system

Abstract

We provide the system. [Solution] A recording means that records the user's voice and generates audio data, A speech recognition means for converting the aforementioned speech data into text data, A generation means that generates a story from text data converted by a speech recognition means, An illustration generation means that generates an appropriate illustration based on the content of the generated story, A layout method that combines generated text data and illustrations to complete the layout of a picture book, A means of exporting data from a completed picture book to save it as paper or convert it into a printable format, A system that includes a reading device that reads aloud the text of the generated picture book.

Description

Technical Field

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

Background Art

[0002] Patent Document 1 discloses a method for controlling a persona chatbot, which is performed by at least one processor, the method including: receiving a user utterance; adding the user utterance to a prompt including an instruction sentence related to an explanation of a character of the chatbot; encoding the prompt; and inputting the encoded prompt into a language model to generate a chatbot utterance in response to the user utterance.

Prior Art Documents

Patent Documents

[0003]

Patent Document 1

Summary of the Invention

Problems to be Solved by the Invention

[0004] Modern children are exposed to a lot of digital technology, resulting in an increase in stereotyped activities and a decrease in opportunities to exercise their free imagination. In addition, in order to stimulate children's creativity, an environment that concretizes and enjoys their free ideas is required, but such a system is not provided by the current technology. Furthermore, there is a problem that it is difficult to provide an interactive experience in which children can visually and audibly enjoy the stories they create themselves.

Means for Solving the Problems

[0005] As means for solving this problem, a system including the following elements is provided:

[0006] The system uses recording equipment to record the user's voice and generate audio data.

[0007] The voice data is converted into text data using speech recognition means.

[0008] A story is generated from the text data using the generation means.

[0009] An illustration generation means is used to generate an illustration suitable for the content of the story.

[0010] The layout of the picture book is completed by combining the text data and illustrations using a layout means.

[0011] To enable the creation of picture books using the export method to be saved as paper copies.

[0012] To enable people to enjoy the content of picture books aurally using reading aids.

[0013] "Recording means" refers to a device or function that records the user's voice and generates audio data.

[0014] "Speech recognition means" refers to a technology or device that analyzes speech data generated by a recording means and converts it into text data.

[0015] "Generation means" refers to a technology or system that generates a story from text data converted by speech recognition means.

[0016] "Illustration generation means" refers to a technology or system that generates appropriate illustrations based on the content of the generated story.

[0017] "Layout method" refers to a technology or system that combines generated text data and illustrations to complete the layout of a picture book.

[0018] "Output means" refers to a technology or system that converts the data of a completed picture book into a form that can be stored or printed on paper media.

[0019] "Reading aloud means" refers to a technology or system that reads aloud the text of a generated picture book in voice.

Brief Explanation of Drawings

[0020] [Figure 1] It is a conceptual diagram showing an example of the configuration of a data processing system according to the first embodiment. [Figure 2] It is a conceptual diagram showing an example of the main functions of a data processing device and a smart device according to the first embodiment. [Figure 3] It is a conceptual diagram showing an example of the configuration of a data processing system according to the second embodiment. [Figure 4] It is a conceptual diagram showing an example of the main functions of a data processing device and smart glasses according to the second embodiment. [Figure 5] It is a conceptual diagram showing an example of the configuration of a data processing system according to the third embodiment. [Figure 6] It is a conceptual diagram showing an example of the main functions of a data processing device and a headset-type terminal according to the third embodiment. [Figure 7] It is a conceptual diagram showing an example of the configuration of a data processing system according to the fourth embodiment. [Figure 8] It is a conceptual diagram showing an example of the main functions of a data processing device and a robot according to the fourth embodiment. [Figure 9] It shows an emotion map to which a plurality of emotions are mapped. [Figure 10] It shows an emotion map to which a plurality of emotions are mapped. [Figure 11] It is a sequence diagram showing the processing flow of the data processing system in Example 1. [Figure 12] It is a sequence diagram showing the processing flow of the data processing system in Application Example 1. [Figure 13]This is a sequence diagram showing the processing flow of the data processing system in Example 2, which incorporates an emotion engine. [Figure 14] This is a sequence diagram showing the processing flow of the data processing system in Application Example 2, which combines an emotion engine. [Modes for carrying out the invention]

[0021] Hereinafter, an example of an embodiment of the system relating to the technology of this disclosure will be described with reference to the attached drawings.

[0022] First, let's explain the terminology used in the following explanation.

[0023] In the following embodiments, the signed processor (hereinafter simply referred to as "processor") may be a single arithmetic unit or a combination of multiple arithmetic units. Furthermore, the processor may be a single type of arithmetic unit or a combination of multiple types of arithmetic units. Examples of arithmetic units include CPU (Central Processing Unit), GPU (Graphics Processing Unit), GPGPU (General-Purpose computing on Graphics Processing Units), and APU (Accelerated Processing Unit).

[0024] In the following embodiments, signed RAM (Random Access Memory) is a memory that temporarily stores information and is used as work memory by the processor.

[0025] In the following embodiments, the signed storage is one or more non-volatile storage devices that store various programs and various parameters. Examples of non-volatile storage devices include flash memory (SSD (Solid State Drive)), magnetic disks (e.g., hard disks), or magnetic tapes.

[0026] In the following embodiments, the signed communication interface (I / F) is an interface that includes a communication processor and an antenna, etc. The communication interface manages communication between multiple computers. Examples of communication standards applicable to the communication interface include wireless communication standards such as 5G (5th Generation Mobile Communication System), Wi-Fi (registered trademark), or Bluetooth (registered trademark).

[0027] In the following embodiments, "A and / or B" is synonymous with "at least one of A and B." That is, "A and / or B" means that it may be A alone, or B alone, or a combination of A and B. Furthermore, in this specification, the same concept as "A and / or B" applies when expressing three or more things linked by "and / or."

[0028] [First Embodiment]

[0029] Figure 1 shows an example of the configuration of the data processing system 10 according to the first embodiment.

[0030] As shown in Figure 1, the data processing system 10 includes a data processing device 12 and a smart device 14. An example of the data processing device 12 is a server.

[0031] The data processing device 12 comprises a computer 22, a database 24, and a communication interface 26. The computer 22 is an example of a "computer" related to the technology of this disclosure. The computer 22 comprises a processor 28, RAM 30, and storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication interface 26 are also connected to the bus 34. The communication interface 26 is connected to a network 54. An example of the network 54 is a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0032] The smart device 14 comprises a computer 36, a reception device 38, an output device 40, a camera 42, and a communication interface 44. The computer 36 comprises a processor 46, RAM 48, and storage 50. The processor 46, RAM 48, and storage 50 are connected to a bus 52. The reception device 38, output device 40, and camera 42 are also connected to the bus 52.

[0033] The reception device 38 is equipped with a touch panel 38A and a microphone 38B, etc., and receives user input. The touch panel 38A receives user input by detecting contact with an object (e.g., a pen or finger). The microphone 38B receives user input by detecting the user's voice. The control unit 46A transmits data indicating the user input received by the touch panel 38A and microphone 38B to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the data indicating the user input.

[0034] The output device 40 includes a display 40A and a speaker 40B, and presents data to the user 20 by outputting the data in a form perceptible to the user 20 (e.g., audio and / or text). The display 40A displays visible information such as text and images according to instructions from the processor 46. The speaker 40B outputs audio according to instructions from the processor 46. The camera 42 is a small digital camera equipped with an optical system such as a lens, aperture, and shutter, and an image sensor such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor.

[0035] Communication interface 44 is connected to network 54. Communication interfaces 44 and 26 are responsible for the exchange of various types of information between processor 46 and processor 28 via network 54.

[0036] Figure 2 shows an example of the main functions of the data processing device 12 and the smart device 14.

[0037] As shown in Figure 2, in the data processing device 12, a specific processing is performed by the processor 28. A specific processing program 56 is stored in the storage 32. The specific processing program 56 is an example of a "program" related to the technology of this disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 according to the specific processing program 56 executed on the RAM 30.

[0038] The storage 32 stores the data generation model 58 and the emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[0039] In the smart device 14, the processor 46 performs the reception output processing. The storage 50 stores the reception output program 60. The reception output program 60 is used in conjunction with a specific processing program 56 by the data processing system 10. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output processing is realized by the processor 46 operating as a control unit 46A according to the reception output program 60 executed on the RAM 48.

[0040] Next, the specific processing performed by the specific processing unit 290 of the data processing device 12 will be described. In the following description, the data processing device 12 will be referred to as the "server" and the smart device 14 as the "terminal".

[0041] The system according to this invention is a system that automatically generates a story based on a child's spoken language and creates a picture book by adding illustrations related to that story. An embodiment of this system is described in detail below.

[0042] 1. Access to the app and recording

[0043] The user installs the provided application on their device and accesses the app.

[0044] When the user presses the record button, recording mode begins, and the child starts talking freely. The app's UI indicates that recording is in progress.

[0045] 2. Sending audio files to the server

[0046] Once recording is complete, the device sends the recorded data to the server. This process takes place in the background, so it doesn't interfere with the user performing other operations.

[0047] 3. Speech-to-Text Recognition

[0048] The server analyzes the received audio data and converts it into text data using a speech recognition engine. This text data represents the content of the child's speech.

[0049] 4. Story Generation

[0050] Based on the obtained text data, the server uses a generation AI model to construct a story. The constructed story is supplemented to create a coherent narrative while retaining the child's original spoken language.

[0051] 5. Illustration generation

[0052] The server uses a text generation engine to generate illustrations appropriate for each scene in the story. This adds visual elements that match the content of the narrative.

[0053] 6. Picture book layout and design

[0054] The server integrates the generated story and illustrations to complete the picture book layout. This includes the process of determining the placement of text and illustrations on each page.

[0055] 7. Sending and displaying picture book data

[0056] The completed picture book data is sent to the device and becomes viewable on the device. Users can view the picture book within the app and turn the pages.

[0057] 8. Reading and saving picture books

[0058] The device offers a text-to-speech function, playing the text portion of the story aloud. This allows children to enjoy what they've said using both their visual and auditory senses.

[0059] Users can choose to save the picture book and download it in PDF format. They can also print it as a paper copy if needed.

[0060] Specific example

[0061] Let's say a user opens the app, presses the record button, and their child tells a story, saying, "Today I made friends with a big bear in the forest." Once the recording is complete, the device sends the audio data to the server, which converts it into text data. A generative AI then uses this text to create a story, generating a narrative like, "Today in the forest, I met a big bear and we went on an adventure together." The server then generates illustrations that match the story, completing picture book pages depicting the bear and the forest scenery. Finally, the picture book data is returned to the device, allowing the user to listen to and read the book using the text-to-speech function, and also to save it as a printed copy.

[0062] As described above, this system automatically generates picture books that can be enjoyed both visually and aurally, giving shape to children's free-thinking ideas.

[0063] The following describes the processing flow.

[0064] Step 1:

[0065] The user opens the app. A recording start button is displayed on the app's main screen. The user presses the recording button to activate recording mode.

[0066] Step 2:

[0067] The device displays a notification that recording has started and begins voice input using the device's microphone. Once the user starts speaking, the audio is recorded in real time.

[0068] Step 3:

[0069] The user presses the stop button to end the recording. The recording stops, and the audio data is temporarily stored on the device.

[0070] Step 4:

[0071] The device sends the recorded data to the server. The progress of the file upload is displayed in the UI, and a notification is displayed when the data transmission is complete.

[0072] Step 5:

[0073] The server receives the audio file. The server inputs the audio data into the speech recognition engine and starts speech analysis.

[0074] Step 6:

[0075] The server converts the audio data into text data. The speech recognition engine analyzes the content of the audio and generates the corresponding text. This text data is temporarily stored.

[0076] Step 7:

[0077] The server inputs the generated text data into a story generation model. The model analyzes the text to identify the elements of the story and generates a coherent narrative.

[0078] Step 8:

[0079] The server generates illustrations appropriate for each scene using an illustration generation model based on the generated story. These illustrations are temporarily stored for each scene in the story.

[0080] Step 9:

[0081] The server integrates the generated text and illustrations to determine the page layout of the picture book. The design for each page is finalized, and the final picture book data is generated.

[0082] Step 10:

[0083] The server sends the completed picture book data to the device. The device receives the picture book data and displays it within the app.

[0084] Step 11:

[0085] The device displays picture book data and provides an interface that allows the user to view the picture book's content. The user can read the picture book by turning the pages.

[0086] Step 12:

[0087] The device provides a text-to-speech function, and when the user presses the read-aloud button, the text portion of the picture book is read aloud using speech synthesis technology.

[0088] Step 13:

[0089] Users can select a save option and download the picture book in PDF format to save it as a physical copy. They can also use the print function to save it as a physical copy if needed.

[0090] Through this series of steps, a story created by a child is transformed from audio data into text, then into a picture book, encompassing the process of adding illustrations, laying out the story, and finally saving it.

[0091] (Example 1)

[0092] Next, we will describe Example 1. In the following description, the data processing device 12 will be referred to as the "server," and the smart device 14 will be referred to as the "terminal."

[0093] Traditional picture book creation systems struggled to automatically generate stories that reflected children's free imaginations and to add suitable illustrations. Manually creating stories and inserting illustrations was time-consuming and laborious, making it difficult to quickly translate children's imaginations into tangible forms.

[0094] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 1 is realized by the following means.

[0095] In this invention, the server includes means for transmitting audio data to the server, means for constructing a story using a generative AI model, and means for generating illustrations corresponding to each scene of the story. This enables the rapid construction of a story based on children's spoken language and the automatic generation of suitable illustrations, thereby allowing picture books to be created in a short amount of time.

[0096] "Recording means" refers to a device or function that records the user's voice and generates audio data.

[0097] "Speech recognition means" refers to technologies and devices that convert recorded speech data into text data.

[0098] "Generation means" refers to technologies and devices that automatically construct a story based on text data obtained by speech recognition means.

[0099] "Illustration generation means" refers to technologies or devices that automatically generate illustrations corresponding to the content of a story.

[0100] "Layout means" refers to the techniques and devices used to appropriately arrange the generated story and illustrations and determine the layout of a picture book.

[0101] "Exporting method" refers to the technology or device that saves the data of a laid-out picture book and outputs it as a file such as PDF.

[0102] "Reading aloud methods" refer to technologies and devices that reproduce the text portion of a picture book as audio.

[0103] "Means of sending audio data to a server" refers to technologies and devices that transmit audio data recorded on a terminal to a server via a network.

[0104] "Methods for constructing narratives using generative AI models" refers to technologies and devices that use generative AI models to generate meaningful narratives based on input text data.

[0105] "Means for generating illustrations corresponding to each scene of a story" refers to technologies or devices that automatically generate illustrations appropriate for each scene based on the content of the story.

[0106] The system according to this invention automatically generates a story based on a child's spoken language and creates a picture book by adding illustrations related to that story. An embodiment of this system is described in detail below.

[0107] First, the system begins with the user installing the provided application on their device. The user opens the app and presses the record button to start recording mode. As the child begins to speak freely, the device's microphone records the audio, generating a recording. This recording takes place in the background, allowing the user to perform other operations.

[0108] Once recording is complete, the device sends the acquired audio data to the server. The server analyzes the received audio data and converts it into text data using a speech recognition engine (for example, Google Speech-to-Text API). This text data is a direct transcription of the child's spoken words.

[0109] Next, the server uses a generative AI model (e.g., GPT-3) to generate a story using this text data. The server prompts the generative AI model and requests it to generate a story. The generative AI model constructs a meaningful story based on the text and returns it to the server. This story is supplemented to create a coherent narrative while retaining the natural language of a child.

[0110] Next, the server uses an illustration generation engine (for example, DALLE-2) to generate illustrations corresponding to each scene in the story. Based on the content of the story, it generates illustrations suitable for each scene and imports them while aligning them with the story.

[0111] The server also integrates the story and illustrations and determines the layout of the picture book. It decides the placement of text and illustrations on each page, completing it as a digital picture book. After that, the completed picture book data is sent to the terminal, and the user can view this picture book within the application. The application also provides a page-turning function, allowing the user to intuitively read the picture book.

[0112] Finally, the device has a text-to-speech function that can play the text portion of the story aloud. This allows children to enjoy what they say not only visually but also aurally. In addition, users can choose the option to save the picture book and download it in PDF format. This PDF can be printed out as needed and enjoyed as a physical picture book.

[0113] As a concrete example, suppose a user opens the app, presses the record button, and records their child saying, "Today I made friends with a big bear in the forest." Once the recording is complete, the device sends the audio data to the server, which converts it into text data. A generative AI model uses this text to create a story, generating a narrative such as, "Today in the forest, I met a big bear and we went on an adventure together." The server generates illustrations that match the story, completing picture book pages depicting the bear and the forest scenery. Finally, the picture book data is returned to the device, allowing the user to listen to and read the book using the text-to-speech function, and also to save it as a paper copy.

[0114] An example of a prompt for a generative AI model is the sentence, "Generate a coherent children's story based on this audio data."

[0115] As described above, this system automatically generates picture books that transform children's free-thinking ideas into engaging forms and can be enjoyed both visually and aurally.

[0116] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0117] Step 1:

[0118] The user installs the app.

[0119] Specifically, the user downloads the application from the app store to their device and installs it. Once the installation is complete, the user launches the app, and the main screen is displayed. This is the initial setup stage.

[0120] Input: Application installation request

[0121] Output: Applications installed on the device

[0122] Step 2:

[0123] The user accesses the app and presses the record button to start recording mode.

[0124] Specifically, when the user taps the recording button displayed on the main screen, the device's microphone is activated. At this point, the app's UI switches to a display indicating that recording is in progress. The user then instructs the child to speak freely.

[0125] Input: User taps the record button.

[0126] Output: Start of recording mode, initialization of recording data

[0127] Step 3:

[0128] Record the child's spoken words.

[0129] Specifically, the device's microphone records the child's speech as audio data. While recording is in progress, the user can check the current recording time and progress on the screen.

[0130] Input: Children's spoken language

[0131] Output: Recorded audio data

[0132] Step 4:

[0133] After recording is complete, the audio data is saved and sent to the server.

[0134] When the user presses the record button again to end the recording, the device saves the audio data. The device then checks its internet connection and sends the saved audio data to the server. This process runs in the background, allowing the user to continue other operations.

[0135] Input: Instruction to end recording

[0136] Output: Audio data sent to the server

[0137] Step 5:

[0138] The server receives the audio data and converts it into text data using a speech recognition engine.

[0139] Specifically, when the server receives audio data, it calls a speech recognition engine (e.g., Google Speech-to-Text API) to convert the audio data into text data. The converted text data is then temporarily stored on the server.

[0140] Input: Audio data

[0141] Output: Text data

[0142] Step 6:

[0143] The server generates a story using a generation AI model.

[0144] The server takes the text data obtained through speech recognition as input and sends a prompt message to a generative AI model (e.g., GPT-3). This prompt message contains instructions to generate a story. The generative AI model generates the story text, and the result is returned to the server.

[0145] Input: Text data, prompt message

[0146] Output: Generated narrative text

[0147] Step 7:

[0148] The server generates illustrations corresponding to each scene in the story.

[0149] The server analyzes the narrative text and extracts keywords and phrases corresponding to each scene. Based on these, it sends prompt text to an illustration generation engine (e.g., DALLE-2) to generate an appropriate illustration for each scene. The generated illustrations are stored on the server.

[0150] Input: Story text, illustration generation prompt

[0151] Output: Generated illustration

[0152] Step 8:

[0153] The server integrates the story and illustrations and creates the layout for the picture book.

[0154] The server arranges the generated story text and illustrations page by page, designing the overall layout of the picture book. It then appropriately places the text and illustrations to generate the digital picture book data. This data is saved in formats such as PDF.

[0155] Input: Story text, illustrations

[0156] Output: Digital picture book data

[0157] Step 9:

[0158] The server sends the completed picture book data to the terminal.

[0159] The server sends the generated picture book data to the device, and the user can then view this data within the application. Once the picture book data is sent, the device receives the data and saves it within the application.

[0160] Input: Digital picture book data

[0161] Output: Picture book data sent to the terminal

[0162] Step 10:

[0163] The device displays picture book data and provides a read-aloud function.

[0164] Users can open picture books within the application and turn the pages. Furthermore, the device uses a speech synthesis engine to play the text portion of the picture book aloud. This feature allows children to enjoy picture books using both their sight and hearing.

[0165] Input: Picture book data

[0166] Output: Displayed picture book, played audio

[0167] Step 11:

[0168] Users can save picture books in PDF format and print them as needed.

[0169] By selecting the save option within the application, users can download the picture book in PDF format. This PDF data can also be printed on a home printer and saved as a physical picture book.

[0170] Input: Save Instructions

[0171] Output: Picture book data in PDF format

[0172] (Application Example 1)

[0173] Next, we will explain Application Example 1. In the following explanation, the data processing device 12 will be referred to as the "server," and the smart device 14 will be referred to as the "terminal."

[0174] Traditional story and picture book generation systems often failed to fully utilize children's creativity, providing only fixed stories and illustrations. Furthermore, the technology for automatically generating stories and illustrations based on children's free-flowing conversations was immature, with challenges in audio data processing and the quality of the generated content. Additionally, features for integrating stories and illustrations to create an enjoyable experience through both visual and auditory means were insufficient.

[0175] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 1 is realized by the following means.

[0176] In this invention, the server includes recording means, speech recognition means, generation means, illustration generation means, layout means, display means, export means, reading means, and communication means. This makes it possible to automatically generate stories and illustrations based on what a child freely says, and to provide a high-quality interactive picture book.

[0177] "Recording means" refers to a device or software for recording a user's voice and generating audio data.

[0178] "Speech recognition means" refers to technology for converting speech data generated by recording means into text data.

[0179] A "generation method" refers to a system or software for constructing a story based on text data.

[0180] "Illustration generation means" refers to a device or software for automatically generating illustrations related to the content of a story.

[0181] "Layout means" refers to a technology that integrates the generated story and illustrations to automatically determine the page layout of a picture book.

[0182] "Display means" refers to a device or software that makes a picture book generated on a terminal viewable.

[0183] "Exporting method" refers to the technology that makes the generated picture book data downloadable in a specific format (e.g., PDF).

[0184] A "read-aloud device" is a device or software used to reproduce the text portion of a story as audio.

[0185] "Communication methods" refer to technologies for sending recorded audio data and generated text data to a server, and for receiving data generated from the server to a terminal.

[0186] This invention is a system that automatically generates a story based on what a child says and provides illustrations related to that story. A specific embodiment of this system is described below.

[0187] 1. Recording method

[0188] The user uses an application installed on their smartphone or tablet. This application has a recording function, and when the user presses the record button, it starts recording the child's speech. The recorded audio is saved as audio data.

[0189] 2. Speech recognition means

[0190] The audio data generated by the recording device is sent to the server via a communication device. The server uses a speech recognition engine (e.g., Google Speech-to-Text API) to convert the audio data into text data. This allows the content of what the child said to be obtained in text format.

[0191] 3. Generation means

[0192] The server uses a generative AI model (for example, OpenAI's GPT-3) to construct a story based on the converted text data. This generative AI model complements the input text to create a coherent and creative narrative.

[0193] 4. Illustration generation means

[0194] To generate illustrations appropriate for each scene in the story, the server uses a text generation engine. This automatically adds visual elements that match the content of the story. Specifically, the generated story text acts as a prompt, and appropriate illustrations are generated based on it.

[0195] 5. Layout methods

[0196] The generated story and illustrations are integrated into a single picture book using a layout mechanism. This layout mechanism determines the placement of text and illustrations on each page, creating a visually appealing composition.

[0197] 6. Display means

[0198] The completed picture book data is then transmitted back to the user's device via communication. The user has a display mechanism within the application that allows them to view the picture book and turn the pages. This allows children to enjoy the generated story visually.

[0199] 7. Text-to-speech method

[0200] The user's device provides a text-to-speech function. It plays the text portion of the generated story aloud, allowing children to enjoy what they've said through auditory means as well.

[0201] 8. Methods for writing

[0202] The picture book data can be exported in PDF format. Users can download this data and print it as a paper copy as needed.

[0203] Usage example

[0204] When a user opens the app and presses the record button, the child tells a story, such as, "Today I made friends with a big bear in the forest." This recording is sent to a server, where a speech recognition engine converts it into text. Next, a generative AI model creates a story based on this text, generating a narrative like, "Today in the forest, I met a big bear and we went on an adventure together." The server then generates illustrations that match the story, completing picture book pages depicting the bear and the forest scenery.

[0205] Example of a prompt

[0206] Tell me a children's story where the main character is a little bear who makes friends with other animals in the forest.

[0207] In this way, this system can transform children's free-thinking ideas into tangible forms and automatically generate original picture books that can be enjoyed both visually and aurally.

[0208] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0209] Step 1:

[0210] The user launches the application installed on their smartphone or tablet and presses the record button. This activates the recording device and begins recording the child's speech. The user's input is the child's speech, and the output is audio data. The audio data is generated by the recording device and temporarily stored locally.

[0211] Step 2:

[0212] When the user finishes recording, the device sends the audio data to the server via a communication method. This process takes place in the background, allowing the user to perform other operations. The input is the audio data, and the output is the audio data sent to the server.

[0213] Step 3:

[0214] The server analyzes the received audio data using speech recognition. Specifically, it uses the Google Speech-to-Text API to convert the audio data into text data. The input is audio data, and the output is the converted text data. The speech recognition engine uses a language model to recognize words from the audio waveform and outputs them as text data.

[0215] Step 4:

[0216] The server sends text data to the generation mechanism, which uses a generative AI model (e.g., OpenAI's GPT-3) to construct a story. The generative AI model generates prompts based on the input text data, producing a consistent story. The input is text data, and the output is the text of the generated story.

[0217] Step 5:

[0218] The server sends the generated story text to the illustration generation system, which then generates illustrations that match the story. A text generation engine is used to generate visual elements appropriate for each scene. The input is the story text, and the output is the associated illustrations. The illustration generation engine analyzes the scenes from the text and generates illustrations based on the prompt text.

[0219] Step 6:

[0220] The server integrates the generated story and illustrations using layout tools to complete the picture book layout. It optimizes the placement of text and illustrations on each page, creating a visually appealing composition. The input is the story text and illustrations, and the output is the completed picture book pages.

[0221] Step 7:

[0222] The server transmits the completed picture book data to the user's terminal via a communication method. The input is the data of the completed picture book, and the output is the picture book displayed on the terminal.

[0223] Step 8:

[0224] The user's device allows them to view the generated picture book using a display device. The user can read the picture book and turn the pages within the application. The input is the completed picture book data, and the output is the picture book displayed on the user interface.

[0225] Step 9:

[0226] The user's device uses a text-to-speech mechanism to play the generated text portion of the story aloud. The user can enjoy the story not only visually but also aurally. The input is the story text, and the output is a spoken version.

[0227] Step 10:

[0228] The user's device can save the picture book data in PDF format using the export function. The user can then download this data and print it as a paper copy as needed. The input is the completed picture book data, and the output is a PDF file.

[0229] As described above, by performing specific actions at each step, it is possible to ultimately provide an interactive picture book that users can enjoy visually and aurally.

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

[0231] The system according to this invention is a system that automatically generates a story based on a child's spoken language and creates a picture book by adding illustrations related to that story. Furthermore, this system incorporates an emotion recognition means that recognizes the user's emotions and can adjust the story content based on the user's emotions.

[0232] 1. Access to the app and recording

[0233] The user installs the provided application on their device and accesses the app. The user presses the record button to activate recording mode.

[0234] 2. Sending audio files to the server

[0235] Once recording is complete, the device sends the recorded data to the server. This process takes place in the background, so it doesn't interfere with the user performing other operations.

[0236] 3. Speech-to-Text and emotion recognition

[0237] The server analyzes the received audio data and converts it into text data using a speech recognition engine. Furthermore, it uses emotion recognition means to analyze and identify the user's emotions from the audio data.

[0238] 4. Story Generation

[0239] Based on the obtained text data and emotional information, the server uses a generation AI model to construct a story. The characters' feelings and the story's progression are adjusted based on the emotional information. The resulting story retains the child's original spoken language while incorporating emotionally relevant content.

[0240] 5. Illustration generation

[0241] The server uses an image generation model to generate illustrations appropriate for each scene in the story. The generated illustrations are also based on emotional information and express the atmosphere of the scene.

[0242] 6. Picture book layout and design

[0243] The server integrates the generated story and illustrations to determine the page layout of the picture book. Text and illustrations are placed on each page, and the final picture book data is generated.

[0244] 7. Sending and displaying picture book data

[0245] The completed picture book data is sent to the device and becomes viewable on the device. Users can view the picture book within the app and turn the pages.

[0246] 8. Reading and saving picture books

[0247] The device offers a text-to-speech function, allowing users to press a button to have the text portion of a picture book read aloud using speech synthesis technology.

[0248] Users can choose to save the picture book and download it in PDF format. They can also print it as a paper copy if needed.

[0249] Specific example

[0250] Let's say a user opens the app, presses the record button, and their child excitedly says, "Today I made friends with a big bear in the forest." Once the recording is complete, the device sends the audio data to a server, which converts it into text data. An emotion recognition system identifies "joy" from the audio data, and a generative AI creates a story based on this text and emotional information. A story like, "Today in the forest, I met a big bear and we had a fun adventure together," is generated. The server generates illustrations that match the story's content and emotions, depicting scenes of the bear and child happily adventuring. Finally, the picture book data is returned to the device, allowing the user to listen to and read the book using the text-to-speech function, and also to save it as a paper copy.

[0251] This system automatically generates interactive picture books that include stories and illustrations that reflect the user's emotions. This allows children to enjoy expressing their feelings through stories, fostering richer creativity.

[0252] The following describes the processing flow.

[0253] Step 1:

[0254] The user opens the app and presses the record button. The app's main screen displays a "Start Recording" button, and pressing this button initiates recording mode.

[0255] Step 2:

[0256] The device displays a notification that recording has started and begins voice input using the device's microphone. The UI indicates that recording is in progress, and the user can start speaking freely.

[0257] Step 3:

[0258] The user presses the stop button to end the recording. The recording stops, and the audio data is temporarily stored on the device.

[0259] Step 4:

[0260] The device sends the recorded data to the server. The user is shown the progress of the transmission, and when the data transmission is complete, a notification of upload completion is displayed.

[0261] Step 5:

[0262] The server receives the audio file. The server uses a speech recognition engine to convert the audio file into text data. Once the text data is generated, it is temporarily stored.

[0263] Step 6:

[0264] The server uses emotion recognition technology to analyze the user's emotions from the audio data. The analysis results are output as emotion tags such as "joy" and "sadness" and are temporarily stored.

[0265] Step 7:

[0266] The server inputs the generated text data and emotion tags into the story generation model. The story generation model analyzes the input data to identify the elements of the story and generates a story that matches the emotion tags.

[0267] Step 8:

[0268] Based on the generated story, the server uses an illustration generation model to create illustrations appropriate for each scene. The illustrations match each scene in the story and also include colors and expressions that reflect emotional information.

[0269] Step 9:

[0270] The server integrates the generated text and illustrations to determine the layout of the picture book. The text and illustrations are then placed on each page, generating the final picture book data.

[0271] Step 10:

[0272] The server sends the completed picture book data to the device. The device receives the picture book data and makes it viewable within the app.

[0273] Step 11:

[0274] The device displays the picture book data, allowing the user to view the picture book's content. The user can enjoy the story by turning the pages.

[0275] Step 12:

[0276] The device provides a text-to-speech function, and when the user presses the read-aloud button, the text portion of the picture book is read aloud using speech synthesis technology. This allows the user to enjoy the story using both their sight and hearing.

[0277] Step 13:

[0278] Users can select the save option and download the picture book in PDF format. If desired, they can also print it out as a physical book and read it in person.

[0279] This series of steps automatically generates an interactive picture book containing stories and illustrations that reflect the user's emotions. This allows children to express their feelings as stories and enjoy them visually and aurally.

[0280] (Example 2)

[0281] Next, we will describe Example 2. In the following description, the data processing device 12 will be referred to as the "server" and the smart device 14 as the "terminal".

[0282] In conventional children's story generation systems, it has been difficult to generate interactive stories and illustrations that reflect the user's emotions. In addition, story generation based on children's spoken language and the addition of related illustrations also had to be done manually, which was very time-consuming. As a result, the use in each household and in educational settings was limited.

[0283] The specific processing by the specific processing unit 290 of the data processing device 12 in Example 2 is realized by the following means. In this invention, the server includes an emotion recognition means, a story generation means using a generation AI model, and an image generation means. As a result, it is possible to analyze the emotion from the user's voice data and automatically generate a story and appropriate illustrations based on the emotion information. This system can quickly generate an interactive picture book that makes use of children's spoken language based on the voice data provided by the user.

[0284] The "recording means" is a device or program that has the function of recording the user's voice and storing it as voice data.

[0285] The "voice recognition means" is a device or program that has the function of analyzing the recorded voice data and converting its content into text data.

[0286] The "emotion recognition means" is a device or program that has the function of analyzing and specifying the user's emotional state from the voice data. <00所0906>

[0287] The "generation means" is a device or program that has the function of creating a story using a generation AI model based on the data obtained from the voice recognition means and the emotion recognition means.

[0288] The "illustration generation means" is a device or program that has the function of automatically generating appropriate illustrations based on the content and emotion information of the generated story.

[0289] A "layout means" is a device or program that has the function of integrating the generated story and illustrations and determining the page layout of a picture book.

[0290] "Exporting method" refers to a device or program that has the function of generating and saving integrated data as final picture book data.

[0291] A "reading device" refers to a device or program that has the function of reading aloud the text portion of a generated picture book using speech synthesis technology.

[0292] This invention is a system that automatically generates stories based on children's spoken language and creates picture books by adding illustrations related to those stories. Furthermore, this system incorporates an emotion recognition means that recognizes the user's emotions and can adjust the story content based on the user's emotions. The following describes specific embodiments of this system.

[0293] Hardware and software to be used

[0294] Terminal: A device used by the user to record audio and send / receive data. Specific examples include smartphones and tablets.

[0295] Server: Computing resources for data analysis, story and illustration generation. Cloud services can also be used.

[0296] Speech recognition engine: Software used to convert recorded data into text data. For example, the Google Cloud Speech-to-Text API can be used.

[0297] Emotion recognition engine: Software for analyzing a user's emotions from voice data. For example, using the Emotion API in Azure Cognitive Services.

[0298] Generative AI model: A generative AI for constructing narratives. For example, it uses GPT-4.

[0299] Image generation model: Software for generating illustrations suitable for each scene in a story. For example, DALL-E can be used.

[0300] Design software: Software used to determine the page layout of a picture book. For example, Adobe InDesign can be used.

[0301] Speech synthesis engine: Software for reading picture books aloud. For example, Amazon Polly can be used.

[0302] System processing flow (specific example)

[0303] Explain the program's processing in natural language.

[0304] The user installs the application on their device and accesses it. The user presses the record button to activate recording mode, recording their voice using the device's microphone. Once recording is complete, the device sends the recording data to the server. The server converts this audio data into text using the Google Cloud Speech-to-Text API and further analyzes the user's emotions from the audio data using the Azure Cognitive Services Emotion API. Based on the obtained text data and emotion information, the server generates a story using a generative AI model (e.g., GPT-4).

[0305] Next, the server uses an image generation model (e.g., DALL-E) to generate illustrations suitable for each scene of the story. The generated story and illustrations are integrated on the server, and the page layout of the picture book is determined using design software such as Adobe InDesign. The generated picture book data is sent to the terminal, and the user can view the picture book within the app. Furthermore, using text-to-speech technology (e.g., Amazon Polly), the user can listen to the picture book with the read-aloud function. It is also possible to save the picture book in PDF format and print it if necessary.

[0306] Specific Example

[0307] For example, suppose a child happily says, "Today I became friends with a big bear in the forest." The user presses the recording button to record and then presses the stop button to end the recording. The recorded data is sent from the terminal to the server. The server uses the Google Cloud Speech-to-Text API to convert the voice to text and identifies "joy" using the Emotion API of Azure Cognitive Services. The generative AI model (GPT-4) inputs a prompt sentence based on the text and emotional information and generates a story themed on a fun adventure. A story like "Today in the forest, I met a big bear and had a fun adventure together" is generated. The image generation model (DALL-E) generates an illustration suitable for the story, depicting a scene of a bear and a child smiling and having an adventure. Finally, the picture book data returns to the terminal, and the user can enjoy the picture book while using the read-aloud function. It is also possible to save the picture book in PDF format, print it, and enjoy it as a paper medium.

[0308] With this system, the user can quickly and easily generate an interactive picture book containing a story and illustrations that reflect their own emotions. As a result, children can enjoy their feelings as stories and can richly develop their creativity.

[0309] The flow of the specific process in Example 2 will be described using FIG. 13.

[0310] Step 1:

[0311] The user installs the provided application on their device and launches it. The user presses the record button to record the child's speech through the microphone. The input is the user's voice, and the output is the audio data stored on the device. Specifically, the device's microphone converts the user's voice into a digital signal, which is then stored as binary data.

[0312] Step 2:

[0313] Once recording is complete, the device sends the recorded data to the server. This transmission is performed using an HTTP POST request. The input is the audio data stored on the device, and the output is the audio data sent to the server. Specifically, the device generates an HTTP request, encodes the audio data, and sends it to the server.

[0314] Step 3:

[0315] The server receives audio data and sends it to the Google Cloud Speech-to-Text API, where it is converted into text data. The input is the audio data sent to the server, and the output is the converted text data. Specifically, the server generates an API request, uploads the audio data to the cloud service, and retrieves the returned text data.

[0316] Step 4:

[0317] The server sends the converted text data to the Azure Cognitive Services Emotion API for sentiment analysis. The input is text data, and the output is sentiment information. Specifically, the server sends the text data to the sentiment recognition engine for analysis and receives the resulting sentiment labels.

[0318] Step 5:

[0319] The server generates a story using a generative AI model (such as GPT-4) based on the obtained text data and sentiment information. The input is text data and sentiment information, and the output is the generated story text. Specifically, the server inputs prompt sentences into the generative AI model and receives the generated story text.

[0320] Step 6:

[0321] The server sends the generated narrative text to an image generation model (such as DALL-E) to generate an appropriate illustration. The input is narrative text, and the output is the generated illustration. Specifically, the server generates prompt statements for each scene, requests an illustration from the image generation model based on these prompts, and retrieves the returned illustration.

[0322] Step 7:

[0323] The server integrates the generated story and illustrations using design software such as Adobe InDesign to determine the page layout of the picture book. The input is the story text and illustrations, and the output is the completed picture book data. Specifically, the server inputs the data into the design software, automatically generates the layout, and produces the picture book data in PDF format.

[0324] Step 8:

[0325] The completed picture book data is sent from the server to the device, allowing the user to view it within the app. The input is the completed picture book data, and the output is the picture book data displayed on the device. Specifically, the server encodes the picture book data and sends it to the device as an HTTP response, which the device decodes and displays.

[0326] Step 9:

[0327] The device uses a text-to-speech engine such as Amazon Polly to provide a function that reads aloud the text portion of a picture book. When the user presses the read-aloud button, the device sends the text data to the text-to-speech engine and plays the generated audio. The input is the text data of the picture book, and the output is the audio data. Specifically, the device sends the text data to the text-to-speech engine and plays the returned audio data.

[0328] Step 10:

[0329] Users can save picture books in PDF format and print them as paper copies as needed. The input is the completed picture book data, and the output is the saved PDF data. Specifically, the device exports the picture book data in PDF format, which the user then downloads or prints.

[0330] (Application Example 2)

[0331] Next, we will explain application example 2. In the following explanation, the data processing device 12 will be referred to as a "server" and the smart device 14 as a "terminal".

[0332] There is a need for a system that can automatically generate stories and related illustrations that respond to emotions based on what users, especially children, say, and create interactive picture books. Furthermore, it is desirable that this system be easily accessible to users in physical stores, and that the generated stories can be read aloud, saved, and printed.

[0333] In Application Example 2, the specific processing performed by the specific processing unit 290 of the data processing device 12 is realized by the following means. In this invention, the server includes recording means, speech recognition means, emotion recognition means, generation means, illustration generation means, layout means, writing means, reading means, data transmission means, and speech synthesis means. This makes it possible to automatically generate a story and related illustrations based on what the user, especially a child, says and their emotions, and further enable voice reading, saving, and printing.

[0334] A "recording device" is a device that records the user's voice and generates audio data.

[0335] A "speech recognition means" is a device that converts recorded speech data into text data.

[0336] An "emotion recognition device" is a device that analyzes and identifies a user's emotions from voice data.

[0337] A "generation method" is a device that automatically generates stories based on text data and emotional information.

[0338] An "illustration generation method" is a device that automatically generates illustrations suitable for each scene of a generated story.

[0339] A "layout device" is a device that integrates the generated story and illustrations to determine the page layout of a picture book.

[0340] The "export method" refers to a device that transmits the generated picture book data to a terminal.

[0341] A "reading device" is a device that uses speech synthesis technology to read aloud the text portion of a generated picture book.

[0342] "Data transmission means" refers to a device that transmits recorded data and generated picture book data to a server.

[0343] A "speech synthesis device" is a device that converts text data into speech and reads it aloud.

[0344] The system according to this invention is a system that automatically generates a story based on a child's spoken language and creates a picture book by adding illustrations related to that story. Furthermore, this system incorporates an emotion recognition means that recognizes the user's emotions and can adjust the story content based on the user's emotions.

[0345] Hardware and software to be used

[0346] Hardware: This system requires kiosk terminals or tablet devices, such as those used in physical stores like bookstores or toy shops. These devices incorporate microphones, speakers, and displays.

[0347] software:

[0348] 1. Speech Recognition: Use the Google Cloud Speech-to-Text API to convert recorded audio data into text data.

[0349] 2. Emotion Recognition: IBM Watson Tone Analyzer is used to analyze and identify the user's emotions from voice data.

[0350] 3. Generative AI Model: OpenAI GPT-3 is used to generate stories based on text data and sentiment information.

[0351] 4. Image generation model: DALLE-2 is used to generate illustrations that match each scene of the story.

[0352] 5. Speech synthesis: Use pyttsx3 to convert the generated story text into speech and read it aloud.

[0353] 6. PDF Generation: Use FPDF to combine the generated story and illustrations and save them in PDF format.

[0354] Overview of the program's processing flow

[0355] 1. Recording: The user presses the record button on the kiosk or tablet device, and what the child says is recorded.

[0356] 2. Audio data transmission: The recorded audio data is transmitted to the server by the data transmission means.

[0357] 3. Speech Recognition and Emotion Analysis: The server uses speech recognition to convert speech data into text data, and then uses emotion recognition to analyze the user's emotions.

[0358] 4. Story Generation: The generation method uses a generative AI model (OpenAI GPT-3) to generate stories based on text data and emotional information.

[0359] 5. Illustration Generation: Illustrations are generated using an image generation model (DALLE-2) with illustration generation means, according to each scene of the story.

[0360] 6. Page Layout: The layout method integrates the story and illustrations and determines the page layout of the picture book.

[0361] 7. Data transmission and display: The completed picture book data is sent to the terminal, and the user can view the picture book on a tablet or kiosk terminal.

[0362] 8. Reading Aloud and Saving: The reading aloud function uses speech synthesis to read the generated story aloud. Users can also save the picture book in PDF format and print it as needed.

[0363] Specific example

[0364] The user (child) happily speaks into the microphone of the kiosk terminal, saying, "Today I played with fish at the beach." Once the recording ends on the display, the audio data is sent to the server. The server uses speech recognition to convert the audio data into text data, "Today I played with fish at the beach," and then uses emotion recognition to analyze the emotion of "fun."

[0365] The generative AI model (OpenAI GPT-3) uses this text and emotional information to generate a story such as, "Today I had a fun time at the beach with cute fish." Then, the image generation model (DALLE-2) generates illustrations that match the scenes in the story, such as a background of the sea and illustrations of fish.

[0366] The layout system integrates the generated story and illustrations to determine the page layout. The completed picture book data is sent to a kiosk terminal, where the user can view the picture book on the display and read along while listening to the story using a speech synthesis system. Furthermore, the user can save the picture book in PDF format and print it as needed.

[0367] Example of a prompt

[0368] What the child said: Today I played with fish at the beach.

[0369] Perceived emotion: Enjoyment

[0370] Prompt text to input to the generating AI:

[0371] Please create a story based on what your child excitedly told you, such as, "Today we had a wonderful time at the beach with cute little fish."

[0372] In this way, interactive picture books that reflect children's creativity and emotions can be generated in real time, enriching the in-store experience.

[0373] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0374] Step 1:

[0375] The user presses the record button on the kiosk terminal or tablet device. This puts the device into recording mode and records the child's voice. The input is the user's voice, and the output is an audio data file (e.g., WAV format).

[0376] Step 2:

[0377] Once recording is complete, the device sends the audio data to the server. This transmission occurs in the background via a data transmission method. The input is the audio data file, and the output is the audio data stored on the server.

[0378] Step 3:

[0379] The server receives audio data and converts it into text data using speech recognition. The Google Cloud Speech-to-Text API is used for speech recognition. The input is audio data, and the output is text data.

[0380] Step 4:

[0381] Furthermore, the server uses emotion recognition to analyze the user's emotions from the audio data. IBM Watson Tone Analyzer is used for emotion recognition. The input is audio data, and the output is emotion information (e.g., "joy").

[0382] Step 5:

[0383] The server uses a generative AI model (OpenAI GPT-3) to generate stories based on text data and sentiment information. Prompts are used during this process. Input consists of text data and sentiment information, and output is an automatically generated story.

[0384] Step 6:

[0385] The server uses an image generation model (DALLE-2) to generate illustrations that match each scene of the story. The input is the text data of the story, and the output is illustration data.

[0386] Step 7:

[0387] The server integrates the generated story and illustrations and determines the page layout of the picture book. The input is the story's text data and illustration data, and the output is the completed picture book data (e.g., in PDF format).

[0388] Step 8:

[0389] The completed picture book data is sent to the terminal, and the picture book is displayed on the terminal. The user can view the picture book using the terminal's display. The input is the picture book data sent from the server, and the output is the display on the terminal.

[0390] Step 9:

[0391] When the user presses the read-aloud button, the device uses a speech synthesis system (pyttsx3) to read the story text aloud. The input is the story text data, and the output is audio data.

[0392] Step 10:

[0393] When the user presses the save button, the device saves the generated picture book data in PDF format, which can then be printed as needed. The input is the completed picture book data, and the output is the PDF file saved on the device.

[0394] The specific processing unit 290 transmits the result of the specific processing to the smart device 14. In the smart device 14, the control unit 46A causes the output device 40 to output the result of the specific processing. The microphone 38B acquires audio indicating user input for the result of the specific processing. The control unit 46A transmits the audio data indicating user input acquired by the microphone 38B to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the audio data.

[0395] Data generation model 58 is a type of so-called generative AI (Artificial Intelligence). One example of data generation model 58 is ChatGPT (Internet search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search) <url: https: gemini.google.com ?hl="ja">Examples of generative AI include the following. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 is input with prompts containing instructions, and with inference data such as audio data representing speech, text data representing text, and image data representing images. The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference results in data formats such as audio data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[0396] In the above embodiment, an example was given in which specific processing is performed by the data processing device 12, but the technology of this disclosure is not limited thereto, and the specific processing may also be performed by the smart device 14.

[0397] [Second Embodiment]

[0398] Figure 3 shows an example of the configuration of the data processing system 210 according to the second embodiment.

[0399] As shown in Figure 3, the data processing system 210 includes a data processing device 12 and smart glasses 214. An example of the data processing device 12 is a server.

[0400] The data processing device 12 comprises a computer 22, a database 24, and a communication interface 26. The computer 22 is an example of a "computer" related to the technology of this disclosure. The computer 22 comprises a processor 28, RAM 30, and storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication interface 26 are also connected to the bus 34. The communication interface 26 is connected to a network 54. An example of the network 54 is a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0401] The smart glasses 214 include a computer 36, a microphone 238, a speaker 240, a camera 42, and a communication interface 44. The computer 36 includes a processor 46, RAM 48, and storage 50. The processor 46, RAM 48, and storage 50 are connected to a bus 52. The microphone 238, speaker 240, and camera 42 are also connected to the bus 52.

[0402] The microphone 238 receives voice signals from the user 20 and receives instructions from the user 20. The microphone 238 captures the voice signals from the user 20, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to the instructions from the processor 46.

[0403] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an image sensor such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the area around the user 20 (for example, an imaging range defined by a field of view equivalent to the width of a typical healthy person's field of vision).

[0404] Communication interface 44 is connected to network 54. Communication interfaces 44 and 26 are responsible for the exchange of various information between processor 46 and processor 28 via network 54. The exchange of various information between processor 46 and processor 28 using communication interfaces 44 and 26 is performed in a secure manner.

[0405] Figure 4 shows an example of the main functions of the data processing device 12 and the smart glasses 214. As shown in Figure 4, the data processing device 12 performs specific processing using the processor 28. The storage 32 stores the specific processing program 56.

[0406] The specific processing program 56 is an example of a "program" relating to the technology of this disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[0407] The storage 32 stores the data generation model 58 and the emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[0408] In the smart glasses 214, the processor 46 performs the reception output processing. The storage 50 stores the reception output program 60. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output processing is realized by the processor 46 operating as a control unit 46A according to the reception output program 60 executed on the RAM 48.

[0409] Next, the identification processing performed by the identification processing unit 290 of the data processing device 12 will be described. In the following description, the data processing device 12 will be referred to as the "server" and the smart glasses 214 will be referred to as the "terminal".

[0410] The system according to this invention is a system that automatically generates a story based on a child's spoken language and creates a picture book by adding illustrations related to that story. An embodiment of this system is described in detail below.

[0411] 1. Access to the app and recording

[0412] The user installs the provided application on their device and accesses the app.

[0413] When the user presses the record button, recording mode begins, and the child starts talking freely. The app's UI indicates that recording is in progress.

[0414] 2. Sending audio files to the server

[0415] Once recording is complete, the device sends the recorded data to the server. This process takes place in the background, so it doesn't interfere with the user performing other operations.

[0416] 3. Speech-to-Text Recognition

[0417] The server analyzes the received audio data and converts it into text data using a speech recognition engine. This text data represents the content of the child's speech.

[0418] 4. Story Generation

[0419] Based on the obtained text data, the server uses a generation AI model to construct a story. The constructed story is supplemented to create a coherent narrative while retaining the child's original spoken language.

[0420] 5. Illustration generation

[0421] The server uses a text generation engine to generate illustrations appropriate for each scene in the story. This adds visual elements that match the content of the narrative.

[0422] 6. Picture book layout and design

[0423] The server integrates the generated story and illustrations to complete the picture book layout. This includes the process of determining the placement of text and illustrations on each page.

[0424] 7. Sending and displaying picture book data

[0425] The completed picture book data is sent to the device and becomes viewable on the device. Users can view the picture book within the app and turn the pages.

[0426] 8. Reading and saving picture books

[0427] The device offers a text-to-speech function, playing the text portion of the story aloud. This allows children to enjoy what they've said using both their visual and auditory senses.

[0428] Users can choose to save the picture book and download it in PDF format. They can also print it as a paper copy if needed.

[0429] Specific example

[0430] Let's say a user opens the app, presses the record button, and their child tells a story, saying, "Today I made friends with a big bear in the forest." Once the recording is complete, the device sends the audio data to the server, which converts it into text data. A generative AI then uses this text to create a story, generating a narrative like, "Today in the forest, I met a big bear and we went on an adventure together." The server then generates illustrations that match the story, completing picture book pages depicting the bear and the forest scenery. Finally, the picture book data is returned to the device, allowing the user to listen to and read the book using the text-to-speech function, and also to save it as a printed copy.

[0431] As described above, this system automatically generates picture books that can be enjoyed both visually and aurally, giving shape to children's free-thinking ideas.

[0432] The following describes the processing flow.

[0433] Step 1:

[0434] The user opens the app. A recording start button is displayed on the app's main screen. The user presses the recording button to activate recording mode.

[0435] Step 2:

[0436] The device displays a notification that recording has started and begins voice input using the device's microphone. Once the user starts speaking, the audio is recorded in real time.

[0437] Step 3:

[0438] The user presses the stop button to end the recording. The recording stops, and the audio data is temporarily stored on the device.

[0439] Step 4:

[0440] The device sends the recorded data to the server. The progress of the file upload is displayed in the UI, and a notification is displayed when the data transmission is complete.

[0441] Step 5:

[0442] The server receives the audio file. The server inputs the audio data into the speech recognition engine and starts speech analysis.

[0443] Step 6:

[0444] The server converts the audio data into text data. The speech recognition engine analyzes the content of the audio and generates the corresponding text. This text data is temporarily stored.

[0445] Step 7:

[0446] The server inputs the generated text data into a story generation model. The model analyzes the text to identify the elements of the story and generates a coherent narrative.

[0447] Step 8:

[0448] The server generates illustrations appropriate for each scene using an illustration generation model based on the generated story. These illustrations are temporarily stored for each scene in the story.

[0449] Step 9:

[0450] The server integrates the generated text and illustrations to determine the page layout of the picture book. The design for each page is finalized, and the final picture book data is generated.

[0451] Step 10:

[0452] The server sends the completed picture book data to the device. The device receives the picture book data and displays it within the app.

[0453] Step 11:

[0454] The device displays picture book data and provides an interface that allows the user to view the picture book's content. The user can read the picture book by turning the pages.

[0455] Step 12:

[0456] The device provides a text-to-speech function, and when the user presses the read-aloud button, the text portion of the picture book is read aloud using speech synthesis technology.

[0457] Step 13:

[0458] Users can select a save option and download the picture book in PDF format to save it as a physical copy. They can also use the print function to save it as a physical copy if needed.

[0459] Through this series of steps, a story created by a child is transformed from audio data into text, then into a picture book, encompassing the process of adding illustrations, laying out the story, and finally saving it.

[0460] (Example 1)

[0461] Next, we will describe Example 1. In the following description, the data processing device 12 will be referred to as the "server" and the smart glasses 214 will be referred to as the "terminal".

[0462] Traditional picture book creation systems struggled to automatically generate stories that reflected children's free imaginations and to add suitable illustrations. Manually creating stories and inserting illustrations was time-consuming and laborious, making it difficult to quickly translate children's imaginations into tangible forms.

[0463] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 1 is realized by the following means.

[0464] In this invention, the server includes means for transmitting audio data to the server, means for constructing a story using a generative AI model, and means for generating illustrations corresponding to each scene of the story. This enables the rapid construction of a story based on children's spoken language and the automatic generation of suitable illustrations, thereby allowing picture books to be created in a short amount of time.

[0465] "Recording means" refers to a device or function that records the user's voice and generates audio data.

[0466] "Speech recognition means" refers to technologies and devices that convert recorded speech data into text data.

[0467] "Generation means" refers to technologies and devices that automatically construct a story based on text data obtained by speech recognition means.

[0468] "Illustration generation means" refers to technologies or devices that automatically generate illustrations corresponding to the content of a story.

[0469] "Layout means" refers to the techniques and devices used to appropriately arrange the generated story and illustrations and determine the layout of a picture book.

[0470] "Exporting method" refers to the technology or device that saves the data of a laid-out picture book and outputs it as a file such as PDF.

[0471] "Reading aloud methods" refer to technologies and devices that reproduce the text portion of a picture book as audio.

[0472] "Means of sending audio data to a server" refers to technologies and devices that transmit audio data recorded on a terminal to a server via a network.

[0473] "Methods for constructing narratives using generative AI models" refers to technologies and devices that use generative AI models to generate meaningful narratives based on input text data.

[0474] "Means for generating illustrations corresponding to each scene of a story" refers to technologies or devices that automatically generate illustrations appropriate for each scene based on the content of the story.

[0475] The system according to this invention automatically generates a story based on a child's spoken language and creates a picture book by adding illustrations related to that story. An embodiment of this system is described in detail below.

[0476] First, the system begins with the user installing the provided application on their device. The user opens the app and presses the record button to start recording mode. As the child begins to speak freely, the device's microphone records the audio, generating a recording. This recording takes place in the background, allowing the user to perform other operations.

[0477] Once recording is complete, the device sends the acquired audio data to the server. The server analyzes the received audio data and converts it into text data using a speech recognition engine (for example, Google Speech-to-Text API). This text data is a direct transcription of the child's spoken words.

[0478] Next, the server uses a generative AI model (e.g., GPT-3) to generate a story using this text data. The server prompts the generative AI model and requests it to generate a story. The generative AI model constructs a meaningful story based on the text and returns it to the server. This story is supplemented to create a coherent narrative while retaining the natural language of a child.

[0479] Next, the server uses an illustration generation engine (for example, DALLE-2) to generate illustrations corresponding to each scene in the story. Based on the content of the story, it generates illustrations suitable for each scene and imports them while aligning them with the story.

[0480] The server also integrates the story and illustrations and determines the layout of the picture book. It decides the placement of text and illustrations on each page, completing it as a digital picture book. After that, the completed picture book data is sent to the terminal, and the user can view this picture book within the application. The application also provides a page-turning function, allowing the user to intuitively read the picture book.

[0481] Finally, the device has a text-to-speech function that can play the text portion of the story aloud. This allows children to enjoy what they say not only visually but also aurally. In addition, users can choose the option to save the picture book and download it in PDF format. This PDF can be printed out as needed and enjoyed as a physical picture book.

[0482] As a concrete example, suppose a user opens the app, presses the record button, and records their child saying, "Today I made friends with a big bear in the forest." Once the recording is complete, the device sends the audio data to the server, which converts it into text data. A generative AI model uses this text to create a story, generating a narrative such as, "Today in the forest, I met a big bear and we went on an adventure together." The server generates illustrations that match the story, completing picture book pages depicting the bear and the forest scenery. Finally, the picture book data is returned to the device, allowing the user to listen to and read the book using the text-to-speech function, and also to save it as a paper copy.

[0483] An example of a prompt for a generative AI model is the sentence, "Generate a coherent children's story based on this audio data."

[0484] As described above, this system automatically generates picture books that transform children's free-thinking ideas into engaging forms and can be enjoyed both visually and aurally.

[0485] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0486] Step 1:

[0487] The user installs the app.

[0488] Specifically, the user downloads the application from the app store to their device and installs it. Once the installation is complete, the user launches the app, and the main screen is displayed. This is the initial setup stage.

[0489] Input: Application installation request

[0490] Output: Applications installed on the device

[0491] Step 2:

[0492] The user accesses the app and presses the record button to start recording mode.

[0493] Specifically, when the user taps the recording button displayed on the main screen, the device's microphone is activated. At this point, the app's UI switches to a display indicating that recording is in progress. The user then instructs the child to speak freely.

[0494] Input: User taps the record button.

[0495] Output: Start of recording mode, initialization of recording data

[0496] Step 3:

[0497] Record the child's spoken words.

[0498] Specifically, the device's microphone records the child's speech as audio data. While recording is in progress, the user can check the current recording time and progress on the screen.

[0499] Input: Children's spoken language

[0500] Output: Recorded audio data

[0501] Step 4:

[0502] After recording is complete, the audio data is saved and sent to the server.

[0503] When the user presses the record button again to end the recording, the device saves the audio data. The device then checks its internet connection and sends the saved audio data to the server. This process runs in the background, allowing the user to continue other operations.

[0504] Input: Instruction to end recording

[0505] Output: Audio data sent to the server

[0506] Step 5:

[0507] The server receives the audio data and converts it into text data using a speech recognition engine.

[0508] Specifically, when the server receives audio data, it calls a speech recognition engine (e.g., Google Speech-to-Text API) to convert the audio data into text data. The converted text data is then temporarily stored on the server.

[0509] Input: Audio data

[0510] Output: Text data

[0511] Step 6:

[0512] The server generates a story using a generation AI model.

[0513] The server takes the text data obtained through speech recognition as input and sends a prompt message to a generative AI model (e.g., GPT-3). This prompt message contains instructions to generate a story. The generative AI model generates the story text, and the result is returned to the server.

[0514] Input: Text data, prompt message

[0515] Output: Generated narrative text

[0516] Step 7:

[0517] The server generates illustrations corresponding to each scene in the story.

[0518] The server analyzes the narrative text and extracts keywords and phrases corresponding to each scene. Based on these, it sends prompt text to an illustration generation engine (e.g., DALLE-2) to generate an appropriate illustration for each scene. The generated illustrations are stored on the server.

[0519] Input: Story text, illustration generation prompt

[0520] Output: Generated illustration

[0521] Step 8:

[0522] The server integrates the story and illustrations and creates the layout for the picture book.

[0523] The server arranges the generated story text and illustrations page by page, designing the overall layout of the picture book. It then appropriately places the text and illustrations to generate the digital picture book data. This data is saved in formats such as PDF.

[0524] Input: Story text, illustrations

[0525] Output: Digital picture book data

[0526] Step 9:

[0527] The server sends the completed picture book data to the terminal.

[0528] The server sends the generated picture book data to the device, and the user can then view this data within the application. Once the picture book data is sent, the device receives the data and saves it within the application.

[0529] Input: Digital picture book data

[0530] Output: Picture book data sent to the terminal

[0531] Step 10:

[0532] The device displays picture book data and provides a read-aloud function.

[0533] Users can open picture books within the application and turn the pages. Furthermore, the device uses a speech synthesis engine to play the text portion of the picture book aloud. This feature allows children to enjoy picture books using both their sight and hearing.

[0534] Input: Picture book data

[0535] Output: Displayed picture book, played audio

[0536] Step 11:

[0537] Users can save picture books in PDF format and print them as needed.

[0538] By selecting the save option within the application, users can download the picture book in PDF format. This PDF data can also be printed on a home printer and saved as a physical picture book.

[0539] Input: Save Instructions

[0540] Output: Picture book data in PDF format

[0541] (Application Example 1)

[0542] Next, we will explain Application Example 1. In the following explanation, the data processing device 12 will be referred to as the "server," and the smart glasses 214 will be referred to as the "terminal."

[0543] Traditional story and picture book generation systems often failed to fully utilize children's creativity, providing only fixed stories and illustrations. Furthermore, the technology for automatically generating stories and illustrations based on children's free-flowing conversations was immature, with challenges in audio data processing and the quality of the generated content. Additionally, features for integrating stories and illustrations to create an enjoyable experience through both visual and auditory means were insufficient.

[0544] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 1 is realized by the following means.

[0545] In this invention, the server includes recording means, speech recognition means, generation means, illustration generation means, layout means, display means, export means, reading means, and communication means. This makes it possible to automatically generate stories and illustrations based on what a child freely says, and to provide a high-quality interactive picture book.

[0546] "Recording means" refers to a device or software for recording a user's voice and generating audio data.

[0547] "Speech recognition means" refers to technology for converting speech data generated by recording means into text data.

[0548] A "generation method" refers to a system or software for constructing a story based on text data.

[0549] "Illustration generation means" refers to a device or software for automatically generating illustrations related to the content of a story.

[0550] "Layout means" refers to a technology that integrates the generated story and illustrations to automatically determine the page layout of a picture book.

[0551] "Display means" refers to a device or software that makes a picture book generated on a terminal viewable.

[0552] "Exporting method" refers to the technology that makes the generated picture book data downloadable in a specific format (e.g., PDF).

[0553] A "read-aloud device" is a device or software used to reproduce the text portion of a story as audio.

[0554] "Communication methods" refer to technologies for sending recorded audio data and generated text data to a server, and for receiving data generated from the server to a terminal.

[0555] This invention is a system that automatically generates a story based on what a child says and provides illustrations related to that story. A specific embodiment of this system is described below.

[0556] 1. Recording method

[0557] The user uses an application installed on their smartphone or tablet. This application has a recording function, and when the user presses the record button, it starts recording the child's speech. The recorded audio is saved as audio data.

[0558] 2. Speech recognition means

[0559] The audio data generated by the recording device is sent to the server via a communication device. The server uses a speech recognition engine (e.g., Google Speech-to-Text API) to convert the audio data into text data. This allows the content of what the child said to be obtained in text format.

[0560] 3. Generation means

[0561] The server uses a generative AI model (for example, OpenAI's GPT-3) to construct a story based on the converted text data. This generative AI model complements the input text to create a coherent and creative narrative.

[0562] 4. Illustration generation means

[0563] To generate illustrations appropriate for each scene in the story, the server uses a text generation engine. This automatically adds visual elements that match the content of the story. Specifically, the generated story text acts as a prompt, and appropriate illustrations are generated based on it.

[0564] 5. Layout methods

[0565] The generated story and illustrations are integrated into a single picture book using a layout mechanism. This layout mechanism determines the placement of text and illustrations on each page, creating a visually appealing composition.

[0566] 6. Display means

[0567] The completed picture book data is then transmitted back to the user's device via communication. The user has a display mechanism within the application that allows them to view the picture book and turn the pages. This allows children to enjoy the generated story visually.

[0568] 7. Text-to-speech method

[0569] The user's device provides a text-to-speech function. It plays the text portion of the generated story aloud, allowing children to enjoy what they've said through auditory means as well.

[0570] 8. Methods for writing

[0571] The picture book data can be exported in PDF format. Users can download this data and print it as a paper copy as needed.

[0572] Usage example

[0573] When a user opens the app and presses the record button, the child tells a story, such as, "Today I made friends with a big bear in the forest." This recording is sent to a server, where a speech recognition engine converts it into text. Next, a generative AI model creates a story based on this text, generating a narrative like, "Today in the forest, I met a big bear and we went on an adventure together." The server then generates illustrations that match the story, completing picture book pages depicting the bear and the forest scenery.

[0574] Example of a prompt

[0575] Tell me a children's story where the main character is a little bear who makes friends with other animals in the forest.

[0576] In this way, this system can transform children's free-thinking ideas into tangible forms and automatically generate original picture books that can be enjoyed both visually and aurally.

[0577] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0578] Step 1:

[0579] The user launches the application installed on their smartphone or tablet and presses the record button. This activates the recording device and begins recording the child's speech. The user's input is the child's speech, and the output is audio data. The audio data is generated by the recording device and temporarily stored locally.

[0580] Step 2:

[0581] When the user finishes recording, the device sends the audio data to the server via a communication method. This process takes place in the background, allowing the user to perform other operations. The input is the audio data, and the output is the audio data sent to the server.

[0582] Step 3:

[0583] The server analyzes the received audio data using speech recognition. Specifically, it uses the Google Speech-to-Text API to convert the audio data into text data. The input is audio data, and the output is the converted text data. The speech recognition engine uses a language model to recognize words from the audio waveform and outputs them as text data.

[0584] Step 4:

[0585] The server sends text data to the generation mechanism, which uses a generative AI model (e.g., OpenAI's GPT-3) to construct a story. The generative AI model generates prompts based on the input text data, producing a consistent story. The input is text data, and the output is the text of the generated story.

[0586] Step 5:

[0587] The server sends the generated story text to the illustration generation system, which then generates illustrations that match the story. A text generation engine is used to generate visual elements appropriate for each scene. The input is the story text, and the output is the associated illustrations. The illustration generation engine analyzes the scenes from the text and generates illustrations based on the prompt text.

[0588] Step 6:

[0589] The server integrates the generated story and illustrations using layout tools to complete the picture book layout. It optimizes the placement of text and illustrations on each page, creating a visually appealing composition. The input is the story text and illustrations, and the output is the completed picture book pages.

[0590] Step 7:

[0591] The server transmits the completed picture book data to the user's terminal via a communication method. The input is the data of the completed picture book, and the output is the picture book displayed on the terminal.

[0592] Step 8:

[0593] The user's device allows them to view the generated picture book using a display device. The user can read the picture book and turn the pages within the application. The input is the completed picture book data, and the output is the picture book displayed on the user interface.

[0594] Step 9:

[0595] The user's device uses a text-to-speech mechanism to play the generated text portion of the story aloud. The user can enjoy the story not only visually but also aurally. The input is the story text, and the output is a spoken version.

[0596] Step 10:

[0597] The user's device can save the picture book data in PDF format using the export function. The user can then download this data and print it as a paper copy as needed. The input is the completed picture book data, and the output is a PDF file.

[0598] As described above, by performing specific actions at each step, it is possible to ultimately provide an interactive picture book that users can enjoy visually and aurally.

[0599] Furthermore, an emotion engine that estimates the user's emotions may be incorporated. That is, the identification processing unit 290 may use the emotion identification model 59 to estimate the user's emotions and perform identification processing using the user's emotions.

[0600] The system according to this invention is a system that automatically generates a story based on a child's spoken language and creates a picture book by adding illustrations related to that story. Furthermore, this system incorporates an emotion recognition means that recognizes the user's emotions and can adjust the story content based on the user's emotions.

[0601] 1. Access to the app and recording

[0602] The user installs the provided application on their device and accesses the app. The user presses the record button to activate recording mode.

[0603] 2. Sending audio files to the server

[0604] Once recording is complete, the device sends the recorded data to the server. This process takes place in the background, so it doesn't interfere with the user performing other operations.

[0605] 3. Speech-to-Text and emotion recognition

[0606] The server analyzes the received audio data and converts it into text data using a speech recognition engine. Furthermore, it uses emotion recognition means to analyze and identify the user's emotions from the audio data.

[0607] 4. Story Generation

[0608] Based on the obtained text data and emotional information, the server uses a generation AI model to construct a story. The characters' feelings and the story's progression are adjusted based on the emotional information. The resulting story retains the child's original spoken language while incorporating emotionally relevant content.

[0609] 5. Illustration generation

[0610] The server uses an image generation model to generate illustrations appropriate for each scene in the story. The generated illustrations are also based on emotional information and express the atmosphere of the scene.

[0611] 6. Picture book layout and design

[0612] The server integrates the generated story and illustrations to determine the page layout of the picture book. Text and illustrations are placed on each page, and the final picture book data is generated.

[0613] 7. Sending and displaying picture book data

[0614] The completed picture book data is sent to the device and becomes viewable on the device. Users can view the picture book within the app and turn the pages.

[0615] 8. Reading and saving picture books

[0616] The device offers a text-to-speech function, allowing users to press a button to have the text portion of a picture book read aloud using speech synthesis technology.

[0617] Users can choose to save the picture book and download it in PDF format. They can also print it as a paper copy if needed.

[0618] Specific example

[0619] Let's say a user opens the app, presses the record button, and their child excitedly says, "Today I made friends with a big bear in the forest." Once the recording is complete, the device sends the audio data to a server, which converts it into text data. An emotion recognition system identifies "joy" from the audio data, and a generative AI creates a story based on this text and emotional information. A story like, "Today in the forest, I met a big bear and we had a fun adventure together," is generated. The server generates illustrations that match the story's content and emotions, depicting scenes of the bear and child happily adventuring. Finally, the picture book data is returned to the device, allowing the user to listen to and read the book using the text-to-speech function, and also to save it as a paper copy.

[0620] This system automatically generates interactive picture books that include stories and illustrations that reflect the user's emotions. This allows children to enjoy expressing their feelings through stories, fostering richer creativity.

[0621] The following describes the processing flow.

[0622] Step 1:

[0623] The user opens the app and presses the record button. The app's main screen displays a "Start Recording" button, and pressing this button initiates recording mode.

[0624] Step 2:

[0625] The device displays a notification that recording has started and begins voice input using the device's microphone. The UI indicates that recording is in progress, and the user can start speaking freely.

[0626] Step 3:

[0627] The user presses the stop button to end the recording. The recording stops, and the audio data is temporarily stored on the device.

[0628] Step 4:

[0629] The device sends the recorded data to the server. The user is shown the progress of the transmission, and when the data transmission is complete, a notification of upload completion is displayed.

[0630] Step 5:

[0631] The server receives the audio file. The server uses a speech recognition engine to convert the audio file into text data. Once the text data is generated, it is temporarily stored.

[0632] Step 6:

[0633] The server uses emotion recognition technology to analyze the user's emotions from the audio data. The analysis results are output as emotion tags such as "joy" and "sadness" and are temporarily stored.

[0634] Step 7:

[0635] The server inputs the generated text data and emotion tags into the story generation model. The story generation model analyzes the input data to identify the elements of the story and generates a story that matches the emotion tags.

[0636] Step 8:

[0637] Based on the generated story, the server uses an illustration generation model to create illustrations appropriate for each scene. The illustrations match each scene in the story and also include colors and expressions that reflect emotional information.

[0638] Step 9:

[0639] The server integrates the generated text and illustrations to determine the layout of the picture book. The text and illustrations are then placed on each page, generating the final picture book data.

[0640] Step 10:

[0641] The server sends the completed picture book data to the device. The device receives the picture book data and makes it viewable within the app.

[0642] Step 11:

[0643] The device displays the picture book data, allowing the user to view the picture book's content. The user can enjoy the story by turning the pages.

[0644] Step 12:

[0645] The device provides a text-to-speech function, and when the user presses the read-aloud button, the text portion of the picture book is read aloud using speech synthesis technology. This allows the user to enjoy the story using both their sight and hearing.

[0646] Step 13:

[0647] Users can select the save option and download the picture book in PDF format. If desired, they can also print it out as a physical book and read it in person.

[0648] This series of steps automatically generates an interactive picture book containing stories and illustrations that reflect the user's emotions. This allows children to express their feelings as stories and enjoy them visually and aurally.

[0649] (Example 2)

[0650] Next, we will describe Example 2. In the following description, the data processing device 12 will be referred to as the "server" and the smart glasses 214 will be referred to as the "terminal".

[0651] Traditional story generation systems for children have struggled to create interactive stories and illustrations that reflect the user's emotions. Furthermore, generating stories based on children's spoken language and adding related illustrations required manual work, which was time-consuming. This limited their use in homes and educational settings.

[0652] The identification processing performed by the identification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means. In this invention, the server includes emotion recognition means, story generation means using a generation AI model, and image generation means. This makes it possible to analyze emotions from the user's voice data and automatically generate a story and appropriate illustrations based on that emotion information. This system can quickly generate interactive picture books that utilize children's spoken language based on voice data provided by the user.

[0653] "Recording means" refers to a device or program that has the function of recording the user's voice and saving it as audio data.

[0654] "Speech recognition means" refers to a device or program that has the function of analyzing recorded speech data and converting its content into text data.

[0655] "Emotion recognition means" refers to a device or program that has the function of analyzing and identifying a user's emotional state from voice data.

[0656] A "generation means" is a device or program that has the function of creating a story using a generative AI model based on data obtained from speech recognition means and emotion recognition means.

[0657] "Illustration generation means" refers to a device or program that has the function of automatically generating appropriate illustrations based on the content and emotional information of the generated story.

[0658] A "layout means" is a device or program that has the function of integrating the generated story and illustrations and determining the page layout of a picture book.

[0659] "Exporting method" refers to a device or program that has the function of generating and saving integrated data as final picture book data.

[0660] A "reading device" refers to a device or program that has the function of reading aloud the text portion of a generated picture book using speech synthesis technology.

[0661] This invention is a system that automatically generates stories based on children's spoken language and creates picture books by adding illustrations related to those stories. Furthermore, this system incorporates an emotion recognition means that recognizes the user's emotions and can adjust the story content based on the user's emotions. The following describes specific embodiments of this system.

[0662] Hardware and software to be used

[0663] Terminal: A device used by the user to record audio and send / receive data. Specific examples include smartphones and tablets.

[0664] Server: Computing resources for data analysis, story and illustration generation. Cloud services can also be used.

[0665] Speech recognition engine: Software used to convert recorded data into text data. For example, the Google Cloud Speech-to-Text API can be used.

[0666] Emotion recognition engine: Software for analyzing a user's emotions from voice data. For example, using the Emotion API in Azure Cognitive Services.

[0667] Generative AI model: A generative AI for constructing narratives. For example, it uses GPT-4.

[0668] Image generation model: Software for generating illustrations suitable for each scene in a story. For example, DALL-E can be used.

[0669] Design software: Software used to determine the page layout of a picture book. For example, Adobe InDesign can be used.

[0670] Speech synthesis engine: Software for reading picture books aloud. For example, Amazon Polly can be used.

[0671] System processing flow (specific example)

[0672] Explain the program's processing in natural language.

[0673] The user installs the application on their device and accesses it. The user presses the record button to activate recording mode, recording their voice using the device's microphone. Once recording is complete, the device sends the recording data to the server. The server converts this audio data into text using the Google Cloud Speech-to-Text API and further analyzes the user's emotions from the audio data using the Azure Cognitive Services Emotion API. Based on the obtained text data and emotion information, the server generates a story using a generative AI model (e.g., GPT-4).

[0674] Next, the server uses an image generation model (e.g., DALL-E) to generate illustrations suitable for each scene of the story. The generated story and illustrations are integrated on the server, and the page layout of the picture book is determined using design software such as Adobe InDesign. The generated picture book data is sent to the device, and the user can view the picture book within the app. Furthermore, using speech synthesis technology (e.g., Amazon Polly), the user can listen to the picture book read aloud. It is also possible to save the picture book in PDF format and print it as needed.

[0675] Specific example

[0676] For example, suppose a child excitedly says, "Today I made friends with a big bear in the forest." The user presses the record button to record, and then presses the stop button to end the recording. The recorded data is sent from the device to the server, where the server uses the Google Cloud Speech-to-Text API to convert the speech to text and identifies it as "joy" using the Azure Cognitive Services Emotion API. A generative AI model (GPT-4) inputs a prompt sentence based on the text and emotion information, and generates a story themed around a fun adventure. The generated story is, "Today in the forest, I met a big bear and we had a fun adventure together." An image generation model (DALL-E) generates an illustration that matches the story, depicting a scene of the smiling bear and child on an adventure. Finally, the picture book data is returned to the device, and the user can enjoy the picture book using the text-to-speech function. The picture book can also be saved in PDF format and printed to enjoy it as a paper copy.

[0677] This system allows users to quickly and easily create interactive picture books that include stories and illustrations reflecting their own emotions. This enables children to enjoy expressing their feelings through stories, fostering their creativity.

[0678] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0679] Step 1:

[0680] The user installs the provided application on their device and launches it. The user presses the record button to record the child's speech through the microphone. The input is the user's voice, and the output is the audio data stored on the device. Specifically, the device's microphone converts the user's voice into a digital signal, which is then stored as binary data.

[0681] Step 2:

[0682] Once recording is complete, the device sends the recorded data to the server. This transmission is performed using an HTTP POST request. The input is the audio data stored on the device, and the output is the audio data sent to the server. Specifically, the device generates an HTTP request, encodes the audio data, and sends it to the server.

[0683] Step 3:

[0684] The server receives audio data and sends it to the Google Cloud Speech-to-Text API, where it is converted into text data. The input is the audio data sent to the server, and the output is the converted text data. Specifically, the server generates an API request, uploads the audio data to the cloud service, and retrieves the returned text data.

[0685] Step 4:

[0686] The server sends the converted text data to the Azure Cognitive Services Emotion API for sentiment analysis. The input is text data, and the output is sentiment information. Specifically, the server sends the text data to the sentiment recognition engine for analysis and receives the resulting sentiment labels.

[0687] Step 5:

[0688] The server generates a story using a generative AI model (such as GPT-4) based on the obtained text data and sentiment information. The input is text data and sentiment information, and the output is the generated story text. Specifically, the server inputs prompt sentences into the generative AI model and receives the generated story text.

[0689] Step 6:

[0690] The server sends the generated narrative text to an image generation model (such as DALL-E) to generate an appropriate illustration. The input is narrative text, and the output is the generated illustration. Specifically, the server generates prompt statements for each scene, requests an illustration from the image generation model based on these prompts, and retrieves the returned illustration.

[0691] Step 7:

[0692] The server integrates the generated story and illustrations using design software such as Adobe InDesign to determine the page layout of the picture book. The input is the story text and illustrations, and the output is the completed picture book data. Specifically, the server inputs the data into the design software, automatically generates the layout, and produces the picture book data in PDF format.

[0693] Step 8:

[0694] The completed picture book data is sent from the server to the device, allowing the user to view it within the app. The input is the completed picture book data, and the output is the picture book data displayed on the device. Specifically, the server encodes the picture book data and sends it to the device as an HTTP response, which the device decodes and displays.

[0695] Step 9:

[0696] The device uses a text-to-speech engine such as Amazon Polly to provide a function that reads aloud the text portion of a picture book. When the user presses the read-aloud button, the device sends the text data to the text-to-speech engine and plays the generated audio. The input is the text data of the picture book, and the output is the audio data. Specifically, the device sends the text data to the text-to-speech engine and plays the returned audio data.

[0697] Step 10:

[0698] Users can save picture books in PDF format and print them as paper copies as needed. The input is the completed picture book data, and the output is the saved PDF data. Specifically, the device exports the picture book data in PDF format, which the user then downloads or prints.

[0699] (Application Example 2)

[0700] Next, we will explain application example 2. In the following explanation, the data processing device 12 will be referred to as the "server," and the smart glasses 214 will be referred to as the "terminal."

[0701] There is a need for a system that can automatically generate stories and related illustrations that respond to emotions based on what users, especially children, say, and create interactive picture books. Furthermore, it is desirable that this system be easily accessible to users in physical stores, and that the generated stories can be read aloud, saved, and printed.

[0702] In Application Example 2, the specific processing performed by the specific processing unit 290 of the data processing device 12 is realized by the following means. In this invention, the server includes recording means, speech recognition means, emotion recognition means, generation means, illustration generation means, layout means, writing means, reading means, data transmission means, and speech synthesis means. This makes it possible to automatically generate a story and related illustrations based on what the user, especially a child, says and their emotions, and further enable voice reading, saving, and printing.

[0703] A "recording device" is a device that records the user's voice and generates audio data.

[0704] A "speech recognition means" is a device that converts recorded speech data into text data.

[0705] An "emotion recognition device" is a device that analyzes and identifies a user's emotions from voice data.

[0706] A "generation method" is a device that automatically generates stories based on text data and emotional information.

[0707] An "illustration generation method" is a device that automatically generates illustrations suitable for each scene of a generated story.

[0708] A "layout device" is a device that integrates the generated story and illustrations to determine the page layout of a picture book.

[0709] The "export method" refers to a device that transmits the generated picture book data to a terminal.

[0710] A "reading device" is a device that uses speech synthesis technology to read aloud the text portion of a generated picture book.

[0711] "Data transmission means" refers to a device that transmits recorded data and generated picture book data to a server.

[0712] A "speech synthesis device" is a device that converts text data into speech and reads it aloud.

[0713] The system according to this invention is a system that automatically generates a story based on a child's spoken language and creates a picture book by adding illustrations related to that story. Furthermore, this system incorporates an emotion recognition means that recognizes the user's emotions and can adjust the story content based on the user's emotions.

[0714] Hardware and software to be used

[0715] Hardware: This system requires kiosk terminals or tablet devices, such as those used in physical stores like bookstores or toy shops. These devices incorporate microphones, speakers, and displays.

[0716] software:

[0717] 1. Speech Recognition: Use the Google Cloud Speech-to-Text API to convert recorded audio data into text data.

[0718] 2. Emotion Recognition: IBM Watson Tone Analyzer is used to analyze and identify the user's emotions from voice data.

[0719] 3. Generative AI Model: OpenAI GPT-3 is used to generate stories based on text data and sentiment information.

[0720] 4. Image generation model: DALLE-2 is used to generate illustrations that match each scene of the story.

[0721] 5. Speech synthesis: Use pyttsx3 to convert the generated story text into speech and read it aloud.

[0722] 6. PDF Generation: Use FPDF to combine the generated story and illustrations and save them in PDF format.

[0723] Overview of the program's processing flow

[0724] 1. Recording: The user presses the record button on the kiosk or tablet device, and what the child says is recorded.

[0725] 2. Audio data transmission: The recorded audio data is transmitted to the server by the data transmission means.

[0726] 3. Speech Recognition and Emotion Analysis: The server uses speech recognition to convert speech data into text data, and then uses emotion recognition to analyze the user's emotions.

[0727] 4. Story Generation: The generation method uses a generative AI model (OpenAI GPT-3) to generate stories based on text data and emotional information.

[0728] 5. Illustration Generation: Illustrations are generated using an image generation model (DALLE-2) with illustration generation means, according to each scene of the story.

[0729] 6. Page Layout: The layout method integrates the story and illustrations and determines the page layout of the picture book.

[0730] 7. Data transmission and display: The completed picture book data is sent to the terminal, and the user can view the picture book on a tablet or kiosk terminal.

[0731] 8. Reading Aloud and Saving: The reading aloud function uses speech synthesis to read the generated story aloud. Users can also save the picture book in PDF format and print it as needed.

[0732] Specific example

[0733] The user (child) happily speaks into the microphone of the kiosk terminal, saying, "Today I played with fish at the beach." Once the recording ends on the display, the audio data is sent to the server. The server uses speech recognition to convert the audio data into text data, "Today I played with fish at the beach," and then uses emotion recognition to analyze the emotion of "fun."

[0734] The generative AI model (OpenAI GPT-3) uses this text and emotional information to generate a story such as, "Today I had a fun time at the beach with cute fish." Then, the image generation model (DALLE-2) generates illustrations that match the scenes in the story, such as a background of the sea and illustrations of fish.

[0735] The layout system integrates the generated story and illustrations to determine the page layout. The completed picture book data is sent to a kiosk terminal, where the user can view the picture book on the display and read along while listening to the story using a speech synthesis system. Furthermore, the user can save the picture book in PDF format and print it as needed.

[0736] Example of a prompt

[0737] What the child said: Today I played with fish at the beach.

[0738] Perceived emotion: Enjoyment

[0739] Prompt text to input to the generating AI:

[0740] Please create a story based on what your child excitedly told you, such as, "Today we had a wonderful time at the beach with cute little fish."

[0741] In this way, interactive picture books that reflect children's creativity and emotions can be generated in real time, enriching the in-store experience.

[0742] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0743] Step 1:

[0744] The user presses the record button on the kiosk terminal or tablet device. This puts the device into recording mode and records the child's voice. The input is the user's voice, and the output is an audio data file (e.g., WAV format).

[0745] Step 2:

[0746] Once recording is complete, the device sends the audio data to the server. This transmission occurs in the background via a data transmission method. The input is the audio data file, and the output is the audio data stored on the server.

[0747] Step 3:

[0748] The server receives audio data and converts it into text data using speech recognition. The Google Cloud Speech-to-Text API is used for speech recognition. The input is audio data, and the output is text data.

[0749] Step 4:

[0750] Furthermore, the server uses emotion recognition to analyze the user's emotions from the audio data. IBM Watson Tone Analyzer is used for emotion recognition. The input is audio data, and the output is emotion information (e.g., "joy").

[0751] Step 5:

[0752] The server uses a generative AI model (OpenAI GPT-3) to generate stories based on text data and sentiment information. Prompts are used during this process. Input consists of text data and sentiment information, and output is an automatically generated story.

[0753] Step 6:

[0754] The server uses an image generation model (DALLE-2) to generate illustrations that match each scene of the story. The input is the text data of the story, and the output is illustration data.

[0755] Step 7:

[0756] The server integrates the generated story and illustrations and determines the page layout of the picture book. The input is the story's text data and illustration data, and the output is the completed picture book data (e.g., in PDF format).

[0757] Step 8:

[0758] The completed picture book data is sent to the terminal, and the picture book is displayed on the terminal. The user can view the picture book using the terminal's display. The input is the picture book data sent from the server, and the output is the display on the terminal.

[0759] Step 9:

[0760] When the user presses the read-aloud button, the device uses a speech synthesis system (pyttsx3) to read the story text aloud. The input is the story text data, and the output is audio data.

[0761] Step 10:

[0762] When the user presses the save button, the device saves the generated picture book data in PDF format, which can then be printed as needed. The input is the completed picture book data, and the output is the PDF file saved on the device.

[0763] The specific processing unit 290 transmits the result of the specific processing to the smart glasses 214. In the smart glasses 214, the control unit 46A causes the speaker 240 to output the result of the specific processing. The microphone 238 acquires audio indicating user input for the result of the specific processing. The control unit 46A transmits the audio data indicating user input acquired by the microphone 238 to the data processing unit 12. In the data processing unit 12, the specific processing unit 290 acquires the audio data.

[0764] Data generation model 58 is a type of so-called generative AI (Artificial Intelligence). One example of data generation model 58 is ChatGPT (Internet search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search) <url: https: gemini.google.com ?hl="ja">Examples of generative AI include the following. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 is input with prompts containing instructions, and with inference data such as audio data representing speech, text data representing text, and image data representing images. The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference results in data formats such as audio data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[0765] In the above embodiment, an example was given in which specific processing is performed by the data processing device 12, but the technology of this disclosure is not limited thereto, and the specific processing may also be performed by the smart glasses 214.

[0766] [Third Embodiment]

[0767] Figure 5 shows an example of the configuration of the data processing system 310 according to the third embodiment.

[0768] As shown in Figure 5, the data processing system 310 includes a data processing device 12 and a headset terminal 314. An example of the data processing device 12 is a server.

[0769] The data processing device 12 comprises a computer 22, a database 24, and a communication interface 26. The computer 22 is an example of a "computer" related to the technology of this disclosure. The computer 22 comprises a processor 28, RAM 30, and storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication interface 26 are also connected to the bus 34. The communication interface 26 is connected to a network 54. An example of the network 54 is a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0770] The headset terminal 314 includes a computer 36, a microphone 238, a speaker 240, a camera 42, a communication interface 44, and a display 343. The computer 36 includes a processor 46, RAM 48, and storage 50. The processor 46, RAM 48, and storage 50 are connected to a bus 52. The microphone 238, speaker 240, camera 42, and display 343 are also connected to the bus 52.

[0771] The microphone 238 receives voice signals from the user 20 and receives instructions from the user 20. The microphone 238 captures the voice signals from the user 20, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to the instructions from the processor 46.

[0772] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an image sensor such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the area around the user 20 (for example, an imaging range defined by a field of view equivalent to the width of a typical healthy person's field of vision).

[0773] Communication interface 44 is connected to network 54. Communication interfaces 44 and 26 are responsible for the exchange of various information between processor 46 and processor 28 via network 54. The exchange of various information between processor 46 and processor 28 using communication interfaces 44 and 26 is performed in a secure manner.

[0774] Figure 6 shows an example of the main functions of the data processing device 12 and the headset terminal 314. As shown in Figure 6, the data processing device 12 performs specific processing using the processor 28. The storage 32 stores the specific processing program 56.

[0775] The specific processing program 56 is an example of a "program" relating to the technology of this disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[0776] The storage 32 stores the data generation model 58 and the emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[0777] In the headset terminal 314, the processor 46 performs the reception output processing. The storage 50 stores the reception output program 60. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output processing is realized by the processor 46 operating as a control unit 46A according to the reception output program 60 executed on the RAM 48.

[0778] Next, the specific processing performed by the specific processing unit 290 of the data processing device 12 will be described. In the following description, the data processing device 12 will be referred to as the "server" and the headset terminal 314 will be referred to as the "terminal".

[0779] The system according to this invention is a system that automatically generates a story based on a child's spoken language and creates a picture book by adding illustrations related to that story. An embodiment of this system is described in detail below.

[0780] 1. Access to the app and recording

[0781] The user installs the provided application on their device and accesses the app.

[0782] When the user presses the record button, recording mode begins, and the child starts talking freely. The app's UI indicates that recording is in progress.

[0783] 2. Sending audio files to the server

[0784] Once recording is complete, the device sends the recorded data to the server. This process takes place in the background, so it doesn't interfere with the user performing other operations.

[0785] 3. Speech-to-Text Recognition

[0786] The server analyzes the received audio data and converts it into text data using a speech recognition engine. This text data represents the content of the child's speech.

[0787] 4. Story Generation

[0788] Based on the obtained text data, the server uses a generation AI model to construct a story. The constructed story is supplemented to create a coherent narrative while retaining the child's original spoken language.

[0789] 5. Illustration generation

[0790] The server uses a text generation engine to generate illustrations appropriate for each scene in the story. This adds visual elements that match the content of the narrative.

[0791] 6. Picture book layout and design

[0792] The server integrates the generated story and illustrations to complete the picture book layout. This includes the process of determining the placement of text and illustrations on each page.

[0793] 7. Sending and displaying picture book data

[0794] The completed picture book data is sent to the device and becomes viewable on the device. Users can view the picture book within the app and turn the pages.

[0795] 8. Reading and saving picture books

[0796] The device offers a text-to-speech function, playing the text portion of the story aloud. This allows children to enjoy what they've said using both their visual and auditory senses.

[0797] Users can choose to save the picture book and download it in PDF format. They can also print it as a paper copy if needed.

[0798] Specific example

[0799] Let's say a user opens the app, presses the record button, and their child tells a story, saying, "Today I made friends with a big bear in the forest." Once the recording is complete, the device sends the audio data to the server, which converts it into text data. A generative AI then uses this text to create a story, generating a narrative like, "Today in the forest, I met a big bear and we went on an adventure together." The server then generates illustrations that match the story, completing picture book pages depicting the bear and the forest scenery. Finally, the picture book data is returned to the device, allowing the user to listen to and read the book using the text-to-speech function, and also to save it as a printed copy.

[0800] As described above, this system automatically generates picture books that can be enjoyed both visually and aurally, giving shape to children's free-thinking ideas.

[0801] The following describes the processing flow.

[0802] Step 1:

[0803] The user opens the app. A recording start button is displayed on the app's main screen. The user presses the recording button to activate recording mode.

[0804] Step 2:

[0805] The device displays a notification that recording has started and begins voice input using the device's microphone. Once the user starts speaking, the audio is recorded in real time.

[0806] Step 3:

[0807] The user presses the stop button to end the recording. The recording stops, and the audio data is temporarily stored on the device.

[0808] Step 4:

[0809] The device sends the recorded data to the server. The progress of the file upload is displayed in the UI, and a notification is displayed when the data transmission is complete.

[0810] Step 5:

[0811] The server receives the audio file. The server inputs the audio data into the speech recognition engine and starts speech analysis.

[0812] Step 6:

[0813] The server converts the audio data into text data. The speech recognition engine analyzes the content of the audio and generates the corresponding text. This text data is temporarily stored.

[0814] Step 7:

[0815] The server inputs the generated text data into a story generation model. The model analyzes the text to identify the elements of the story and generates a coherent narrative.

[0816] Step 8:

[0817] The server generates illustrations appropriate for each scene using an illustration generation model based on the generated story. These illustrations are temporarily stored for each scene in the story.

[0818] Step 9:

[0819] The server integrates the generated text and illustrations to determine the page layout of the picture book. The design for each page is finalized, and the final picture book data is generated.

[0820] Step 10:

[0821] The server sends the completed picture book data to the device. The device receives the picture book data and displays it within the app.

[0822] Step 11:

[0823] The device displays picture book data and provides an interface that allows the user to view the picture book's content. The user can read the picture book by turning the pages.

[0824] Step 12:

[0825] The device provides a text-to-speech function, and when the user presses the read-aloud button, the text portion of the picture book is read aloud using speech synthesis technology.

[0826] Step 13:

[0827] Users can select a save option and download the picture book in PDF format to save it as a physical copy. They can also use the print function to save it as a physical copy if needed.

[0828] Through this series of steps, a story created by a child is transformed from audio data into text, then into a picture book, encompassing the process of adding illustrations, laying out the story, and finally saving it.

[0829] (Example 1)

[0830] Next, we will describe Example 1. In the following description, the data processing device 12 will be referred to as the "server," and the headset-type terminal 314 will be referred to as the "terminal."

[0831] Traditional picture book creation systems struggled to automatically generate stories that reflected children's free imaginations and to add suitable illustrations. Manually creating stories and inserting illustrations was time-consuming and laborious, making it difficult to quickly translate children's imaginations into tangible forms.

[0832] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 1 is realized by the following means.

[0833] In this invention, the server includes means for transmitting audio data to the server, means for constructing a story using a generative AI model, and means for generating illustrations corresponding to each scene of the story. This enables the rapid construction of a story based on children's spoken language and the automatic generation of suitable illustrations, thereby allowing picture books to be created in a short amount of time.

[0834] "Recording means" refers to a device or function that records the user's voice and generates audio data.

[0835] "Speech recognition means" refers to technologies and devices that convert recorded speech data into text data.

[0836] "Generation means" refers to technologies and devices that automatically construct a story based on text data obtained by speech recognition means.

[0837] "Illustration generation means" refers to technologies or devices that automatically generate illustrations corresponding to the content of a story.

[0838] "Layout means" refers to the techniques and devices used to appropriately arrange the generated story and illustrations and determine the layout of a picture book.

[0839] "Exporting method" refers to the technology or device that saves the data of a laid-out picture book and outputs it as a file such as PDF.

[0840] "Reading aloud methods" refer to technologies and devices that reproduce the text portion of a picture book as audio.

[0841] "Means of sending audio data to a server" refers to technologies and devices that transmit audio data recorded on a terminal to a server via a network.

[0842] "Methods for constructing narratives using generative AI models" refers to technologies and devices that use generative AI models to generate meaningful narratives based on input text data.

[0843] "Means for generating illustrations corresponding to each scene of a story" refers to technologies or devices that automatically generate illustrations appropriate for each scene based on the content of the story.

[0844] The system according to this invention automatically generates a story based on a child's spoken language and creates a picture book by adding illustrations related to that story. An embodiment of this system is described in detail below.

[0845] First, the system begins with the user installing the provided application on their device. The user opens the app and presses the record button to start recording mode. As the child begins to speak freely, the device's microphone records the audio, generating a recording. This recording takes place in the background, allowing the user to perform other operations.

[0846] Once recording is complete, the device sends the acquired audio data to the server. The server analyzes the received audio data and converts it into text data using a speech recognition engine (for example, Google Speech-to-Text API). This text data is a direct transcription of the child's spoken words.

[0847] Next, the server uses a generative AI model (e.g., GPT-3) to generate a story using this text data. The server prompts the generative AI model and requests it to generate a story. The generative AI model constructs a meaningful story based on the text and returns it to the server. This story is supplemented to create a coherent narrative while retaining the natural language of a child.

[0848] Next, the server uses an illustration generation engine (for example, DALLE-2) to generate illustrations corresponding to each scene in the story. Based on the content of the story, it generates illustrations suitable for each scene and imports them while aligning them with the story.

[0849] The server also integrates the story and illustrations and determines the layout of the picture book. It decides the placement of text and illustrations on each page, completing it as a digital picture book. After that, the completed picture book data is sent to the terminal, and the user can view this picture book within the application. The application also provides a page-turning function, allowing the user to intuitively read the picture book.

[0850] Finally, the device has a text-to-speech function that can play the text portion of the story aloud. This allows children to enjoy what they say not only visually but also aurally. In addition, users can choose the option to save the picture book and download it in PDF format. This PDF can be printed out as needed and enjoyed as a physical picture book.

[0851] As a concrete example, suppose a user opens the app, presses the record button, and records their child saying, "Today I made friends with a big bear in the forest." Once the recording is complete, the device sends the audio data to the server, which converts it into text data. A generative AI model uses this text to create a story, generating a narrative such as, "Today in the forest, I met a big bear and we went on an adventure together." The server generates illustrations that match the story, completing picture book pages depicting the bear and the forest scenery. Finally, the picture book data is returned to the device, allowing the user to listen to and read the book using the text-to-speech function, and also to save it as a paper copy.

[0852] An example of a prompt for a generative AI model is the sentence, "Generate a coherent children's story based on this audio data."

[0853] As described above, this system automatically generates picture books that transform children's free-thinking ideas into engaging forms and can be enjoyed both visually and aurally.

[0854] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0855] Step 1:

[0856] The user installs the app.

[0857] Specifically, the user downloads the application from the app store to their device and installs it. Once the installation is complete, the user launches the app, and the main screen is displayed. This is the initial setup stage.

[0858] Input: Application installation request

[0859] Output: Applications installed on the device

[0860] Step 2:

[0861] The user accesses the app and presses the record button to start recording mode.

[0862] Specifically, when the user taps the recording button displayed on the main screen, the device's microphone is activated. At this point, the app's UI switches to a display indicating that recording is in progress. The user then instructs the child to speak freely.

[0863] Input: User taps the record button.

[0864] Output: Start of recording mode, initialization of recording data

[0865] Step 3:

[0866] Record the child's spoken words.

[0867] Specifically, the device's microphone records the child's speech as audio data. While recording is in progress, the user can check the current recording time and progress on the screen.

[0868] Input: Children's spoken language

[0869] Output: Recorded audio data

[0870] Step 4:

[0871] After recording is complete, the audio data is saved and sent to the server.

[0872] When the user presses the record button again to end the recording, the device saves the audio data. The device then checks its internet connection and sends the saved audio data to the server. This process runs in the background, allowing the user to continue other operations.

[0873] Input: Instruction to end recording

[0874] Output: Audio data sent to the server

[0875] Step 5:

[0876] The server receives the audio data and converts it into text data using a speech recognition engine.

[0877] Specifically, when the server receives audio data, it calls a speech recognition engine (e.g., Google Speech-to-Text API) to convert the audio data into text data. The converted text data is then temporarily stored on the server.

[0878] Input: Audio data

[0879] Output: Text data

[0880] Step 6:

[0881] The server generates a story using a generation AI model.

[0882] The server takes the text data obtained through speech recognition as input and sends a prompt message to a generative AI model (e.g., GPT-3). This prompt message contains instructions to generate a story. The generative AI model generates the story text, and the result is returned to the server.

[0883] Input: Text data, prompt message

[0884] Output: Generated narrative text

[0885] Step 7:

[0886] The server generates illustrations corresponding to each scene in the story.

[0887] The server analyzes the narrative text and extracts keywords and phrases corresponding to each scene. Based on these, it sends prompt text to an illustration generation engine (e.g., DALLE-2) to generate an appropriate illustration for each scene. The generated illustrations are stored on the server.

[0888] Input: Story text, illustration generation prompt

[0889] Output: Generated illustration

[0890] Step 8:

[0891] The server integrates the story and illustrations and creates the layout for the picture book.

[0892] The server arranges the generated story text and illustrations page by page, designing the overall layout of the picture book. It then appropriately places the text and illustrations to generate the digital picture book data. This data is saved in formats such as PDF.

[0893] Input: Story text, illustrations

[0894] Output: Digital picture book data

[0895] Step 9:

[0896] The server sends the completed picture book data to the terminal.

[0897] The server sends the generated picture book data to the device, and the user can then view this data within the application. Once the picture book data is sent, the device receives the data and saves it within the application.

[0898] Input: Digital picture book data

[0899] Output: Picture book data sent to the terminal

[0900] Step 10:

[0901] The device displays picture book data and provides a read-aloud function.

[0902] Users can open picture books within the application and turn the pages. Furthermore, the device uses a speech synthesis engine to play the text portion of the picture book aloud. This feature allows children to enjoy picture books using both their sight and hearing.

[0903] Input: Picture book data

[0904] Output: Displayed picture book, played audio

[0905] Step 11:

[0906] Users can save picture books in PDF format and print them as needed.

[0907] By selecting the save option within the application, users can download the picture book in PDF format. This PDF data can also be printed on a home printer and saved as a physical picture book.

[0908] Input: Save Instructions

[0909] Output: Picture book data in PDF format

[0910] (Application Example 1)

[0911] Next, we will explain Application Example 1. In the following explanation, the data processing device 12 will be referred to as the "server," and the headset-type terminal 314 will be referred to as the "terminal."

[0912] Traditional story and picture book generation systems often failed to fully utilize children's creativity, providing only fixed stories and illustrations. Furthermore, the technology for automatically generating stories and illustrations based on children's free-flowing conversations was immature, with challenges in audio data processing and the quality of the generated content. Additionally, features for integrating stories and illustrations to create an enjoyable experience through both visual and auditory means were insufficient.

[0913] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 1 is realized by the following means.

[0914] In this invention, the server includes recording means, speech recognition means, generation means, illustration generation means, layout means, display means, export means, reading means, and communication means. This makes it possible to automatically generate stories and illustrations based on what a child freely says, and to provide a high-quality interactive picture book.

[0915] "Recording means" refers to a device or software for recording a user's voice and generating audio data.

[0916] "Speech recognition means" refers to technology for converting speech data generated by recording means into text data.

[0917] A "generation method" refers to a system or software for constructing a story based on text data.

[0918] "Illustration generation means" refers to a device or software for automatically generating illustrations related to the content of a story.

[0919] "Layout means" refers to a technology that integrates the generated story and illustrations to automatically determine the page layout of a picture book.

[0920] "Display means" refers to a device or software that makes a picture book generated on a terminal viewable.

[0921] "Exporting method" refers to the technology that makes the generated picture book data downloadable in a specific format (e.g., PDF).

[0922] A "read-aloud device" is a device or software used to reproduce the text portion of a story as audio.

[0923] "Communication methods" refer to technologies for sending recorded audio data and generated text data to a server, and for receiving data generated from the server to a terminal.

[0924] This invention is a system that automatically generates a story based on what a child says and provides illustrations related to that story. A specific embodiment of this system is described below.

[0925] 1. Recording method

[0926] The user uses an application installed on their smartphone or tablet. This application has a recording function, and when the user presses the record button, it starts recording the child's speech. The recorded audio is saved as audio data.

[0927] 2. Speech recognition means

[0928] The audio data generated by the recording device is sent to the server via a communication device. The server uses a speech recognition engine (e.g., Google Speech-to-Text API) to convert the audio data into text data. This allows the content of what the child said to be obtained in text format.

[0929] 3. Generation means

[0930] The server uses a generative AI model (for example, OpenAI's GPT-3) to construct a story based on the converted text data. This generative AI model complements the input text to create a coherent and creative narrative.

[0931] 4. Illustration generation means

[0932] To generate illustrations appropriate for each scene in the story, the server uses a text generation engine. This automatically adds visual elements that match the content of the story. Specifically, the generated story text acts as a prompt, and appropriate illustrations are generated based on it.

[0933] 5. Layout methods

[0934] The generated story and illustrations are integrated into a single picture book using a layout mechanism. This layout mechanism determines the placement of text and illustrations on each page, creating a visually appealing composition.

[0935] 6. Display means

[0936] The completed picture book data is then transmitted back to the user's device via communication. The user has a display mechanism within the application that allows them to view the picture book and turn the pages. This allows children to enjoy the generated story visually.

[0937] 7. Text-to-speech method

[0938] The user's device provides a text-to-speech function. It plays the text portion of the generated story aloud, allowing children to enjoy what they've said through auditory means as well.

[0939] 8. Methods for writing

[0940] The picture book data can be exported in PDF format. Users can download this data and print it as a paper copy as needed.

[0941] Usage example

[0942] When a user opens the app and presses the record button, the child tells a story, such as, "Today I made friends with a big bear in the forest." This recording is sent to a server, where a speech recognition engine converts it into text. Next, a generative AI model creates a story based on this text, generating a narrative like, "Today in the forest, I met a big bear and we went on an adventure together." The server then generates illustrations that match the story, completing picture book pages depicting the bear and the forest scenery.

[0943] Example of a prompt

[0944] Tell me a children's story where the main character is a little bear who makes friends with other animals in the forest.

[0945] In this way, this system can transform children's free-thinking ideas into tangible forms and automatically generate original picture books that can be enjoyed both visually and aurally.

[0946] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0947] Step 1:

[0948] The user launches the application installed on their smartphone or tablet and presses the record button. This activates the recording device and begins recording the child's speech. The user's input is the child's speech, and the output is audio data. The audio data is generated by the recording device and temporarily stored locally.

[0949] Step 2:

[0950] When the user finishes recording, the device sends the audio data to the server via a communication method. This process takes place in the background, allowing the user to perform other operations. The input is the audio data, and the output is the audio data sent to the server.

[0951] Step 3:

[0952] The server analyzes the received audio data using speech recognition. Specifically, it uses the Google Speech-to-Text API to convert the audio data into text data. The input is audio data, and the output is the converted text data. The speech recognition engine uses a language model to recognize words from the audio waveform and outputs them as text data.

[0953] Step 4:

[0954] The server sends text data to the generation mechanism, which uses a generative AI model (e.g., OpenAI's GPT-3) to construct a story. The generative AI model generates prompts based on the input text data, producing a consistent story. The input is text data, and the output is the text of the generated story.

[0955] Step 5:

[0956] The server sends the generated story text to the illustration generation system, which then generates illustrations that match the story. A text generation engine is used to generate visual elements appropriate for each scene. The input is the story text, and the output is the associated illustrations. The illustration generation engine analyzes the scenes from the text and generates illustrations based on the prompt text.

[0957] Step 6:

[0958] The server integrates the generated story and illustrations using layout tools to complete the picture book layout. It optimizes the placement of text and illustrations on each page, creating a visually appealing composition. The input is the story text and illustrations, and the output is the completed picture book pages.

[0959] Step 7:

[0960] The server transmits the completed picture book data to the user's terminal via a communication method. The input is the data of the completed picture book, and the output is the picture book displayed on the terminal.

[0961] Step 8:

[0962] The user's device allows them to view the generated picture book using a display device. The user can read the picture book and turn the pages within the application. The input is the completed picture book data, and the output is the picture book displayed on the user interface.

[0963] Step 9:

[0964] The user's device uses a text-to-speech mechanism to play the generated text portion of the story aloud. The user can enjoy the story not only visually but also aurally. The input is the story text, and the output is a spoken version.

[0965] Step 10:

[0966] The user's device can save the picture book data in PDF format using the export function. The user can then download this data and print it as a paper copy as needed. The input is the completed picture book data, and the output is a PDF file.

[0967] As described above, by performing specific actions at each step, it is possible to ultimately provide an interactive picture book that users can enjoy visually and aurally.

[0968] Furthermore, an emotion engine that estimates the user's emotions may be incorporated. That is, the identification processing unit 290 may use the emotion identification model 59 to estimate the user's emotions and perform identification processing using the user's emotions.

[0969] The system according to this invention is a system that automatically generates a story based on a child's spoken language and creates a picture book by adding illustrations related to that story. Furthermore, this system incorporates an emotion recognition means that recognizes the user's emotions and can adjust the story content based on the user's emotions.

[0970] 1. Access to the app and recording

[0971] The user installs the provided application on their device and accesses the app. The user presses the record button to activate recording mode.

[0972] 2. Sending audio files to the server

[0973] Once recording is complete, the device sends the recorded data to the server. This process takes place in the background, so it doesn't interfere with the user performing other operations.

[0974] 3. Speech-to-Text and emotion recognition

[0975] The server analyzes the received audio data and converts it into text data using a speech recognition engine. Furthermore, it uses emotion recognition means to analyze and identify the user's emotions from the audio data.

[0976] 4. Story Generation

[0977] Based on the obtained text data and emotional information, the server uses a generation AI model to construct a story. The characters' feelings and the story's progression are adjusted based on the emotional information. The resulting story retains the child's original spoken language while incorporating emotionally relevant content.

[0978] 5. Illustration generation

[0979] The server uses an image generation model to generate illustrations appropriate for each scene in the story. The generated illustrations are also based on emotional information and express the atmosphere of the scene.

[0980] 6. Picture book layout and design

[0981] The server integrates the generated story and illustrations to determine the page layout of the picture book. Text and illustrations are placed on each page, and the final picture book data is generated.

[0982] 7. Sending and displaying picture book data

[0983] The completed picture book data is sent to the device and becomes viewable on the device. Users can view the picture book within the app and turn the pages.

[0984] 8. Reading and saving picture books

[0985] The device offers a text-to-speech function, allowing users to press a button to have the text portion of a picture book read aloud using speech synthesis technology.

[0986] Users can choose to save the picture book and download it in PDF format. They can also print it as a paper copy if needed.

[0987] Specific example

[0988] Let's say a user opens the app, presses the record button, and their child excitedly says, "Today I made friends with a big bear in the forest." Once the recording is complete, the device sends the audio data to a server, which converts it into text data. An emotion recognition system identifies "joy" from the audio data, and a generative AI creates a story based on this text and emotional information. A story like, "Today in the forest, I met a big bear and we had a fun adventure together," is generated. The server generates illustrations that match the story's content and emotions, depicting scenes of the bear and child happily adventuring. Finally, the picture book data is returned to the device, allowing the user to listen to and read the book using the text-to-speech function, and also to save it as a paper copy.

[0989] This system automatically generates interactive picture books that include stories and illustrations that reflect the user's emotions. This allows children to enjoy expressing their feelings through stories, fostering richer creativity.

[0990] The following describes the processing flow.

[0991] Step 1:

[0992] The user opens the app and presses the record button. The app's main screen displays a "Start Recording" button, and pressing this button initiates recording mode.

[0993] Step 2:

[0994] The device displays a notification that recording has started and begins voice input using the device's microphone. The UI indicates that recording is in progress, and the user can start speaking freely.

[0995] Step 3:

[0996] The user presses the stop button to end the recording. The recording stops, and the audio data is temporarily stored on the device.

[0997] Step 4:

[0998] The device sends the recorded data to the server. The user is shown the progress of the transmission, and when the data transmission is complete, a notification of upload completion is displayed.

[0999] Step 5:

[1000] The server receives the audio file. The server uses a speech recognition engine to convert the audio file into text data. Once the text data is generated, it is temporarily stored.

[1001] Step 6:

[1002] The server uses emotion recognition technology to analyze the user's emotions from the audio data. The analysis results are output as emotion tags such as "joy" and "sadness" and are temporarily stored.

[1003] Step 7:

[1004] The server inputs the generated text data and emotion tags into the story generation model. The story generation model analyzes the input data to identify the elements of the story and generates a story that matches the emotion tags.

[1005] Step 8:

[1006] Based on the generated story, the server uses an illustration generation model to create illustrations appropriate for each scene. The illustrations match each scene in the story and also include colors and expressions that reflect emotional information.

[1007] Step 9:

[1008] The server integrates the generated text and illustrations to determine the layout of the picture book. The text and illustrations are then placed on each page, generating the final picture book data.

[1009] Step 10:

[1010] The server sends the completed picture book data to the device. The device receives the picture book data and makes it viewable within the app.

[1011] Step 11:

[1012] The device displays the picture book data, allowing the user to view the picture book's content. The user can enjoy the story by turning the pages.

[1013] Step 12:

[1014] The device provides a text-to-speech function, and when the user presses the read-aloud button, the text portion of the picture book is read aloud using speech synthesis technology. This allows the user to enjoy the story using both their sight and hearing.

[1015] Step 13:

[1016] Users can select the save option and download the picture book in PDF format. If desired, they can also print it out as a physical book and read it in person.

[1017] This series of steps automatically generates an interactive picture book containing stories and illustrations that reflect the user's emotions. This allows children to express their feelings as stories and enjoy them visually and aurally.

[1018] (Example 2)

[1019] Next, we will describe Example 2. In the following description, the data processing device 12 will be referred to as the "server," and the headset-type terminal 314 will be referred to as the "terminal."

[1020] Traditional story generation systems for children have struggled to create interactive stories and illustrations that reflect the user's emotions. Furthermore, generating stories based on children's spoken language and adding related illustrations required manual work, which was time-consuming. This limited their use in homes and educational settings.

[1021] The identification processing performed by the identification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means. In this invention, the server includes emotion recognition means, story generation means using a generation AI model, and image generation means. This makes it possible to analyze emotions from the user's voice data and automatically generate a story and appropriate illustrations based on that emotion information. This system can quickly generate interactive picture books that utilize children's spoken language based on voice data provided by the user.

[1022] "Recording means" refers to a device or program that has the function of recording the user's voice and saving it as audio data.

[1023] "Speech recognition means" refers to a device or program that has the function of analyzing recorded speech data and converting its content into text data.

[1024] "Emotion recognition means" refers to a device or program that has the function of analyzing and identifying a user's emotional state from voice data.

[1025] A "generation means" is a device or program that has the function of creating a story using a generative AI model based on data obtained from speech recognition means and emotion recognition means.

[1026] "Illustration generation means" refers to a device or program that has the function of automatically generating appropriate illustrations based on the content and emotional information of the generated story.

[1027] A "layout means" is a device or program that has the function of integrating the generated story and illustrations and determining the page layout of a picture book.

[1028] "Exporting method" refers to a device or program that has the function of generating and saving integrated data as final picture book data.

[1029] A "reading device" refers to a device or program that has the function of reading aloud the text portion of a generated picture book using speech synthesis technology.

[1030] This invention is a system that automatically generates stories based on children's spoken language and creates picture books by adding illustrations related to those stories. Furthermore, this system incorporates an emotion recognition means that recognizes the user's emotions and can adjust the story content based on the user's emotions. The following describes specific embodiments of this system.

[1031] Hardware and software to be used

[1032] Terminal: A device used by the user to record audio and send / receive data. Specific examples include smartphones and tablets.

[1033] Server: Computing resources for data analysis, story and illustration generation. Cloud services can also be used.

[1034] Speech recognition engine: Software used to convert recorded data into text data. For example, the Google Cloud Speech-to-Text API can be used.

[1035] Emotion recognition engine: Software for analyzing a user's emotions from voice data. For example, using the Emotion API in Azure Cognitive Services.

[1036] Generative AI model: A generative AI for constructing narratives. For example, it uses GPT-4.

[1037] Image generation model: Software for generating illustrations suitable for each scene in a story. For example, DALL-E can be used.

[1038] Design software: Software used to determine the page layout of a picture book. For example, Adobe InDesign can be used.

[1039] Speech synthesis engine: Software for reading picture books aloud. For example, Amazon Polly can be used.

[1040] System processing flow (specific example)

[1041] Explain the program's processing in natural language.

[1042] The user installs the application on their device and accesses it. The user presses the record button to activate recording mode, recording their voice using the device's microphone. Once recording is complete, the device sends the recording data to the server. The server converts this audio data into text using the Google Cloud Speech-to-Text API and further analyzes the user's emotions from the audio data using the Azure Cognitive Services Emotion API. Based on the obtained text data and emotion information, the server generates a story using a generative AI model (e.g., GPT-4).

[1043] Next, the server uses an image generation model (e.g., DALL-E) to generate illustrations suitable for each scene of the story. The generated story and illustrations are integrated on the server, and the page layout of the picture book is determined using design software such as Adobe InDesign. The generated picture book data is sent to the device, and the user can view the picture book within the app. Furthermore, using speech synthesis technology (e.g., Amazon Polly), the user can listen to the picture book read aloud. It is also possible to save the picture book in PDF format and print it as needed.

[1044] Specific example

[1045] For example, suppose a child excitedly says, "Today I made friends with a big bear in the forest." The user presses the record button to record, and then presses the stop button to end the recording. The recorded data is sent from the device to the server, where the server uses the Google Cloud Speech-to-Text API to convert the speech to text and identifies it as "joy" using the Azure Cognitive Services Emotion API. A generative AI model (GPT-4) inputs a prompt sentence based on the text and emotion information, and generates a story themed around a fun adventure. The generated story is, "Today in the forest, I met a big bear and we had a fun adventure together." An image generation model (DALL-E) generates an illustration that matches the story, depicting a scene of the smiling bear and child on an adventure. Finally, the picture book data is returned to the device, and the user can enjoy the picture book using the text-to-speech function. The picture book can also be saved in PDF format and printed to enjoy it as a paper copy.

[1046] This system allows users to quickly and easily create interactive picture books that include stories and illustrations reflecting their own emotions. This enables children to enjoy expressing their feelings through stories, fostering their creativity.

[1047] The flow of the specific processing in Example 2 will be explained using Figure 13.

[1048] Step 1:

[1049] The user installs the provided application on their device and launches it. The user presses the record button to record the child's speech through the microphone. The input is the user's voice, and the output is the audio data stored on the device. Specifically, the device's microphone converts the user's voice into a digital signal, which is then stored as binary data.

[1050] Step 2:

[1051] Once recording is complete, the device sends the recorded data to the server. This transmission is performed using an HTTP POST request. The input is the audio data stored on the device, and the output is the audio data sent to the server. Specifically, the device generates an HTTP request, encodes the audio data, and sends it to the server.

[1052] Step 3:

[1053] The server receives audio data and sends it to the Google Cloud Speech-to-Text API, where it is converted into text data. The input is the audio data sent to the server, and the output is the converted text data. Specifically, the server generates an API request, uploads the audio data to the cloud service, and retrieves the returned text data.

[1054] Step 4:

[1055] The server sends the converted text data to the Azure Cognitive Services Emotion API for sentiment analysis. The input is text data, and the output is sentiment information. Specifically, the server sends the text data to the sentiment recognition engine for analysis and receives the resulting sentiment labels.

[1056] Step 5:

[1057] The server generates a story using a generative AI model (such as GPT-4) based on the obtained text data and sentiment information. The input is text data and sentiment information, and the output is the generated story text. Specifically, the server inputs prompt sentences into the generative AI model and receives the generated story text.

[1058] Step 6:

[1059] The server sends the generated narrative text to an image generation model (such as DALL-E) to generate an appropriate illustration. The input is narrative text, and the output is the generated illustration. Specifically, the server generates prompt statements for each scene, requests an illustration from the image generation model based on these prompts, and retrieves the returned illustration.

[1060] Step 7:

[1061] The server integrates the generated story and illustrations using design software such as Adobe InDesign to determine the page layout of the picture book. The input is the story text and illustrations, and the output is the completed picture book data. Specifically, the server inputs the data into the design software, automatically generates the layout, and produces the picture book data in PDF format.

[1062] Step 8:

[1063] The completed picture book data is sent from the server to the device, allowing the user to view it within the app. The input is the completed picture book data, and the output is the picture book data displayed on the device. Specifically, the server encodes the picture book data and sends it to the device as an HTTP response, which the device decodes and displays.

[1064] Step 9:

[1065] The device uses a text-to-speech engine such as Amazon Polly to provide a function that reads aloud the text portion of a picture book. When the user presses the read-aloud button, the device sends the text data to the text-to-speech engine and plays the generated audio. The input is the text data of the picture book, and the output is the audio data. Specifically, the device sends the text data to the text-to-speech engine and plays the returned audio data.

[1066] Step 10:

[1067] Users can save picture books in PDF format and print them as paper copies as needed. The input is the completed picture book data, and the output is the saved PDF data. Specifically, the device exports the picture book data in PDF format, which the user then downloads or prints.

[1068] (Application Example 2)

[1069] Next, we will explain application example 2. In the following explanation, the data processing device 12 will be referred to as the "server," and the headset-type terminal 314 will be referred to as the "terminal."

[1070] There is a need for a system that can automatically generate stories and related illustrations that respond to emotions based on what users, especially children, say, and create interactive picture books. Furthermore, it is desirable that this system be easily accessible to users in physical stores, and that the generated stories can be read aloud, saved, and printed.

[1071] In Application Example 2, the specific processing performed by the specific processing unit 290 of the data processing device 12 is realized by the following means. In this invention, the server includes recording means, speech recognition means, emotion recognition means, generation means, illustration generation means, layout means, writing means, reading means, data transmission means, and speech synthesis means. This makes it possible to automatically generate a story and related illustrations based on what the user, especially a child, says and their emotions, and further enable voice reading, saving, and printing.

[1072] A "recording device" is a device that records the user's voice and generates audio data.

[1073] A "speech recognition means" is a device that converts recorded speech data into text data.

[1074] An "emotion recognition device" is a device that analyzes and identifies a user's emotions from voice data.

[1075] A "generation method" is a device that automatically generates stories based on text data and emotional information.

[1076] An "illustration generation method" is a device that automatically generates illustrations suitable for each scene of a generated story.

[1077] A "layout device" is a device that integrates the generated story and illustrations to determine the page layout of a picture book.

[1078] The "export method" refers to a device that transmits the generated picture book data to a terminal.

[1079] A "reading device" is a device that uses speech synthesis technology to read aloud the text portion of a generated picture book.

[1080] "Data transmission means" refers to a device that transmits recorded data and generated picture book data to a server.

[1081] A "speech synthesis device" is a device that converts text data into speech and reads it aloud.

[1082] The system according to this invention is a system that automatically generates a story based on a child's spoken language and creates a picture book by adding illustrations related to that story. Furthermore, this system incorporates an emotion recognition means that recognizes the user's emotions and can adjust the story content based on the user's emotions.

[1083] Hardware and software to be used

[1084] Hardware: This system requires kiosk terminals or tablet devices, such as those used in physical stores like bookstores or toy shops. These devices incorporate microphones, speakers, and displays.

[1085] software:

[1086] 1. Speech Recognition: Use the Google Cloud Speech-to-Text API to convert recorded audio data into text data.

[1087] 2. Emotion Recognition: IBM Watson Tone Analyzer is used to analyze and identify the user's emotions from voice data.

[1088] 3. Generative AI Model: OpenAI GPT-3 is used to generate stories based on text data and sentiment information.

[1089] 4. Image generation model: DALLE-2 is used to generate illustrations that match each scene of the story.

[1090] 5. Speech synthesis: Use pyttsx3 to convert the generated story text into speech and read it aloud.

[1091] 6. PDF Generation: Use FPDF to combine the generated story and illustrations and save them in PDF format.

[1092] Overview of the program's processing flow

[1093] 1. Recording: The user presses the record button on the kiosk or tablet device, and what the child says is recorded.

[1094] 2. Audio data transmission: The recorded audio data is transmitted to the server by the data transmission means.

[1095] 3. Speech Recognition and Emotion Analysis: The server uses speech recognition to convert speech data into text data, and then uses emotion recognition to analyze the user's emotions.

[1096] 4. Story Generation: The generation method uses a generative AI model (OpenAI GPT-3) to generate stories based on text data and emotional information.

[1097] 5. Illustration Generation: Illustrations are generated using an image generation model (DALLE-2) with illustration generation means, according to each scene of the story.

[1098] 6. Page Layout: The layout method integrates the story and illustrations and determines the page layout of the picture book.

[1099] 7. Data transmission and display: The completed picture book data is sent to the terminal, and the user can view the picture book on a tablet or kiosk terminal.

[1100] 8. Reading Aloud and Saving: The reading aloud function uses speech synthesis to read the generated story aloud. Users can also save the picture book in PDF format and print it as needed.

[1101] Specific example

[1102] The user (child) happily speaks into the microphone of the kiosk terminal, saying, "Today I played with fish at the beach." Once the recording ends on the display, the audio data is sent to the server. The server uses speech recognition to convert the audio data into text data, "Today I played with fish at the beach," and then uses emotion recognition to analyze the emotion of "fun."

[1103] The generative AI model (OpenAI GPT-3) uses this text and emotional information to generate a story such as, "Today I had a fun time at the beach with cute fish." Then, the image generation model (DALLE-2) generates illustrations that match the scenes in the story, such as a background of the sea and illustrations of fish.

[1104] The layout system integrates the generated story and illustrations to determine the page layout. The completed picture book data is sent to a kiosk terminal, where the user can view the picture book on the display and read along while listening to the story using a speech synthesis system. Furthermore, the user can save the picture book in PDF format and print it as needed.

[1105] Example of a prompt

[1106] What the child said: Today I played with fish at the beach.

[1107] Perceived emotion: Enjoyment

[1108] Prompt text to input to the generating AI:

[1109] Please create a story based on what your child excitedly told you, such as, "Today we had a wonderful time at the beach with cute little fish."

[1110] In this way, interactive picture books that reflect children's creativity and emotions can be generated in real time, enriching the in-store experience.

[1111] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[1112] Step 1:

[1113] The user presses the record button on the kiosk terminal or tablet device. This puts the device into recording mode and records the child's voice. The input is the user's voice, and the output is an audio data file (e.g., WAV format).

[1114] Step 2:

[1115] Once recording is complete, the device sends the audio data to the server. This transmission occurs in the background via a data transmission method. The input is the audio data file, and the output is the audio data stored on the server.

[1116] Step 3:

[1117] The server receives audio data and converts it into text data using speech recognition. The Google Cloud Speech-to-Text API is used for speech recognition. The input is audio data, and the output is text data.

[1118] Step 4:

[1119] Furthermore, the server uses emotion recognition to analyze the user's emotions from the audio data. IBM Watson Tone Analyzer is used for emotion recognition. The input is audio data, and the output is emotion information (e.g., "joy").

[1120] Step 5:

[1121] The server uses a generative AI model (OpenAI GPT-3) to generate stories based on text data and sentiment information. Prompts are used during this process. Input consists of text data and sentiment information, and output is an automatically generated story.

[1122] Step 6:

[1123] The server uses an image generation model (DALLE-2) to generate illustrations that match each scene of the story. The input is the text data of the story, and the output is illustration data.

[1124] Step 7:

[1125] The server integrates the generated story and illustrations and determines the page layout of the picture book. The input is the story's text data and illustration data, and the output is the completed picture book data (e.g., in PDF format).

[1126] Step 8:

[1127] The completed picture book data is sent to the terminal, and the picture book is displayed on the terminal. The user can view the picture book using the terminal's display. The input is the picture book data sent from the server, and the output is the display on the terminal.

[1128] Step 9:

[1129] When the user presses the read-aloud button, the device uses a speech synthesis system (pyttsx3) to read the story text aloud. The input is the story text data, and the output is audio data.

[1130] Step 10:

[1131] When the user presses the save button, the device saves the generated picture book data in PDF format, which can then be printed as needed. The input is the completed picture book data, and the output is the PDF file saved on the device.

[1132] The specific processing unit 290 transmits the result of the specific processing to the headset terminal 314. In the headset terminal 314, the control unit 46A causes the speaker 240 and display 343 to output the result of the specific processing. The microphone 238 acquires audio indicating user input for the result of the specific processing. The control unit 46A transmits the audio data indicating user input acquired by the microphone 238 to the data processing unit 12. In the data processing unit 12, the specific processing unit 290 acquires the audio data.

[1133] Data generation model 58 is a type of so-called generative AI (Artificial Intelligence). One example of data generation model 58 is ChatGPT (Internet search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search) <url: https: gemini.google.com ?hl="ja">Examples of generative AI include the following. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 is input with prompts containing instructions, and with inference data such as audio data representing speech, text data representing text, and image data representing images. The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference results in data formats such as audio data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[1134] In the above embodiment, an example was given in which specific processing is performed by the data processing device 12, but the technology of this disclosure is not limited thereto, and specific processing may also be performed by the headset terminal 314.

[1135] [Fourth Embodiment]

[1136] Figure 7 shows an example of the configuration of the data processing system 410 according to the fourth embodiment.

[1137] As shown in Figure 7, the data processing system 410 includes a data processing device 12 and a robot 414. An example of the data processing device 12 is a server.

[1138] The data processing device 12 comprises a computer 22, a database 24, and a communication interface 26. The computer 22 is an example of a "computer" related to the technology of this disclosure. The computer 22 comprises a processor 28, RAM 30, and storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication interface 26 are also connected to the bus 34. The communication interface 26 is connected to a network 54. An example of the network 54 is a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[1139] The robot 414 includes a computer 36, a microphone 238, a speaker 240, a camera 42, a communication interface 44, and a controlled object 443. The computer 36 includes a processor 46, RAM 48, and storage 50. The processor 46, RAM 48, and storage 50 are connected to a bus 52. The microphone 238, speaker 240, camera 42, and controlled object 443 are also connected to the bus 52.

[1140] The microphone 238 receives voice signals from the user 20 and receives instructions from the user 20. The microphone 238 captures the voice signals from the user 20, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to the instructions from the processor 46.

[1141] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an image sensor such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the area around the user 20 (for example, an imaging range defined by a field of view equivalent to the width of a typical healthy person's field of vision).

[1142] Communication interface 44 is connected to network 54. Communication interfaces 44 and 26 are responsible for the exchange of various information between processor 46 and processor 28 via network 54. The exchange of various information between processor 46 and processor 28 using communication interfaces 44 and 26 is performed in a secure manner.

[1143] The controlled object 443 includes a display device, LEDs in the eyes, and motors that drive the arms, hands, and feet. The posture and gestures of the robot 414 are controlled by controlling the motors of the arms, hands, and feet. Some of the robot 414's emotions can be expressed by controlling these motors. Furthermore, the robot 414's facial expressions can also be expressed by controlling the illumination state of the LEDs in its eyes.

[1144] Figure 8 shows an example of the main functions of the data processing device 12 and the robot 414. As shown in Figure 8, the data processing device 12 performs specific processing using the processor 28. The storage 32 stores the specific processing program 56.

[1145] The specific processing program 56 is an example of a "program" relating to the technology of this disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[1146] The storage 32 stores the data generation model 58 and the emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[1147] In robot 414, the processor 46 performs the reception output processing. The storage 50 stores the reception output program 60. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output processing is realized by the processor 46 operating as a control unit 46A according to the reception output program 60 executed on the RAM 48.

[1148] Next, the specific processing performed by the specific processing unit 290 of the data processing device 12 will be described. In the following description, the data processing device 12 will be referred to as the "server" and the robot 414 as the "terminal".

[1149] The system according to this invention is a system that automatically generates a story based on a child's spoken language and creates a picture book by adding illustrations related to that story. An embodiment of this system is described in detail below.

[1150] 1. Access to the app and recording

[1151] The user installs the provided application on their device and accesses the app.

[1152] When the user presses the record button, recording mode begins, and the child starts talking freely. The app's UI indicates that recording is in progress.

[1153] 2. Sending audio files to the server

[1154] Once recording is complete, the device sends the recorded data to the server. This process takes place in the background, so it doesn't interfere with the user performing other operations.

[1155] 3. Speech-to-Text Recognition

[1156] The server analyzes the received audio data and converts it into text data using a speech recognition engine. This text data represents the content of the child's speech.

[1157] 4. Story Generation

[1158] Based on the obtained text data, the server uses a generation AI model to construct a story. The constructed story is supplemented to create a coherent narrative while retaining the child's original spoken language.

[1159] 5. Illustration generation

[1160] The server uses a text generation engine to generate illustrations appropriate for each scene in the story. This adds visual elements that match the content of the narrative.

[1161] 6. Picture book layout and design

[1162] The server integrates the generated story and illustrations to complete the picture book layout. This includes the process of determining the placement of text and illustrations on each page.

[1163] 7. Sending and displaying picture book data

[1164] The completed picture book data is sent to the device and becomes viewable on the device. Users can view the picture book within the app and turn the pages.

[1165] 8. Reading and saving picture books

[1166] The device offers a text-to-speech function, playing the text portion of the story aloud. This allows children to enjoy what they've said using both their visual and auditory senses.

[1167] Users can choose to save the picture book and download it in PDF format. They can also print it as a paper copy if needed.

[1168] Specific example

[1169] Let's say a user opens the app, presses the record button, and their child tells a story, saying, "Today I made friends with a big bear in the forest." Once the recording is complete, the device sends the audio data to the server, which converts it into text data. A generative AI then uses this text to create a story, generating a narrative like, "Today in the forest, I met a big bear and we went on an adventure together." The server then generates illustrations that match the story, completing picture book pages depicting the bear and the forest scenery. Finally, the picture book data is returned to the device, allowing the user to listen to and read the book using the text-to-speech function, and also to save it as a printed copy.

[1170] As described above, this system automatically generates picture books that can be enjoyed both visually and aurally, giving shape to children's free-thinking ideas.

[1171] The following describes the processing flow.

[1172] Step 1:

[1173] The user opens the app. A recording start button is displayed on the app's main screen. The user presses the recording button to activate recording mode.

[1174] Step 2:

[1175] The device displays a notification that recording has started and begins voice input using the device's microphone. Once the user starts speaking, the audio is recorded in real time.

[1176] Step 3:

[1177] The user presses the stop button to end the recording. The recording stops, and the audio data is temporarily stored on the device.

[1178] Step 4:

[1179] The device sends the recorded data to the server. The progress of the file upload is displayed in the UI, and a notification is displayed when the data transmission is complete.

[1180] Step 5:

[1181] The server receives the audio file. The server inputs the audio data into the speech recognition engine and starts speech analysis.

[1182] Step 6:

[1183] The server converts the audio data into text data. The speech recognition engine analyzes the content of the audio and generates the corresponding text. This text data is temporarily stored.

[1184] Step 7:

[1185] The server inputs the generated text data into a story generation model. The model analyzes the text to identify the elements of the story and generates a coherent narrative.

[1186] Step 8:

[1187] The server generates illustrations appropriate for each scene using an illustration generation model based on the generated story. These illustrations are temporarily stored for each scene in the story.

[1188] Step 9:

[1189] The server integrates the generated text and illustrations to determine the page layout of the picture book. The design for each page is finalized, and the final picture book data is generated.

[1190] Step 10:

[1191] The server sends the completed picture book data to the device. The device receives the picture book data and displays it within the app.

[1192] Step 11:

[1193] The device displays picture book data and provides an interface that allows the user to view the picture book's content. The user can read the picture book by turning the pages.

[1194] Step 12:

[1195] The device provides a text-to-speech function, and when the user presses the read-aloud button, the text portion of the picture book is read aloud using speech synthesis technology.

[1196] Step 13:

[1197] Users can select a save option and download the picture book in PDF format to save it as a physical copy. They can also use the print function to save it as a physical copy if needed.

[1198] Through this series of steps, a story created by a child is transformed from audio data into text, then into a picture book, encompassing the process of adding illustrations, laying out the story, and finally saving it.

[1199] (Example 1)

[1200] Next, we will describe Example 1. In the following description, the data processing device 12 will be referred to as the "server" and the robot 414 as the "terminal".

[1201] Traditional picture book creation systems struggled to automatically generate stories that reflected children's free imaginations and to add suitable illustrations. Manually creating stories and inserting illustrations was time-consuming and laborious, making it difficult to quickly translate children's imaginations into tangible forms.

[1202] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 1 is realized by the following means.

[1203] In this invention, the server includes means for transmitting audio data to the server, means for constructing a story using a generative AI model, and means for generating illustrations corresponding to each scene of the story. This enables the rapid construction of a story based on children's spoken language and the automatic generation of suitable illustrations, thereby allowing picture books to be created in a short amount of time.

[1204] "Recording means" refers to a device or function that records the user's voice and generates audio data.

[1205] "Speech recognition means" refers to technologies and devices that convert recorded speech data into text data.

[1206] "Generation means" refers to technologies and devices that automatically construct a story based on text data obtained by speech recognition means.

[1207] "Illustration generation means" refers to technologies or devices that automatically generate illustrations corresponding to the content of a story.

[1208] "Layout means" refers to the techniques and devices used to appropriately arrange the generated story and illustrations and determine the layout of a picture book.

[1209] "Exporting method" refers to the technology or device that saves the data of a laid-out picture book and outputs it as a file such as PDF.

[1210] "Reading aloud methods" refer to technologies and devices that reproduce the text portion of a picture book as audio.

[1211] "Means of sending audio data to a server" refers to technologies and devices that transmit audio data recorded on a terminal to a server via a network.

[1212] "Methods for constructing narratives using generative AI models" refers to technologies and devices that use generative AI models to generate meaningful narratives based on input text data.

[1213] "Means for generating illustrations corresponding to each scene of a story" refers to technologies or devices that automatically generate illustrations appropriate for each scene based on the content of the story.

[1214] The system according to this invention automatically generates a story based on a child's spoken language and creates a picture book by adding illustrations related to that story. An embodiment of this system is described in detail below.

[1215] First, the system begins with the user installing the provided application on their device. The user opens the app and presses the record button to start recording mode. As the child begins to speak freely, the device's microphone records the audio, generating a recording. This recording takes place in the background, allowing the user to perform other operations.

[1216] Once recording is complete, the device sends the acquired audio data to the server. The server analyzes the received audio data and converts it into text data using a speech recognition engine (for example, Google Speech-to-Text API). This text data is a direct transcription of the child's spoken words.

[1217] Next, the server uses a generative AI model (e.g., GPT-3) to generate a story using this text data. The server prompts the generative AI model and requests it to generate a story. The generative AI model constructs a meaningful story based on the text and returns it to the server. This story is supplemented to create a coherent narrative while retaining the natural language of a child.

[1218] Next, the server uses an illustration generation engine (for example, DALLE-2) to generate illustrations corresponding to each scene in the story. Based on the content of the story, it generates illustrations suitable for each scene and imports them while aligning them with the story.

[1219] The server also integrates the story and illustrations and determines the layout of the picture book. It decides the placement of text and illustrations on each page, completing it as a digital picture book. After that, the completed picture book data is sent to the terminal, and the user can view this picture book within the application. The application also provides a page-turning function, allowing the user to intuitively read the picture book.

[1220] Finally, the device has a text-to-speech function that can play the text portion of the story aloud. This allows children to enjoy what they say not only visually but also aurally. In addition, users can choose the option to save the picture book and download it in PDF format. This PDF can be printed out as needed and enjoyed as a physical picture book.

[1221] As a concrete example, suppose a user opens the app, presses the record button, and records their child saying, "Today I made friends with a big bear in the forest." Once the recording is complete, the device sends the audio data to the server, which converts it into text data. A generative AI model uses this text to create a story, generating a narrative such as, "Today in the forest, I met a big bear and we went on an adventure together." The server generates illustrations that match the story, completing picture book pages depicting the bear and the forest scenery. Finally, the picture book data is returned to the device, allowing the user to listen to and read the book using the text-to-speech function, and also to save it as a paper copy.

[1222] An example of a prompt for a generative AI model is the sentence, "Generate a coherent children's story based on this audio data."

[1223] As described above, this system automatically generates picture books that transform children's free-thinking ideas into engaging forms and can be enjoyed both visually and aurally.

[1224] The flow of the specific processing in Example 1 will be explained using Figure 11.

[1225] Step 1:

[1226] The user installs the app.

[1227] Specifically, the user downloads the application from the app store to their device and installs it. Once the installation is complete, the user launches the app, and the main screen is displayed. This is the initial setup stage.

[1228] Input: Application installation request

[1229] Output: Applications installed on the device

[1230] Step 2:

[1231] The user accesses the app and presses the record button to start recording mode.

[1232] Specifically, when the user taps the recording button displayed on the main screen, the device's microphone is activated. At this point, the app's UI switches to a display indicating that recording is in progress. The user then instructs the child to speak freely.

[1233] Input: User taps the record button.

[1234] Output: Start of recording mode, initialization of recording data

[1235] Step 3:

[1236] Record the child's spoken words.

[1237] Specifically, the device's microphone records the child's speech as audio data. While recording is in progress, the user can check the current recording time and progress on the screen.

[1238] Input: Children's spoken language

[1239] Output: Recorded audio data

[1240] Step 4:

[1241] After recording is complete, the audio data is saved and sent to the server.

[1242] When the user presses the record button again to end the recording, the device saves the audio data. The device then checks its internet connection and sends the saved audio data to the server. This process runs in the background, allowing the user to continue other operations.

[1243] Input: Instruction to end recording

[1244] Output: Audio data sent to the server

[1245] Step 5:

[1246] The server receives the audio data and converts it into text data using a speech recognition engine.

[1247] Specifically, when the server receives audio data, it calls a speech recognition engine (e.g., Google Speech-to-Text API) to convert the audio data into text data. The converted text data is then temporarily stored on the server.

[1248] Input: Audio data

[1249] Output: Text data

[1250] Step 6:

[1251] The server generates a story using a generation AI model.

[1252] The server takes the text data obtained through speech recognition as input and sends a prompt message to a generative AI model (e.g., GPT-3). This prompt message contains instructions to generate a story. The generative AI model generates the story text, and the result is returned to the server.

[1253] Input: Text data, prompt message

[1254] Output: Generated narrative text

[1255] Step 7:

[1256] The server generates illustrations corresponding to each scene in the story.

[1257] The server analyzes the narrative text and extracts keywords and phrases corresponding to each scene. Based on these, it sends prompt text to an illustration generation engine (e.g., DALLE-2) to generate an appropriate illustration for each scene. The generated illustrations are stored on the server.

[1258] Input: Story text, illustration generation prompt

[1259] Output: Generated illustration

[1260] Step 8:

[1261] The server integrates the story and illustrations and creates the layout for the picture book.

[1262] The server arranges the generated story text and illustrations page by page, designing the overall layout of the picture book. It then appropriately places the text and illustrations to generate the digital picture book data. This data is saved in formats such as PDF.

[1263] Input: Story text, illustrations

[1264] Output: Digital picture book data

[1265] Step 9:

[1266] The server sends the completed picture book data to the terminal.

[1267] The server sends the generated picture book data to the device, and the user can then view this data within the application. Once the picture book data is sent, the device receives the data and saves it within the application.

[1268] Input: Digital picture book data

[1269] Output: Picture book data sent to the terminal

[1270] Step 10:

[1271] The device displays picture book data and provides a read-aloud function.

[1272] Users can open picture books within the application and turn the pages. Furthermore, the device uses a speech synthesis engine to play the text portion of the picture book aloud. This feature allows children to enjoy picture books using both their sight and hearing.

[1273] Input: Picture book data

[1274] Output: Displayed picture book, played audio

[1275] Step 11:

[1276] Users can save picture books in PDF format and print them as needed.

[1277] By selecting the save option within the application, users can download the picture book in PDF format. This PDF data can also be printed on a home printer and saved as a physical picture book.

[1278] Input: Save Instructions

[1279] Output: Picture book data in PDF format

[1280] (Application Example 1)

[1281] Next, we will explain Application Example 1. In the following explanation, the data processing device 12 will be referred to as the "server" and the robot 414 as the "terminal".

[1282] Traditional story and picture book generation systems often failed to fully utilize children's creativity, providing only fixed stories and illustrations. Furthermore, the technology for automatically generating stories and illustrations based on children's free-flowing conversations was immature, with challenges in audio data processing and the quality of the generated content. Additionally, features for integrating stories and illustrations to create an enjoyable experience through both visual and auditory means were insufficient.

[1283] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 1 is realized by the following means.

[1284] In this invention, the server includes recording means, speech recognition means, generation means, illustration generation means, layout means, display means, export means, reading means, and communication means. This makes it possible to automatically generate stories and illustrations based on what a child freely says, and to provide a high-quality interactive picture book.

[1285] "Recording means" refers to a device or software for recording a user's voice and generating audio data.

[1286] "Speech recognition means" refers to technology for converting speech data generated by recording means into text data.

[1287] A "generation method" refers to a system or software for constructing a story based on text data.

[1288] "Illustration generation means" refers to a device or software for automatically generating illustrations related to the content of a story.

[1289] "Layout means" refers to a technology that integrates the generated story and illustrations to automatically determine the page layout of a picture book.

[1290] "Display means" refers to a device or software that makes a picture book generated on a terminal viewable.

[1291] "Exporting method" refers to the technology that makes the generated picture book data downloadable in a specific format (e.g., PDF).

[1292] A "read-aloud device" is a device or software used to reproduce the text portion of a story as audio.

[1293] "Communication methods" refer to technologies for sending recorded audio data and generated text data to a server, and for receiving data generated from the server to a terminal.

[1294] This invention is a system that automatically generates a story based on what a child says and provides illustrations related to that story. A specific embodiment of this system is described below.

[1295] 1. Recording method

[1296] The user uses an application installed on their smartphone or tablet. This application has a recording function, and when the user presses the record button, it starts recording the child's speech. The recorded audio is saved as audio data.

[1297] 2. Speech recognition means

[1298] The audio data generated by the recording device is sent to the server via a communication device. The server uses a speech recognition engine (e.g., Google Speech-to-Text API) to convert the audio data into text data. This allows the content of what the child said to be obtained in text format.

[1299] 3. Generation means

[1300] The server uses a generative AI model (for example, OpenAI's GPT-3) to construct a story based on the converted text data. This generative AI model complements the input text to create a coherent and creative narrative.

[1301] 4. Illustration generation means

[1302] To generate illustrations appropriate for each scene in the story, the server uses a text generation engine. This automatically adds visual elements that match the content of the story. Specifically, the generated story text acts as a prompt, and appropriate illustrations are generated based on it.

[1303] 5. Layout methods

[1304] The generated story and illustrations are integrated into a single picture book using a layout mechanism. This layout mechanism determines the placement of text and illustrations on each page, creating a visually appealing composition.

[1305] 6. Display means

[1306] The completed picture book data is then transmitted back to the user's device via communication. The user has a display mechanism within the application that allows them to view the picture book and turn the pages. This allows children to enjoy the generated story visually.

[1307] 7. Text-to-speech method

[1308] The user's device provides a text-to-speech function. It plays the text portion of the generated story aloud, allowing children to enjoy what they've said through auditory means as well.

[1309] 8. Methods for writing

[1310] The picture book data can be exported in PDF format. Users can download this data and print it as a paper copy as needed.

[1311] Usage example

[1312] When a user opens the app and presses the record button, the child tells a story, such as, "Today I made friends with a big bear in the forest." This recording is sent to a server, where a speech recognition engine converts it into text. Next, a generative AI model creates a story based on this text, generating a narrative like, "Today in the forest, I met a big bear and we went on an adventure together." The server then generates illustrations that match the story, completing picture book pages depicting the bear and the forest scenery.

[1313] Example of a prompt

[1314] Tell me a children's story where the main character is a little bear who makes friends with other animals in the forest.

[1315] In this way, this system can transform children's free-thinking ideas into tangible forms and automatically generate original picture books that can be enjoyed both visually and aurally.

[1316] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[1317] Step 1:

[1318] The user launches the application installed on their smartphone or tablet and presses the record button. This activates the recording device and begins recording the child's speech. The user's input is the child's speech, and the output is audio data. The audio data is generated by the recording device and temporarily stored locally.

[1319] Step 2:

[1320] When the user finishes recording, the device sends the audio data to the server via a communication method. This process takes place in the background, allowing the user to perform other operations. The input is the audio data, and the output is the audio data sent to the server.

[1321] Step 3:

[1322] The server analyzes the received audio data using speech recognition. Specifically, it uses the Google Speech-to-Text API to convert the audio data into text data. The input is audio data, and the output is the converted text data. The speech recognition engine uses a language model to recognize words from the audio waveform and outputs them as text data.

[1323] Step 4:

[1324] The server sends text data to the generation mechanism, which uses a generative AI model (e.g., OpenAI's GPT-3) to construct a story. The generative AI model generates prompts based on the input text data, producing a consistent story. The input is text data, and the output is the text of the generated story.

[1325] Step 5:

[1326] The server sends the generated story text to the illustration generation system, which then generates illustrations that match the story. A text generation engine is used to generate visual elements appropriate for each scene. The input is the story text, and the output is the associated illustrations. The illustration generation engine analyzes the scenes from the text and generates illustrations based on the prompt text.

[1327] Step 6:

[1328] The server integrates the generated story and illustrations using layout tools to complete the picture book layout. It optimizes the placement of text and illustrations on each page, creating a visually appealing composition. The input is the story text and illustrations, and the output is the completed picture book pages.

[1329] Step 7:

[1330] The server transmits the completed picture book data to the user's terminal via a communication method. The input is the data of the completed picture book, and the output is the picture book displayed on the terminal.

[1331] Step 8:

[1332] The user's device allows them to view the generated picture book using a display device. The user can read the picture book and turn the pages within the application. The input is the completed picture book data, and the output is the picture book displayed on the user interface.

[1333] Step 9:

[1334] The user's device uses a text-to-speech mechanism to play the generated text portion of the story aloud. The user can enjoy the story not only visually but also aurally. The input is the story text, and the output is a spoken version.

[1335] Step 10:

[1336] The user's device can save the picture book data in PDF format using the export function. The user can then download this data and print it as a paper copy as needed. The input is the completed picture book data, and the output is a PDF file.

[1337] As described above, by performing specific actions at each step, it is possible to ultimately provide an interactive picture book that users can enjoy visually and aurally.

[1338] Furthermore, an emotion engine that estimates the user's emotions may be incorporated. That is, the identification processing unit 290 may use the emotion identification model 59 to estimate the user's emotions and perform identification processing using the user's emotions.

[1339] The system according to this invention is a system that automatically generates a story based on a child's spoken language and creates a picture book by adding illustrations related to that story. Furthermore, this system incorporates an emotion recognition means that recognizes the user's emotions and can adjust the story content based on the user's emotions.

[1340] 1. Access to the app and recording

[1341] The user installs the provided application on their device and accesses the app. The user presses the record button to activate recording mode.

[1342] 2. Sending audio files to the server

[1343] Once recording is complete, the device sends the recorded data to the server. This process takes place in the background, so it doesn't interfere with the user performing other operations.

[1344] 3. Speech-to-Text and emotion recognition

[1345] The server analyzes the received audio data and converts it into text data using a speech recognition engine. Furthermore, it uses emotion recognition means to analyze and identify the user's emotions from the audio data.

[1346] 4. Story Generation

[1347] Based on the obtained text data and emotional information, the server uses a generation AI model to construct a story. The characters' feelings and the story's progression are adjusted based on the emotional information. The resulting story retains the child's original spoken language while incorporating emotionally relevant content.

[1348] 5. Illustration generation

[1349] The server uses an image generation model to generate illustrations appropriate for each scene in the story. The generated illustrations are also based on emotional information and express the atmosphere of the scene.

[1350] 6. Picture book layout and design

[1351] The server integrates the generated story and illustrations to determine the page layout of the picture book. Text and illustrations are placed on each page, and the final picture book data is generated.

[1352] 7. Sending and displaying picture book data

[1353] The completed picture book data is sent to the device and becomes viewable on the device. Users can view the picture book within the app and turn the pages.

[1354] 8. Reading and saving picture books

[1355] The device offers a text-to-speech function, allowing users to press a button to have the text portion of a picture book read aloud using speech synthesis technology.

[1356] Users can choose to save the picture book and download it in PDF format. They can also print it as a paper copy if needed.

[1357] Specific example

[1358] Let's say a user opens the app, presses the record button, and their child excitedly says, "Today I made friends with a big bear in the forest." Once the recording is complete, the device sends the audio data to a server, which converts it into text data. An emotion recognition system identifies "joy" from the audio data, and a generative AI creates a story based on this text and emotional information. A story like, "Today in the forest, I met a big bear and we had a fun adventure together," is generated. The server generates illustrations that match the story's content and emotions, depicting scenes of the bear and child happily adventuring. Finally, the picture book data is returned to the device, allowing the user to listen to and read the book using the text-to-speech function, and also to save it as a paper copy.

[1359] This system automatically generates interactive picture books that include stories and illustrations that reflect the user's emotions. This allows children to enjoy expressing their feelings through stories, fostering richer creativity.

[1360] The following describes the processing flow.

[1361] Step 1:

[1362] The user opens the app and presses the record button. The app's main screen displays a "Start Recording" button, and pressing this button initiates recording mode.

[1363] Step 2:

[1364] The device displays a notification that recording has started and begins voice input using the device's microphone. The UI indicates that recording is in progress, and the user can start speaking freely.

[1365] Step 3:

[1366] The user presses the stop button to end the recording. The recording stops, and the audio data is temporarily stored on the device.

[1367] Step 4:

[1368] The device sends the recorded data to the server. The user is shown the progress of the transmission, and when the data transmission is complete, a notification of upload completion is displayed.

[1369] Step 5:

[1370] The server receives the audio file. The server uses a speech recognition engine to convert the audio file into text data. Once the text data is generated, it is temporarily stored.

[1371] Step 6:

[1372] The server uses emotion recognition technology to analyze the user's emotions from the audio data. The analysis results are output as emotion tags such as "joy" and "sadness" and are temporarily stored.

[1373] Step 7:

[1374] The server inputs the generated text data and emotion tags into the story generation model. The story generation model analyzes the input data to identify the elements of the story and generates a story that matches the emotion tags.

[1375] Step 8:

[1376] Based on the generated story, the server uses an illustration generation model to create illustrations appropriate for each scene. The illustrations match each scene in the story and also include colors and expressions that reflect emotional information.

[1377] Step 9:

[1378] The server integrates the generated text and illustrations to determine the layout of the picture book. The text and illustrations are then placed on each page, generating the final picture book data.

[1379] Step 10:

[1380] The server sends the completed picture book data to the device. The device receives the picture book data and makes it viewable within the app.

[1381] Step 11:

[1382] The device displays the picture book data, allowing the user to view the picture book's content. The user can enjoy the story by turning the pages.

[1383] Step 12:

[1384] The device provides a text-to-speech function, and when the user presses the read-aloud button, the text portion of the picture book is read aloud using speech synthesis technology. This allows the user to enjoy the story using both their sight and hearing.

[1385] Step 13:

[1386] Users can select the save option and download the picture book in PDF format. If desired, they can also print it out as a physical book and read it in person.

[1387] This series of steps automatically generates an interactive picture book containing stories and illustrations that reflect the user's emotions. This allows children to express their feelings as stories and enjoy them visually and aurally.

[1388] (Example 2)

[1389] Next, we will describe Example 2. In the following description, the data processing device 12 will be referred to as the "server" and the robot 414 as the "terminal".

[1390] Traditional story generation systems for children have struggled to create interactive stories and illustrations that reflect the user's emotions. Furthermore, generating stories based on children's spoken language and adding related illustrations required manual work, which was time-consuming. This limited their use in homes and educational settings.

[1391] The identification processing performed by the identification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means. In this invention, the server includes emotion recognition means, story generation means using a generation AI model, and image generation means. This makes it possible to analyze emotions from the user's voice data and automatically generate a story and appropriate illustrations based on that emotion information. This system can quickly generate interactive picture books that utilize children's spoken language based on voice data provided by the user.

[1392] "Recording means" refers to a device or program that has the function of recording the user's voice and saving it as audio data.

[1393] "Speech recognition means" refers to a device or program that has the function of analyzing recorded speech data and converting its content into text data.

[1394] "Emotion recognition means" refers to a device or program that has the function of analyzing and identifying a user's emotional state from voice data.

[1395] A "generation means" is a device or program that has the function of creating a story using a generative AI model based on data obtained from speech recognition means and emotion recognition means.

[1396] "Illustration generation means" refers to a device or program that has the function of automatically generating appropriate illustrations based on the content and emotional information of the generated story.

[1397] A "layout means" is a device or program that has the function of integrating the generated story and illustrations and determining the page layout of a picture book.

[1398] "Exporting method" refers to a device or program that has the function of generating and saving integrated data as final picture book data.

[1399] A "reading device" refers to a device or program that has the function of reading aloud the text portion of a generated picture book using speech synthesis technology.

[1400] This invention is a system that automatically generates stories based on children's spoken language and creates picture books by adding illustrations related to those stories. Furthermore, this system incorporates an emotion recognition means that recognizes the user's emotions and can adjust the story content based on the user's emotions. The following describes specific embodiments of this system.

[1401] Hardware and software to be used

[1402] Terminal: A device used by the user to record audio and send / receive data. Specific examples include smartphones and tablets.

[1403] Server: Computing resources for data analysis, story and illustration generation. Cloud services can also be used.

[1404] Speech recognition engine: Software used to convert recorded data into text data. For example, the Google Cloud Speech-to-Text API can be used.

[1405] Emotion recognition engine: Software for analyzing a user's emotions from voice data. For example, using the Emotion API in Azure Cognitive Services.

[1406] Generative AI model: A generative AI for constructing narratives. For example, it uses GPT-4.

[1407] Image generation model: Software for generating illustrations suitable for each scene in a story. For example, DALL-E can be used.

[1408] Design software: Software used to determine the page layout of a picture book. For example, Adobe InDesign can be used.

[1409] Speech synthesis engine: Software for reading picture books aloud. For example, Amazon Polly can be used.

[1410] System processing flow (specific example)

[1411] Explain the program's processing in natural language.

[1412] The user installs the application on their device and accesses it. The user presses the record button to activate recording mode, recording their voice using the device's microphone. Once recording is complete, the device sends the recording data to the server. The server converts this audio data into text using the Google Cloud Speech-to-Text API and further analyzes the user's emotions from the audio data using the Azure Cognitive Services Emotion API. Based on the obtained text data and emotion information, the server generates a story using a generative AI model (e.g., GPT-4).

[1413] Next, the server uses an image generation model (e.g., DALL-E) to generate illustrations suitable for each scene of the story. The generated story and illustrations are integrated on the server, and the page layout of the picture book is determined using design software such as Adobe InDesign. The generated picture book data is sent to the device, and the user can view the picture book within the app. Furthermore, using speech synthesis technology (e.g., Amazon Polly), the user can listen to the picture book read aloud. It is also possible to save the picture book in PDF format and print it as needed.

[1414] Specific example

[1415] For example, suppose a child excitedly says, "Today I made friends with a big bear in the forest." The user presses the record button to record, and then presses the stop button to end the recording. The recorded data is sent from the device to the server, where the server uses the Google Cloud Speech-to-Text API to convert the speech to text and identifies it as "joy" using the Azure Cognitive Services Emotion API. A generative AI model (GPT-4) inputs a prompt sentence based on the text and emotion information, and generates a story themed around a fun adventure. The generated story is, "Today in the forest, I met a big bear and we had a fun adventure together." An image generation model (DALL-E) generates an illustration that matches the story, depicting a scene of the smiling bear and child on an adventure. Finally, the picture book data is returned to the device, and the user can enjoy the picture book using the text-to-speech function. The picture book can also be saved in PDF format and printed to enjoy it as a paper copy.

[1416] This system allows users to quickly and easily create interactive picture books that include stories and illustrations reflecting their own emotions. This enables children to enjoy expressing their feelings through stories, fostering their creativity.

[1417] The flow of the specific processing in Example 2 will be explained using Figure 13.

[1418] Step 1:

[1419] The user installs the provided application on their device and launches it. The user presses the record button to record the child's speech through the microphone. The input is the user's voice, and the output is the audio data stored on the device. Specifically, the device's microphone converts the user's voice into a digital signal, which is then stored as binary data.

[1420] Step 2:

[1421] Once recording is complete, the device sends the recorded data to the server. This transmission is performed using an HTTP POST request. The input is the audio data stored on the device, and the output is the audio data sent to the server. Specifically, the device generates an HTTP request, encodes the audio data, and sends it to the server.

[1422] Step 3:

[1423] The server receives audio data and sends it to the Google Cloud Speech-to-Text API, where it is converted into text data. The input is the audio data sent to the server, and the output is the converted text data. Specifically, the server generates an API request, uploads the audio data to the cloud service, and retrieves the returned text data.

[1424] Step 4:

[1425] The server sends the converted text data to the Azure Cognitive Services Emotion API for sentiment analysis. The input is text data, and the output is sentiment information. Specifically, the server sends the text data to the sentiment recognition engine for analysis and receives the resulting sentiment labels.

[1426] Step 5:

[1427] The server generates a story using a generative AI model (such as GPT-4) based on the obtained text data and sentiment information. The input is text data and sentiment information, and the output is the generated story text. Specifically, the server inputs prompt sentences into the generative AI model and receives the generated story text.

[1428] Step 6:

[1429] The server sends the generated narrative text to an image generation model (such as DALL-E) to generate an appropriate illustration. The input is narrative text, and the output is the generated illustration. Specifically, the server generates prompt statements for each scene, requests an illustration from the image generation model based on these prompts, and retrieves the returned illustration.

[1430] Step 7:

[1431] The server integrates the generated story and illustrations using design software such as Adobe InDesign to determine the page layout of the picture book. The input is the story text and illustrations, and the output is the completed picture book data. Specifically, the server inputs the data into the design software, automatically generates the layout, and produces the picture book data in PDF format.

[1432] Step 8:

[1433] The completed picture book data is sent from the server to the device, allowing the user to view it within the app. The input is the completed picture book data, and the output is the picture book data displayed on the device. Specifically, the server encodes the picture book data and sends it to the device as an HTTP response, which the device decodes and displays.

[1434] Step 9:

[1435] The device uses a text-to-speech engine such as Amazon Polly to provide a function that reads aloud the text portion of a picture book. When the user presses the read-aloud button, the device sends the text data to the text-to-speech engine and plays the generated audio. The input is the text data of the picture book, and the output is the audio data. Specifically, the device sends the text data to the text-to-speech engine and plays the returned audio data.

[1436] Step 10:

[1437] Users can save picture books in PDF format and print them as paper copies as needed. The input is the completed picture book data, and the output is the saved PDF data. Specifically, the device exports the picture book data in PDF format, which the user then downloads or prints.

[1438] (Application Example 2)

[1439] Next, we will explain application example 2. In the following explanation, the data processing device 12 will be referred to as the "server" and the robot 414 as the "terminal".

[1440] There is a need for a system that can automatically generate stories and related illustrations that respond to emotions based on what users, especially children, say, and create interactive picture books. Furthermore, it is desirable that this system be easily accessible to users in physical stores, and that the generated stories can be read aloud, saved, and printed.

[1441] In Application Example 2, the specific processing performed by the specific processing unit 290 of the data processing device 12 is realized by the following means. In this invention, the server includes recording means, speech recognition means, emotion recognition means, generation means, illustration generation means, layout means, writing means, reading means, data transmission means, and speech synthesis means. This makes it possible to automatically generate a story and related illustrations based on what the user, especially a child, says and their emotions, and further enable voice reading, saving, and printing.

[1442] A "recording device" is a device that records the user's voice and generates audio data.

[1443] A "speech recognition means" is a device that converts recorded speech data into text data.

[1444] An "emotion recognition device" is a device that analyzes and identifies a user's emotions from voice data.

[1445] A "generation method" is a device that automatically generates stories based on text data and emotional information.

[1446] An "illustration generation method" is a device that automatically generates illustrations suitable for each scene of a generated story.

[1447] A "layout device" is a device that integrates the generated story and illustrations to determine the page layout of a picture book.

[1448] The "export method" refers to a device that transmits the generated picture book data to a terminal.

[1449] A "reading device" is a device that uses speech synthesis technology to read aloud the text portion of a generated picture book.

[1450] "Data transmission means" refers to a device that transmits recorded data and generated picture book data to a server.

[1451] A "speech synthesis device" is a device that converts text data into speech and reads it aloud.

[1452] The system according to this invention is a system that automatically generates a story based on a child's spoken language and creates a picture book by adding illustrations related to that story. Furthermore, this system incorporates an emotion recognition means that recognizes the user's emotions and can adjust the story content based on the user's emotions.

[1453] Hardware and software to be used

[1454] Hardware: This system requires kiosk terminals or tablet devices, such as those used in physical stores like bookstores or toy shops. These devices incorporate microphones, speakers, and displays.

[1455] software:

[1456] 1. Speech Recognition: Use the Google Cloud Speech-to-Text API to convert recorded audio data into text data.

[1457] 2. Emotion Recognition: IBM Watson Tone Analyzer is used to analyze and identify the user's emotions from voice data.

[1458] 3. Generative AI Model: OpenAI GPT-3 is used to generate stories based on text data and sentiment information.

[1459] 4. Image generation model: DALLE-2 is used to generate illustrations that match each scene of the story.

[1460] 5. Speech synthesis: Use pyttsx3 to convert the generated story text into speech and read it aloud.

[1461] 6. PDF Generation: Use FPDF to combine the generated story and illustrations and save them in PDF format.

[1462] Overview of the program's processing flow

[1463] 1. Recording: The user presses the record button on the kiosk or tablet device, and what the child says is recorded.

[1464] 2. Audio data transmission: The recorded audio data is transmitted to the server by the data transmission means.

[1465] 3. Speech Recognition and Emotion Analysis: The server uses speech recognition to convert speech data into text data, and then uses emotion recognition to analyze the user's emotions.

[1466] 4. Story Generation: The generation method uses a generative AI model (OpenAI GPT-3) to generate stories based on text data and emotional information.

[1467] 5. Illustration Generation: Illustrations are generated using an image generation model (DALLE-2) with illustration generation means, according to each scene of the story.

[1468] 6. Page Layout: The layout method integrates the story and illustrations and determines the page layout of the picture book.

[1469] 7. Data transmission and display: The completed picture book data is sent to the terminal, and the user can view the picture book on a tablet or kiosk terminal.

[1470] 8. Reading Aloud and Saving: The reading aloud function uses speech synthesis to read the generated story aloud. Users can also save the picture book in PDF format and print it as needed.

[1471] Specific example

[1472] The user (child) happily speaks into the microphone of the kiosk terminal, saying, "Today I played with fish at the beach." Once the recording ends on the display, the audio data is sent to the server. The server uses speech recognition to convert the audio data into text data, "Today I played with fish at the beach," and then uses emotion recognition to analyze the emotion of "fun."

[1473] The generative AI model (OpenAI GPT-3) uses this text and emotional information to generate a story such as, "Today I had a fun time at the beach with cute fish." Then, the image generation model (DALLE-2) generates illustrations that match the scenes in the story, such as a background of the sea and illustrations of fish.

[1474] The layout system integrates the generated story and illustrations to determine the page layout. The completed picture book data is sent to a kiosk terminal, where the user can view the picture book on the display and read along while listening to the story using a speech synthesis system. Furthermore, the user can save the picture book in PDF format and print it as needed.

[1475] Example of a prompt

[1476] What the child said: Today I played with fish at the beach.

[1477] Perceived emotion: Enjoyment

[1478] Prompt text to input to the generating AI:

[1479] Please create a story based on what your child excitedly told you, such as, "Today we had a wonderful time at the beach with cute little fish."

[1480] In this way, interactive picture books that reflect children's creativity and emotions can be generated in real time, enriching the in-store experience.

[1481] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[1482] Step 1:

[1483] The user presses the record button on the kiosk terminal or tablet device. This puts the device into recording mode and records the child's voice. The input is the user's voice, and the output is an audio data file (e.g., WAV format).

[1484] Step 2:

[1485] Once recording is complete, the device sends the audio data to the server. This transmission occurs in the background via a data transmission method. The input is the audio data file, and the output is the audio data stored on the server.

[1486] Step 3:

[1487] The server receives audio data and converts it into text data using speech recognition. The Google Cloud Speech-to-Text API is used for speech recognition. The input is audio data, and the output is text data.

[1488] Step 4:

[1489] Furthermore, the server uses emotion recognition to analyze the user's emotions from the audio data. IBM Watson Tone Analyzer is used for emotion recognition. The input is audio data, and the output is emotion information (e.g., "joy").

[1490] Step 5:

[1491] The server uses a generative AI model (OpenAI GPT-3) to generate stories based on text data and sentiment information. Prompts are used during this process. Input consists of text data and sentiment information, and output is an automatically generated story.

[1492] Step 6:

[1493] The server uses an image generation model (DALLE-2) to generate illustrations that match each scene of the story. The input is the text data of the story, and the output is illustration data.

[1494] Step 7:

[1495] The server integrates the generated story and illustrations and determines the page layout of the picture book. The input is the story's text data and illustration data, and the output is the completed picture book data (e.g., in PDF format).

[1496] Step 8:

[1497] The completed picture book data is sent to the terminal, and the picture book is displayed on the terminal. The user can view the picture book using the terminal's display. The input is the picture book data sent from the server, and the output is the display on the terminal.

[1498] Step 9:

[1499] When the user presses the read-aloud button, the device uses a speech synthesis system (pyttsx3) to read the story text aloud. The input is the story text data, and the output is audio data.

[1500] Step 10:

[1501] When the user presses the save button, the device saves the generated picture book data in PDF format, which can then be printed as needed. The input is the completed picture book data, and the output is the PDF file saved on the device.

[1502] The specific processing unit 290 transmits the result of the specific processing to the robot 414. In the robot 414, the control unit 46A causes the speaker 240 and the controlled object 443 to output the result of the specific processing. The microphone 238 acquires audio indicating user input for the result of the specific processing. The control unit 46A transmits the audio data indicating user input acquired by the microphone 238 to the data processing unit 12. In the data processing unit 12, the specific processing unit 290 acquires the audio data.

[1503] Data generation model 58 is a type of so-called generative AI (Artificial Intelligence). One example of data generation model 58 is ChatGPT (Internet search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search) <url: https: gemini.google.com ?hl="ja">Examples of generative AI include the following. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 is input with prompts containing instructions, and with inference data such as audio data representing speech, text data representing text, and image data representing images. The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference results in data formats such as audio data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[1504] In the above embodiment, an example was given in which the specific processing is performed by the data processing device 12, but the technology of this disclosure is not limited thereto, and the specific processing may also be performed by the robot 414.

[1505] Furthermore, the emotion identification model 59, acting as an emotion engine, may determine the user's emotion according to a specific mapping. Specifically, the emotion identification model 59 may determine the user's emotion according to a specific mapping, which is an emotion map (see Figure 9). Similarly, the emotion identification model 59 may also determine the robot's emotion, and the identification processing unit 290 may perform identification processing using the robot's emotion.

[1506] Figure 9 shows an emotion map 400 in which multiple emotions are mapped. In the emotion map 400, emotions are arranged in concentric circles radiating from the center. The closer to the center of the concentric circles, the more primitive the emotions are located. Further out of the concentric circles, emotions representing states and actions arising from mental states are located. Emotion is a concept that includes feelings and mental states. On the left side of the concentric circles, emotions that are generally generated from reactions occurring in the brain are located. On the right side of the concentric circles, emotions that are generally induced by situational judgment are located. Above and below the concentric circles, emotions that are generally generated from reactions occurring in the brain and induced by situational judgment are located. In addition, the emotion of "pleasure" is located on the upper side of the concentric circles, and the emotion of "displeasure" is located on the lower side. Thus, in the emotion map 400, multiple emotions are mapped based on the structure in which emotions arise, and emotions that are likely to occur simultaneously are mapped close together.

[1507] These emotions are distributed at the 3 o'clock position on the Emotion Map 400, and usually fluctuate between feelings of security and anxiety. In the right half of the Emotion Map 400, situational awareness takes precedence over internal feelings, resulting in a calm impression.

[1508] The inside of the Emotion Map 400 represents inner thoughts, while the outside represents actions. Therefore, the further you go from the outside of the Emotion Map 400, the more visible (expressed in actions) your emotions become.

[1509] Here, human emotions are based on various balances, such as posture and blood sugar levels. When these balances deviate from the ideal, it results in discomfort, and when they approach the ideal, it results in pleasure. Similarly, in robots, cars, motorcycles, etc., emotions can be created based on various balances, such as posture and battery level. When these balances deviate from the ideal, it results in discomfort, and when they approach the ideal, it results in pleasure. The emotion map can be generated, for example, based on Dr. Mitsuyoshi's emotion map (Research on a system for analyzing brain physiological signals of speech emotion recognition and emotion, Tokushima University, doctoral dissertation: https: / / ci.nii.ac.jp / naid / 500000375379). The left half of the emotion map contains emotions belonging to a region called "response," where sensation is dominant. The right half of the emotion map contains emotions belonging to a region called "situation," where situational awareness is dominant.

[1510] The emotion map defines two emotions that promote learning. One is the emotion around the middle of the negative "repentance" and "reflection" on the situation side. In other words, it is when the robot experiences negative emotions such as "I never want to feel this way again" or "I don't want to be scolded again." The other is the emotion around the positive "desire" on the reaction side. In other words, it is when the robot has positive feelings such as "I want more" or "I want to know more."

[1511] The emotion identification model 59 inputs user input into a pre-trained neural network, obtains emotion values ​​representing each emotion shown in the emotion map 400, and determines the user's emotion. This neural network is pre-trained based on multiple training data sets, which are combinations of user input and emotion values ​​representing each emotion shown in the emotion map 400. Furthermore, this neural network is trained so that emotions located close together have similar values, as shown in the emotion map 900 in Figure 10. Figure 10 shows an example where multiple emotions such as "reassured," "calm," and "confident" have similar emotion values.

[1512] The above description primarily focuses on the functions of the data processing device 12 in relation to this disclosure. However, the system related to this disclosure is not necessarily implemented on a server. The system related to this disclosure may be implemented as a general information processing system. This disclosure may be implemented, for example, as a software program that runs on a personal computer or as an application that runs on a smartphone. The method related to this disclosure may be provided to users in SaaS (Software as a Service) format.

[1513] In the above embodiment, an example was given in which a specific process is performed by a single computer 22. However, the technology of this disclosure is not limited thereto, and a distributed processing of the specific process may be performed by multiple computers, including computer 22. For example, a data generation model 58 may be provided in an external device of the data processing device 12, and the external device may generate data according to the input data.

[1514] In the above embodiment, an example was given in which the specific processing program 56 is stored in the storage 32, but the technology of this disclosure is not limited thereto. For example, the specific processing program 56 may be stored in a portable, computer-readable, non-temporary storage medium such as a USB (Universal Serial Bus) memory. The specific processing program 56 stored in the non-temporary storage medium is installed in the computer 22 of the data processing device 12. The processor 28 executes specific processing according to the specific processing program 56.

[1515] 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.

[1516] Furthermore, it is not necessary to store the entirety of the specific processing program 56 in a storage device such as a server connected to the data processing device 12 via the network 54, or to store the entirety of the specific processing program 56 in the storage 32; it is acceptable to store only a portion of the specific processing program 56.

[1517] The following types of processors can be used as hardware resources to perform specific processing. Examples of processors include a CPU, a general-purpose processor that functions as a hardware resource to perform specific processing by executing software, i.e., a program. Other examples of processors include dedicated electrical circuits, such as FPGAs (Field-Programmable Gate Arrays), PLDs (Programmable Logic Devices), or ASICs (Application Specific Integrated Circuits), which have circuit configurations specifically designed to perform specific processing. All of these processors have built-in or connected memory, and all of them perform specific processing by using memory.

[1518] The hardware resource that performs a specific process may consist of one of these various processors, or it may consist of a combination of two or more processors of the same or different types (for example, a combination of multiple FPGAs, or a combination of a CPU and an FPGA). Alternatively, the hardware resource that performs a specific process may consist of a single processor.

[1519] Examples of configurations using a single processor include, firstly, a configuration in which one or more CPUs and software are combined to form a single processor, and this processor functions as a hardware resource that performs a specific process. Secondly, there is a configuration using a processor that realizes the functions of the entire system, including multiple hardware resources that perform a specific process, on a single IC chip, as exemplified by SoCs (System-on-a-chip). In this way, a specific process is realized using one or more of the above types of processors as hardware resources.

[1520] Furthermore, the hardware structure of these various processors can more specifically utilize electrical circuits that combine circuit elements such as semiconductor devices. Also, the specific processing described above is merely an example. Therefore, it goes without saying that unnecessary steps can be deleted, new steps added, or the processing order rearranged, as long as it does not deviate from the main purpose.

[1521] The descriptions and illustrations presented above are detailed explanations of the technical aspects of this disclosure and are merely examples of the technical aspects. For example, the above descriptions of the structure, function, operation, and effect are examples of the structure, function, operation, and effect of the technical aspects of this disclosure. Therefore, it goes without saying that you may delete unnecessary parts, add new elements, or replace elements in the descriptions and illustrations presented above, as long as you do not deviate from the essence of the technical aspects of this disclosure. Furthermore, in order to avoid confusion and facilitate understanding of the technical aspects of this disclosure, explanations of common technical knowledge and the like that do not require special explanation to enable the implementation of the technical aspects of this disclosure have been omitted from the descriptions and illustrations presented above.

[1522] All documents, patent applications, and technical standards described herein are incorporated by reference to the same extent as if each individual document, patent application, and technical standard were specifically and individually noted to be incorporated by reference.

[1523] The following is further disclosed regarding the embodiments described above.

[1524] (Claim 1)

[1525] Recording means and

[1526] Voice recognition means and

[1527] means of generation,

[1528] Illustration generation method,

[1529] Layout methods,

[1530] Methods for writing,

[1531] A system that includes a text-to-speech mechanism.

[1532] (Claim 2)

[1533] The system according to claim 1, wherein the recording means is a means for recording the user's voice and generating audio data.

[1534] (Claim 3)

[1535] The system according to claim 1, wherein the speech recognition means is a means for converting the speech data into text data.

[1536] "Example 1"

[1537] (Claim 1)

[1538] Recording means and

[1539] Voice recognition means and

[1540] means of generation,

[1541] Illustration generation method,

[1542] Layout methods,

[1543] Methods for writing,

[1544] Text-to-speech methods,

[1545] A means of sending audio data to a server,

[1546] A means of constructing a story using a generative AI model,

[1547] A system that includes means for generating illustrations corresponding to each scene in a story.

[1548] (Claim 2)

[1549] The system according to claim 1, wherein the recording means is a means for recording the user's voice and generating audio data.

[1550] (Claim 3)

[1551] The system according to claim 1, wherein the speech recognition means is a means for converting the speech data into text data.

[1552] "Application Example 1"

[1553] (Claim 1)

[1554] Recording means and

[1555] Voice recognition means and

[1556] means of generation,

[1557] Illustration generation method,

[1558] Layout methods,

[1559] Display means and

[1560] Methods for writing,

[1561] Text-to-speech methods,

[1562] A system including means of communication.

[1563] (Claim 2)

[1564] The system according to claim 1, wherein the recording means is a means for recording the user's voice and generating audio data, and the means includes a means for transmitting the audio data to a server via the communication means.

[1565] (Claim 3)

[1566] The system according to claim 1, wherein the speech recognition means is a means for converting the speech data into text data, and the means includes a means for transmitting the text data to a generating AI model to generate a story.

[1567] "Example 2 of combining an emotion engine"

[1568] (Claim 1)

[1569] Recording means and

[1570] Voice recognition means and

[1571] Means of recognizing emotions,

[1572] means of generation,

[1573] Illustration generation method,

[1574] Layout methods,

[1575] Methods for writing,

[1576] A system that includes a text-to-speech mechanism.

[1577] (Claim 2)

[1578] The system according to claim 1, wherein the recording means is a means for recording the user's voice and generating voice data, and the emotion recognition means is a means for analyzing and identifying the user's emotions from the voice data.

[1579] (Claim 3)

[1580] The system according to claim 1, wherein the speech recognition means is a means for converting the speech data into text data, and the generation means is a means for generating a story using a generation AI model based on the text data and the emotion information.

[1581] "Application example 2 when combining with an emotional engine"

[1582] (Claim 1)

[1583] Recording means and

[1584] Voice recognition means and

[1585] Means of recognizing emotions,

[1586] means of generation,

[1587] Illustration generation method,

[1588] Layout methods,

[1589] Methods for writing,

[1590] Text-to-speech method,

[1591] Data transmission means,

[1592] A system including a speech synthesis mechanism.

[1593] (Claim 2)

[1594] The system according to claim 1, wherein the recording means is a means for recording the user's voice and generating audio data, and the data transmission means transmits the audio data to a server.

[1595] (Claim 3)

[1596] The system according to claim 1, wherein the speech recognition means converts the speech data into text data, and the emotion recognition means further analyzes and identifies the user's emotions from the speech data. [Explanation of Symbols]

[1597] 10, 210, 310, 410 Data Processing Systems 12 Data Processing Devices 14 Smart Devices 214 Smart Glasses 314 Headset-type terminal 414 Robots< / url:> < / url:> < / url:> < / url:>

Claims

[Claim 1] A recording means for recording the user's voice and generating audio data, A speech recognition means for converting the aforementioned speech data into text data, A generation means that generates a story from text data converted by a speech recognition means, An illustration generation means that generates an appropriate illustration based on the content of the generated story, A layout method that combines generated text data and illustrations to complete the layout of a picture book, A means of exporting data from a completed picture book to save it as paper or convert it into a printable format, A system that includes a reading device that reads aloud the text of the generated picture book.

Images