognizes the user's emotion of joy, it can adjust the tone of the story to be even brighter.

[1511] "Taro is a five-year-old boy. His favorite thing is dinosaurs. One day, while Taro was having fun playing in the park, a big, smiling dinosaur suddenly appeared! Taro was startled and stepped back a little, but the dinosaur's eyes were kind, and the two quickly became friends."

[1512] When the user selects print mode, the story is displayed on the device screen. When the user selects read-aloud mode, the story is read aloud using text-to-speech technology. This way, children can have fun on their own and parents can have an educational experience even when they're busy.

[1513] The processing flow will be explained below.

[1514] Step 1:

[1515] User: Enter basic information such as the child's name, age, and favorite things into the input form on the device. For example, enter the child's name "Taro," age "5 years old," and favorite thing "dinosaurs."

[1516] Step 2:

[1517] Device: Convert the entered basic information into JSON format. The converted data is {"name": "Taro", "age": "5 years old", "likes": "dinosaur"}.

[1518] Step 3:

[1519] Terminal: The converted JSON data is sent to the server as an HTTP POST request.

[1520] Step 4:

[1521] Server: Receives the transmitted data and checks whether the format of the received data is correct.

[1522] Step 5:

[1523] Server: Store the received data in a database. For example, store it in a NoSQL database as {"name": "Taro", "age": "5 years old", "likes": "Dinosaur"}.

[1524] Step 6:

[1525] Server: Activates the generation method based on the stored data. Specifically, it generates a story using a natural language processing algorithm (e.g., GPT-3).

[1526] Step 7:

[1527] Server: Generates a story from an AI model. For example, it generates a story like, "Taro is a 5-year-old boy. His favorite thing is dinosaurs. One day, while Taro was playing in the park, a huge dinosaur suddenly appeared! Taro was startled and stepped back a little, but the dinosaur had kind eyes."

[1528] Step 8:

[1529] Terminal: Receives the generated story and activates the emotion engine, which is a function for analyzing the user's voice and facial expressions.

[1530] Step 9:

[1531] Terminal: The emotion engine analyzes the user's voice input and generates the user's emotion data. For example, if a happy voice pattern is detected, the emotion data for "joy" is generated.

[1532] Step 10:

[1533] Device: The emotion engine analyzes the user's facial expressions and complements the user's emotional data. For example, if a smiling expression is detected, the "joy" emotion data is strengthened.

[1534] Step 11:

[1535] Terminal: Sends the generated emotion data to the server.

[1536] Step 12:

[1537] Server: Analyzes the received emotional data and adjusts the tone and content of the generated story. For example, if it receives emotional data of "joy," it brightens the tone of the story. It adjusts the story to something like, "Taro was having fun playing in the park when suddenly, a big, smiling dinosaur appeared!"

[1538] Step 13:

[1539] Server: Sends the adjusted story data to the device.

[1540] Step 14:

[1541] Terminal: Prepares an interface for displaying received story data. Presents the user with the choice between print mode and reading mode.

[1542] Step 15:

[1543] User: Select print mode or speech mode.

[1544] Step 16:

[1545] Device: If the user selects print mode, the story is displayed on the screen. If the user selects reading mode, the story is read aloud using a speech synthesis API.

[1546] Step 17:

[1547] Terminal: Based on the selection, presents the story to the user: in print mode, it displays the text; in read-aloud mode, it plays the story aloud.

[1548] The above are specific processing steps including the roles of the user, terminal, server, and emotion engine.

[1549] Example 2

[1550] 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."

[1551] Conventional personalized story generation systems lack the ability to dynamically adjust the content of a story based on the user's emotions. This makes it difficult to provide stories that reflect the user's emotions and children's preferences. Furthermore, since users have limited options for listening to stories through audio, there is a need to provide a more interactive and richer experience.

[1552] The specific processing by the specific processing unit 290 of the data processing device 12 in the second embodiment is realized by the following means.

[1553] In this invention, the server includes means for accepting basic information about the child entered by the user, means for converting the accepted basic information into JSON format and transmitting it to the server, means for storing the accepted basic information in a database, means for generating a story using a generative AI model based on the stored basic information, means for adjusting the content of the generated story using an emotion recognition engine that analyzes the user's emotions, means for displaying the generated story on a user interface, and means for reciting the generated story using speech synthesis. This enables the provision of a personalized story that reflects the user's emotions and the child's preferences. Furthermore, by providing the user with the option of reading the story as text or listening to it audibly, a more interactive and richer experience can be provided.

[1554] "User" refers to the person who operates the system and enters basic information about the child.

[1555] "Basic information" refers to personally identifiable information such as the child's name, age, and likes.

[1556] "Terminal" refers to an electronic device that a user uses to input information.

[1557] "JSON format" refers to a standard data format that represents data in text.

[1558] "Server" refers to a remote computer for processing and storing received data.

[1559] "Database" means a data management system for storing received Basic Information.

[1560] A "generative AI model" refers to artificial intelligence technology that generates stories using natural language processing technology.

[1561] An "emotion recognition engine" refers to technology that recognizes emotions by analyzing a user's voice and facial expressions.

[1562] "User interface" refers to the screen or display device through which a user can view the generated story.

[1563] "Speech synthesis" refers to the technology of reading text data aloud.

[1564] "Interactive" refers to a dynamic experience that involves interaction with the user.

[1565] MODE FOR CARRYING OUT THE INVENTION

[1566] This section describes an embodiment of the present invention. This system accepts basic information about a child entered by a user, generates a personalized story based on that information, and also has the ability to adjust the content of the story by recognizing the user's emotions. This system consists of four main components: a terminal, a server, a user, and an emotion recognition engine.

[1567] User Input

[1568] The user uses the device to enter basic information about the child. The device provides an interface for the user to enter information. For example, the user can enter the child's name, age, favorite things, etc. through a form. This basic information is converted into JSON format and sent to the server.

[1569] Examples:

[1570] The user enters the child's name as "Taro," their age as "5 years old," and their favorite thing as "dinosaurs" through a form on the device.

[1571] Receiving and storing data

[1572] The server receives the basic information sent from the device and checks for errors. The received information is stored in a database. A NoSQL database (e.g., MongoDB) can be used for the database.

[1573] Examples:

[1574] The server receives basic information such as "Taro," "5 years old," and "dinosaur," and stores this in MongoDB.

[1575] Narrative Generation

[1576] The server then activates a generation mechanism based on the stored basic information. Specifically, it uses a generative AI model (e.g., GPT-3 natural language processing technology) to create a personalized story with the child as the protagonist. The story is generated with appropriate context and content based on the information entered by the user.

[1577] Examples:

[1578] The server uses GPT-3 to generate a story with Taro as the main character.

[1579] Example prompt sentence:

[1580] "I have a 5-year-old boy named Taro who loves dinosaurs. Please create a fun story with Taro as the main character, where he meets a big dinosaur in the park."

[1581] Use of emotion engine

[1582] When the generation means operates, the emotion recognition engine recognizes the user's emotions. The emotion engine analyzes the user's voice input and facial expressions to recognize emotions and sends that information to the server. Specifically, it can use a speech recognition API (e.g., Google Cloud Speech-to-Text) or a facial expression recognition API (e.g., Microsoft Azure Face API).

[1583] Examples:

[1584] The emotion engine uses Google Cloud Speech-to-Text to recognize the emotion of joy from the user's voice and send that information to the server.

[1585] Emotion-based narrative adjustment

[1586] The server adjusts the content of the generated story based on information from the emotion engine. For example, if the user expresses happy emotions, it adjusts the tone of the story to be lighter.

[1587] Examples:

[1588] The server recognizes the user's emotions of joy and lightens the tone of the story.

[1589] Providing a Generative Story

[1590] The generated story data is sent back to the terminal and displayed on the terminal. The terminal provides the user and the child with the choice of a print mode or a reading mode. The user can select from these modes.

[1591] Examples:

[1592] The device offers a choice between print mode and read-aloud mode below the displayed story, and the user can choose one.

[1593] Display or read the mode

[1594] If the user selects print mode, the device displays the generated story on the screen, allowing the child to read the story by themselves. If the user selects read-aloud mode, the device uses speech synthesis technology (e.g., Amazon Polly) to read the story aloud, allowing parents to use the system as an alternative to reading aloud to their children.

[1595] Examples:

[1596] If the user selects print mode, Tarou begins reading the story displayed on the device. If the user selects read-aloud mode, Tarou listens to the story read aloud by Amazon Polly.

[1597] The flow of the identification process in the second embodiment will be described with reference to FIG.

[1598] Step 1: Enter your user information

[1599] The user uses the terminal to enter basic information about the child. The terminal provides an interface for the user to enter information. The entered information includes the child's name, age, favorite things, etc. This basic information is converted into JSON format and sent to the server.

[1600] Specific behavior:

[1601] The user enters information such as "Taro," "5 years old," and "dinosaur" into a form on the device.

[1602] Input: Basic information such as your child's name, age, and favorite things

[1603] Output: JSON format data

[1604] Step 2: Sending and receiving basic information

[1605] The device sends basic information converted to JSON format to the server, which then receives the JSON data and checks for errors.

[1606] Specific behavior:

[1607] The device converts the information into JSON format and sends it to the server, which then analyzes the received JSON data and checks for errors.

[1608] Input: Basic information in JSON format

[1609] Output: Parsed basic information

[1610] Step 3: Save your basic information

[1611] The server stores the parsed basic information in a database, which can be a NoSQL database (e.g., MongoDB).

[1612] Specific behavior:

[1613] The server stores the parsed basic information in MongoDB.

[1614] Input: Parsed basic information

[1615] Output: Basic information stored in the database

[1616] Step 4: Narrative generation

[1617] The server then uses the stored basic information to launch a generative AI model (e.g., GPT-3) to generate a personalized story with the child as the protagonist. The story is generated with appropriate context and content according to the prompt text entered by the user.

[1618] Specific behavior:

[1619] The server inputs the prompt "Taro is the main character, and his favorite thing is dinosaurs" into GPT-3 and generates a story.

[1620] Input: Basic information, prompt

[1621] Output: The generated story

[1622] Step 5: Recognize emotions

[1623] When the generator is running, the emotion recognition engine recognizes the user's emotions. The emotion engine uses a speech recognition API (e.g., Google Cloud Speech-to-Text) or a facial expression recognition API (e.g., Microsoft Azure Face API) to analyze the user's voice input and facial expressions and recognize the emotions. This information is sent to the server.

[1624] Specific behavior:

[1625] The emotion engine uses Google Cloud Speech-to-Text to recognize the emotion of joy from the user's voice and send that information to the server.

[1626] Input: User's voice or facial expression

[1627] Output: Recognized user emotion information

[1628] Step 6: Adjust the story

[1629] The server adjusts the content of the generated story based on the user's emotional information received from the emotion engine. For example, if the user expresses a happy emotion, the server adjusts the tone of the story to be brighter.

[1630] Specific behavior:

[1631] The server recognizes that the user is happy and adjusts the tone of the story to be even lighter.

[1632] Input: User's emotion information, generated story

[1633] Output: Adjusted narrative

[1634] Step 7: Submit and view your story

[1635] The generated story data is sent back to the terminal from the server and displayed on the terminal, which provides the user and the child with the choice of a print mode or a reading mode.

[1636] Specific behavior:

[1637] The server sends the generated story data to the terminal, which displays it on the screen, and the user can choose between print mode and reading mode.

[1638] Input: Adjusted Narrative

[1639] Output: The story displayed on the terminal

[1640] Step 8: Select a Mode

[1641] The user selects one of the options displayed on the terminal: print mode or reading mode.

[1642] Specific behavior:

[1643] The user selects print mode or speech mode from the options displayed on the device screen.

[1644] Input: Mode selection

[1645] Output: Selected mode

[1646] Step 9: Show or read the story

[1647] If the user selects print mode, the device displays the generated story on the screen. If the user selects read-aloud mode, the device uses speech synthesis technology (e.g., Amazon Polly) to read the story aloud.

[1648] Specific behavior:

[1649] When the user selects print mode, the device displays the story on the screen for the user to read, and when the user selects read aloud mode, the story is played aloud using Amazon Polly.

[1650] Input: Selected mode

[1651] Output: A story displayed on a screen or read aloud

[1652] (Application example 2)

[1653] 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."

[1654] Conventional story generation systems are unable to dynamically adjust story content to match the user's emotions, making it difficult to provide children with a more engaging and personalized educational experience. Furthermore, they lack comprehensive methods for easily storing, viewing, and reciting stories.

[1655] 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.

[1656] In this invention, the server includes means for accepting basic information about the child input by the user, means for generating a story based on the accepted basic information, means for recognizing the user's emotions and adjusting the content of the story, means for displaying the generated story on a user interface, and means for reciting the generated story by voice synthesis. This enables the generation of a personalized story according to the user's emotions, providing a more engaging and educational experience for the child.

[1657] "User-entered basic information about the child" is information the user enters to personalize the story, such as the child's name, age, and favorite things.

[1658] The "generation means" is a mechanism for generating a story based on the received basic information, and primarily uses natural language processing technology.

[1659] "Display means" is a mechanism for displaying the generated story on the user interface of the terminal.

[1660] The "reading means" is a mechanism for reading aloud a story generated using speech synthesis technology.

[1661] The "means for recognizing emotions and adjusting the content of the story" is a mechanism for analyzing the user's voice input and facial expressions, and dynamically changing the content and tone of the story based on the results.

[1662] The "storage means" is a mechanism for storing basic information received from a user in a database.

[1663] "Natural language processing" is a technology that enables computers to understand and generate human language.

[1664] "Speech synthesis" is a technology that converts text data into speech.

[1665] Specific embodiments for carrying out the present invention will be described below.

[1666] 1. System Program

[1667] This invention is a system consisting of four main elements: a server, a terminal, a user, and an emotion engine. The terminal provides an interface for inputting basic information about the child, the server generates a story based on that information, and the emotion engine recognizes the user's emotions and adjusts the content of the story. The terminal is equipped with a means for displaying the story and a means for reading it aloud.

[1668] 1.1 Enter your child's basic information

[1669] The user uses a terminal to enter basic information about their child, such as their name, age, and interests. This information is converted into JSON format and sent to the server.

[1670] 1.2 Receipt and storage of data

[1671] The server receives the basic information sent from the device, checks that the information is correct, and then stores it in a database, which may be a NoSQL database, for example.

[1672] 1.3 Narrative Generation

[1673] The server uses the stored basic information to generate a personalized story using a generative AI model (e.g., OpenAI's GPT-3), which generates a story with appropriate context and content based on the information entered by the user.

[1674] 1.4 Using the Emotion Engine

[1675] When the generator is running, the emotion engine analyzes the user's voice input and facial expressions to recognize emotions. The emotion engine uses the Google Cloud Speech API and Microsoft Azure Face API. This information is sent to the server in real time, and the content of the story is adjusted according to the user's emotions.

[1676] 1.5 Displaying and Reading Stories

[1677] The generated story is sent to the device, which presents the user with the choice of print mode or reading mode. If print mode is selected, the device displays the story on the screen. If reading mode is selected, the device reads the story aloud using speech synthesis technology (e.g., Google Text-to-Speech or Amazon Polly).

[1678] 2. Hardware and Software Details

[1679] To realize this system, the following hardware and software are used:

[1680] Hardware: Devices such as smartphones, tablets, and computers.

[1681] Software: Natural language processing algorithms (e.g., GPT-3), speech recognition APIs (e.g., Google Cloud Speech-to-Text), facial expression recognition APIs (e.g., Microsoft Azure Face API), and speech synthesis APIs (e.g., Google Text-to-Speech, Amazon Polly).

[1682] 3. Specific Examples

[1683] For example, suppose a user inputs their child's name as "Taro," their age as "5 years old," and their favorite thing as "dinosaurs." Based on this information, the following story will be generated:

[1684] Example prompt sentence:

[1685] Taro is a 5-year-old boy. His favorite thing is dinosaurs. One day, while he was playing in the park, a huge dinosaur suddenly appeared!

[1686] Examples of generated narrative contributions:

[1687] Taro is a five-year-old boy. His favorite thing is dinosaurs. One day, while Taro was playing in the park, a huge dinosaur suddenly appeared! Taro was startled and stepped back a little, but the dinosaur had kind eyes.

[1688] If the emotion engine recognizes the user's emotion of joy, the story content is adjusted as follows:

[1689] Taro is a five-year-old boy. His favorite thing is dinosaurs. One day, while Taro was having fun playing in the park, a big, smiling dinosaur suddenly appeared! Taro was surprised and stepped back a little, but the dinosaur's eyes were kind, and the two quickly became friends.

[1690] In this way, the present invention provides a system that provides a personalized story for children and dynamically adjusts the content based on the user's emotions, providing a more engaging and educational experience.

[1691] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[1692] Step 1:

[1693] The user uses the terminal to enter basic information about their child (such as name, age, and favorite things). The terminal converts this information into JSON format and sends it to the server. This process prepares the terminal to send the entered information to the server in the appropriate format. The input data is the child's basic information entered by the user into the interface, and the output is the data converted to JSON format.

[1694] Step 2:

[1695] The server receives the child's basic information in JSON format sent from the device and verifies that the information is correct. During the verification process, the data format and content are checked to ensure they are correct. Once the data is confirmed to be correct, it is stored in a NoSQL database. The input data is the child's basic information in JSON format, and the output is the information stored in the database.

[1696] Step 3:

[1697] The server runs a generative AI model (e.g., OpenAI's GPT-3) based on the stored basic information to generate a story. In the generation process, the basic information entered by the user is converted into a prompt sentence and sent to the AI ​​model. The AI ​​model generates a story based on the prompt sentence and returns the result to the server. The input data is the basic information stored in the database, and the output is the generated story.

[1698] Step 4:

[1699] After the generated story is returned to the server, the server launches an emotion engine to analyze the user's emotions. The user's emotions are analyzed in real time using voice input and facial expression recognition APIs (such as Google Cloud Speech-to-Text or Microsoft Azure Face API). Once the emotion data is analyzed, the server uses that information to adjust the tone and content of the generated story. The input data are the generated story and emotion data, and the output is the adjusted story.

[1700] Step 5:

[1701] The server sends the adapted story to the terminal, which displays it on its user interface. The terminal then offers the user a choice between a print mode and a reading mode. When the user selects one of the modes, the terminal displays or reads the story based on the user's selection. The input data is the adapted story and the user's mode selection, and the output is a visual display or audio reading of the story.

[1702] Step 6:

[1703] If the device displays a story based on the user's selection, the story will be displayed on the screen. The user can read the story themselves. If read-aloud mode is selected, the device will read the story using a speech synthesis API (such as Google Text-to-Speech or Amazon Polly). The speech synthesis API converts text data into speech and plays it through the speaker. The input data is the story text, and the output is synthesized speech.

[1704] 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.

[1705] 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.

[1706] 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 robot 414.

[1707] 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.

[1708] 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.

[1709] 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.

[1710] 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).

[1711] 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.

[1712] 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."

[1713] 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.

[1714] 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).

[1715] 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.

[1716] 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.

[1717] 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.

[1718] 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.

[1719] 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.

[1720] 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.

[1721] 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.

[1722] 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.

[1723] 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.

[1724] 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.

[1725] The following is further disclosed regarding the above embodiment.

[1726] (Claim 1)

[1727] means for accepting basic information of a child input by a user;

[1728] A generating means for generating a story based on the received basic information;

[1729] a display means for displaying the generated story on a user interface;

[1730] a reading means for reading the generated story by voice synthesis;

[1731] A system including:

[1732] (Claim 2)

[1733] 2. The system according to claim 1, further comprising a storage means for storing basic information of the child received from the user in a database.

[1734] (Claim 3)

[1735] 2. The system of claim 1, wherein the generating means generates the story using natural language processing.

[1736] "Example 1"

[1737] (Claim 1)

[1738] means for accepting basic information of a child input by a user;

[1739] A means to convert the received basic information into JSON format and send it to the server,

[1740] a means for checking the received basic information for errors and storing the information in a database;

[1741] A generator that generates a personalized story based on the stored basic information;

[1742] a display means for displaying the generated story on a user interface;

[1743] a reading means for reading the generated story by voice synthesis;

[1744] means for presenting a user with a choice between print mode and speech mode;

[1745] A system including:

[1746] (Claim 2)

[1747] 10. The system of claim 1, further comprising means for checking the received basic information for errors and storing the errors in a database.

[1748] (Claim 3)

[1749] 2. The system of claim 1, wherein the generating means generates the story using natural language processing techniques.

[1750] "Application Example 1"

[1751] (Claim 1)

[1752] means for accepting basic information input by a user;

[1753] A generating means for generating a story based on the received basic information;

[1754] a display means for displaying the generated story on a user interface;

[1755] a reading means for reading the generated story by voice synthesis;

[1756] a means for providing through a user interface a choice between print mode and read-aloud mode;

[1757] A system including:

[1758] (Claim 2)

[1759] 2. The system according to claim 1, further comprising a storage means for storing the basic information received from the user in a database.

[1760] (Claim 3)

[1761] 2. The system of claim 1, wherein the generating means generates the story using natural language processing.

[1762] (Claim 4)

[1763] 10. The system of claim 1, further comprising a generating means for converting basic information entered by a user into prompt sentences and generating a personalized story using a generative AI model.

[1764] "Example 2: Combining Emotion Engines"

[1765] (Claim 1)

[1766] means for accepting basic information of a child input by a user;

[1767] A means to convert the received basic information into JSON format and send it to the server,

[1768] a means for storing the received basic information in a database;

[1769] A means of generating a story using a generative AI model based on the stored basic information;

[1770] a means for adjusting the content of the story generated using an emotion recognition engine that analyzes the emotions of the user;

[1771] means for displaying the generated story in a user interface;

[1772] a means for reading the generated story aloud by speech synthesis;

[1773] A system including:

[1774] (Claim 2)

[1775] 2. The system according to claim 1, further comprising means for storing the basic information of the child received from the user in a database.

[1776] (Claim 3)

[1777] 2. The system of claim 1, wherein the generating means generates the story using natural language processing.

[1778] "Application example 2 when combining emotion engines"

[1779] (Claim 1)

[1780] means for accepting basic information of a child input by a user;

[1781] A generating means for generating a story based on the received basic information;

[1782] a display means for displaying the generated story on a user interface;

[1783] a reading means for reading the generated story by voice synthesis;

[1784] A means for recognizing a user's emotions and adjusting the content of the story;

[1785] A system including:

[1786] (Claim 2)

[1787] 2. The system according to claim 1, further comprising a storage means for storing basic information of the child received from the user in a database.

[1788] (Claim 3)

[1789] 2. The system of claim 1, wherein the generating means generates the story using natural language processing.

[1790] (Claim 4)

[1791] 10. The system of claim 1, wherein the user's emotions are recognized using voice input and facial expression recognition.

[1792] (Claim 5)

[1793] 10. The system of claim 1, wherein the system reads a story generated using speech synthesis technology. [Explanation of symbols]

[1794] 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. means for accepting basic information of a child input by a user; A generating means for generating a story based on the received basic information; a display means for displaying the generated story on a user interface; a reading means for reading the generated story by voice synthesis; A system including:

2. 2. The system according to claim 1, further comprising a storage means for storing basic information about the child received from the user in a database.

3. The system of claim 1 , wherein the generating means generates the story using natural language processing.

Images