System

Abstract

A system is provided.SOLUTION: The system includes a user authentication means, a character voice selection means, a voice input means, a voice data transmission means, a voice recognition means, a conversation generation means based on text data, a means for converting the generated conversation contents into character voices, and a means for reproducing the converted voice data.SELECTED DRAWING: Figure 1

Description

[Technical Field]

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

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

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

[0004] Today, there is a demand for interactive systems to support children's learning and growth at home and at school. However, conventional systems do not adequately function as a substitute for parents or teachers, making it difficult for children to maintain their interest. Furthermore, there are no systems that allow children to learn while having fun by using character voice responses. The purpose of this invention is to solve the above problems and provide an interactive learning support system that can maintain children's interest. [Means for solving the problem]

[0005] The present invention provides a system including a user authentication means, a character voice selection means, a voice input means, a voice data transmission means, a voice recognition means, a conversation generation means based on text data, a means for converting the generated conversation content into a character voice, and a means for playing the converted voice data. This system allows users to select their favorite character voice after logging in and learn or acquire information through dialogue with that character. Furthermore, by combining voice recognition technology and character voice generation technology, it is possible to provide users with natural and enjoyable responses.

[0006] "User authentication means" means a means for verifying and authenticating the identity of a user when accessing a system.

[0007] The "character voice selection means" is a means for the user to select the voice of the character of his / her choice.

[0008] "Audio input means" refers to a means for inputting a user's voice into the system, and typically includes a microphone.

[0009] The "voice data transmission means" is a means for transmitting the user's voice data to the server.

[0010] The "voice recognition means" is a means for converting voice data into text data.

[0011] The "means for generating a conversation based on text data" is a means for generating appropriate conversation content based on the converted text data.

[0012] The "means for converting the generated conversation content into character voice" refers to a means for converting the generated text conversation content into voice data that can be played in the voice of a selected character.

[0013] The "means for playing back converted voice data" refers to a means for playing back to the user voice data that has been converted into a character voice. [Brief explanation of the drawings]

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

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

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

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

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

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

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

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

[0022] [First embodiment]

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

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

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

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

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

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

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

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

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

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

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

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

[0035] This invention is a system including a user authentication means, a character voice selection means, a voice input means, a voice data transmission means, a voice recognition means, a conversation generation means based on text data, a means for converting the generated conversation content into a character voice, and a means for playing back the converted voice data. This system enables users to learn and acquire information through conversations with their favorite characters.

[0036] 1. System startup and user authentication

[0037] The server handles system startup, loading required resources and establishing database connections.

[0038] The terminal displays a login screen to the user, who then enters their login ID and password.

[0039] The terminal sends the entered information to the server. The server references the database and performs user authentication. If authentication is successful, a session is created and a message indicating authentication success is sent to the terminal.

[0040] The device displays a successful authentication screen to the user.

[0041] 2. Character voice selection

[0042] The device displays a character voice selection menu to the user.

[0043] The user selects the desired character, and the device sends the selected character information to the server.

[0044] The server retrieves the character voice data, loads the necessary voice files, and notifies the device when the loading is complete.

[0045] 3. Speech Recognition and Speech Generation

[0046] The device activates the microphone and waits for voice input from the user.

[0047] The user speaks into the device (e.g., "What's my homework for today?").

[0048] The device records the voice input and sends it to the server, which uses speech recognition technology to convert the voice into text data (e.g., "What is today's homework?").

[0049] The server passes the converted text data to a conversation generation system, which generates an appropriate response (e.g., "There are three math problems today. The first one is...").

[0050] 4. Character voice response

[0051] The server converts the generated conversation content into voice using the character's voice data.

[0052] The server sends the audio data to the terminal.

[0053] The device plays the transmitted audio data, allowing the character's voice to respond to the user (e.g., "Today, there are three math problems. The first one is...").

[0054] Specific examples

[0055] For example, when User A, a third-grade elementary school student, uses this system, the process will be as follows:

[0056] 1. Mr. A logs in to the system. He enters his ID and password to verify his identity and is authenticated.

[0057] 2. After logging in, Mr. A selects "Character X" on the character selection screen.

[0058] 3. Mr. A speaks to the device, saying, "Please tell me today's homework." The device records the voice and sends it to the server.

[0059] 4. The server performs speech recognition, converts it into text data, and generates a conversation. The generated content is then converted into voice data in the voice of Character X and sent to the device.

[0060] 5. The device will play "Today we have three math problems. The first one is..." in the voice of Character X.

[0061] In this way, the system can convey information in an enjoyable and effective way and support learning through interaction between the user and the selected character.

[0062] The processing flow will be explained below.

[0063] Step 1:

[0064] The server handles system startup, loading required resources and establishing database connections.

[0065] Step 2:

[0066] The device presents the user with a login screen.

[0067] Step 3:

[0068] The user enters their login ID and password. The device sends the entered information to the server.

[0069] Step 4:

[0070] The server refers to the database and performs user authentication. If authentication is successful, it creates a session and sends a message to the terminal indicating that authentication was successful.

[0071] Step 5:

[0072] The device displays a successful authentication screen to the user.

[0073] Step 6:

[0074] The device displays a character voice selection menu to the user.

[0075] Step 7:

[0076] The user selects the desired character, and the device sends the selected character information to the server.

[0077] Step 8:

[0078] The server retrieves the character voice data, loads the necessary voice files, and notifies the device when the loading is complete.

[0079] Step 9:

[0080] The device activates the microphone and waits for voice input from the user.

[0081] Step 10:

[0082] The user speaks into the device (for example, "What's my homework for today?") and the device records the voice input.

[0083] Step 11:

[0084] The device sends the recorded audio data to the server.

[0085] Step 12:

[0086] The server uses voice recognition technology to convert the transmitted voice data into text data.

[0087] Step 13:

[0088] The server passes the converted text data to a conversation generation system, which generates an appropriate response (e.g., "There are three math problems today. The first one is...").

[0089] Step 14:

[0090] The server converts the generated conversation content into voice using the character's voice data.

[0091] Step 15:

[0092] The server transmits the generated voice data to the terminal.

[0093] Step 16:

[0094] The device plays the transmitted audio data, and responds to the user in a character's voice (e.g., "Today you have three math problems. The first one is...").

[0095] Example 1

[0096] Next, a description will be given of Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the smart device 14 will be referred to as a "terminal."

[0097] In modern educational systems, interactive and personalized dialogue systems are necessary for users to learn in an enjoyable and effective manner. However, conventional systems have limited the user experience due to limitations in speech recognition and conversation generation technology. There is a need for a system that can provide a more engaging learning experience by responding with the voice of a character selected by the user.

[0098] The specific processing by the specific processing unit 290 of the data processing device 12 in the first embodiment is realized by the following means.

[0099] In this invention, the server includes means for loading necessary resources and establishing a database connection at system startup, means for generating a session and sending a message of successful authentication to the terminal if authentication is successful, means for the terminal to acquire voice data of a character corresponding to the server and load it, and means for generating conversation content for the generative AI model using prompt sentences. This allows the user to learn and acquire information through dialogue with the selected character, realizing a more interactive and engaging learning experience.

[0100] "User authentication means" means a means for verifying a user's identity when accessing a system.

[0101] The "character voice selection means" is a means for allowing the user to select the voice of the character they desire.

[0102] "Voice input means" refers to a means by which a user inputs voice into the system.

[0103] The "voice data transmission means" is a means for transmitting voice data input by the user to the server.

[0104] The "voice recognition means" is a means for analyzing input voice data and converting it into text data.

[0105] The "means for generating conversation based on text data" is a means for generating appropriate conversation content based on text data generated by speech recognition.

[0106] The "means for converting the generated conversation content into a character's voice" refers to a means for converting the generated text-based conversation content into the voice of a character selected by the user.

[0107] The "means for playing back converted voice data" refers to a means for playing back to the user voice data that has been converted into a character voice.

[0108] The "means for loading required resources and establishing a database connection at system startup" refers to a means for loading required software resources into memory at system startup and establishing a connection with a database.

[0109] The "means for generating a session when authentication is successful and transmitting a message of authentication success to the terminal" refers to a means for generating a session when user authentication is successful and notifying the terminal of that information.

[0110] "Means for the terminal to obtain from the server and load voice data of a character that corresponds to the terminal" refers to means for obtaining from the server voice data of a character selected by the user and loading it into the terminal.

[0111] "Means for generating conversational content for a generative AI model using a prompt sentence" means means for using a generative AI model with a specified prompt sentence as input to generate appropriate conversational content.

[0112] This invention is an interactive system for users to learn and acquire information through interaction with characters of their choice. The system includes the following major hardware and software components:

[0113] First, the system is started by the server, which loads the necessary resources and establishes a database connection. Specifically, it loads the system libraries and configuration files into memory and connects to the SQL database. At this stage, all the necessary initial configuration and preparation is complete.

[0114] The device then presents the user with a login screen, which contains text fields and buttons for the user to enter their login ID and password, and the login information entered by the user is sent from the device to the server in encrypted form.

[0115] The server compares the received login information with the database and authenticates the user. If authentication is successful, the server generates a valid session ID and sends a message of successful authentication to the terminal. The terminal displays the message "Login successful" to the user.

[0116] After user authentication is complete, the device displays a character voice selection menu to the user. This screen displays thumbnail images and names of multiple characters, and the user selects the desired character. The selection information is sent from the device to the server. The server obtains the voice data for the specified character and loads the voice file. After loading is complete, the server notifies the device of this information. The device then displays a message to the user that the character voice is ready.

[0117] Next, the device waits for the user's voice input. The user speaks into the device. For example, "Tell me what my homework is today." This voice input is recorded by the device and sent to the server. The server receives the voice data and converts it into text data using voice recognition technology (e.g., Google® Speech-to-Text API).

[0118] The server then inputs the generated text data as a prompt into the generative AI model to generate appropriate conversational content. For example, in response to the prompt "Tell me about today's homework," the generative AI model generates a response such as "There are three math problems today. The first one is..." This response is then converted into speech using the voice data of the selected character.

[0119] Finally, the server sends the audio data to the device, which then plays it back, allowing the user to hear a response in the character's voice, such as "Today, we have three math problems. The first one is..."

[0120] Prompt Sentence Examples

[0121] Below are some examples of prompt sentences that may be used in this invention:

[0122] 1. "Tell me about today's homework."

[0123] 2. "Explain the ecosystem."

[0124] 3. "Tell me about the different types of ecosystems within ecosystems."

[0125] 4. "What is needed to maintain an ecosystem?"

[0126] 5. "What is the importance of biodiversity?"

[0127] This allows users to learn and acquire information in a fun and effective way through interactions with the characters they select.

[0128] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0129] Step 1:

[0130] System startup

[0131] Input: System startup instructions

[0132] What happens next: The server boots the system, loads the necessary resources, and establishes a database connection. Specifically, it loads libraries and configuration files into memory and connects to the SQL database.

[0133] Output: Initialization is complete and the system is ready for user interaction.

[0134] Step 2:

[0135] Displaying the login screen

[0136] Input: After the system starts, the screen prompts the user to begin using the system.

[0137] Specific behavior: The device displays a login screen to the user. The screen displays a text field and a login button. The user enters their login ID and password.

[0138] Output: Login information (ID and password)

[0139] Step 3:

[0140] Sending authentication information

[0141] Input: The login information entered by the user

[0142] Specific operation: The device sends the entered login information to the server. The login information is encrypted before being sent.

[0143] Output: Login information sent to the server

[0144] Step 4:

[0145] User authentication

[0146] Input: Login information received by the server

[0147] Specific operation: The server refers to the database and verifies the entered login information with the registration information. If authentication is successful, the server creates a session and sends a message to the terminal indicating successful authentication.

[0148] Output: Session ID and authentication success message upon successful authentication

[0149] Step 5:

[0150] Viewing authentication results

[0151] Input: Authentication success message sent by the server

[0152] Specific operation: The device displays a screen to the user confirming successful authentication, such as a message saying "Login successful."

[0153] Output: A confirmation message of successful authentication

[0154] Step 6:

[0155] Display the character voice selection menu

[0156] Input: User actions after login

[0157] Specific behavior: The device will display a character voice selection menu to the user, showing thumbnail images and names of multiple characters.

[0158] Output: Display the character selection menu

[0159] Step 7:

[0160] Character Selection

[0161] Input: User selects desired character

[0162] Specific operation: The user selects the desired character. For example, clicks "Character X." The selected character information is sent from the device to the server.

[0163] Output: Selected character information

[0164] Step 8:

[0165] Acquiring and loading character voice data

[0166] Input: Character information sent to the server

[0167] Specific operation: The server retrieves the voice data of the specified character and loads the necessary voice file. For example, it loads the voice file for character X from storage.

[0168] Output: Voice data of the loaded character

[0169] Step 9:

[0170] Viewing notifications

[0171] Input: Notification information from the server to the device

[0172] Specific operation: The server notifies the device that the audio data has been loaded, and the device displays a message to the user that the device is ready.

[0173] Output: Audio data ready message

[0174] Step 10:

[0175] Microphone activation

[0176] Input: User operation after character voice data is ready

[0177] Specific behavior: The device activates the microphone and waits for voice input from the user. For example, the microphone icon becomes active.

[0178] Output: Audio input standby

[0179] Step 11:

[0180] User voice input

[0181] Input: The user speaks into the device

[0182] Specific actions: The user speaks to the device, for example, "Tell me what my homework is today." This is recorded by the device.

[0183] Output: Recorded audio data

[0184] Step 12:

[0185] Recording and sending audio

[0186] Input: User voice input

[0187] Specific operation: The device sends the recorded audio data to the server. The data is in audio file format (e.g., .wav).

[0188] Output: Audio data sent to the server

[0189] Step 13:

[0190] Voice Recognition

[0191] Input: Audio data received by the server

[0192] Specific operation: The server uses speech recognition technology to convert the speech into text data. Specifically, it uses a speech recognition API (e.g., Google Speech-to-Text API) to generate the text data "Please tell me today's homework."

[0193] Output: Generated text data

[0194] Step 14:

[0195] Conversation Generation

[0196] Input: Text data generated by speech recognition

[0197] Specific operation: The server inputs the generated text data as a prompt into the generative AI model, and generates appropriate conversation content. For example, in response to the prompt "Tell me about today's homework," the model generates a response such as "There are three math problems today. The first one is..."

[0198] Output: Generated conversation

[0199] Step 15:

[0200] Voice conversion of conversation content

[0201] Input: Generated conversation

[0202] Specific operation: The server converts the generated dialogue into audio using the character's voice data. For example, it uses a voice synthesizer to generate an audio file that reads the dialogue in the voice of Character X.

[0203] Output: Generated audio data

[0204] Step 16:

[0205] Sending audio data

[0206] Input: Generated audio data

[0207] Specific operation: The server sends audio data to the device in a common audio file format (e.g., .mp3).

[0208] Output: Audio data sent to the device

[0209] Step 17:

[0210] Playing audio data

[0211] Input: Audio data sent to the device

[0212] Specific operation: The device plays the received voice data. For example, a play button appears and Character X's voice responds to the user, saying, "Today, we have three math problems. The first one is..."

[0213] Output: Played back voice response

[0214] (Application example 1)

[0215] Next, a description will be given of Application Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the smart device 14 will be referred to as a "terminal."

[0216] Conventional learning support systems have had the problem of making it difficult for users to maintain their interest while studying. Furthermore, even in dialogue-based systems, there are limitations to the interactive dialogue that uses character voices, making it difficult to maximize learning effectiveness.

[0217] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 1 is realized by the following means.

[0218] In this invention, the server includes a user authentication means, a character voice selection means, a voice input means, a voice data transmission means, a voice recognition means, a conversation generation means based on text data, a means for converting the generated conversation content into a character voice, a means for playing the converted voice data, and an interactive learning support means for effectively learning the learning content, thereby enabling the user to progress with their learning in an enjoyable and effective manner through interactive dialogue with the selected character.

[0219] "User authentication means" refers to the means by which a user enters authentication information such as a login ID and password to verify their identity in order to be granted access to the system.

[0220] The "character voice selection means" is a means for allowing the user to select the voice of the character they desire.

[0221] "Audio input means" refers to a means for inputting a user's voice, and generally includes a microphone.

[0222] The "voice data transmission means" is a means for transmitting the user's voice data to another device or server.

[0223] The "voice recognition means" is a means for converting input voice data into text data.

[0224] The "conversation generation means based on text data" is a means for generating an appropriate response based on the text data generated by the speech recognition means.

[0225] The "means for converting the generated conversation content into character voice" is a means for converting the generated text-format conversation content into voice data using the voice data of the selected character.

[0226] The "means for reproducing the converted voice data" refers to a means for reproducing the generated voice data so that the user can hear it.

[0227] An "interactive learning support means for effectively learning learning content" is a means for effectively supporting learning by recognizing the user's voice input, generating an appropriate response, and playing back the voice data in a character's voice.

[0228] The present invention provides an interactive learning support system that supports learning by allowing a user to have an interactive conversation with a character selected by the user. The system includes the following series of means.

[0229] First, the server provides a means for user authentication. To access the system, a user must enter their ID and password for authentication. If authentication is successful, the system provides a means for selecting a character voice, allowing the user to select which character's voice they wish to use. When the user selects a character, the information is sent to the server, and the required character voice data is loaded.

[0230] Next, the terminal uses a microphone as a voice input means and waits for voice input from the user. When the user speaks, the voice data is sent to the server using a voice data sending means. The server uses a voice recognition means to convert the voice data into text data. The converted text data is passed to a conversation generation means, which generates an appropriate response. The response content is converted into a character's voice and sent from the server to the terminal. Finally, the terminal plays back the converted voice data.

[0231] Through this process, users can enjoy interacting with the character they have selected. The server also provides interactive learning support to help users effectively learn the content, and can provide appropriate learning support based on the content of the user's speech.

[0232] As a specific example of an embodiment, a case will be described in which a user says, "Tell me about today's homework." The device records this voice and sends it to the server. The server performs speech recognition and converts it into text data, "Tell me about today's homework." Based on this text data, the server generates an appropriate response (e.g., "There are three math problems today. The first one is..."). This response is converted into audio data in the character's voice and is finally played on the device.

[0233] An example of a prompt is:

[0234] User: What's today's homework?

[0235] System: We have three math problems for you today. The first one is...

[0236] As described above, this system can provide a fun and interactive learning environment through dialogue with characters selected by the user.

[0237] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0238] Step 1:

[0239] The server is responsible for starting the system, loading the necessary resources, and establishing database connections, which allow for user authentication and character voice data management.

[0240] Step 2:

[0241] The terminal displays a login screen to the user. The user enters a login ID and password. The terminal sends the entered authentication information to the server. The input is the user's ID and password, and the output is the authentication result. The server refers to the database to authenticate the user, and creates a session if authentication is successful. It sends a message of successful authentication to the terminal, and the terminal displays a screen of successful authentication to the user.

[0242] Step 3:

[0243] The terminal displays a character voice selection menu to the user. The user selects the desired character. The terminal sends the selected character information to the server. The input is the user's character selection, and the output is a notification that the character voice data has been loaded. The server obtains the character voice data and loads the necessary voice files. Once loading is complete, the terminal is notified.

[0244] Step 4:

[0245] The terminal activates a microphone, which is a voice input means, and waits for voice input from the user. The user speaks into the terminal. The input is the user's voice, and the output is recorded voice data. The terminal records this voice and transmits it to the server using a voice data transmission means.

[0246] Step 5:

[0247] The server converts the received voice data into text data using a voice recognition means. The input is voice data and the output is text data. The voice recognition means uses voice recognition technology to convert, for example, the voice saying "Please tell me today's homework" into the text "Please tell me today's homework."

[0248] Step 6:

[0249] The server passes the converted text data to the conversation generation means, which generates an appropriate response. The input is text data, and the output is response text. The conversation generation means utilizes a generative AI model to generate a natural language response based on the text data. For example, in response to the question, "What's today's homework for me?", the response generated is, "There are three math problems today. The first one is..."

[0250] Step 7:

[0251] The server converts the generated response text into character voice. The input is the response text and the output is voice data. The server uses the voice data of the selected character to convert the response text into voice data.

[0252] Step 8:

[0253] The server sends the converted voice data to the terminal. The terminal plays back the sent voice data. The input is the voice data, and the output is a voice response to the user. The terminal plays back in the character's voice, "Today we have three math problems. The first one is...", and conveys the response to the user.

[0254] These steps allow users to progress through learning interactively through dialogue with the character of their choice.

[0255] Furthermore, an emotion engine that estimates the user's emotion may be combined. That is, the identification processing unit 290 may estimate the user's emotion using the emotion identification model 59 and perform identification processing using the user's emotion.

[0256] This invention is a system including a user authentication means, a character voice selection means, a voice input means, a voice data transmission means, a voice recognition means, a conversation generation means based on text data, a means for converting the generated conversation content into a character voice, a means for playing the converted voice data, and an emotion engine for recognizing the user's emotions. This system not only enables a user to learn or acquire information through conversation with a favorite character, but also provides appropriate responses according to the user's emotional state.

[0257] 1. System startup and user authentication

[0258] The server handles system startup, loading required resources and establishing database connections.

[0259] The terminal displays a login screen to the user, who then enters their login ID and password.

[0260] The terminal sends the entered information to the server. The server references the database and performs user authentication. If authentication is successful, a session is created and a message indicating successful authentication is sent to the terminal.

[0261] The device displays a successful authentication screen to the user.

[0262] 2. Character voice selection

[0263] The device displays a character voice selection menu to the user.

[0264] The user selects the desired character, and the device sends the selected character information to the server.

[0265] The server retrieves the character voice data, loads the necessary voice files, and notifies the device when the loading is complete.

[0266] 3. Speech Recognition and Speech Generation

[0267] The device activates the microphone and waits for voice input from the user.

[0268] The user speaks into the device (for example, "What's my homework for today?") and the device records the voice input.

[0269] The device sends the recorded voice data to the server, which uses voice recognition technology to convert the voice into text data (e.g., "Please tell me what my homework is today").

[0270] The server passes the converted text data to a conversation generation system, which generates an appropriate response (e.g., "There are three math problems today. The first one is...").

[0271] 4. Emotion Recognition by Emotion Engine

[0272] The server sends the voice data to the emotion engine.

[0273] The emotion engine extracts the user's emotional state from the voice data, for example recognizing emotions such as "happy," "sad," or "angry" from the tone of voice and choice of words.

[0274] The emotion engine passes the extracted emotion data to the conversation generation system, which then adjusts the response based on the emotion data. For example, if the user appears sad, it generates an encouraging response.

[0275] 5. Character voice response

[0276] The server converts the generated conversation content into voice using the character's voice data.

[0277] The server transmits the generated voice data to the terminal.

[0278] The device plays back the transmitted voice data, which then responds to the user in the character's voice (e.g., "There are three math problems today. They're a little tough, but let's do our best together!").

[0279] Specific examples

[0280] For example, when User A, a third-grade elementary school student, uses this system, the process will be as follows:

[0281] 1. Mr. A logs in to the system. He enters his ID and password to verify his identity and is authenticated.

[0282] 2. After logging in, Mr. A selects "Character X" on the character selection screen.

[0283] 3. Mr. A speaks to the device, saying, "Please tell me today's homework." The device records the voice and sends it to the server.

[0284] 4. The server performs speech recognition, converts it into text data, and generates a conversation. The speech data is then sent to the emotion engine, which extracts emotion data. For example, if Mr. A sounds happy, the conversation generation system generates a positive response such as, "That's great! Let's try it together."

[0285] 5. The server converts the generated content into audio data in the voice of Character X and sends it to the device.

[0286] 6. The device will play back in Character X's voice, "Today we have three math problems. They're a little difficult, but let's do our best together!"

[0287] In this way, the system can communicate information in an enjoyable and effective way through interactions between the user and the selected character, assisting learning and providing more personalized responses through emotion recognition.

[0288] The processing flow will be explained below.

[0289] Step 1:

[0290] The server handles system startup, loading required resources and establishing database connections.

[0291] Step 2:

[0292] The device presents the user with a login screen.

[0293] Step 3:

[0294] The user enters their login ID and password. The device sends the entered information to the server.

[0295] Step 4:

[0296] The server refers to the database and performs user authentication. If authentication is successful, it creates a session and sends a message to the terminal indicating that authentication was successful.

[0297] Step 5:

[0298] The device displays a successful authentication screen to the user.

[0299] Step 6:

[0300] The device displays a character voice selection menu to the user.

[0301] Step 7:

[0302] The user selects the desired character, and the device sends the selected character information to the server.

[0303] Step 8:

[0304] The server retrieves the character voice data, loads the necessary voice files, and notifies the device when the loading is complete.

[0305] Step 9:

[0306] The device activates the microphone and waits for voice input from the user.

[0307] Step 10:

[0308] The user speaks into the device (for example, "What's my homework for today?") and the device records the voice input.

[0309] Step 11:

[0310] The device sends the recorded audio data to the server.

[0311] Step 12:

[0312] The server uses voice recognition technology to convert the transmitted voice data into text data.

[0313] Step 13:

[0314] The server sends the text data to the emotion engine.

[0315] Step 14:

[0316] An emotion engine built into the server extracts the user's emotions from the voice data, for example, determining emotions from the tone and speed of the voice.

[0317] Step 15:

[0318] The emotion data extracted by the emotion engine is sent to the conversation generation system.

[0319] Step 16:

[0320] The server generates appropriate conversational content based on the emotion data. For example, if the user looks sad, it generates encouraging content (e.g., "Cheer up, let's do our best together!").

[0321] Step 17:

[0322] The server converts the generated conversation content into voice using the character's voice data.

[0323] Step 18:

[0324] The server transmits the generated voice data to the terminal.

[0325] Step 19:

[0326] The device plays back the transmitted audio data, and responds to the user in the character's voice (e.g., "There are three math problems today. They're a little tough, but let's do our best together!").

[0327] Example 2

[0328] Next, a description will be given of Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the smart device 14 will be referred to as a "terminal."

[0329] Conventional voice dialogue systems have difficulty in properly recognizing the user's emotional state and generating responses that correspond to that emotion. Furthermore, they can only provide fixed responses, which limits the user experience and reduces the effectiveness of learning support and information acquisition. Furthermore, the dialogue provided by the character voices is weak, which fails to fully stimulate the user's interest and motivation.

[0330] The identification process by the identification processing unit 290 of the data processing device 12 in the second embodiment is realized by the following means. In this invention, the server includes a user authentication means, a character voice selection means, a voice input means, a voice data transmission means, a voice recognition means, a conversation generation means based on text data, a means for converting the generated conversation content into a character voice, a means for playing the converted voice data, and an emotion engine for recognizing the user's emotions. This enables an appropriate response according to the user's emotional state, and provides individually personalized dialogue. Furthermore, by responding with the voice of the selected character, the user's interest and motivation can be enhanced, improving the effectiveness of learning support and information acquisition.

[0331] "User authentication means" is a function that identifies and authenticates individuals by having the user enter an ID and password.

[0332] The "character voice selection means" is a function that allows the user to select the voice of the character they want and transmit that information to the system.

[0333] "Voice input means" is a function for detecting and recording the voice spoken by the user.

[0334] The "audio data transmission means" is a function for transmitting recorded audio data to the server.

[0335] The "voice recognition means" is a function that converts transmitted voice data into text data.

[0336] The "conversation generation means based on text data" is a function that generates an appropriate response based on the text data generated by the voice recognition means.

[0337] The "means for converting the generated conversation content into a character's voice" is a function for converting the generated conversation content into a voice using the voice data of the selected character.

[0338] The "means for reproducing converted audio data" is a function for reproducing data converted into audio.

[0339] The "emotion engine" is a function that extracts the user's emotional state from their voice data and analyzes that data.

[0340] This invention is a system including a user authentication means, a character voice selection means, a voice input means, a voice data transmission means, a voice recognition means, a conversation generation means based on text data, a means for converting the generated conversation content into a character voice, a means for playing the converted voice data, and an emotion engine. This system allows a user to learn and acquire information through conversation with a favorite character, and further, is capable of providing appropriate responses according to the user's emotional state.

[0341] System configuration and operation

[0342] The system consists of a server and a terminal. The server is responsible for key processes such as user authentication, voice recognition, conversation generation, emotion recognition, and voice conversion. The terminal acts as an interface with the user, providing functions such as voice input, voice playback, and character selection.

[0343] Hardware and software used

[0344] Server Hardware: High performance machine (e.g. Intel Xeon processor, 64GB RAM)

[0345] Server Software:

[0346] OS: Linux (registered trademark)

[0347] Web framework: Django

[0348] Database: PostgreSQL

[0349] Speech Recognition API: Google Cloud Speech-to-Text

[0350] Emotion recognition engine: IBM Watson(R) Tone Analyzer

[0351] Speech synthesis engine: Amazon Polly

[0352] Device hardware: PC or tablet, microphone, speakers

[0353] Terminal software:

[0354] Browser: GOOGLE CHROME (registered trademark), Mozilla Firefox

[0355] JavaScript (registered trademark) library: React.js

[0356] Processing flow

[0357] When the system starts, the server loads the necessary resources and establishes a database connection. The terminal displays a login screen for the user, and the user enters their ID and password. The server refers to the database to authenticate the user, and if authentication is successful, it creates a session and sends a success message to the terminal.

[0358] The user selects the desired character from the character voice selection menu and sends this information to the server, which retrieves the character voice data and loads the voice file.

[0359] For speech recognition and conversation generation, the device activates the microphone and waits for voice input from the user. When the user speaks, the device records the audio and sends it to a server. The server uses the Google Cloud Speech-to-Text API to convert the audio into text data, which is then fed into a generative AI model (e.g., GPT-3 (registered trademark)) to generate an appropriate response.

[0360] The emotion engine extracts the user's emotional state from their voice and passes the extracted emotion data to the conversation generation system, which then tailors the responses to the user's current emotions. For example, if the user sounds sad, an encouraging response will be generated.

[0361] Finally, the server converts the generated conversation content into voice using the character voice data and transmits the voice data to the terminal, which then plays the voice data and responds to the user in the character's voice.

[0362] Specific examples

[0363] For example, if a third-grader asks the device, "What's my homework for today?", the system will act as follows:

[0364] 1. The device records the audio and sends it to the server.

[0365] 2. The server performs speech recognition and converts it into text data.

[0366] 3. The conversation generation system generates a response: "There are three math problems today."

[0367] 4. The emotion engine analyzes the user's emotions, and if the user appears to be having fun, it complements the response by saying, "Try your best to solve it."

[0368] 5. The server converts this response into voice using the character's voice data and sends it to the device.

[0369] 6. The device will play a character voice saying, "Today there are three math problems, let's do our best together!"

[0370] Prompt Sentence Examples

[0371] "Tell me about today's homework."

[0372] "How are you feeling right now?"

[0373] "Tell me the next step."

[0374] In this way, the system can provide personalized responses that also take into account the user's emotional state, thereby improving the effectiveness of learning support and information acquisition.

[0375] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0376] Step 1:

[0377] The server starts the system, which includes loading the necessary resources and establishing a database connection. The server runs Linux and uses the Django framework to manage web applications. When the server starts, it connects to the database (PostgreSQL) and prepares the necessary tables and data. The input is the command to start the server, and the output is a startup completion message and the establishment of a database connection.

[0378] Step 2:

[0379] The device displays a login screen. The user enters their ID and password and clicks the "Login" button. The input is the user's ID and password, and the output is an HTTP request containing this information. The device's browser (Google Chrome or Mozilla Firefox) accepts this operation.

[0380] Step 3:

[0381] The terminal sends the entered login information to the server. The server compares the received ID and password with the database and performs authentication. The server verifies the user information using Django's authentication function. The input is the user ID and password, and the output is the authentication result (success or failure).

[0382] Step 4:

[0383] If the server is successful in authentication, it creates a session and sends a success message to the terminal. It uses Django's session management functionality to generate a session ID for the user. The input is the success message, and the output is the new session ID.

[0384] Step 5:

[0385] The device displays an authentication success screen to the user. JavaScript is used to dynamically update the screen and show the user a successful authentication message. The input is the successful authentication message sent by the server, and the output is the successful authentication screen visible to the user.

[0386] Step 6:

[0387] The device displays a character voice selection menu. The user selects the desired character. The input is the user's selection, and the output is an HTTP request containing the selected character information. The selection menu is displayed using React.js.

[0388] Step 7:

[0389] The device sends the selected character information to the server. The server retrieves the character's voice data and loads the voice file. Django processes the HTTP request and loads the voice file for the selected character from the database. The input is the selected character information, and the output is the loaded voice file.

[0390] Step 8:

[0391] The device activates the microphone and waits for the user's voice input. The microphone is controlled using JavaScript's Audio API. The input triggers the microphone activation, and the output is in a voice-waiting state. The user speaks, saying something like, "Tell me about today's homework."

[0392] Step 9:

[0393] The device records what the user says and sends the audio data to the server. The recorded data is saved in WAV format and sent to the server. The input is the user's voice data, and the output is a WAV audio file.

[0394] Step 10:

[0395] The server uses speech recognition technology to convert the recorded voice data into text data. The Google Cloud Speech-to-Text API is used to analyze the voice data and convert it into text. The input is a WAV format audio file, and the output is text data.

[0396] Step 11:

[0397] The server passes the text data to a conversation generation system, which uses a generative AI model (e.g., GPT-3) to generate an appropriate response. The input is the converted text data, and the output is the generated response text.

[0398] Step 12:

[0399] The server sends the voice data to the emotion engine to extract the user's emotional state. The emotion data is generated using IBM Watson's Tone Analyzer. The input is voice data, and the output is emotion data.

[0400] Step 13:

[0401] The server passes the extracted emotion data to the conversation generation system, which then checks and adjusts the response. The response is adjusted based on the emotion data. The input is emotion data, and the output is the adjusted response text.

[0402] Step 14:

[0403] The server converts the tailored response into speech using the voice data of the selected character. It uses Amazon Polly for speech synthesis. The input is the response text and the output is an audio file.

[0404] Step 15:

[0405] The server sends the generated audio file to the terminal. The input is the generated audio file, and the output is an HTTP response with the audio file.

[0406] Step 16:

[0407] Plays an audio file received by the device. It uses the JavaScript Audio object to play the audio and responds to the user in a character's voice. The input is the generated audio file, and the output is the audio that is played.

[0408] By dividing the process flow into detailed sections like this, it becomes clear how each step works, and what data is input and output, making it easier to understand specific embodiments of the invention.

[0409] (Application example 2)

[0410] Next, a description will be given of Application Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the smart device 14 will be referred to as a "terminal."

[0411] Conventional voice dialogue systems often generate uniform responses without considering the user's emotional state. This makes it difficult to provide personalized dialogue that is sensitive to the user's emotions, which can increase user stress, especially in the workplace. Another issue is insufficient integration with smart devices, making various operations cumbersome.

[0412] The specific processing by the specific processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means. In this invention, the server includes a user authentication means, a character voice selection means, a voice input means, a voice data transmission means, a voice recognition means, a conversation generation means based on text data, a means for converting the generated conversation content into a character voice, a means for playing the converted voice data, an emotion recognition means for recognizing the emotional state of the user, a means for adjusting the conversation content based on the recognized emotional state, and a display means of the smart device. This enables personalized responses according to the user's emotions, improves the quality of conversations at the workplace, and reduces user stress.

[0413] "User authentication means" is a function that verifies the ID and password of users accessing the system and confirms the legitimacy of the users.

[0414] The "character voice selection means" is a function that allows the user to select the voice of the character to be used in the dialogue.

[0415] "Voice input means" refers to a function for receiving voice from the user, and typically includes a microphone.

[0416] The "voice data transmission means" is a function for transmitting collected voice data to a server.

[0417] The "voice recognition means" is a function that analyzes transmitted voice data and converts the content into text data.

[0418] The "conversation generation means based on text data" is a function that generates appropriate response content based on text data that has been speech-recognized.

[0419] The "means for converting the generated conversation content into character voice" is a function for converting the conversation content generated in text into voice using voice data of a pre-selected character.

[0420] "Means for playing converted voice data" is a function for playing data converted into a character's voice so that the user can hear it.

[0421] The "emotion recognition means for recognizing the user's emotional state" is a function for extracting the user's emotional state from the user's voice data or other input.

[0422] The "means for adjusting the content of the conversation based on the recognized emotional state" is a function for adjusting the content of the generated response based on the user's emotion detected by the emotion recognition means.

[0423] The "display means of the smart device" refers to a device for displaying information and operation screens of the interactive system, and typically includes smart glasses, tablets, etc.

[0424] System Overview

[0425] This invention is a system that enables users to communicate through character voices by wearing a smart device and operating it with voice. The system mainly uses a server, a smart device (such as smart glasses or a tablet), a microphone for user input, a speaker for voice playback, and software for emotion recognition.

[0426] Program Structure Overview

[0427] The system consists of a program with the following main functions:

[0428] 1. User Authentication

[0429] 2. Character voice selection

[0430] 3. Speech Recognition and Speech Generation

[0431] 4. Emotion recognition

[0432] 5. Voice Response

[0433] Processing flow and technologies used

[0434] 1. User Authentication

[0435] The server receives the user ID and password sent from the smart device and authenticates the user by referencing the database, thereby preventing unauthorized access and providing services to the appropriate user.

[0436] Required Hardware / Software:

[0437] Database server (MySQL (registered trademark), etc.)

[0438] Authentication Server

[0439] Smart Devices

[0440] 2. Character voice selection

[0441] The smart device displays multiple character voice options to the user, the user selects the desired character, and the selection data is sent to the server, which loads the voice data for the selected character and notifies the smart device.

[0442] Required Hardware / Software:

[0443] Smart devices (smart glasses, tablets, etc.)

[0444] server

[0445] 3. Speech Recognition and Speech Generation

[0446] When a user speaks into a smart device, the microphone records the audio. The recording is sent to a server where it is converted into text using speech recognition technology (such as the Google Speech-to-Text API). This text is then passed to a generative AI model (such as GPT-3.5 Turbo) to generate an appropriate response.

[0447] Required Hardware / Software:

[0448] microphone

[0449] server

[0450] Speech Recognition API

[0451] Generative AI Models

[0452] 4. Emotion recognition

[0453] The converted text data is passed to emotion recognition software (such as DistilRoBERTa) to analyze the user's emotional state. The server then adjusts the generated response content based on the emotional data and selects an appropriate response.

[0454] Required Hardware / Software:

[0455] server

[0456] Emotion Recognition Model

[0457] 5. Voice Response

[0458] The adjusted response content is converted into voice using the character voice data and transmitted to the smart device, which responds to the user in the character's voice using a speaker.

[0459] Required Hardware / Software:

[0460] Smart device (with built-in speaker)

[0461] server

[0462] Specific examples

[0463] For example, suppose a factory worker wears smart glasses and asks, "What's the current status of the production line?" In this case, the system first performs speech recognition and passes the text data to the generative AI model. The generative AI model generates a response such as, "The current production line is running smoothly. The production rate is 80%." If the model then performs emotion recognition and determines that the user is satisfied, it will convey this in a positive tone. The system then converts this text into speech in a character's voice and conveys it to the user.

[0464] Prompt Sentence Examples

[0465] User is interested. Please tell me the current status of the production line.

[0466] In this way, the system can provide personalized responses according to the user's emotions, improving the user experience at the workplace.

[0467] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[0468] Step 1:

[0469] The user starts up the smart device and accesses the login screen. The user enters their login ID and password. The device sends this information to the server, which then refers to the database to authenticate the user. If authentication is successful, a message indicating successful authentication is sent to the device, and a screen indicating successful authentication is displayed to the user.

[0470] Input: Login ID, Password

[0471] Data processing / calculation: Verification of authentication data (database reference)

[0472] Output: Authentication success message

[0473] Step 2:

[0474] After the user logs in, the device displays a character voice selection menu. The user selects the desired character, and that information is sent from the device to the server. The server retrieves the voice data for the selected character and notifies the device when the required voice files have been loaded. The device then informs the user that it is ready to play.

[0475] Input: Character selection information

[0476] Data processing / calculation: Acquiring and loading audio data

[0477] Output: Playback ready notification

[0478] Step 3:

[0479] The user speaks into the device. The device's microphone records the voice and sends the voice data to the server. The server uses voice recognition technology to convert the voice data into text data. For example, a user's speech such as "Tell me about the current status of the production line" is converted into text data.

[0480] Input: Audio data

[0481] Data processing / calculation: Speech recognition (voice to text conversion)

[0482] Output: Text data

[0483] Step 4:

[0484] The server passes the converted text data to the emotion recognition means, which extracts the user's emotional state from the voice and text data. For example, if the user's voice sounds happy, it will be recognized as "positive."

[0485] Input: Text data, audio data

[0486] Data processing / calculation: Emotion recognition (emotion data extraction)

[0487] Output: Emotion data

[0488] Step 5:

[0489] The server generates a response using a conversation generation system based on the text data and emotional data. A generative AI model (such as GPT-3.5 Turbo) generates an appropriate response. For example, if the user's question is "What is the current status of the production line?" and the emotional state is "positive," the server generates a response such as "The current production line is going smoothly. The production rate is 80%."

[0490] Input: Text data, emotion data

[0491] Data processing / calculation: Response generation (generative AI model)

[0492] Output: The generated text response

[0493] Step 6:

[0494] The generated text response is converted into voice using the voice data of the selected character, and the server converts the text response into voice data and transmits it to the terminal.

[0495] Input: Generated text response, character voice data

[0496] Data processing / calculation: Text to speech conversion

[0497] Output: Audio data

[0498] Step 7:

[0499] The terminal plays the received audio data, and the user receives a response in the voice of the character they selected. For example, the character's voice may say, "The current production line is running smoothly. The production rate is 80%."

[0500] Input: Audio data

[0501] Data processing / calculation: Audio playback

[0502] Output: Playback of a response to the user

[0503] The specific processing unit 290 transmits the result of the specific processing to the smart device 14. In the smart device 14, the control unit 46A causes the output device 40 to output the result of the specific processing. The microphone 38B acquires audio indicating a user input regarding the result of the specific processing. The control unit 46A transmits audio data indicating the user input acquired by the microphone 38B to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the audio data.

[0504] The data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of the data generation model 58 is ChatGPT (registered trademark) (Internet search engine).<URL: https: / / openai.com / blog / chatgpt> ), Gemini (registered trademark) (Internet search <url: https: gemini.google.com ?hl="ja">) and other generation AIs. The data generation model 58 is obtained by performing deep learning on a neural network. A prompt including an instruction is input to the data generation model 58, and inference data such as voice data indicating voice, text data indicating text, and image data indicating an image is also input. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt, and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[0505] In the above embodiment, an example in which the specific process is performed by the data processing device 12 has been given, but the technology of the present disclosure is not limited to this, and the specific process may be performed by the smart device 14.

[0506] [Second embodiment]

[0507] FIG. 3 shows an example of the configuration of a data processing system 210 according to the second embodiment.

[0508] 3, the data processing system 210 includes the data processing device 12 and smart glasses 214. An example of the data processing device 12 is a server.

[0509] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 is an example of a "computer" according to the technology of the present disclosure. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, the RAM 30, and the storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0510] The smart glasses 214 include a computer 36, a microphone 238, a speaker 240, a camera 42, and a communication I / F 44. The computer 36 includes a processor 46, a RAM 48, and a storage 50. The processor 46, the RAM 48, and the storage 50 are connected to a bus 52. The microphone 238, the speaker 240, and the camera 42 are also connected to the bus 52.

[0511] The microphone 238 receives instructions and the like from the user 20 by receiving voice uttered by the user 20. The microphone 238 captures the voice uttered by the user 20, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio in accordance with instructions from the processor 46.

[0512] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an imaging element such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the surroundings of user 20 (for example, an imaging range defined by an angle of view equivalent to the field of vision of a typical healthy person).

[0513] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 are responsible for the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is carried out in a secure state.

[0514] Fig. 4 shows an example of the main functions of the data processing device 12 and the smart glasses 214. As shown in Fig. 4, in the data processing device 12, a specific process is performed by the processor 28. A specific process program 56 is stored in the storage 32.

[0515] The specific processing program 56 is an example of a "program" according to the technology of the present disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[0516] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[0517] In the smart glasses 214, the reception output process is performed by the processor 46. A reception output program 60 is stored in the storage 50. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output process is realized by the processor 46 operating as the control unit 46A in accordance with the reception output program 60 executed on the RAM 48.

[0518] Next, a description will be given of the identification process performed by the identification processing unit 290 of the data processing device 12. In the following description, the data processing device 12 will be referred to as the "server" and the smart glasses 214 will be referred to as the "terminal."

[0519] This invention is a system including a user authentication means, a character voice selection means, a voice input means, a voice data transmission means, a voice recognition means, a conversation generation means based on text data, a means for converting the generated conversation content into a character voice, and a means for playing back the converted voice data. This system enables users to learn and acquire information through conversations with their favorite characters.

[0520] 1. System startup and user authentication

[0521] The server handles system startup, loading required resources and establishing database connections.

[0522] The terminal displays a login screen to the user, who then enters their login ID and password.

[0523] The terminal sends the entered information to the server. The server references the database and performs user authentication. If authentication is successful, a session is created and a message indicating authentication success is sent to the terminal.

[0524] The device displays a successful authentication screen to the user.

[0525] 2. Character voice selection

[0526] The device displays a character voice selection menu to the user.

[0527] The user selects the desired character, and the device sends the selected character information to the server.

[0528] The server retrieves the character voice data, loads the necessary voice files, and notifies the device when the loading is complete.

[0529] 3. Speech Recognition and Speech Generation

[0530] The device activates the microphone and waits for voice input from the user.

[0531] The user speaks into the device (e.g., "What's my homework for today?").

[0532] The device records the voice input and sends it to the server, which uses speech recognition technology to convert the voice into text data (e.g., "What is today's homework?").

[0533] The server passes the converted text data to a conversation generation system, which generates an appropriate response (e.g., "There are three math problems today. The first one is...").

[0534] 4. Character voice response

[0535] The server converts the generated conversation content into voice using the character's voice data.

[0536] The server sends the audio data to the terminal.

[0537] The device plays the transmitted audio data, allowing the character's voice to respond to the user (e.g., "Today, there are three math problems. The first one is...").

[0538] Specific examples

[0539] For example, when User A, a third-grade elementary school student, uses this system, the process will be as follows:

[0540] 1. Mr. A logs in to the system. He enters his ID and password to verify his identity and is authenticated.

[0541] 2. After logging in, Mr. A selects "Character X" on the character selection screen.

[0542] 3. Mr. A speaks to the device, saying, "Please tell me today's homework." The device records the voice and sends it to the server.

[0543] 4. The server performs speech recognition, converts it into text data, and generates a conversation. The generated content is then converted into voice data in the voice of Character X and sent to the device.

[0544] 5. The device will play "Today we have three math problems. The first one is..." in the voice of Character X.

[0545] In this way, the system can convey information in an enjoyable and effective way and support learning through interaction between the user and the selected character.

[0546] The processing flow will be explained below.

[0547] Step 1:

[0548] The server handles system startup, loading required resources and establishing database connections.

[0549] Step 2:

[0550] The device presents the user with a login screen.

[0551] Step 3:

[0552] The user enters their login ID and password. The device sends the entered information to the server.

[0553] Step 4:

[0554] The server refers to the database and performs user authentication. If authentication is successful, it creates a session and sends a message to the terminal indicating that authentication was successful.

[0555] Step 5:

[0556] The device displays a successful authentication screen to the user.

[0557] Step 6:

[0558] The device displays a character voice selection menu to the user.

[0559] Step 7:

[0560] The user selects the desired character, and the device sends the selected character information to the server.

[0561] Step 8:

[0562] The server retrieves the character voice data, loads the necessary voice files, and notifies the device when the loading is complete.

[0563] Step 9:

[0564] The device activates the microphone and waits for voice input from the user.

[0565] Step 10:

[0566] The user speaks into the device (for example, "What's my homework for today?") and the device records the voice input.

[0567] Step 11:

[0568] The device sends the recorded audio data to the server.

[0569] Step 12:

[0570] The server uses voice recognition technology to convert the transmitted voice data into text data.

[0571] Step 13:

[0572] The server passes the converted text data to a conversation generation system, which generates an appropriate response (e.g., "There are three math problems today. The first one is...").

[0573] Step 14:

[0574] The server converts the generated conversation content into voice using the character's voice data.

[0575] Step 15:

[0576] The server transmits the generated voice data to the terminal.

[0577] Step 16:

[0578] The device plays the transmitted audio data, and responds to the user in a character's voice (e.g., "Today you have three math problems. The first one is...").

[0579] Example 1

[0580] Next, a description will be given of Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the smart glasses 214 will be referred to as a "terminal."

[0581] In modern educational systems, interactive and personalized dialogue systems are necessary for users to learn in an enjoyable and effective manner. However, conventional systems have limited the user experience due to limitations in speech recognition and conversation generation technology. There is a need for a system that can provide a more engaging learning experience by responding with the voice of a character selected by the user.

[0582] The specific processing by the specific processing unit 290 of the data processing device 12 in the first embodiment is realized by the following means.

[0583] In this invention, the server includes means for loading necessary resources and establishing a database connection at system startup, means for generating a session and sending a message of successful authentication to the terminal if authentication is successful, means for the terminal to acquire voice data of a character corresponding to the server and load it, and means for generating conversation content for the generative AI model using prompt sentences. This allows the user to learn and acquire information through dialogue with the selected character, realizing a more interactive and engaging learning experience.

[0584] "User authentication means" means a means for verifying a user's identity when accessing a system.

[0585] The "character voice selection means" is a means for allowing the user to select the voice of the character they desire.

[0586] "Voice input means" refers to a means by which a user inputs voice into the system.

[0587] The "voice data transmission means" is a means for transmitting voice data input by the user to the server.

[0588] The "voice recognition means" is a means for analyzing input voice data and converting it into text data.

[0589] The "means for generating conversation based on text data" is a means for generating appropriate conversation content based on text data generated by speech recognition.

[0590] The "means for converting the generated conversation content into a character's voice" refers to a means for converting the generated text-based conversation content into the voice of a character selected by the user.

[0591] The "means for playing back converted voice data" refers to a means for playing back to the user voice data that has been converted into a character voice.

[0592] The "means for loading required resources and establishing a database connection at system startup" refers to a means for loading required software resources into memory at system startup and establishing a connection with a database.

[0593] The "means for generating a session when authentication is successful and transmitting a message of authentication success to the terminal" refers to a means for generating a session when user authentication is successful and notifying the terminal of that information.

[0594] "Means for the terminal to obtain from the server and load voice data of a character that corresponds to the terminal" refers to means for obtaining from the server voice data of a character selected by the user and loading it into the terminal.

[0595] "Means for generating conversational content for a generative AI model using a prompt sentence" means means for using a generative AI model with a specified prompt sentence as input to generate appropriate conversational content.

[0596] This invention is an interactive system for users to learn and acquire information through interaction with characters of their choice. The system includes the following major hardware and software components:

[0597] First, the system is started by the server, which loads the necessary resources and establishes a database connection. Specifically, it loads the system libraries and configuration files into memory and connects to the SQL database. At this stage, all the necessary initial configuration and preparation is complete.

[0598] The device then presents the user with a login screen, which contains text fields and buttons for the user to enter their login ID and password, and the login information entered by the user is sent from the device to the server in encrypted form.

[0599] The server compares the received login information with the database and authenticates the user. If authentication is successful, the server generates a valid session ID and sends a message of successful authentication to the terminal. The terminal displays the message "Login successful" to the user.

[0600] After user authentication is complete, the device displays a character voice selection menu to the user. This screen displays thumbnail images and names of multiple characters, and the user selects the desired character. The selection information is sent from the device to the server. The server obtains the voice data for the specified character and loads the voice file. After loading is complete, the server notifies the device of this information. The device then displays a message to the user that the character voice is ready.

[0601] Next, the device waits for the user's voice input. The user speaks into the device, for example, "Tell me what my homework is today." This voice input is recorded by the device and sent to the server. The server receives the voice data and converts it into text data using speech recognition technology (e.g., Google Speech-to-Text API).

[0602] The server then inputs the generated text data as a prompt into the generative AI model to generate appropriate conversational content. For example, in response to the prompt "Tell me about today's homework," the generative AI model generates a response such as "There are three math problems today. The first one is..." This response is then converted into speech using the voice data of the selected character.

[0603] Finally, the server sends the audio data to the device, which then plays it back, allowing the user to hear a response in the character's voice, such as "Today, we have three math problems. The first one is..."

[0604] Prompt Sentence Examples

[0605] Below are some examples of prompt sentences that may be used in this invention:

[0606] 1. "Tell me about today's homework."

[0607] 2. "Explain the ecosystem."

[0608] 3. "Tell me about the different types of ecosystems within ecosystems."

[0609] 4. "What is needed to maintain an ecosystem?"

[0610] 5. "What is the importance of biodiversity?"

[0611] This allows users to learn and acquire information in a fun and effective way through interactions with the characters they select.

[0612] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0613] Step 1:

[0614] System startup

[0615] Input: System startup instructions

[0616] What happens next: The server boots the system, loads the necessary resources, and establishes a database connection. Specifically, it loads libraries and configuration files into memory and connects to the SQL database.

[0617] Output: Initialization is complete and the system is ready for user interaction.

[0618] Step 2:

[0619] Displaying the login screen

[0620] Input: After the system starts, the screen prompts the user to begin using the system.

[0621] Specific behavior: The device displays a login screen to the user. The screen displays a text field and a login button. The user enters their login ID and password.

[0622] Output: Login information (ID and password)

[0623] Step 3:

[0624] Sending authentication information

[0625] Input: The login information entered by the user

[0626] Specific operation: The device sends the entered login information to the server. The login information is encrypted before being sent.

[0627] Output: Login information sent to the server

[0628] Step 4:

[0629] User authentication

[0630] Input: Login information received by the server

[0631] Specific operation: The server refers to the database and verifies the entered login information with the registration information. If authentication is successful, the server creates a session and sends a message to the terminal indicating successful authentication.

[0632] Output: Session ID and authentication success message upon successful authentication

[0633] Step 5:

[0634] Viewing authentication results

[0635] Input: Authentication success message sent by the server

[0636] Specific operation: The device displays a screen to the user confirming successful authentication, such as a message saying "Login successful."

[0637] Output: A confirmation message of successful authentication

[0638] Step 6:

[0639] Display the character voice selection menu

[0640] Input: User actions after login

[0641] Specific behavior: The device will display a character voice selection menu to the user, showing thumbnail images and names of multiple characters.

[0642] Output: Display the character selection menu

[0643] Step 7:

[0644] Character Selection

[0645] Input: User selects desired character

[0646] Specific operation: The user selects the desired character. For example, clicks "Character X." The selected character information is sent from the device to the server.

[0647] Output: Selected character information

[0648] Step 8:

[0649] Acquiring and loading character voice data

[0650] Input: Character information sent to the server

[0651] Specific operation: The server retrieves the voice data of the specified character and loads the necessary voice file. For example, it loads the voice file for character X from storage.

[0652] Output: Voice data of the loaded character

[0653] Step 9:

[0654] Viewing notifications

[0655] Input: Notification information from the server to the device

[0656] Specific operation: The server notifies the device that the audio data has been loaded, and the device displays a message to the user that the device is ready.

[0657] Output: Audio data ready message

[0658] Step 10:

[0659] Microphone activation

[0660] Input: User operation after character voice data is ready

[0661] Specific behavior: The device activates the microphone and waits for voice input from the user. For example, the microphone icon becomes active.

[0662] Output: Audio input standby

[0663] Step 11:

[0664] User voice input

[0665] Input: The user speaks into the device

[0666] Specific actions: The user speaks to the device, for example, "Tell me what my homework is today." This is recorded by the device.

[0667] Output: Recorded audio data

[0668] Step 12:

[0669] Recording and sending audio

[0670] Input: User voice input

[0671] Specific operation: The device sends the recorded audio data to the server. The data is in audio file format (e.g., .wav).

[0672] Output: Audio data sent to the server

[0673] Step 13:

[0674] Voice Recognition

[0675] Input: Audio data received by the server

[0676] Specific operation: The server uses speech recognition technology to convert the speech into text data. Specifically, it uses a speech recognition API (e.g., Google Speech-to-Text API) to generate the text data "Please tell me today's homework."

[0677] Output: Generated text data

[0678] Step 14:

[0679] Conversation Generation

[0680] Input: Text data generated by speech recognition

[0681] Specific operation: The server inputs the generated text data as a prompt into the generative AI model, and generates appropriate conversation content. For example, in response to the prompt "Tell me about today's homework," the model generates a response such as "There are three math problems today. The first one is..."

[0682] Output: Generated conversation

[0683] Step 15:

[0684] Voice conversion of conversation content

[0685] Input: Generated conversation

[0686] Specific operation: The server converts the generated dialogue into audio using the character's voice data. For example, it uses a voice synthesizer to generate an audio file that reads the dialogue in the voice of Character X.

[0687] Output: Generated audio data

[0688] Step 16:

[0689] Sending audio data

[0690] Input: Generated audio data

[0691] Specific operation: The server sends audio data to the device in a common audio file format (e.g., .mp3).

[0692] Output: Audio data sent to the device

[0693] Step 17:

[0694] Playing audio data

[0695] Input: Audio data sent to the device

[0696] Specific operation: The device plays the received voice data. For example, a play button appears and Character X's voice responds to the user, saying, "Today, we have three math problems. The first one is..."

[0697] Output: Played back voice response

[0698] (Application example 1)

[0699] Next, a description will be given of Application Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the smart glasses 214 will be referred to as a "terminal."

[0700] Conventional learning support systems have had the problem of making it difficult for users to maintain their interest while studying. Furthermore, even in dialogue-based systems, there are limitations to the interactive dialogue that uses character voices, making it difficult to maximize learning effectiveness.

[0701] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 1 is realized by the following means.

[0702] In this invention, the server includes a user authentication means, a character voice selection means, a voice input means, a voice data transmission means, a voice recognition means, a conversation generation means based on text data, a means for converting the generated conversation content into a character voice, a means for playing the converted voice data, and an interactive learning support means for effectively learning the learning content, thereby enabling the user to progress with their learning in an enjoyable and effective manner through interactive dialogue with the selected character.

[0703] "User authentication means" refers to the means by which a user enters authentication information such as a login ID and password to verify their identity in order to be granted access to the system.

[0704] The "character voice selection means" is a means for allowing the user to select the voice of the character they desire.

[0705] "Audio input means" refers to a means for inputting a user's voice, and generally includes a microphone.

[0706] The "voice data transmission means" is a means for transmitting the user's voice data to another device or server.

[0707] The "voice recognition means" is a means for converting input voice data into text data.

[0708] The "conversation generation means based on text data" is a means for generating an appropriate response based on the text data generated by the speech recognition means.

[0709] The "means for converting the generated conversation content into character voice" is a means for converting the generated text-format conversation content into voice data using the voice data of the selected character.

[0710] The "means for reproducing the converted voice data" refers to a means for reproducing the generated voice data so that the user can hear it.

[0711] An "interactive learning support means for effectively learning learning content" is a means for effectively supporting learning by recognizing the user's voice input, generating an appropriate response, and playing back the voice data in a character's voice.

[0712] The present invention provides an interactive learning support system that supports learning by allowing a user to have an interactive conversation with a character selected by the user. The system includes the following series of means.

[0713] First, the server provides a means for user authentication. To access the system, a user must enter their ID and password for authentication. If authentication is successful, the system provides a means for selecting a character voice, allowing the user to select which character's voice they wish to use. When the user selects a character, the information is sent to the server, and the required character voice data is loaded.

[0714] Next, the terminal uses a microphone as a voice input means and waits for voice input from the user. When the user speaks, the voice data is sent to the server using a voice data sending means. The server uses a voice recognition means to convert the voice data into text data. The converted text data is passed to a conversation generation means, which generates an appropriate response. The response content is converted into a character's voice and sent from the server to the terminal. Finally, the terminal plays back the converted voice data.

[0715] Through this process, users can enjoy interacting with the character they have selected. The server also provides interactive learning support to help users effectively learn the content, and can provide appropriate learning support based on the content of the user's speech.

[0716] As a specific example of an embodiment, a case will be described in which a user says, "Tell me about today's homework." The device records this voice and sends it to the server. The server performs speech recognition and converts it into text data, "Tell me about today's homework." Based on this text data, the server generates an appropriate response (e.g., "There are three math problems today. The first one is..."). This response is converted into audio data in the character's voice and is finally played on the device.

[0717] An example of a prompt is:

[0718] User: What's today's homework?

[0719] System: We have three math problems for you today. The first one is...

[0720] As described above, this system can provide a fun and interactive learning environment through dialogue with characters selected by the user.

[0721] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0722] Step 1:

[0723] The server is responsible for starting the system, loading the necessary resources, and establishing database connections, which allow for user authentication and character voice data management.

[0724] Step 2:

[0725] The terminal displays a login screen to the user. The user enters a login ID and password. The terminal sends the entered authentication information to the server. The input is the user's ID and password, and the output is the authentication result. The server refers to the database to authenticate the user, and creates a session if authentication is successful. It sends a message of successful authentication to the terminal, and the terminal displays a screen of successful authentication to the user.

[0726] Step 3:

[0727] The terminal displays a character voice selection menu to the user. The user selects the desired character. The terminal sends the selected character information to the server. The input is the user's character selection, and the output is a notification that the character voice data has been loaded. The server obtains the character voice data and loads the necessary voice files. Once loading is complete, the terminal is notified.

[0728] Step 4:

[0729] The terminal activates a microphone, which is a voice input means, and waits for voice input from the user. The user speaks into the terminal. The input is the user's voice, and the output is recorded voice data. The terminal records this voice and transmits it to the server using a voice data transmission means.

[0730] Step 5:

[0731] The server converts the received voice data into text data using a voice recognition means. The input is voice data and the output is text data. The voice recognition means uses voice recognition technology to convert, for example, the voice saying "Please tell me today's homework" into the text "Please tell me today's homework."

[0732] Step 6:

[0733] The server passes the converted text data to the conversation generation means, which generates an appropriate response. The input is text data, and the output is response text. The conversation generation means utilizes a generative AI model to generate a natural language response based on the text data. For example, in response to the question, "What's today's homework for me?", the response generated is, "There are three math problems today. The first one is..."

[0734] Step 7:

[0735] The server converts the generated response text into character voice. The input is the response text and the output is voice data. The server uses the voice data of the selected character to convert the response text into voice data.

[0736] Step 8:

[0737] The server sends the converted voice data to the terminal. The terminal plays back the sent voice data. The input is the voice data, and the output is a voice response to the user. The terminal plays back in the character's voice, "Today we have three math problems. The first one is...", and conveys the response to the user.

[0738] These steps allow users to progress through learning interactively through dialogue with the character of their choice.

[0739] Furthermore, an emotion engine that estimates the user's emotion may be further combined. That is, the identification processing unit 290 may estimate the user's emotion using the emotion identification model 59, and perform identification processing using the user's emotion.

[0740] This invention is a system including a user authentication means, a character voice selection means, a voice input means, a voice data transmission means, a voice recognition means, a conversation generation means based on text data, a means for converting the generated conversation content into a character voice, a means for playing the converted voice data, and an emotion engine for recognizing the user's emotions. This system not only enables a user to learn or acquire information through conversation with a favorite character, but also provides appropriate responses according to the user's emotional state.

[0741] 1. System startup and user authentication

[0742] The server handles system startup, loading required resources and establishing database connections.

[0743] The terminal displays a login screen to the user, who then enters their login ID and password.

[0744] The terminal sends the entered information to the server. The server references the database and performs user authentication. If authentication is successful, a session is created and a message indicating successful authentication is sent to the terminal.

[0745] The device displays a successful authentication screen to the user.

[0746] 2. Character voice selection

[0747] The device displays a character voice selection menu to the user.

[0748] The user selects the desired character, and the device sends the selected character information to the server.

[0749] The server retrieves the character voice data, loads the necessary voice files, and notifies the device when the loading is complete.

[0750] 3. Speech Recognition and Speech Generation

[0751] The device activates the microphone and waits for voice input from the user.

[0752] The user speaks into the device (for example, "What's my homework for today?") and the device records the voice input.

[0753] The device sends the recorded voice data to the server, which uses voice recognition technology to convert the voice into text data (e.g., "Please tell me what my homework is today").

[0754] The server passes the converted text data to a conversation generation system, which generates an appropriate response (e.g., "There are three math problems today. The first one is...").

[0755] 4. Emotion Recognition by Emotion Engine

[0756] The server sends the voice data to the emotion engine.

[0757] The emotion engine extracts the user's emotional state from the voice data, for example recognizing emotions such as "happy," "sad," or "angry" from the tone of voice and choice of words.

[0758] The emotion engine passes the extracted emotion data to the conversation generation system, which then adjusts the response based on the emotion data. For example, if the user appears sad, it generates an encouraging response.

[0759] 5. Character voice response

[0760] The server converts the generated conversation content into voice using the character's voice data.

[0761] The server transmits the generated voice data to the terminal.

[0762] The device plays back the transmitted voice data, which then responds to the user in the character's voice (e.g., "There are three math problems today. They're a little tough, but let's do our best together!").

[0763] Specific examples

[0764] For example, when User A, a third-grade elementary school student, uses this system, the process will be as follows:

[0765] 1. Mr. A logs in to the system. He enters his ID and password to verify his identity and is authenticated.

[0766] 2. After logging in, Mr. A selects "Character X" on the character selection screen.

[0767] 3. Mr. A speaks to the device, saying, "Please tell me today's homework." The device records the voice and sends it to the server.

[0768] 4. The server performs speech recognition, converts it into text data, and generates a conversation. The speech data is then sent to the emotion engine, which extracts emotion data. For example, if Mr. A sounds happy, the conversation generation system generates a positive response such as, "That's great! Let's try it together."

[0769] 5. The server converts the generated content into audio data in the voice of Character X and sends it to the device.

[0770] 6. The device will play back in Character X's voice, "Today we have three math problems. They're a little difficult, but let's do our best together!"

[0771] In this way, the system can communicate information in an enjoyable and effective way through interactions between the user and the selected character, assisting learning and providing more personalized responses through emotion recognition.

[0772] The processing flow will be explained below.

[0773] Step 1:

[0774] The server handles system startup, loading required resources and establishing database connections.

[0775] Step 2:

[0776] The device presents the user with a login screen.

[0777] Step 3:

[0778] The user enters their login ID and password. The device sends the entered information to the server.

[0779] Step 4:

[0780] The server refers to the database and performs user authentication. If authentication is successful, it creates a session and sends a message to the terminal indicating that authentication was successful.

[0781] Step 5:

[0782] The device displays a successful authentication screen to the user.

[0783] Step 6:

[0784] The device displays a character voice selection menu to the user.

[0785] Step 7:

[0786] The user selects the desired character, and the device sends the selected character information to the server.

[0787] Step 8:

[0788] The server retrieves the character voice data, loads the necessary voice files, and notifies the device when the loading is complete.

[0789] Step 9:

[0790] The device activates the microphone and waits for voice input from the user.

[0791] Step 10:

[0792] The user speaks into the device (for example, "What's my homework for today?") and the device records the voice input.

[0793] Step 11:

[0794] The device sends the recorded audio data to the server.

[0795] Step 12:

[0796] The server uses voice recognition technology to convert the transmitted voice data into text data.

[0797] Step 13:

[0798] The server sends the text data to the emotion engine.

[0799] Step 14:

[0800] An emotion engine built into the server extracts the user's emotions from the voice data, for example, determining emotions from the tone and speed of the voice.

[0801] Step 15:

[0802] The emotion data extracted by the emotion engine is sent to the conversation generation system.

[0803] Step 16:

[0804] The server generates appropriate conversational content based on the emotion data. For example, if the user looks sad, it generates encouraging content (e.g., "Cheer up, let's do our best together!").

[0805] Step 17:

[0806] The server converts the generated conversation content into voice using the character's voice data.

[0807] Step 18:

[0808] The server transmits the generated voice data to the terminal.

[0809] Step 19:

[0810] The device plays back the transmitted audio data, and responds to the user in the character's voice (e.g., "There are three math problems today. They're a little tough, but let's do our best together!").

[0811] Example 2

[0812] Next, a description will be given of Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the smart glasses 214 will be referred to as a "terminal."

[0813] Conventional voice dialogue systems have difficulty in properly recognizing the user's emotional state and generating responses that correspond to that emotion. Furthermore, they can only provide fixed responses, which limits the user experience and reduces the effectiveness of learning support and information acquisition. Furthermore, the dialogue provided by the character voices is weak, which fails to fully stimulate the user's interest and motivation.

[0814] The identification process by the identification processing unit 290 of the data processing device 12 in the second embodiment is realized by the following means. In this invention, the server includes a user authentication means, a character voice selection means, a voice input means, a voice data transmission means, a voice recognition means, a conversation generation means based on text data, a means for converting the generated conversation content into a character voice, a means for playing the converted voice data, and an emotion engine for recognizing the user's emotions. This enables an appropriate response according to the user's emotional state, and provides individually personalized dialogue. Furthermore, by responding with the voice of the selected character, the user's interest and motivation can be enhanced, improving the effectiveness of learning support and information acquisition.

[0815] "User authentication means" is a function that identifies and authenticates individuals by having the user enter an ID and password.

[0816] The "character voice selection means" is a function that allows the user to select the voice of the character they want and transmit that information to the system.

[0817] "Voice input means" is a function for detecting and recording the voice spoken by the user.

[0818] The "audio data transmission means" is a function for transmitting recorded audio data to the server.

[0819] The "voice recognition means" is a function that converts transmitted voice data into text data.

[0820] The "conversation generation means based on text data" is a function that generates an appropriate response based on the text data generated by the voice recognition means.

[0821] The "means for converting the generated conversation content into a character's voice" is a function for converting the generated conversation content into a voice using the voice data of the selected character.

[0822] The "means for reproducing converted audio data" is a function for reproducing data converted into audio.

[0823] The "emotion engine" is a function that extracts the user's emotional state from their voice data and analyzes that data.

[0824] This invention is a system including a user authentication means, a character voice selection means, a voice input means, a voice data transmission means, a voice recognition means, a conversation generation means based on text data, a means for converting the generated conversation content into a character voice, a means for playing the converted voice data, and an emotion engine. This system allows a user to learn and acquire information through conversation with a favorite character, and further, is capable of providing appropriate responses according to the user's emotional state.

[0825] System configuration and operation

[0826] The system consists of a server and a terminal. The server is responsible for key processes such as user authentication, voice recognition, conversation generation, emotion recognition, and voice conversion. The terminal acts as an interface with the user, providing functions such as voice input, voice playback, and character selection.

[0827] Hardware and software used

[0828] Server Hardware: High performance machine (e.g. Intel Xeon processor, 64GB RAM)

[0829] Server Software:

[0830] OS:Linux

[0831] Web framework: Django

[0832] Database: PostgreSQL

[0833] Speech Recognition API: Google Cloud Speech-to-Text

[0834] Emotion recognition engine: IBM Watson Tone Analyzer

[0835] Speech synthesis engine: Amazon Polly

[0836] Device hardware: PC or tablet, microphone, speakers

[0837] Terminal software:

[0838] Browser: Google Chrome, Mozilla Firefox

[0839] JavaScript library: React.js

[0840] Processing flow

[0841] When the system starts, the server loads the necessary resources and establishes a database connection. The terminal displays a login screen for the user, and the user enters their ID and password. The server refers to the database to authenticate the user, and if authentication is successful, it creates a session and sends a success message to the terminal.

[0842] The user selects the desired character from the character voice selection menu and sends this information to the server, which retrieves the character voice data and loads the voice file.

[0843] For speech recognition and conversation generation, the device activates the microphone and waits for voice input from the user. When the user speaks, the device records the audio and sends it to a server. The server uses the Google Cloud Speech-to-Text API to convert the audio into text data, which is then fed into a generative AI model (e.g., GPT-3) to generate an appropriate response.

[0844] The emotion engine extracts the user's emotional state from their voice and passes the extracted emotion data to the conversation generation system, which then tailors the responses to the user's current emotions. For example, if the user sounds sad, an encouraging response will be generated.

[0845] Finally, the server converts the generated conversation content into voice using the character voice data and transmits the voice data to the terminal, which then plays the voice data and responds to the user in the character's voice.

[0846] Specific examples

[0847] For example, if a third-grader asks the device, "What's my homework for today?", the system will act as follows:

[0848] 1. The device records the audio and sends it to the server.

[0849] 2. The server performs speech recognition and converts it into text data.

[0850] 3. The conversation generation system generates a response: "There are three math problems today."

[0851] 4. The emotion engine analyzes the user's emotions, and if the user appears to be having fun, it complements the response by saying, "Try your best to solve it."

[0852] 5. The server converts this response into voice using the character's voice data and sends it to the device.

[0853] 6. The device will play a character voice saying, "Today there are three math problems, let's do our best together!"

[0854] Prompt Sentence Examples

[0855] "Tell me about today's homework."

[0856] "How are you feeling right now?"

[0857] "Tell me the next step."

[0858] In this way, the system can provide personalized responses that also take into account the user's emotional state, thereby improving the effectiveness of learning support and information acquisition.

[0859] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0860] Step 1:

[0861] The server starts the system, which includes loading the necessary resources and establishing a database connection. The server runs Linux and uses the Django framework to manage web applications. When the server starts, it connects to the database (PostgreSQL) and prepares the necessary tables and data. The input is the command to start the server, and the output is a startup completion message and the establishment of a database connection.

[0862] Step 2:

[0863] The device displays a login screen. The user enters their ID and password and clicks the "Login" button. The input is the user's ID and password, and the output is an HTTP request containing this information. The device's browser (Google Chrome or Mozilla Firefox) accepts this operation.

[0864] Step 3:

[0865] The terminal sends the entered login information to the server. The server compares the received ID and password with the database and performs authentication. The server verifies the user information using Django's authentication function. The input is the user ID and password, and the output is the authentication result (success or failure).

[0866] Step 4:

[0867] If the server is successful in authentication, it creates a session and sends a success message to the terminal. It uses Django's session management functionality to generate a session ID for the user. The input is the success message, and the output is the new session ID.

[0868] Step 5:

[0869] The device displays an authentication success screen to the user. JavaScript is used to dynamically update the screen and show the user a successful authentication message. The input is the successful authentication message sent by the server, and the output is the successful authentication screen visible to the user.

[0870] Step 6:

[0871] The device displays a character voice selection menu. The user selects the desired character. The input is the user's selection, and the output is an HTTP request containing the selected character information. The selection menu is displayed using React.js.

[0872] Step 7:

[0873] The device sends the selected character information to the server. The server retrieves the character's voice data and loads the voice file. Django processes the HTTP request and loads the voice file for the selected character from the database. The input is the selected character information, and the output is the loaded voice file.

[0874] Step 8:

[0875] The device activates the microphone and waits for the user's voice input. The microphone is controlled using JavaScript's Audio API. The input triggers the microphone activation, and the output is in a voice-waiting state. The user speaks, saying something like, "Tell me about today's homework."

[0876] Step 9:

[0877] The device records what the user says and sends the audio data to the server. The recorded data is saved in WAV format and sent to the server. The input is the user's voice data, and the output is a WAV audio file.

[0878] Step 10:

[0879] The server uses speech recognition technology to convert the recorded voice data into text data. The Google Cloud Speech-to-Text API is used to analyze the voice data and convert it into text. The input is a WAV format audio file, and the output is text data.

[0880] Step 11:

[0881] The server passes the text data to a conversation generation system, which uses a generative AI model (e.g., GPT-3) to generate an appropriate response. The input is the converted text data, and the output is the generated response text.

[0882] Step 12:

[0883] The server sends the voice data to the emotion engine to extract the user's emotional state. The emotion data is generated using IBM Watson's Tone Analyzer. The input is voice data, and the output is emotion data.

[0884] Step 13:

[0885] The server passes the extracted emotion data to the conversation generation system, which then checks and adjusts the response. The response is adjusted based on the emotion data. The input is emotion data, and the output is the adjusted response text.

[0886] Step 14:

[0887] The server converts the tailored response into speech using the voice data of the selected character. It uses Amazon Polly for speech synthesis. The input is the response text and the output is an audio file.

[0888] Step 15:

[0889] The server sends the generated audio file to the terminal. The input is the generated audio file, and the output is an HTTP response with the audio file.

[0890] Step 16:

[0891] Plays an audio file received by the device. It uses the JavaScript Audio object to play the audio and responds to the user in a character's voice. The input is the generated audio file, and the output is the audio that is played.

[0892] By dividing the process flow into detailed sections like this, it becomes clear how each step works, and what data is input and output, making it easier to understand specific embodiments of the invention.

[0893] (Application example 2)

[0894] Next, a description will be given of Application Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the smart glasses 214 will be referred to as a "terminal."

[0895] Conventional voice dialogue systems often generate uniform responses without considering the user's emotional state. This makes it difficult to provide personalized dialogue that is sensitive to the user's emotions, which can increase user stress, especially in the workplace. Another issue is insufficient integration with smart devices, making various operations cumbersome.

[0896] The specific processing by the specific processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means. In this invention, the server includes a user authentication means, a character voice selection means, a voice input means, a voice data transmission means, a voice recognition means, a conversation generation means based on text data, a means for converting the generated conversation content into a character voice, a means for playing the converted voice data, an emotion recognition means for recognizing the emotional state of the user, a means for adjusting the conversation content based on the recognized emotional state, and a display means of the smart device. This enables personalized responses according to the user's emotions, improves the quality of conversations at the workplace, and reduces user stress.

[0897] "User authentication means" is a function that verifies the ID and password of users accessing the system and confirms the legitimacy of the users.

[0898] The "character voice selection means" is a function that allows the user to select the voice of the character to be used in the dialogue.

[0899] "Voice input means" refers to a function for receiving voice from the user, and typically includes a microphone.

[0900] The "voice data transmission means" is a function for transmitting collected voice data to a server.

[0901] The "voice recognition means" is a function that analyzes transmitted voice data and converts the content into text data.

[0902] The "conversation generation means based on text data" is a function that generates appropriate response content based on text data that has been speech-recognized.

[0903] The "means for converting the generated conversation content into character voice" is a function for converting the conversation content generated in text into voice using voice data of a pre-selected character.

[0904] "Means for playing converted voice data" is a function for playing data converted into a character's voice so that the user can hear it.

[0905] The "emotion recognition means for recognizing the user's emotional state" is a function for extracting the user's emotional state from the user's voice data or other input.

[0906] The "means for adjusting the content of the conversation based on the recognized emotional state" is a function for adjusting the content of the generated response based on the user's emotion detected by the emotion recognition means.

[0907] The "display means of the smart device" refers to a device for displaying information and operation screens of the interactive system, and typically includes smart glasses, tablets, etc.

[0908] System Overview

[0909] This invention is a system that enables users to communicate through character voices by wearing a smart device and operating it with voice. The system mainly uses a server, a smart device (such as smart glasses or a tablet), a microphone for user input, a speaker for voice playback, and software for emotion recognition.

[0910] Program Structure Overview

[0911] The system consists of a program with the following main functions:

[0912] 1. User Authentication

[0913] 2. Character voice selection

[0914] 3. Speech Recognition and Speech Generation

[0915] 4. Emotion recognition

[0916] 5. Voice Response

[0917] Processing flow and technologies used

[0918] 1. User Authentication

[0919] The server receives the user ID and password sent from the smart device and authenticates the user by referencing the database, thereby preventing unauthorized access and providing services to the appropriate user.

[0920] Required Hardware / Software:

[0921] Database server (MySQL, etc.)

[0922] Authentication Server

[0923] Smart Devices

[0924] 2. Character voice selection

[0925] The smart device displays multiple character voice options to the user, the user selects the desired character, and the selection data is sent to the server, which loads the voice data for the selected character and notifies the smart device.

[0926] Required Hardware / Software:

[0927] Smart devices (smart glasses, tablets, etc.)

[0928] server

[0929] 3. Speech Recognition and Speech Generation

[0930] When a user speaks into a smart device, the microphone records the audio. The recording is sent to a server where it is converted into text using speech recognition technology (such as the Google Speech-to-Text API). This text is then passed to a generative AI model (such as GPT-3.5 Turbo) to generate an appropriate response.

[0931] Required Hardware / Software:

[0932] microphone

[0933] server

[0934] Speech Recognition API

[0935] Generative AI Models

[0936] 4. Emotion recognition

[0937] The converted text data is passed to emotion recognition software (such as DistilRoBERTa) to analyze the user's emotional state. The server then adjusts the generated response content based on the emotional data and selects an appropriate response.

[0938] Required Hardware / Software:

[0939] server

[0940] Emotion Recognition Model

[0941] 5. Voice Response

[0942] The adjusted response content is converted into voice using the character voice data and transmitted to the smart device, which responds to the user in the character's voice using a speaker.

[0943] Required Hardware / Software:

[0944] Smart device (with built-in speaker)

[0945] server

[0946] Specific examples

[0947] For example, suppose a factory worker wears smart glasses and asks, "What's the current status of the production line?" In this case, the system first performs speech recognition and passes the text data to the generative AI model. The generative AI model generates a response such as, "The current production line is running smoothly. The production rate is 80%." If the model then performs emotion recognition and determines that the user is satisfied, it will convey this in a positive tone. The system then converts this text into speech in a character's voice and conveys it to the user.

[0948] Prompt Sentence Examples

[0949] User is interested. Please tell me the current status of the production line.

[0950] In this way, the system can provide personalized responses according to the user's emotions, improving the user experience at the workplace.

[0951] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[0952] Step 1:

[0953] The user starts up the smart device and accesses the login screen. The user enters their login ID and password. The device sends this information to the server, which then refers to the database to authenticate the user. If authentication is successful, a message indicating successful authentication is sent to the device, and a screen indicating successful authentication is displayed to the user.

[0954] Input: Login ID, Password

[0955] Data processing / calculation: Verification of authentication data (database reference)

[0956] Output: Authentication success message

[0957] Step 2:

[0958] After the user logs in, the device displays a character voice selection menu. The user selects the desired character, and that information is sent from the device to the server. The server retrieves the voice data for the selected character and notifies the device when the required voice files have been loaded. The device then informs the user that it is ready to play.

[0959] Input: Character selection information

[0960] Data processing / calculation: Acquiring and loading audio data

[0961] Output: Playback ready notification

[0962] Step 3:

[0963] The user speaks into the device. The device's microphone records the voice and sends the voice data to the server. The server uses voice recognition technology to convert the voice data into text data. For example, a user's speech such as "Tell me about the current status of the production line" is converted into text data.

[0964] Input: Audio data

[0965] Data processing / calculation: Speech recognition (voice to text conversion)

[0966] Output: Text data

[0967] Step 4:

[0968] The server passes the converted text data to the emotion recognition means, which extracts the user's emotional state from the voice and text data. For example, if the user's voice sounds happy, it will be recognized as "positive."

[0969] Input: Text data, audio data

[0970] Data processing / calculation: Emotion recognition (emotion data extraction)

[0971] Output: Emotion data

[0972] Step 5:

[0973] The server generates a response using a conversation generation system based on the text data and emotional data. A generative AI model (such as GPT-3.5 Turbo) generates an appropriate response. For example, if the user's question is "What is the current status of the production line?" and the emotional state is "positive," the server generates a response such as "The current production line is going smoothly. The production rate is 80%."

[0974] Input: Text data, emotion data

[0975] Data processing / calculation: Response generation (generative AI model)

[0976] Output: The generated text response

[0977] Step 6:

[0978] The generated text response is converted into voice using the voice data of the selected character, and the server converts the text response into voice data and transmits it to the terminal.

[0979] Input: Generated text response, character voice data

[0980] Data processing / calculation: Text to speech conversion

[0981] Output: Audio data

[0982] Step 7:

[0983] The terminal plays the received audio data, and the user receives a response in the voice of the character they selected. For example, the character's voice may say, "The current production line is running smoothly. The production rate is 80%."

[0984] Input: Audio data

[0985] Data processing / calculation: Audio playback

[0986] Output: Playback of a response to the user

[0987] The specific processing unit 290 transmits the result of the specific processing to the smart glasses 214. In the smart glasses 214, the control unit 46A causes the speaker 240 to output the result of the specific processing. The microphone 238 acquires audio indicating a user input regarding the result of the specific processing. The control unit 46A transmits audio data indicating the user input acquired by the microphone 238 to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the audio data.

[0988] The data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of the data generation model 58 is ChatGPT (Internet Search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search <url: https: gemini.google.com ?hl="ja">) and other generation AIs. The data generation model 58 is obtained by performing deep learning on a neural network. A prompt including an instruction is input to the data generation model 58, and inference data such as voice data indicating voice, text data indicating text, and image data indicating an image is also input. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt, and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[0989] In the above embodiment, an example in which the specific processing is performed by the data processing device 12 has been given, but the technology of the present disclosure is not limited to this, and the specific processing may be performed by the smart glasses 214.

[0990] [Third embodiment]

[0991] FIG. 5 shows an example of the configuration of a data processing system 310 according to the third embodiment.

[0992] 5, the data processing system 310 includes the data processing device 12 and a headset type terminal 314. An example of the data processing device 12 is a server.

[0993] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 is an example of a "computer" according to the technology of the present disclosure. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, the RAM 30, and the storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0994] The headset type terminal 314 includes a computer 36, a microphone 238, a speaker 240, a camera 42, a communication I / F 44, and a display 343. The computer 36 includes a processor 46, a RAM 48, and a storage 50. The processor 46, the RAM 48, and the storage 50 are connected to a bus 52. The microphone 238, the speaker 240, the camera 42, and the display 343 are also connected to the bus 52.

[0995] The microphone 238 receives instructions and the like from the user 20 by receiving voice uttered by the user 20. The microphone 238 captures the voice uttered by the user 20, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio in accordance with instructions from the processor 46.

[0996] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an imaging element such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the surroundings of user 20 (for example, an imaging range defined by an angle of view equivalent to the field of vision of a typical healthy person).

[0997] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 are responsible for the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is carried out in a secure state.

[0998] Fig. 6 shows an example of the main functions of the data processing device 12 and the headset type terminal 314. As shown in Fig. 6, in the data processing device 12, a specific process is performed by the processor 28. A specific process program 56 is stored in the storage 32.

[0999] The specific processing program 56 is an example of a "program" according to the technology of the present disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[1000] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[1001] In the headset type terminal 314, a reception output process is performed by the processor 46. A reception output program 60 is stored in the storage 50. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output process is realized by the processor 46 operating as the control unit 46A in accordance with the reception output program 60 executed on the RAM 48.

[1002] Next, a description will be given of the identification process performed by the identification processing unit 290 of the data processing device 12. In the following description, the data processing device 12 will be referred to as the "server" and the headset type terminal 314 will be referred to as the "terminal."

[1003] This invention is a system including a user authentication means, a character voice selection means, a voice input means, a voice data transmission means, a voice recognition means, a conversation generation means based on text data, a means for converting the generated conversation content into a character voice, and a means for playing back the converted voice data. This system enables users to learn and acquire information through conversations with their favorite characters.

[1004] 1. System startup and user authentication

[1005] The server handles system startup, loading required resources and establishing database connections.

[1006] The terminal displays a login screen to the user, who then enters their login ID and password.

[1007] The terminal sends the entered information to the server. The server references the database and performs user authentication. If authentication is successful, a session is created and a message indicating authentication success is sent to the terminal.

[1008] The device displays a successful authentication screen to the user.

[1009] 2. Character voice selection

[1010] The device displays a character voice selection menu to the user.

[1011] The user selects the desired character, and the device sends the selected character information to the server.

[1012] The server retrieves the character voice data, loads the necessary voice files, and notifies the device when the loading is complete.

[1013] 3. Speech Recognition and Speech Generation

[1014] The device activates the microphone and waits for voice input from the user.

[1015] The user speaks into the device (e.g., "What's my homework for today?").

[1016] The device records the voice input and sends it to the server, which uses speech recognition technology to convert the voice into text data (e.g., "What is today's homework?").

[1017] The server passes the converted text data to a conversation generation system, which generates an appropriate response (e.g., "There are three math problems today. The first one is...").

[1018] 4. Character voice response

[1019] The server converts the generated conversation content into voice using the character's voice data.

[1020] The server sends the audio data to the terminal.

[1021] The device plays the transmitted audio data, allowing the character's voice to respond to the user (e.g., "Today, there are three math problems. The first one is...").

[1022] Specific examples

[1023] For example, when User A, a third-grade elementary school student, uses this system, the process will be as follows:

[1024] 1. Mr. A logs in to the system. He enters his ID and password to verify his identity and is authenticated.

[1025] 2. After logging in, Mr. A selects "Character X" on the character selection screen.

[1026] 3. Mr. A speaks to the device, saying, "Please tell me today's homework." The device records the voice and sends it to the server.

[1027] 4. The server performs speech recognition, converts it into text data, and generates a conversation. The generated content is then converted into voice data in the voice of Character X and sent to the device.

[1028] 5. The device will play "Today we have three math problems. The first one is..." in the voice of Character X.

[1029] In this way, the system can convey information in an enjoyable and effective way and support learning through interaction between the user and the selected character.

[1030] The processing flow will be explained below.

[1031] Step 1:

[1032] The server handles system startup, loading required resources and establishing database connections.

[1033] Step 2:

[1034] The device presents the user with a login screen.

[1035] Step 3:

[1036] The user enters their login ID and password. The device sends the entered information to the server.

[1037] Step 4:

[1038] The server refers to the database and performs user authentication. If authentication is successful, it creates a session and sends a message to the terminal indicating that authentication was successful.

[1039] Step 5:

[1040] The device displays a successful authentication screen to the user.

[1041] Step 6:

[1042] The device displays a character voice selection menu to the user.

[1043] Step 7:

[1044] The user selects the desired character, and the device sends the selected character information to the server.

[1045] Step 8:

[1046] The server retrieves the character voice data, loads the necessary voice files, and notifies the device when the loading is complete.

[1047] Step 9:

[1048] The device activates the microphone and waits for voice input from the user.

[1049] Step 10:

[1050] The user speaks into the device (for example, "What's my homework for today?") and the device records the voice input.

[1051] Step 11:

[1052] The device sends the recorded audio data to the server.

[1053] Step 12:

[1054] The server uses voice recognition technology to convert the transmitted voice data into text data.

[1055] Step 13:

[1056] The server passes the converted text data to a conversation generation system, which generates an appropriate response (e.g., "There are three math problems today. The first one is...").

[1057] Step 14:

[1058] The server converts the generated conversation content into voice using the character's voice data.

[1059] Step 15:

[1060] The server transmits the generated voice data to the terminal.

[1061] Step 16:

[1062] The device plays the transmitted audio data, and responds to the user in a character's voice (e.g., "Today you have three math problems. The first one is...").

[1063] Example 1

[1064] Next, a description will be given of Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the headset type terminal 314 will be referred to as a "terminal."

[1065] In modern educational systems, interactive and personalized dialogue systems are necessary for users to learn in an enjoyable and effective manner. However, conventional systems have limited the user experience due to limitations in speech recognition and conversation generation technology. There is a need for a system that can provide a more engaging learning experience by responding with the voice of a character selected by the user.

[1066] The specific processing by the specific processing unit 290 of the data processing device 12 in the first embodiment is realized by the following means.

[1067] In this invention, the server includes means for loading necessary resources and establishing a database connection at system startup, means for generating a session and sending a message of successful authentication to the terminal if authentication is successful, means for the terminal to acquire voice data of a character corresponding to the server and load it, and means for generating conversation content for the generative AI model using prompt sentences. This allows the user to learn and acquire information through dialogue with the selected character, realizing a more interactive and engaging learning experience.

[1068] "User authentication means" means a means for verifying a user's identity when accessing a system.

[1069] The "character voice selection means" is a means for allowing the user to select the voice of the character they desire.

[1070] "Voice input means" refers to a means by which a user inputs voice into the system.

[1071] The "voice data transmission means" is a means for transmitting voice data input by the user to the server.

[1072] The "voice recognition means" is a means for analyzing input voice data and converting it into text data.

[1073] The "means for generating conversation based on text data" is a means for generating appropriate conversation content based on text data generated by speech recognition.

[1074] The "means for converting the generated conversation content into a character's voice" refers to a means for converting the generated text-based conversation content into the voice of a character selected by the user.

[1075] The "means for playing back converted voice data" refers to a means for playing back to the user voice data that has been converted into a character voice.

[1076] The "means for loading required resources and establishing a database connection at system startup" refers to a means for loading required software resources into memory at system startup and establishing a connection with a database.

[1077] The "means for generating a session when authentication is successful and transmitting a message of authentication success to the terminal" refers to a means for generating a session when user authentication is successful and notifying the terminal of that information.

[1078] "Means for the terminal to obtain from the server and load voice data of a character that corresponds to the terminal" refers to means for obtaining from the server voice data of a character selected by the user and loading it into the terminal.

[1079] "Means for generating conversational content for a generative AI model using a prompt sentence" means means for using a generative AI model with a specified prompt sentence as input to generate appropriate conversational content.

[1080] This invention is an interactive system for users to learn and acquire information through interaction with characters of their choice. The system includes the following major hardware and software components:

[1081] First, the system is started by the server, which loads the necessary resources and establishes a database connection. Specifically, it loads the system libraries and configuration files into memory and connects to the SQL database. At this stage, all the necessary initial configuration and preparation is complete.

[1082] The device then presents the user with a login screen, which contains text fields and buttons for the user to enter their login ID and password, and the login information entered by the user is sent from the device to the server in encrypted form.

[1083] The server compares the received login information with the database and authenticates the user. If authentication is successful, the server generates a valid session ID and sends a message of successful authentication to the terminal. The terminal displays the message "Login successful" to the user.

[1084] After user authentication is complete, the device displays a character voice selection menu to the user. This screen displays thumbnail images and names of multiple characters, and the user selects the desired character. The selection information is sent from the device to the server. The server obtains the voice data for the specified character and loads the voice file. After loading is complete, the server notifies the device of this information. The device then displays a message to the user that the character voice is ready.

[1085] Next, the device waits for the user's voice input. The user speaks into the device, for example, "Tell me what my homework is today." This voice input is recorded by the device and sent to the server. The server receives the voice data and converts it into text data using speech recognition technology (e.g., Google Speech-to-Text API).

[1086] The server then inputs the generated text data as a prompt into the generative AI model to generate appropriate conversational content. For example, in response to the prompt "Tell me about today's homework," the generative AI model generates a response such as "There are three math problems today. The first one is..." This response is then converted into speech using the voice data of the selected character.

[1087] Finally, the server sends the audio data to the device, which then plays it back, allowing the user to hear a response in the character's voice, such as "Today, we have three math problems. The first one is..."

[1088] Prompt Sentence Examples

[1089] Below are some examples of prompt sentences that may be used in this invention:

[1090] 1. "Tell me about today's homework."

[1091] 2. "Explain the ecosystem."

[1092] 3. "Tell me about the different types of ecosystems within ecosystems."

[1093] 4. "What is needed to maintain an ecosystem?"

[1094] 5. "What is the importance of biodiversity?"

[1095] This allows users to learn and acquire information in a fun and effective way through interactions with the characters they select.

[1096] The flow of the identification process in the first embodiment will be described with reference to FIG.

[1097] Step 1:

[1098] System startup

[1099] Input: System startup instructions

[1100] What happens next: The server boots the system, loads the necessary resources, and establishes a database connection. Specifically, it loads libraries and configuration files into memory and connects to the SQL database.

[1101] Output: Initialization is complete and the system is ready for user interaction.

[1102] Step 2:

[1103] Displaying the login screen

[1104] Input: After the system starts, the screen prompts the user to begin using the system.

[1105] Specific behavior: The device displays a login screen to the user. The screen displays a text field and a login button. The user enters their login ID and password.

[1106] Output: Login information (ID and password)

[1107] Step 3:

[1108] Sending authentication information

[1109] Input: The login information entered by the user

[1110] Specific operation: The device sends the entered login information to the server. The login information is encrypted before being sent.

[1111] Output: Login information sent to the server

[1112] Step 4:

[1113] User authentication

[1114] Input: Login information received by the server

[1115] Specific operation: The server refers to the database and verifies the entered login information with the registration information. If authentication is successful, the server creates a session and sends a message to the terminal indicating successful authentication.

[1116] Output: Session ID and authentication success message upon successful authentication

[1117] Step 5:

[1118] Viewing authentication results

[1119] Input: Authentication success message sent by the server

[1120] Specific operation: The device displays a screen to the user confirming successful authentication, such as a message saying "Login successful."

[1121] Output: A confirmation message of successful authentication

[1122] Step 6:

[1123] Display the character voice selection menu

[1124] Input: User actions after login

[1125] Specific behavior: The device will display a character voice selection menu to the user, showing thumbnail images and names of multiple characters.

[1126] Output: Display the character selection menu

[1127] Step 7:

[1128] Character Selection

[1129] Input: User selects desired character

[1130] Specific operation: The user selects the desired character. For example, clicks "Character X." The selected character information is sent from the device to the server.

[1131] Output: Selected character information

[1132] Step 8:

[1133] Acquiring and loading character voice data

[1134] Input: Character information sent to the server

[1135] Specific operation: The server retrieves the voice data of the specified character and loads the necessary voice file. For example, it loads the voice file for character X from storage.

[1136] Output: Voice data of the loaded character

[1137] Step 9:

[1138] Viewing notifications

[1139] Input: Notification information from the server to the device

[1140] Specific operation: The server notifies the device that the audio data has been loaded, and the device displays a message to the user that the device is ready.

[1141] Output: Audio data ready message

[1142] Step 10:

[1143] Microphone activation

[1144] Input: User operation after character voice data is ready

[1145] Specific behavior: The device activates the microphone and waits for voice input from the user. For example, the microphone icon becomes active.

[1146] Output: Audio input standby

[1147] Step 11:

[1148] User voice input

[1149] Input: The user speaks into the device

[1150] Specific actions: The user speaks to the device, for example, "Tell me what my homework is today." This is recorded by the device.

[1151] Output: Recorded audio data

[1152] Step 12:

[1153] Recording and sending audio

[1154] Input: User voice input

[1155] Specific operation: The device sends the recorded audio data to the server. The data is in audio file format (e.g., .wav).

[1156] Output: Audio data sent to the server

[1157] Step 13:

[1158] Voice Recognition

[1159] Input: Audio data received by the server

[1160] Specific operation: The server uses speech recognition technology to convert the speech into text data. Specifically, it uses a speech recognition API (e.g., Google Speech-to-Text API) to generate the text data "Please tell me today's homework."

[1161] Output: Generated text data

[1162] Step 14:

[1163] Conversation Generation

[1164] Input: Text data generated by speech recognition

[1165] Specific operation: The server inputs the generated text data as a prompt into the generative AI model, and generates appropriate conversation content. For example, in response to the prompt "Tell me about today's homework," the model generates a response such as "There are three math problems today. The first one is..."

[1166] Output: Generated conversation

[1167] Step 15:

[1168] Voice conversion of conversation content

[1169] Input: Generated conversation

[1170] Specific operation: The server converts the generated dialogue into audio using the character's voice data. For example, it uses a voice synthesizer to generate an audio file that reads the dialogue in the voice of Character X.

[1171] Output: Generated audio data

[1172] Step 16:

[1173] Sending audio data

[1174] Input: Generated audio data

[1175] Specific operation: The server sends audio data to the device in a common audio file format (e.g., .mp3).

[1176] Output: Audio data sent to the device

[1177] Step 17:

[1178] Playing audio data

[1179] Input: Audio data sent to the device

[1180] Specific operation: The device plays the received voice data. For example, a play button appears and Character X's voice responds to the user, saying, "Today, we have three math problems. The first one is..."

[1181] Output: Played back voice response

[1182] (Application example 1)

[1183] Next, a description will be given of Application Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the headset type terminal 314 will be referred to as a "terminal."

[1184] Conventional learning support systems have had the problem of making it difficult for users to maintain their interest while studying. Furthermore, even in dialogue-based systems, there are limitations to the interactive dialogue that uses character voices, making it difficult to maximize learning effectiveness.

[1185] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 1 is realized by the following means.

[1186] In this invention, the server includes a user authentication means, a character voice selection means, a voice input means, a voice data transmission means, a voice recognition means, a conversation generation means based on text data, a means for converting the generated conversation content into a character voice, a means for playing the converted voice data, and an interactive learning support means for effectively learning the learning content, thereby enabling the user to progress with their learning in an enjoyable and effective manner through interactive dialogue with the selected character.

[1187] "User authentication means" refers to the means by which a user enters authentication information such as a login ID and password to verify their identity in order to be granted access to the system.

[1188] The "character voice selection means" is a means for allowing the user to select the voice of the character they desire.

[1189] "Audio input means" refers to a means for inputting a user's voice, and generally includes a microphone.

[1190] The "voice data transmission means" is a means for transmitting the user's voice data to another device or server.

[1191] The "voice recognition means" is a means for converting input voice data into text data.

[1192] The "conversation generation means based on text data" is a means for generating an appropriate response based on the text data generated by the speech recognition means.

[1193] The "means for converting the generated conversation content into character voice" is a means for converting the generated text-format conversation content into voice data using the voice data of the selected character.

[1194] The "means for reproducing the converted voice data" refers to a means for reproducing the generated voice data so that the user can hear it.

[1195] An "interactive learning support means for effectively learning learning content" is a means for effectively supporting learning by recognizing the user's voice input, generating an appropriate response, and playing back the voice data in a character's voice.

[1196] The present invention provides an interactive learning support system that supports learning by allowing a user to have an interactive conversation with a character selected by the user. The system includes the following series of means.

[1197] First, the server provides a means for user authentication. To access the system, a user must enter their ID and password for authentication. If authentication is successful, the system provides a means for selecting a character voice, allowing the user to select which character's voice they wish to use. When the user selects a character, the information is sent to the server, and the required character voice data is loaded.

[1198] Next, the terminal uses a microphone as a voice input means and waits for voice input from the user. When the user speaks, the voice data is sent to the server using a voice data sending means. The server uses a voice recognition means to convert the voice data into text data. The converted text data is passed to a conversation generation means, which generates an appropriate response. The response content is converted into a character's voice and sent from the server to the terminal. Finally, the terminal plays back the converted voice data.

[1199] Through this process, users can enjoy interacting with the character they have selected. The server also provides interactive learning support to help users effectively learn the content, and can provide appropriate learning support based on the content of the user's speech.

[1200] As a specific example of an embodiment, a case will be described in which a user says, "Tell me about today's homework." The device records this voice and sends it to the server. The server performs speech recognition and converts it into text data, "Tell me about today's homework." Based on this text data, the server generates an appropriate response (e.g., "There are three math problems today. The first one is..."). This response is converted into audio data in the character's voice and is finally played on the device.

[1201] An example of a prompt is:

[1202] User: What's today's homework?

[1203] System: We have three math problems for you today. The first one is...

[1204] As described above, this system can provide a fun and interactive learning environment through dialogue with characters selected by the user.

[1205] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[1206] Step 1:

[1207] The server is responsible for starting the system, loading the necessary resources, and establishing database connections, which allow for user authentication and character voice data management.

[1208] Step 2:

[1209] The terminal displays a login screen to the user. The user enters a login ID and password. The terminal sends the entered authentication information to the server. The input is the user's ID and password, and the output is the authentication result. The server refers to the database to authenticate the user, and creates a session if authentication is successful. It sends a message of successful authentication to the terminal, and the terminal displays a screen of successful authentication to the user.

[1210] Step 3:

[1211] The terminal displays a character voice selection menu to the user. The user selects the desired character. The terminal sends the selected character information to the server. The input is the user's character selection, and the output is a notification that the character voice data has been loaded. The server obtains the character voice data and loads the necessary voice files. Once loading is complete, the terminal is notified.

[1212] Step 4:

[1213] The terminal activates a microphone, which is a voice input means, and waits for voice input from the user. The user speaks into the terminal. The input is the user's voice, and the output is recorded voice data. The terminal records this voice and transmits it to the server using a voice data transmission means.

[1214] Step 5:

[1215] The server converts the received voice data into text data using a voice recognition means. The input is voice data and the output is text data. The voice recognition means uses voice recognition technology to convert, for example, the voice saying "Please tell me today's homework" into the text "Please tell me today's homework."

[1216] Step 6:

[1217] The server passes the converted text data to the conversation generation means, which generates an appropriate response. The input is text data, and the output is response text. The conversation generation means utilizes a generative AI model to generate a natural language response based on the text data. For example, in response to the question, "What's today's homework for me?", the response generated is, "There are three math problems today. The first one is..."

[1218] Step 7:

[1219] The server converts the generated response text into character voice. The input is the response text and the output is voice data. The server uses the voice data of the selected character to convert the response text into voice data.

[1220] Step 8:

[1221] The server sends the converted voice data to the terminal. The terminal plays back the sent voice data. The input is the voice data, and the output is a voice response to the user. The terminal plays back in the character's voice, "Today we have three math problems. The first one is...", and conveys the response to the user.

[1222] These steps allow users to progress through learning interactively through dialogue with the character of their choice.

[1223] Furthermore, an emotion engine that estimates the user's emotion may be further combined. That is, the identification processing unit 290 may estimate the user's emotion using the emotion identification model 59, and perform identification processing using the user's emotion.

[1224] This invention is a system including a user authentication means, a character voice selection means, a voice input means, a voice data transmission means, a voice recognition means, a conversation generation means based on text data, a means for converting the generated conversation content into a character voice, a means for playing the converted voice data, and an emotion engine for recognizing the user's emotions. This system not only enables a user to learn or acquire information through conversation with a favorite character, but also provides appropriate responses according to the user's emotional state.

[1225] 1. System startup and user authentication

[1226] The server handles system startup, loading required resources and establishing database connections.

[1227] The terminal displays a login screen to the user, who then enters their login ID and password.

[1228] The terminal sends the entered information to the server. The server references the database and performs user authentication. If authentication is successful, a session is created and a message indicating successful authentication is sent to the terminal.

[1229] The device displays a successful authentication screen to the user.

[1230] 2. Character voice selection

[1231] The device displays a character voice selection menu to the user.

[1232] The user selects the desired character, and the device sends the selected character information to the server.

[1233] The server retrieves the character voice data, loads the necessary voice files, and notifies the device when the loading is complete.

[1234] 3. Speech Recognition and Speech Generation

[1235] The device activates the microphone and waits for voice input from the user.

[1236] The user speaks into the device (for example, "What's my homework for today?") and the device records the voice input.

[1237] The device sends the recorded voice data to the server, which uses voice recognition technology to convert the voice into text data (e.g., "Please tell me what my homework is today").

[1238] The server passes the converted text data to a conversation generation system, which generates an appropriate response (e.g., "There are three math problems today. The first one is...").

[1239] 4. Emotion Recognition by Emotion Engine

[1240] The server sends the voice data to the emotion engine.

[1241] The emotion engine extracts the user's emotional state from the voice data, for example recognizing emotions such as "happy," "sad," or "angry" from the tone of voice and choice of words.

[1242] The emotion engine passes the extracted emotion data to the conversation generation system, which then adjusts the response based on the emotion data. For example, if the user appears sad, it generates an encouraging response.

[1243] 5. Character voice response

[1244] The server converts the generated conversation content into voice using the character's voice data.

[1245] The server transmits the generated voice data to the terminal.

[1246] The device plays back the transmitted voice data, which then responds to the user in the character's voice (e.g., "There are three math problems today. They're a little tough, but let's do our best together!").

[1247] Specific examples

[1248] For example, when User A, a third-grade elementary school student, uses this system, the process will be as follows:

[1249] 1. Mr. A logs in to the system. He enters his ID and password to verify his identity and is authenticated.

[1250] 2. After logging in, Mr. A selects "Character X" on the character selection screen.

[1251] 3. Mr. A speaks to the device, saying, "Please tell me today's homework." The device records the voice and sends it to the server.

[1252] 4. The server performs speech recognition, converts it into text data, and generates a conversation. The speech data is then sent to the emotion engine, which extracts emotion data. For example, if Mr. A sounds happy, the conversation generation system generates a positive response such as, "That's great! Let's try it together."

[1253] 5. The server converts the generated content into audio data in the voice of Character X and sends it to the device.

[1254] 6. The device will play back in Character X's voice, "Today we have three math problems. They're a little difficult, but let's do our best together!"

[1255] In this way, the system can communicate information in an enjoyable and effective way through interactions between the user and the selected character, assisting learning and providing more personalized responses through emotion recognition.

[1256] The processing flow will be explained below.

[1257] Step 1:

[1258] The server handles system startup, loading required resources and establishing database connections.

[1259] Step 2:

[1260] The device presents the user with a login screen.

[1261] Step 3:

[1262] The user enters their login ID and password. The device sends the entered information to the server.

[1263] Step 4:

[1264] The server refers to the database and performs user authentication. If authentication is successful, it creates a session and sends a message to the terminal indicating that authentication was successful.

[1265] Step 5:

[1266] The device displays a successful authentication screen to the user.

[1267] Step 6:

[1268] The device displays a character voice selection menu to the user.

[1269] Step 7:

[1270] The user selects the desired character, and the device sends the selected character information to the server.

[1271] Step 8:

[1272] The server retrieves the character voice data, loads the necessary voice files, and notifies the device when the loading is complete.

[1273] Step 9:

[1274] The device activates the microphone and waits for voice input from the user.

[1275] Step 10:

[1276] The user speaks into the device (for example, "What's my homework for today?") and the device records the voice input.

[1277] Step 11:

[1278] The device sends the recorded audio data to the server.

[1279] Step 12:

[1280] The server uses voice recognition technology to convert the transmitted voice data into text data.

[1281] Step 13:

[1282] The server sends the text data to the emotion engine.

[1283] Step 14:

[1284] An emotion engine built into the server extracts the user's emotions from the voice data, for example, determining emotions from the tone and speed of the voice.

[1285] Step 15:

[1286] The emotion data extracted by the emotion engine is sent to the conversation generation system.

[1287] Step 16:

[1288] The server generates appropriate conversational content based on the emotion data. For example, if the user looks sad, it generates encouraging content (e.g., "Cheer up, let's do our best together!").

[1289] Step 17:

[1290] The server converts the generated conversation content into voice using the character's voice data.

[1291] Step 18:

[1292] The server transmits the generated voice data to the terminal.

[1293] Step 19:

[1294] The device plays back the transmitted audio data, and responds to the user in the character's voice (e.g., "There are three math problems today. They're a little tough, but let's do our best together!").

[1295] Example 2

[1296] Next, a description will be given of Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the headset type terminal 314 will be referred to as a "terminal."

[1297] Conventional voice dialogue systems have difficulty in properly recognizing the user's emotional state and generating responses that correspond to that emotion. Furthermore, they can only provide fixed responses, which limits the user experience and reduces the effectiveness of learning support and information acquisition. Furthermore, the dialogue provided by the character voices is weak, which fails to fully stimulate the user's interest and motivation.

[1298] The identification process by the identification processing unit 290 of the data processing device 12 in the second embodiment is realized by the following means. In this invention, the server includes a user authentication means, a character voice selection means, a voice input means, a voice data transmission means, a voice recognition means, a conversation generation means based on text data, a means for converting the generated conversation content into a character voice, a means for playing the converted voice data, and an emotion engine for recognizing the user's emotions. This enables an appropriate response according to the user's emotional state, and provides individually personalized dialogue. Furthermore, by responding with the voice of the selected character, the user's interest and motivation can be enhanced, improving the effectiveness of learning support and information acquisition.

[1299] "User authentication means" is a function that identifies and authenticates individuals by having the user enter an ID and password.

[1300] The "character voice selection means" is a function that allows the user to select the voice of the character they want and transmit that information to the system.

[1301] "Voice input means" is a function for detecting and recording the voice spoken by the user.

[1302] The "audio data transmission means" is a function for transmitting recorded audio data to the server.

[1303] The "voice recognition means" is a function that converts transmitted voice data into text data.

[1304] The "conversation generation means based on text data" is a function that generates an appropriate response based on the text data generated by the voice recognition means.

[1305] The "means for converting the generated conversation content into a character's voice" is a function for converting the generated conversation content into a voice using the voice data of the selected character.

[1306] The "means for reproducing converted audio data" is a function for reproducing data converted into audio.

[1307] The "emotion engine" is a function that extracts the user's emotional state from their voice data and analyzes that data.

[1308] This invention is a system including a user authentication means, a character voice selection means, a voice input means, a voice data transmission means, a voice recognition means, a conversation generation means based on text data, a means for converting the generated conversation content into a character voice, a means for playing the converted voice data, and an emotion engine. This system allows a user to learn and acquire information through conversation with a favorite character, and further, is capable of providing appropriate responses according to the user's emotional state.

[1309] System configuration and operation

[1310] The system consists of a server and a terminal. The server is responsible for key processes such as user authentication, voice recognition, conversation generation, emotion recognition, and voice conversion. The terminal acts as an interface with the user, providing functions such as voice input, voice playback, and character selection.

[1311] Hardware and software used

[1312] Server Hardware: High performance machine (e.g. Intel Xeon processor, 64GB RAM)

[1313] Server Software:

[1314] OS:Linux

[1315] Web framework: Django

[1316] Database: PostgreSQL

[1317] Speech Recognition API: Google Cloud Speech-to-Text

[1318] Emotion recognition engine: IBM Watson Tone Analyzer

[1319] Speech synthesis engine: Amazon Polly

[1320] Device hardware: PC or tablet, microphone, speakers

[1321] Terminal software:

[1322] Browser: Google Chrome, Mozilla Firefox

[1323] JavaScript library: React.js

[1324] Processing flow

[1325] When the system starts, the server loads the necessary resources and establishes a database connection. The terminal displays a login screen for the user, and the user enters their ID and password. The server refers to the database to authenticate the user, and if authentication is successful, it creates a session and sends a success message to the terminal.

[1326] The user selects the desired character from the character voice selection menu and sends this information to the server, which retrieves the character voice data and loads the voice file.

[1327] For speech recognition and conversation generation, the device activates the microphone and waits for voice input from the user. When the user speaks, the device records the audio and sends it to a server. The server uses the Google Cloud Speech-to-Text API to convert the audio into text data, which is then fed into a generative AI model (e.g., GPT-3) to generate an appropriate response.

[1328] The emotion engine extracts the user's emotional state from their voice and passes the extracted emotion data to the conversation generation system, which then tailors the responses to the user's current emotions. For example, if the user sounds sad, an encouraging response will be generated.

[1329] Finally, the server converts the generated conversation content into voice using the character voice data and transmits the voice data to the terminal, which then plays the voice data and responds to the user in the character's voice.

[1330] Specific examples

[1331] For example, if a third-grader asks the device, "What's my homework for today?", the system will act as follows:

[1332] 1. The device records the audio and sends it to the server.

[1333] 2. The server performs speech recognition and converts it into text data.

[1334] 3. The conversation generation system generates a response: "There are three math problems today."

[1335] 4. The emotion engine analyzes the user's emotions, and if the user appears to be having fun, it complements the response by saying, "Try your best to solve it."

[1336] 5. The server converts this response into voice using the character's voice data and sends it to the device.

[1337] 6. The device will play a character voice saying, "Today there are three math problems, let's do our best together!"

[1338] Prompt Sentence Examples

[1339] "Tell me about today's homework."

[1340] "How are you feeling right now?"

[1341] "Tell me the next step."

[1342] In this way, the system can provide personalized responses that also take into account the user's emotional state, thereby improving the effectiveness of learning support and information acquisition.

[1343] The flow of the identification process in the second embodiment will be described with reference to FIG.

[1344] Step 1:

[1345] The server starts the system, which includes loading the necessary resources and establishing a database connection. The server runs Linux and uses the Django framework to manage web applications. When the server starts, it connects to the database (PostgreSQL) and prepares the necessary tables and data. The input is the command to start the server, and the output is a startup completion message and the establishment of a database connection.

[1346] Step 2:

[1347] The device displays a login screen. The user enters their ID and password and clicks the "Login" button. The input is the user's ID and password, and the output is an HTTP request containing this information. The device's browser (Google Chrome or Mozilla Firefox) accepts this operation.

[1348] Step 3:

[1349] The terminal sends the entered login information to the server. The server compares the received ID and password with the database and performs authentication. The server verifies the user information using Django's authentication function. The input is the user ID and password, and the output is the authentication result (success or failure).

[1350] Step 4:

[1351] If the server is successful in authentication, it creates a session and sends a success message to the terminal. It uses Django's session management functionality to generate a session ID for the user. The input is the success message, and the output is the new session ID.

[1352] Step 5:

[1353] The device displays an authentication success screen to the user. JavaScript is used to dynamically update the screen and show the user a successful authentication message. The input is the successful authentication message sent by the server, and the output is the successful authentication screen visible to the user.

[1354] Step 6:

[1355] The device displays a character voice selection menu. The user selects the desired character. The input is the user's selection, and the output is an HTTP request containing the selected character information. The selection menu is displayed using React.js.

[1356] Step 7:

[1357] The device sends the selected character information to the server. The server retrieves the character's voice data and loads the voice file. Django processes the HTTP request and loads the voice file for the selected character from the database. The input is the selected character information, and the output is the loaded voice file.

[1358] Step 8:

[1359] The device activates the microphone and waits for the user's voice input. The microphone is controlled using JavaScript's Audio API. The input triggers the microphone activation, and the output is in a voice-waiting state. The user speaks, saying something like, "Tell me about today's homework."

[1360] Step 9:

[1361] The device records what the user says and sends the audio data to the server. The recorded data is saved in WAV format and sent to the server. The input is the user's voice data, and the output is a WAV audio file.

[1362] Step 10:

[1363] The server uses speech recognition technology to convert the recorded voice data into text data. The Google Cloud Speech-to-Text API is used to analyze the voice data and convert it into text. The input is a WAV format audio file, and the output is text data.

[1364] Step 11:

[1365] The server passes the text data to a conversation generation system, which uses a generative AI model (e.g., GPT-3) to generate an appropriate response. The input is the converted text data, and the output is the generated response text.

[1366] Step 12:

[1367] The server sends the voice data to the emotion engine to extract the user's emotional state. The emotion data is generated using IBM Watson's Tone Analyzer. The input is voice data, and the output is emotion data.

[1368] Step 13:

[1369] The server passes the extracted emotion data to the conversation generation system, which then checks and adjusts the response. The response is adjusted based on the emotion data. The input is emotion data, and the output is the adjusted response text.

[1370] Step 14:

[1371] The server converts the tailored response into speech using the voice data of the selected character. It uses Amazon Polly for speech synthesis. The input is the response text and the output is an audio file.

[1372] Step 15:

[1373] The server sends the generated audio file to the terminal. The input is the generated audio file, and the output is an HTTP response with the audio file.

[1374] Step 16:

[1375] Plays an audio file received by the device. It uses the JavaScript Audio object to play the audio and responds to the user in a character's voice. The input is the generated audio file, and the output is the audio that is played.

[1376] By dividing the process flow into detailed sections like this, it becomes clear how each step works, and what data is input and output, making it easier to understand specific embodiments of the invention.

[1377] (Application example 2)

[1378] Next, a description will be given of Application Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the headset type terminal 314 will be referred to as a "terminal."

[1379] Conventional voice dialogue systems often generate uniform responses without considering the user's emotional state. This makes it difficult to provide personalized dialogue that is sensitive to the user's emotions, which can increase user stress, especially in the workplace. Another issue is insufficient integration with smart devices, making various operations cumbersome.

[1380] The specific processing by the specific processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means. In this invention, the server includes a user authentication means, a character voice selection means, a voice input means, a voice data transmission means, a voice recognition means, a conversation generation means based on text data, a means for converting the generated conversation content into a character voice, a means for playing the converted voice data, an emotion recognition means for recognizing the emotional state of the user, a means for adjusting the conversation content based on the recognized emotional state, and a display means of the smart device. This enables personalized responses according to the user's emotions, improves the quality of conversations at the workplace, and reduces user stress.

[1381] "User authentication means" is a function that verifies the ID and password of users accessing the system and confirms the legitimacy of the users.

[1382] The "character voice selection means" is a function that allows the user to select the voice of the character to be used in the dialogue.

[1383] "Voice input means" refers to a function for receiving voice from the user, and typically includes a microphone.

[1384] The "voice data transmission means" is a function for transmitting collected voice data to a server.

[1385] The "voice recognition means" is a function that analyzes transmitted voice data and converts the content into text data.

[1386] The "conversation generation means based on text data" is a function that generates appropriate response content based on text data that has been speech-recognized.

[1387] The "means for converting the generated conversation content into character voice" is a function for converting the conversation content generated in text into voice using voice data of a pre-selected character.

[1388] "Means for playing converted voice data" is a function for playing data converted into a character's voice so that the user can hear it.

[1389] The "emotion recognition means for recognizing the user's emotional state" is a function for extracting the user's emotional state from the user's voice data or other input.

[1390] The "means for adjusting the content of the conversation based on the recognized emotional state" is a function for adjusting the content of the generated response based on the user's emotion detected by the emotion recognition means.

[1391] The "display means of the smart device" refers to a device for displaying information and operation screens of the interactive system, and typically includes smart glasses, tablets, etc.

[1392] System Overview

[1393] This invention is a system that enables users to communicate through character voices by wearing a smart device and operating it with voice. The system mainly uses a server, a smart device (such as smart glasses or a tablet), a microphone for user input, a speaker for voice playback, and software for emotion recognition.

[1394] Program Structure Overview

[1395] The system consists of a program with the following main functions:

[1396] 1. User Authentication

[1397] 2. Character voice selection

[1398] 3. Speech Recognition and Speech Generation

[1399] 4. Emotion recognition

[1400] 5. Voice Response

[1401] Processing flow and technologies used

[1402] 1. User Authentication

[1403] The server receives the user ID and password sent from the smart device and authenticates the user by referencing the database, thereby preventing unauthorized access and providing services to the appropriate user.

[1404] Required Hardware / Software:

[1405] Database server (MySQL, etc.)

[1406] Authentication Server

[1407] Smart Devices

[1408] 2. Character voice selection

[1409] The smart device displays multiple character voice options to the user, the user selects the desired character, and the selection data is sent to the server, which loads the voice data for the selected character and notifies the smart device.

[1410] Required Hardware / Software:

[1411] Smart devices (smart glasses, tablets, etc.)

[1412] server

[1413] 3. Speech Recognition and Speech Generation

[1414] When a user speaks into a smart device, the microphone records the audio. The recording is sent to a server where it is converted into text using speech recognition technology (such as the Google Speech-to-Text API). This text is then passed to a generative AI model (such as GPT-3.5 Turbo) to generate an appropriate response.

[1415] Required Hardware / Software:

[1416] microphone

[1417] server

[1418] Speech Recognition API

[1419] Generative AI Models

[1420] 4. Emotion recognition

[1421] The converted text data is passed to emotion recognition software (such as DistilRoBERTa) to analyze the user's emotional state. The server then adjusts the generated response content based on the emotional data and selects an appropriate response.

[1422] Required Hardware / Software:

[1423] server

[1424] Emotion Recognition Model

[1425] 5. Voice Response

[1426] The adjusted response content is converted into voice using the character voice data and transmitted to the smart device, which responds to the user in the character's voice using a speaker.

[1427] Required Hardware / Software:

[1428] Smart device (with built-in speaker)

[1429] server

[1430] Specific examples

[1431] For example, suppose a factory worker wears smart glasses and asks, "What's the current status of the production line?" In this case, the system first performs speech recognition and passes the text data to the generative AI model. The generative AI model generates a response such as, "The current production line is running smoothly. The production rate is 80%." If the model then performs emotion recognition and determines that the user is satisfied, it will convey this in a positive tone. The system then converts this text into speech in a character's voice and conveys it to the user.

[1432] Prompt Sentence Examples

[1433] User is interested. Please tell me the current status of the production line.

[1434] In this way, the system can provide personalized responses according to the user's emotions, improving the user experience at the workplace.

[1435] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[1436] Step 1:

[1437] The user starts up the smart device and accesses the login screen. The user enters their login ID and password. The device sends this information to the server, which then refers to the database to authenticate the user. If authentication is successful, a message indicating successful authentication is sent to the device, and a screen indicating successful authentication is displayed to the user.

[1438] Input: Login ID, Password

[1439] Data processing / calculation: Verification of authentication data (database reference)

[1440] Output: Authentication success message

[1441] Step 2:

[1442] After the user logs in, the device displays a character voice selection menu. The user selects the desired character, and that information is sent from the device to the server. The server retrieves the voice data for the selected character and notifies the device when the required voice files have been loaded. The device then informs the user that it is ready to play.

[1443] Input: Character selection information

[1444] Data processing / calculation: Acquiring and loading audio data

[1445] Output: Playback ready notification

[1446] Step 3:

[1447] The user speaks into the device. The device's microphone records the voice and sends the voice data to the server. The server uses voice recognition technology to convert the voice data into text data. For example, a user's speech such as "Tell me about the current status of the production line" is converted into text data.

[1448] Input: Audio data

[1449] Data processing / calculation: Speech recognition (voice to text conversion)

[1450] Output: Text data

[1451] Step 4:

[1452] The server passes the converted text data to the emotion recognition means, which extracts the user's emotional state from the voice and text data. For example, if the user's voice sounds happy, it will be recognized as "positive."

[1453] Input: Text data, audio data

[1454] Data processing / calculation: Emotion recognition (emotion data extraction)

[1455] Output: Emotion data

[1456] Step 5:

[1457] The server generates a response using a conversation generation system based on the text data and emotional data. A generative AI model (such as GPT-3.5 Turbo) generates an appropriate response. For example, if the user's question is "What is the current status of the production line?" and the emotional state is "positive," the server generates a response such as "The current production line is going smoothly. The production rate is 80%."

[1458] Input: Text data, emotion data

[1459] Data processing / calculation: Response generation (generative AI model)

[1460] Output: The generated text response

[1461] Step 6:

[1462] The generated text response is converted into voice using the voice data of the selected character, and the server converts the text response into voice data and transmits it to the terminal.

[1463] Input: Generated text response, character voice data

[1464] Data processing / calculation: Text to speech conversion

[1465] Output: Audio data

[1466] Step 7:

[1467] The terminal plays the received audio data, and the user receives a response in the voice of the character they selected. For example, the character's voice may say, "The current production line is running smoothly. The production rate is 80%."

[1468] Input: Audio data

[1469] Data processing / calculation: Audio playback

[1470] Output: Playback of a response to the user

[1471] The specific processing unit 290 transmits the result of the specific processing to the headset type terminal 314. In the headset type terminal 314, the control unit 46A causes the speaker 240 and the display 343 to output the result of the specific processing. The microphone 238 acquires audio indicating a user input regarding the result of the specific processing. The control unit 46A transmits audio data indicating the user input acquired by the microphone 238 to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the audio data.

[1472] The data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of the data generation model 58 is ChatGPT (Internet Search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search <url: https: gemini.google.com ?hl="ja">) and other generation AIs. The data generation model 58 is obtained by performing deep learning on a neural network. A prompt including an instruction is input to the data generation model 58, and inference data such as voice data indicating voice, text data indicating text, and image data indicating an image is also input. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt, and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[1473] In the above embodiment, an example was given in which the specific processing is performed by the data processing device 12, but the technology of the present disclosure is not limited to this, and the specific processing may be performed by the headset type terminal 314.

[1474] [Fourth embodiment]

[1475] FIG. 7 shows an example of the configuration of a data processing system 410 according to the fourth embodiment.

[1476] 7, a data processing system 410 includes a data processing device 12 and a robot 414. An example of the data processing device 12 is a server.

[1477] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 is an example of a "computer" according to the technology of the present disclosure. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, the RAM 30, and the storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[1478] The robot 414 includes a computer 36, a microphone 238, a speaker 240, a camera 42, a communication I / F 44, and a control target 443. The computer 36 includes a processor 46, a RAM 48, and a storage 50. The processor 46, the RAM 48, and the storage 50 are connected to a bus 52. The microphone 238, the speaker 240, the camera 42, and the control target 443 are also connected to the bus 52.

[1479] The microphone 238 receives instructions and the like from the user 20 by receiving voice uttered by the user 20. The microphone 238 captures the voice uttered by the user 20, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio in accordance with instructions from the processor 46.

[1480] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an imaging element such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the surroundings of user 20 (for example, an imaging range defined by an angle of view equivalent to the field of vision of a typical healthy person).

[1481] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 are responsible for the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is carried out in a secure state.

[1482] The control object 443 includes a display device, LEDs in the eyes, and motors for driving the arms, hands, and feet. The posture and gestures of the robot 414 are controlled by controlling the motors of the arms, hands, and feet. Some of the emotions of the robot 414 can be expressed by controlling these motors. In addition, the facial expressions of the robot 414 can also be expressed by controlling the light emission state of the LEDs in the eyes of the robot 414.

[1483] Fig. 8 shows an example of the main functions of the data processing device 12 and the robot 414. As shown in Fig. 8, in the data processing device 12, a specific process is performed by the processor 28. A specific process program 56 is stored in the storage 32.

[1484] The specific processing program 56 is an example of a "program" according to the technology of the present disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[1485] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[1486] In the robot 414, the processor 46 performs the reception output process. A reception output program 60 is stored in the storage 50. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output process is realized by the processor 46 operating as the control unit 46A in accordance with the reception output program 60 executed on the RAM 48.

[1487] Next, a description will be given of the specific processing performed by the specific processing unit 290 of the data processing device 12. In the following description, the data processing device 12 will be referred to as a "server" and the robot 414 will be referred to as a "terminal."

[1488] This invention is a system including a user authentication means, a character voice selection means, a voice input means, a voice data transmission means, a voice recognition means, a conversation generation means based on text data, a means for converting the generated conversation content into a character voice, and a means for playing back the converted voice data. This system enables users to learn and acquire information through conversations with their favorite characters.

[1489] 1. System startup and user authentication

[1490] The server handles system startup, loading required resources and establishing database connections.

[1491] The terminal displays a login screen to the user, who then enters their login ID and password.

[1492] The terminal sends the entered information to the server. The server references the database and performs user authentication. If authentication is successful, a session is created and a message indicating authentication success is sent to the terminal.

[1493] The device displays a successful authentication screen to the user.

[1494] 2. Character voice selection

[1495] The device displays a character voice selection menu to the user.

[1496] The user selects the desired character, and the device sends the selected character information to the server.

[1497] The server retrieves the character voice data, loads the necessary voice files, and notifies the device when the loading is complete.

[1498] 3. Speech Recognition and Speech Generation

[1499] The device activates the microphone and waits for voice input from the user.

[1500] The user speaks into the device (e.g., "What's my homework for today?").

[1501] The device records the voice input and sends it to the server, which uses speech recognition technology to convert the voice into text data (e.g., "What is today's homework?").

[1502] The server passes the converted text data to a conversation generation system, which generates an appropriate response (e.g., "There are three math problems today. The first one is...").

[1503] 4. Character voice response

[1504] The server converts the generated conversation content into voice using the character's voice data.

[1505] The server sends the audio data to the terminal.

[1506] The device plays the transmitted audio data, allowing the character's voice to respond to the user (e.g., "Today, there are three math problems. The first one is...").

[1507] Specific examples

[1508] For example, when User A, a third-grade elementary school student, uses this system, the process will be as follows:

[1509] 1. Mr. A logs in to the system. He enters his ID and password to verify his identity and is authenticated.

[1510] 2. After logging in, Mr. A selects "Character X" on the character selection screen.

[1511] 3. Mr. A speaks to the device, saying, "Please tell me today's homework." The device records the voice and sends it to the server.

[1512] 4. The server performs speech recognition, converts it into text data, and generates a conversation. The generated content is then converted into voice data in the voice of Character X and sent to the device.

[1513] 5. The device will play "Today we have three math problems. The first one is..." in the voice of Character X.

[1514] In this way, the system can convey information in an enjoyable and effective way and support learning through interaction between the user and the selected character.

[1515] The processing flow will be explained below.

[1516] Step 1:

[1517] The server handles system startup, loading required resources and establishing database connections.

[1518] Step 2:

[1519] The device presents the user with a login screen.

[1520] Step 3:

[1521] The user enters their login ID and password. The device sends the entered information to the server.

[1522] Step 4:

[1523] The server refers to the database and performs user authentication. If authentication is successful, it creates a session and sends a message to the terminal indicating that authentication was successful.

[1524] Step 5:

[1525] The device displays a successful authentication screen to the user.

[1526] Step 6:

[1527] The device displays a character voice selection menu to the user.

[1528] Step 7:

[1529] The user selects the desired character, and the device sends the selected character information to the server.

[1530] Step 8:

[1531] The server retrieves the character voice data, loads the necessary voice files, and notifies the device when the loading is complete.

[1532] Step 9:

[1533] The device activates the microphone and waits for voice input from the user.

[1534] Step 10:

[1535] The user speaks into the device (for example, "What's my homework for today?") and the device records the voice input.

[1536] Step 11:

[1537] The device sends the recorded audio data to the server.

[1538] Step 12:

[1539] The server uses voice recognition technology to convert the transmitted voice data into text data.

[1540] Step 13:

[1541] The server passes the converted text data to a conversation generation system, which generates an appropriate response (e.g., "There are three math problems today. The first one is...").

[1542] Step 14:

[1543] The server converts the generated conversation content into voice using the character's voice data.

[1544] Step 15:

[1545] The server transmits the generated voice data to the terminal.

[1546] Step 16:

[1547] The device plays the transmitted audio data, and responds to the user in a character's voice (e.g., "Today you have three math problems. The first one is...").

[1548] Example 1

[1549] Next, a description will be given of Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the robot 414 will be referred to as a "terminal."

[1550] In modern educational systems, interactive and personalized dialogue systems are necessary for users to learn in an enjoyable and effective manner. However, conventional systems have limited the user experience due to limitations in speech recognition and conversation generation technology. There is a need for a system that can provide a more engaging learning experience by responding with the voice of a character selected by the user.

[1551] The specific processing by the specific processing unit 290 of the data processing device 12 in the first embodiment is realized by the following means.

[1552] In this invention, the server includes means for loading necessary resources and establishing a database connection at system startup, means for generating a session and sending a message of successful authentication to the terminal if authentication is successful, means for the terminal to acquire voice data of a character corresponding to the server and load it, and means for generating conversation content for the generative AI model using prompt sentences. This allows the user to learn and acquire information through dialogue with the selected character, realizing a more interactive and engaging learning experience.

[1553] "User authentication means" means a means for verifying a user's identity when accessing a system.

[1554] The "character voice selection means" is a means for allowing the user to select the voice of the character they desire.

[1555] "Voice input means" refers to a means by which a user inputs voice into the system.

[1556] The "voice data transmission means" is a means for transmitting voice data input by the user to the server.

[1557] The "voice recognition means" is a means for analyzing input voice data and converting it into text data.

[1558] The "means for generating conversation based on text data" is a means for generating appropriate conversation content based on text data generated by speech recognition.

[1559] The "means for converting the generated conversation content into a character's voice" refers to a means for converting the generated text-based conversation content into the voice of a character selected by the user.

[1560] The "means for playing back converted voice data" refers to a means for playing back to the user voice data that has been converted into a character voice.

[1561] The "means for loading required resources and establishing a database connection at system startup" refers to a means for loading required software resources into memory at system startup and establishing a connection with a database.

[1562] The "means for generating a session when authentication is successful and transmitting a message of authentication success to the terminal" refers to a means for generating a session when user authentication is successful and notifying the terminal of that information.

[1563] "Means for the terminal to obtain from the server and load voice data of a character that corresponds to the terminal" refers to means for obtaining from the server voice data of a character selected by the user and loading it into the terminal.

[1564] "Means for generating conversational content for a generative AI model using a prompt sentence" means means for using a generative AI model with a specified prompt sentence as input to generate appropriate conversational content.

[1565] This invention is an interactive system for users to learn and acquire information through interaction with characters of their choice. The system includes the following major hardware and software components:

[1566] First, the system is started by the server, which loads the necessary resources and establishes a database connection. Specifically, it loads the system libraries and configuration files into memory and connects to the SQL database. At this stage, all the necessary initial configuration and preparation is complete.

[1567] The device then presents the user with a login screen, which contains text fields and buttons for the user to enter their login ID and password, and the login information entered by the user is sent from the device to the server in encrypted form.

[1568] The server compares the received login information with the database and authenticates the user. If authentication is successful, the server generates a valid session ID and sends a message of successful authentication to the terminal. The terminal displays the message "Login successful" to the user.

[1569] After user authentication is complete, the device displays a character voice selection menu to the user. This screen displays thumbnail images and names of multiple characters, and the user selects the desired character. The selection information is sent from the device to the server. The server obtains the voice data for the specified character and loads the voice file. After loading is complete, the server notifies the device of this information. The device then displays a message to the user that the character voice is ready.

[1570] Next, the device waits for the user's voice input. The user speaks into the device, for example, "Tell me what my homework is today." This voice input is recorded by the device and sent to the server. The server receives the voice data and converts it into text data using speech recognition technology (e.g., Google Speech-to-Text API).

[1571] The server then inputs the generated text data as a prompt into the generative AI model to generate appropriate conversational content. For example, in response to the prompt "Tell me about today's homework," the generative AI model generates a response such as "There are three math problems today. The first one is..." This response is then converted into speech using the voice data of the selected character.

[1572] Finally, the server sends the audio data to the device, which then plays it back, allowing the user to hear a response in the character's voice, such as "Today, we have three math problems. The first one is..."

[1573] Prompt Sentence Examples

[1574] Below are some examples of prompt sentences that may be used in this invention:

[1575] 1. "Tell me about today's homework."

[1576] 2. "Explain the ecosystem."

[1577] 3. "Tell me about the different types of ecosystems within ecosystems."

[1578] 4. "What is needed to maintain an ecosystem?"

[1579] 5. "What is the importance of biodiversity?"

[1580] This allows users to learn and acquire information in a fun and effective way through interactions with the characters they select.

[1581] The flow of the identification process in the first embodiment will be described with reference to FIG.

[1582] Step 1:

[1583] System startup

[1584] Input: System startup instructions

[1585] What happens next: The server boots the system, loads the necessary resources, and establishes a database connection. Specifically, it loads libraries and configuration files into memory and connects to the SQL database.

[1586] Output: Initialization is complete and the system is ready for user interaction.

[1587] Step 2:

[1588] Displaying the login screen

[1589] Input: After the system starts, the screen prompts the user to begin using the system.

[1590] Specific behavior: The device displays a login screen to the user. The screen displays a text field and a login button. The user enters their login ID and password.

[1591] Output: Login information (ID and password)

[1592] Step 3:

[1593] Sending authentication information

[1594] Input: The login information entered by the user

[1595] Specific operation: The device sends the entered login information to the server. The login information is encrypted before being sent.

[1596] Output: Login information sent to the server

[1597] Step 4:

[1598] User authentication

[1599] Input: Login information received by the server

[1600] Specific operation: The server refers to the database and verifies the entered login information with the registration information. If authentication is successful, the server creates a session and sends a message to the terminal indicating successful authentication.

[1601] Output: Session ID and authentication success message upon successful authentication

[1602] Step 5:

[1603] Viewing authentication results

[1604] Input: Authentication success message sent by the server

[1605] Specific operation: The device displays a screen to the user confirming successful authentication, such as a message saying "Login successful."

[1606] Output: A confirmation message of successful authentication

[1607] Step 6:

[1608] Display the character voice selection menu

[1609] Input: User actions after login

[1610] Specific behavior: The device will display a character voice selection menu to the user, showing thumbnail images and names of multiple characters.

[1611] Output: Display the character selection menu

[1612] Step 7:

[1613] Character Selection

[1614] Input: User selects desired character

[1615] Specific operation: The user selects the desired character. For example, clicks "Character X." The selected character information is sent from the device to the server.

[1616] Output: Selected character information

[1617] Step 8:

[1618] Acquiring and loading character voice data

[1619] Input: Character information sent to the server

[1620] Specific operation: The server retrieves the voice data of the specified character and loads the necessary voice file. For example, it loads the voice file for character X from storage.

[1621] Output: Voice data of the loaded character

[1622] Step 9:

[1623] Viewing notifications

[1624] Input: Notification information from the server to the device

[1625] Specific operation: The server notifies the device that the audio data has been loaded, and the device displays a message to the user that the device is ready.

[1626] Output: Audio data ready message

[1627] Step 10:

[1628] Microphone activation

[1629] Input: User operation after character voice data is ready

[1630] Specific behavior: The device activates the microphone and waits for voice input from the user. For example, the microphone icon becomes active.

[1631] Output: Audio input standby

[1632] Step 11:

[1633] User voice input

[1634] Input: The user speaks into the device

[1635] Specific actions: The user speaks to the device, for example, "Tell me what my homework is today." This is recorded by the device.

[1636] Output: Recorded audio data

[1637] Step 12:

[1638] Recording and sending audio

[1639] Input: User voice input

[1640] Specific operation: The device sends the recorded audio data to the server. The data is in audio file format (e.g., .wav).

[1641] Output: Audio data sent to the server

[1642] Step 13:

[1643] Voice Recognition

[1644] Input: Audio data received by the server

[1645] Specific operation: The server uses speech recognition technology to convert the speech into text data. Specifically, it uses a speech recognition API (e.g., Google Speech-to-Text API) to generate the text data "Please tell me today's homework."

[1646] Output: Generated text data

[1647] Step 14:

[1648] Conversation Generation

[1649] Input: Text data generated by speech recognition

[1650] Specific operation: The server inputs the generated text data as a prompt into the generative AI model, and generates appropriate conversation content. For example, in response to the prompt "Tell me about today's homework," the model generates a response such as "There are three math problems today. The first one is..."

[1651] Output: Generated conversation

[1652] Step 15:

[1653] Voice conversion of conversation content

[1654] Input: Generated conversation

[1655] Specific operation: The server converts the generated dialogue into audio using the character's voice data. For example, it uses a voice synthesizer to generate an audio file that reads the dialogue in the voice of Character X.

[1656] Output: Generated audio data

[1657] Step 16:

[1658] Sending audio data

[1659] Input: Generated audio data

[1660] Specific operation: The server sends audio data to the device in a common audio file format (e.g., .mp3).

[1661] Output: Audio data sent to the device

[1662] Step 17:

[1663] Playing audio data

[1664] Input: Audio data sent to the device

[1665] Specific operation: The device plays the received voice data. For example, a play button appears and Character X's voice responds to the user, saying, "Today, we have three math problems. The first one is..."

[1666] Output: Played back voice response

[1667] (Application example 1)

[1668] Next, a description will be given of Application Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the robot 414 will be referred to as a "terminal."

[1669] Conventional learning support systems have had the problem of making it difficult for users to maintain their interest while studying. Furthermore, even in dialogue-based systems, there are limitations to the interactive dialogue that uses character voices, making it difficult to maximize learning effectiveness.

[1670] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 1 is realized by the following means.

[1671] In this invention, the server includes a user authentication means, a character voice selection means, a voice input means, a voice data transmission means, a voice recognition means, a conversation generation means based on text data, a means for converting the generated conversation content into a character voice, a means for playing the converted voice data, and an interactive learning support means for effectively learning the learning content, thereby enabling the user to progress with their learning in an enjoyable and effective manner through interactive dialogue with the selected character.

[1672] "User authentication means" refers to the means by which a user enters authentication information such as a login ID and password to verify their identity in order to be granted access to the system.

[1673] The "character voice selection means" is a means for allowing the user to select the voice of the character they desire.

[1674] "Audio input means" refers to a means for inputting a user's voice, and generally includes a microphone.

[1675] The "voice data transmission means" is a means for transmitting the user's voice data to another device or server.

[1676] The "voice recognition means" is a means for converting input voice data into text data.

[1677] The "conversation generation means based on text data" is a means for generating an appropriate response based on the text data generated by the speech recognition means.

[1678] The "means for converting the generated conversation content into character voice" is a means for converting the generated text-format conversation content into voice data using the voice data of the selected character.

[1679] The "means for reproducing the converted voice data" refers to a means for reproducing the generated voice data so that the user can hear it.

[1680] An "interactive learning support means for effectively learning learning content" is a means for effectively supporting learning by recognizing the user's voice input, generating an appropriate response, and playing back the voice data in a character's voice.

[1681] The present invention provides an interactive learning support system that supports learning by allowing a user to have an interactive conversation with a character selected by the user. The system includes the following series of means.

[1682] First, the server provides a means for user authentication. To access the system, a user must enter their ID and password for authentication. If authentication is successful, the system provides a means for selecting a character voice, allowing the user to select which character's voice they wish to use. When the user selects a character, the information is sent to the server, and the required character voice data is loaded.

[1683] Next, the terminal uses a microphone as a voice input means and waits for voice input from the user. When the user speaks, the voice data is sent to the server using a voice data sending means. The server uses a voice recognition means to convert the voice data into text data. The converted text data is passed to a conversation generation means, which generates an appropriate response. The response content is converted into a character's voice and sent from the server to the terminal. Finally, the terminal plays back the converted voice data.

[1684] Through this process, users can enjoy interacting with the character they have selected. The server also provides interactive learning support to help users effectively learn the content, and can provide appropriate learning support based on the content of the user's speech.

[1685] As a specific example of an embodiment, a case will be described in which a user says, "Tell me about today's homework." The device records this voice and sends it to the server. The server performs speech recognition and converts it into text data, "Tell me about today's homework." Based on this text data, the server generates an appropriate response (e.g., "There are three math problems today. The first one is..."). This response is converted into audio data in the character's voice and is finally played on the device.

[1686] An example of a prompt is:

[1687] User: What's today's homework?

[1688] System: We have three math problems for you today. The first one is...

[1689] As described above, this system can provide a fun and interactive learning environment through dialogue with characters selected by the user.

[1690] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[1691] Step 1:

[1692] The server is responsible for starting the system, loading the necessary resources, and establishing database connections, which allow for user authentication and character voice data management.

[1693] Step 2:

[1694] The terminal displays a login screen to the user. The user enters a login ID and password. The terminal sends the entered authentication information to the server. The input is the user's ID and password, and the output is the authentication result. The server refers to the database to authenticate the user, and creates a session if authentication is successful. It sends a message of successful authentication to the terminal, and the terminal displays a screen of successful authentication to the user.

[1695] Step 3:

[1696] The terminal displays a character voice selection menu to the user. The user selects the desired character. The terminal sends the selected character information to the server. The input is the user's character selection, and the output is a notification that the character voice data has been loaded. The server obtains the character voice data and loads the necessary voice files. Once loading is complete, the terminal is notified.

[1697] Step 4:

[1698] The terminal activates a microphone, which is a voice input means, and waits for voice input from the user. The user speaks into the terminal. The input is the user's voice, and the output is recorded voice data. The terminal records this voice and transmits it to the server using a voice data transmission means.

[1699] Step 5:

[1700] The server converts the received voice data into text data using a voice recognition means. The input is voice data and the output is text data. The voice recognition means uses voice recognition technology to convert, for example, the voice saying "Please tell me today's homework" into the text "Please tell me today's homework."

[1701] Step 6:

[1702] The server passes the converted text data to the conversation generation means, which generates an appropriate response. The input is text data, and the output is response text. The conversation generation means utilizes a generative AI model to generate a natural language response based on the text data. For example, in response to the question, "What's today's homework for me?", the response generated is, "There are three math problems today. The first one is..."

[1703] Step 7:

[1704] The server converts the generated response text into character voice. The input is the response text and the output is voice data. The server uses the voice data of the selected character to convert the response text into voice data.

[1705] Step 8:

[1706] The server sends the converted voice data to the terminal. The terminal plays back the sent voice data. The input is the voice data, and the output is a voice response to the user. The terminal plays back in the character's voice, "Today we have three math problems. The first one is...", and conveys the response to the user.

[1707] These steps allow users to progress through learning interactively through dialogue with the character of their choice.

[1708] Furthermore, an emotion engine that estimates the user's emotion may be further combined. That is, the identification processing unit 290 may estimate the user's emotion using the emotion identification model 59, and perform identification processing using the user's emotion.

[1709] This invention is a system including a user authentication means, a character voice selection means, a voice input means, a voice data transmission means, a voice recognition means, a conversation generation means based on text data, a means for converting the generated conversation content into a character voice, a means for playing the converted voice data, and an emotion engine for recognizing the user's emotions. This system not only enables a user to learn or acquire information through conversation with a favorite character, but also provides appropriate responses according to the user's emotional state.

[1710] 1. System startup and user authentication

[1711] The server handles system startup, loading required resources and establishing database connections.

[1712] The terminal displays a login screen to the user, who then enters their login ID and password.

[1713] The terminal sends the entered information to the server. The server references the database and performs user authentication. If authentication is successful, a session is created and a message indicating successful authentication is sent to the terminal.

[1714] The device displays a successful authentication screen to the user.

[1715] 2. Character voice selection

[1716] The device displays a character voice selection menu to the user.

[1717] The user selects the desired character, and the device sends the selected character information to the server.

[1718] The server retrieves the character voice data, loads the necessary voice files, and notifies the device when the loading is complete.

[1719] 3. Speech Recognition and Speech Generation

[1720] The device activates the microphone and waits for voice input from the user.

[1721] The user speaks into the device (for example, "What's my homework for today?") and the device records the voice input.

[1722] The device sends the recorded voice data to the server, which uses voice recognition technology to convert the voice into text data (e.g., "Please tell me what my homework is today").

[1723] The server passes the converted text data to a conversation generation system, which generates an appropriate response (e.g., "There are three math problems today. The first one is...").

[1724] 4. Emotion Recognition by Emotion Engine

[1725] The server sends the voice data to the emotion engine.

[1726] The emotion engine extracts the user's emotional state from the voice data, for example recognizing emotions such as "happy," "sad," or "angry" from the tone of voice and choice of words.

[1727] The emotion engine passes the extracted emotion data to the conversation generation system, which then adjusts the response based on the emotion data. For example, if the user appears sad, it generates an encouraging response.

[1728] 5. Character voice response

[1729] The server converts the generated conversation content into voice using the character's voice data.

[1730] The server transmits the generated voice data to the terminal.

[1731] The device plays back the transmitted voice data, which then responds to the user in the character's voice (e.g., "There are three math problems today. They're a little tough, but let's do our best together!").

[1732] Specific examples

[1733] For example, when User A, a third-grade elementary school student, uses this system, the process will be as follows:

[1734] 1. Mr. A logs in to the system. He enters his ID and password to verify his identity and is authenticated.

[1735] 2. After logging in, Mr. A selects "Character X" on the character selection screen.

[1736] 3. Mr. A speaks to the device, saying, "Please tell me today's homework." The device records the voice and sends it to the server.

[1737] 4. The server performs speech recognition, converts it into text data, and generates a conversation. The speech data is then sent to the emotion engine, which extracts emotion data. For example, if Mr. A sounds happy, the conversation generation system generates a positive response such as, "That's great! Let's try it together."

[1738] 5. The server converts the generated content into audio data in the voice of Character X and sends it to the device.

[1739] 6. The device will play back in Character X's voice, "Today we have three math problems. They're a little difficult, but let's do our best together!"

[1740] In this way, the system can communicate information in an enjoyable and effective way through interactions between the user and the selected character, assisting learning and providing more personalized responses through emotion recognition.

[1741] The processing flow will be explained below.

[1742] Step 1:

[1743] The server handles system startup, loading required resources and establishing database connections.

[1744] Step 2:

[1745] The device presents the user with a login screen.

[1746] Step 3:

[1747] The user enters their login ID and password. The device sends the entered information to the server.

[1748] Step 4:

[1749] The server refers to the database and performs user authentication. If authentication is successful, it creates a session and sends a message to the terminal indicating that authentication was successful.

[1750] Step 5:

[1751] The device displays a successful authentication screen to the user.

[1752] Step 6:

[1753] The device displays a character voice selection menu to the user.

[1754] Step 7:

[1755] The user selects the desired character, and the device sends the selected character information to the server.

[1756] Step 8:

[1757] The server retrieves the character voice data, loads the necessary voice files, and notifies the device when the loading is complete.

[1758] Step 9:

[1759] The device activates the microphone and waits for voice input from the user.

[1760] Step 10:

[1761] The user speaks into the device (for example, "What's my homework for today?") and the device records the voice input.

[1762] Step 11:

[1763] The device sends the recorded audio data to the server.

[1764] Step 12:

[1765] The server uses voice recognition technology to convert the transmitted voice data into text data.

[1766] Step 13:

[1767] The server sends the text data to the emotion engine.

[1768] Step 14:

[1769] An emotion engine built into the server extracts the user's emotions from the voice data, for example, determining emotions from the tone and speed of the voice.

[1770] Step 15:

[1771] The emotion data extracted by the emotion engine is sent to the conversation generation system.

[1772] Step 16:

[1773] The server generates appropriate conversational content based on the emotion data. For example, if the user looks sad, it generates encouraging content (e.g., "Cheer up, let's do our best together!").

[1774] Step 17:

[1775] The server converts the generated conversation content into voice using the character's voice data.

[1776] Step 18:

[1777] The server transmits the generated voice data to the terminal.

[1778] Step 19:

[1779] The device plays back the transmitted audio data, and responds to the user in the character's voice (e.g., "There are three math problems today. They're a little tough, but let's do our best together!").

[1780] Example 2

[1781] Next, a description will be given of Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the robot 414 will be referred to as a "terminal."

[1782] Conventional voice dialogue systems have difficulty in properly recognizing the user's emotional state and generating responses that correspond to that emotion. Furthermore, they can only provide fixed responses, which limits the user experience and reduces the effectiveness of learning support and information acquisition. Furthermore, the dialogue provided by the character voices is weak, which fails to fully stimulate the user's interest and motivation.

[1783] The identification process by the identification processing unit 290 of the data processing device 12 in the second embodiment is realized by the following means. In this invention, the server includes a user authentication means, a character voice selection means, a voice input means, a voice data transmission means, a voice recognition means, a conversation generation means based on text data, a means for converting the generated conversation content into a character voice, a means for playing the converted voice data, and an emotion engine for recognizing the user's emotions. This enables an appropriate response according to the user's emotional state, and provides individually personalized dialogue. Furthermore, by responding with the voice of the selected character, the user's interest and motivation can be enhanced, improving the effectiveness of learning support and information acquisition.

[1784] "User authentication means" is a function that identifies and authenticates individuals by having the user enter an ID and password.

[1785] The "character voice selection means" is a function that allows the user to select the voice of the character they want and transmit that information to the system.

[1786] "Voice input means" is a function for detecting and recording the voice spoken by the user.

[1787] The "audio data transmission means" is a function for transmitting recorded audio data to the server.

[1788] The "voice recognition means" is a function that converts transmitted voice data into text data.

[1789] The "conversation generation means based on text data" is a function that generates an appropriate response based on the text data generated by the voice recognition means.

[1790] The "means for converting the generated conversation content into a character's voice" is a function for converting the generated conversation content into a voice using the voice data of the selected character.

[1791] The "means for reproducing converted audio data" is a function for reproducing data converted into audio.

[1792] The "emotion engine" is a function that extracts the user's emotional state from their voice data and analyzes that data.

[1793] This invention is a system including a user authentication means, a character voice selection means, a voice input means, a voice data transmission means, a voice recognition means, a conversation generation means based on text data, a means for converting the generated conversation content into a character voice, a means for playing the converted voice data, and an emotion engine. This system allows a user to learn and acquire information through conversation with a favorite character, and further, is capable of providing appropriate responses according to the user's emotional state.

[1794] System configuration and operation

[1795] The system consists of a server and a terminal. The server is responsible for key processes such as user authentication, voice recognition, conversation generation, emotion recognition, and voice conversion. The terminal acts as an interface with the user, providing functions such as voice input, voice playback, and character selection.

[1796] Hardware and software used

[1797] Server Hardware: High performance machine (e.g. Intel Xeon processor, 64GB RAM)

[1798] Server Software:

[1799] OS:Linux

[1800] Web framework: Django

[1801] Database: PostgreSQL

[1802] Speech Recognition API: Google Cloud Speech-to-Text

[1803] Emotion recognition engine: IBM Watson Tone Analyzer

[1804] Speech synthesis engine: Amazon Polly

[1805] Device hardware: PC or tablet, microphone, speakers

[1806] Terminal software:

[1807] Browser: Google Chrome, Mozilla Firefox

[1808] JavaScript library: React.js

[1809] Processing flow

[1810] When the system starts, the server loads the necessary resources and establishes a database connection. The terminal displays a login screen for the user, and the user enters their ID and password. The server refers to the database to authenticate the user, and if authentication is successful, it creates a session and sends a success message to the terminal.

[1811] The user selects the desired character from the character voice selection menu and sends this information to the server, which retrieves the character voice data and loads the voice file.

[1812] For speech recognition and conversation generation, the device activates the microphone and waits for voice input from the user. When the user speaks, the device records the audio and sends it to a server. The server uses the Google Cloud Speech-to-Text API to convert the audio into text data, which is then fed into a generative AI model (e.g., GPT-3) to generate an appropriate response.

[1813] The emotion engine extracts the user's emotional state from their voice and passes the extracted emotion data to the conversation generation system, which then tailors the responses to the user's current emotions. For example, if the user sounds sad, an encouraging response will be generated.

[1814] Finally, the server converts the generated conversation content into voice using the character voice data and transmits the voice data to the terminal, which then plays the voice data and responds to the user in the character's voice.

[1815] Specific examples

[1816] For example, if a third-grader asks the device, "What's my homework for today?", the system will act as follows:

[1817] 1. The device records the audio and sends it to the server.

[1818] 2. The server performs speech recognition and converts it into text data.

[1819] 3. The conversation generation system generates a response: "There are three math problems today."

[1820] 4. The emotion engine analyzes the user's emotions, and if the user appears to be having fun, it complements the response by saying, "Try your best to solve it."

[1821] 5. The server converts this response into voice using the character's voice data and sends it to the device.

[1822] 6. The device will play a character voice saying, "Today there are three math problems, let's do our best together!"

[1823] Prompt Sentence Examples

[1824] "Tell me about today's homework."

[1825] "How are you feeling right now?"

[1826] "Tell me the next step."

[1827] In this way, the system can provide personalized responses that also take into account the user's emotional state, thereby improving the effectiveness of learning support and information acquisition.

[1828] The flow of the identification process in the second embodiment will be described with reference to FIG.

[1829] Step 1:

[1830] The server starts the system, which includes loading the necessary resources and establishing a database connection. The server runs Linux and uses the Django framework to manage web applications. When the server starts, it connects to the database (PostgreSQL) and prepares the necessary tables and data. The input is the command to start the server, and the output is a startup completion message and the establishment of a database connection.

[1831] Step 2:

[1832] The device displays a login screen. The user enters their ID and password and clicks the "Login" button. The input is the user's ID and password, and the output is an HTTP request containing this information. The device's browser (Google Chrome or Mozilla Firefox) accepts this operation.

[1833] Step 3:

[1834] The terminal sends the entered login information to the server. The server compares the received ID and password with the database and performs authentication. The server verifies the user information using Django's authentication function. The input is the user ID and password, and the output is the authentication result (success or failure).

[1835] Step 4:

[1836] If the server is successful in authentication, it creates a session and sends a success message to the terminal. It uses Django's session management functionality to generate a session ID for the user. The input is the success message, and the output is the new session ID.

[1837] Step 5:

[1838] The device displays an authentication success screen to the user. JavaScript is used to dynamically update the screen and show the user a successful authentication message. The input is the successful authentication message sent by the server, and the output is the successful authentication screen visible to the user.

[1839] Step 6:

[1840] The device displays a character voice selection menu. The user selects the desired character. The input is the user's selection, and the output is an HTTP request containing the selected character information. The selection menu is displayed using React.js.

[1841] Step 7:

[1842] The device sends the selected character information to the server. The server retrieves the character's voice data and loads the voice file. Django processes the HTTP request and loads the voice file for the selected character from the database. The input is the selected character information, and the output is the loaded voice file.

[1843] Step 8:

[1844] The device activates the microphone and waits for the user's voice input. The microphone is controlled using JavaScript's Audio API. The input triggers the microphone activation, and the output is in a voice-waiting state. The user speaks, saying something like, "Tell me about today's homework."

[1845] Step 9:

[1846] The device records what the user says and sends the audio data to the server. The recorded data is saved in WAV format and sent to the server. The input is the user's voice data, and the output is a WAV audio file.

[1847] Step 10:

[1848] The server uses speech recognition technology to convert the recorded voice data into text data. The Google Cloud Speech-to-Text API is used to analyze the voice data and convert it into text. The input is a WAV format audio file, and the output is text data.

[1849] Step 11:

[1850] The server passes the text data to a conversation generation system, which uses a generative AI model (e.g., GPT-3) to generate an appropriate response. The input is the converted text data, and the output is the generated response text.

[1851] Step 12:

[1852] The server sends the voice data to the emotion engine to extract the user's emotional state. The emotion data is generated using IBM Watson's Tone Analyzer. The input is voice data, and the output is emotion data.

[1853] Step 13:

[1854] The server passes the extracted emotion data to the conversation generation system, which then checks and adjusts the response. The response is adjusted based on the emotion data. The input is emotion data, and the output is the adjusted response text.

[1855] Step 14:

[1856] The server converts the tailored response into speech using the voice data of the selected character. It uses Amazon Polly for speech synthesis. The input is the response text and the output is an audio file.

[1857] Step 15:

[1858] The server sends the generated audio file to the terminal. The input is the generated audio file, and the output is an HTTP response with the audio file.

[1859] Step 16:

[1860] Plays an audio file received by the device. It uses the JavaScript Audio object to play the audio and responds to the user in a character's voice. The input is the generated audio file, and the output is the audio that is played.

[1861] By dividing the process flow into detailed sections like this, it becomes clear how each step works, and what data is input and output, making it easier to understand specific embodiments of the invention.

[1862] (Application example 2)

[1863] Next, a description will be given of Application Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the robot 414 will be referred to as a "terminal."

[1864] Conventional voice dialogue systems often generate uniform responses without considering the user's emotional state. This makes it difficult to provide personalized dialogue that is sensitive to the user's emotions, which can increase user stress, especially in the workplace. Another issue is insufficient integration with smart devices, making various operations cumbersome.

[1865] The specific processing by the specific processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means. In this invention, the server includes a user authentication means, a character voice selection means, a voice input means, a voice data transmission means, a voice recognition means, a conversation generation means based on text data, a means for converting the generated conversation content into a character voice, a means for playing the converted voice data, an emotion recognition means for recognizing the emotional state of the user, a means for adjusting the conversation content based on the recognized emotional state, and a display means of the smart device. This enables personalized responses according to the user's emotions, improves the quality of conversations at the workplace, and reduces user stress.

[1866] "User authentication means" is a function that verifies the ID and password of users accessing the system and confirms the legitimacy of the users.

[1867] The "character voice selection means" is a function that allows the user to select the voice of the character to be used in the dialogue.

[1868] "Voice input means" refers to a function for receiving voice from the user, and typically includes a microphone.

[1869] The "voice data transmission means" is a function for transmitting collected voice data to a server.

[1870] The "voice recognition means" is a function that analyzes transmitted voice data and converts the content into text data.

[1871] The "conversation generation means based on text data" is a function that generates appropriate response content based on text data that has been speech-recognized.

[1872] The "means for converting the generated conversation content into character voice" is a function for converting the conversation content generated in text into voice using voice data of a pre-selected character.

[1873] "Means for playing converted voice data" is a function for playing data converted into a character's voice so that the user can hear it.

[1874] The "emotion recognition means for recognizing the user's emotional state" is a function for extracting the user's emotional state from the user's voice data or other input.

[1875] The "means for adjusting the content of the conversation based on the recognized emotional state" is a function for adjusting the content of the generated response based on the user's emotion detected by the emotion recognition means.

[1876] The "display means of the smart device" refers to a device for displaying information and operation screens of the interactive system, and typically includes smart glasses, tablets, etc.

[1877] System Overview

[1878] This invention is a system that enables users to communicate through character voices by wearing a smart device and operating it with voice. The system mainly uses a server, a smart device (such as smart glasses or a tablet), a microphone for user input, a speaker for voice playback, and software for emotion recognition.

[1879] Program Structure Overview

[1880] The system consists of a program with the following main functions:

[1881] 1. User Authentication

[1882] 2. Character voice selection

[1883] 3. Speech Recognition and Speech Generation

[1884] 4. Emotion recognition

[1885] 5. Voice Response

[1886] Processing flow and technologies used

[1887] 1. User Authentication

[1888] The server receives the user ID and password sent from the smart device and authenticates the user by referencing the database, thereby preventing unauthorized access and providing services to the appropriate user.

[1889] Required Hardware / Software:

[1890] Database server (MySQL, etc.)

[1891] Authentication Server

[1892] Smart Devices

[1893] 2. Character voice selection

[1894] The smart device displays multiple character voice options to the user, the user selects the desired character, and the selection data is sent to the server, which loads the voice data for the selected character and notifies the smart device.

[1895] Required Hardware / Software:

[1896] Smart devices (smart glasses, tablets, etc.)

[1897] server

[1898] 3. Speech Recognition and Speech Generation

[1899] When a user speaks into a smart device, the microphone records the audio. The recording is sent to a server where it is converted into text using speech recognition technology (such as the Google Speech-to-Text API). This text is then passed to a generative AI model (such as GPT-3.5 Turbo) to generate an appropriate response.

[1900] Required Hardware / Software:

[1901] microphone

[1902] server

[1903] Speech Recognition API

[1904] Generative AI Models

[1905] 4. Emotion recognition

[1906] The converted text data is passed to emotion recognition software (such as DistilRoBERTa) to analyze the user's emotional state. The server then adjusts the generated response content based on the emotional data and selects an appropriate response.

[1907] Required Hardware / Software:

[1908] server

[1909] Emotion Recognition Model

[1910] 5. Voice Response

[1911] The adjusted response content is converted into voice using the character voice data and transmitted to the smart device, which responds to the user in the character's voice using a speaker.

[1912] Required Hardware / Software:

[1913] Smart device (with built-in speaker)

[1914] server

[1915] Specific examples

[1916] For example, suppose a factory worker wears smart glasses and asks, "What's the current status of the production line?" In this case, the system first performs speech recognition and passes the text data to the generative AI model. The generative AI model generates a response such as, "The current production line is running smoothly. The production rate is 80%." If the model then performs emotion recognition and determines that the user is satisfied, it will convey this in a positive tone. The system then converts this text into speech in a character's voice and conveys it to the user.

[1917] Prompt Sentence Examples

[1918] User is interested. Please tell me the current status of the production line.

[1919] In this way, the system can provide personalized responses according to the user's emotions, improving the user experience at the workplace.

[1920] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[1921] Step 1:

[1922] The user starts up the smart device and accesses the login screen. The user enters their login ID and password. The device sends this information to the server, which then refers to the database to authenticate the user. If authentication is successful, a message indicating successful authentication is sent to the device, and a screen indicating successful authentication is displayed to the user.

[1923] Input: Login ID, Password

[1924] Data processing / calculation: Verification of authentication data (database reference)

[1925] Output: Authentication success message

[1926] Step 2:

[1927] After the user logs in, the device displays a character voice selection menu. The user selects the desired character, and that information is sent from the device to the server. The server retrieves the voice data for the selected character and notifies the device when the required voice files have been loaded. The device then informs the user that it is ready to play.

[1928] Input: Character selection information

[1929] Data processing / calculation: Acquiring and loading audio data

[1930] Output: Playback ready notification

[1931] Step 3:

[1932] The user speaks into the device. The device's microphone records the voice and sends the voice data to the server. The server uses voice recognition technology to convert the voice data into text data. For example, a user's speech such as "Tell me about the current status of the production line" is converted into text data.

[1933] Input: Audio data

[1934] Data processing / calculation: Speech recognition (voice to text conversion)

[1935] Output: Text data

[1936] Step 4:

[1937] The server passes the converted text data to the emotion recognition means, which extracts the user's emotional state from the voice and text data. For example, if the user's voice sounds happy, it will be recognized as "positive."

[1938] Input: Text data, audio data

[1939] Data processing / calculation: Emotion recognition (emotion data extraction)

[1940] Output: Emotion data

[1941] Step 5:

[1942] The server generates a response using a conversation generation system based on the text data and emotional data. A generative AI model (such as GPT-3.5 Turbo) generates an appropriate response. For example, if the user's question is "What is the current status of the production line?" and the emotional state is "positive," the server generates a response such as "The current production line is going smoothly. The production rate is 80%."

[1943] Input: Text data, emotion data

[1944] Data processing / calculation: Response generation (generative AI model)

[1945] Output: The generated text response

[1946] Step 6:

[1947] The generated text response is converted into voice using the voice data of the selected character, and the server converts the text response into voice data and transmits it to the terminal.

[1948] Input: Generated text response, character voice data

[1949] Data processing / calculation: Text to speech conversion

[1950] Output: Audio data

[1951] Step 7:

[1952] The terminal plays the received audio data, and the user receives a response in the voice of the character they selected. For example, the character's voice may say, "The current production line is running smoothly. The production rate is 80%."

[1953] Input: Audio data

[1954] Data processing / calculation: Audio playback

[1955] Output: Playback of a response to the user

[1956] The specific processing unit 290 transmits the result of the specific processing to the robot 414. In the robot 414, the control unit 46A causes the speaker 240 and the control target 443 to output the result of the specific processing. The microphone 238 acquires voice indicating a user input regarding the result of the specific processing. The control unit 46A transmits voice data indicating the user input acquired by the microphone 238 to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the voice data.

[1957] The data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of the data generation model 58 is ChatGPT (Internet Search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search <url: https: gemini.google.com ?hl="ja">) and other generation AIs. The data generation model 58 is obtained by performing deep learning on a neural network. A prompt including an instruction is input to the data generation model 58, and inference data such as voice data indicating voice, text data indicating text, and image data indicating an image is also input. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt, and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[1958] In the above embodiment, an example was given in which the specific processing is performed by the data processing device 12, but the technology of the present disclosure is not limited to this, and the specific processing may be performed by the robot 414.

[1959] The emotion identification model 59 as an emotion engine may determine the user's emotion according to a specific mapping. Specifically, the emotion identification model 59 may determine the user's emotion according to an emotion map (see FIG. 9), which is a specific mapping. Similarly, the emotion identification model 59 may determine the robot's emotion, and the identification processing unit 290 may perform identification processing using the robot's emotion.

[1960] FIG. 9 is a diagram illustrating an emotion map 400 on which multiple emotions are mapped. In the emotion map 400, emotions are arranged in concentric circles radiating from the center. Emotions closer to the center of the concentric circles are more primitive. Emotions representing states and actions arising from a state of mind are arranged on the outer edges of the concentric circles. The concept of emotion includes both affect and mental states. Emotions generally generated from reactions occurring in the brain are arranged on the left side of the concentric circles. Emotions generally induced by situational judgment are arranged on the right side of the concentric circles. Emotions generally generated from reactions occurring in the brain and induced by situational judgment are arranged on the upper and lower sides of the concentric circles. Furthermore, the emotion of "pleasure" is arranged on the upper side of the concentric circles, and the emotion of "discomfort" is arranged on the lower side. In this way, in the emotion map 400, multiple emotions are mapped based on the structure by which emotions are generated, and emotions that tend to occur simultaneously are mapped close to each other.

[1961] These emotions are distributed in the 3 o'clock direction on emotion map 400, and typically fluctuate between relief and anxiety. In the right half of emotion map 400, situational awareness dominates over internal sensations, resulting in a sense of calm.

[1962] The inside of emotion map 400 represents what is going on in the mind, and the outside of emotion map 400 represents behavior, so the further you go outside emotion map 400, the more visible the emotions become (the more they are expressed in behavior).

[1963] Human emotions are based on various balances, such as posture and blood sugar levels. When these balances deviate from the ideal, a state of discomfort is indicated, and when they approach the ideal, a state of pleasure is indicated. Emotions can also be created for robots, automobiles, and motorcycles, based on various balances, such as posture and remaining battery life. When these balances deviate from the ideal, a state of discomfort is indicated, and when they approach the ideal, a state of pleasure is indicated. An emotion map can be generated, for example, based on Dr. Mitsuyoshi's emotion map (Research on Voice Emotion Recognition and Emotional Brain Physiological Signal Analysis Systems, Tokushima University, Doctoral Dissertation: https: / / ci.nii.ac.jp / naid / 500000375379). The left half of the emotion map lists emotions belonging to the "reaction" domain, where sensation is dominant. The right half of the emotion map lists emotions belonging to the "situation" domain, where situational awareness is dominant.

[1964] The emotion map defines two emotions that promote learning. One is a negative emotion on the situation side, around the middle of "repentance" or "reflection." In other words, this occurs when the robot experiences negative emotions such as "I never want to feel this way again" or "I don't want to be scolded again." The other is a positive emotion on the response side, around "desire." In other words, this occurs when the robot experiences positive feelings such as "I want more" or "I want to know more."

[1965] The emotion identification model 59 inputs user input into a pre-trained neural network, obtains emotion values ​​indicating each emotion shown in the emotion map 400, and determines the user's emotion. This neural network is pre-trained based on multiple pieces of training data that are combinations of user input and emotion values ​​indicating each emotion shown in the emotion map 400. Furthermore, this neural network is trained so that emotions that are located close to each other have similar values, as in the emotion map 900 shown in FIG. 10. FIG. 10 shows an example in which multiple emotions, "relieved," "calm," and "reassuring," have similar emotion values.

[1966] The system according to the present disclosure has been described above mainly with respect to the functions of the data processing device 12, but the system according to the present disclosure is not necessarily implemented on a server. The system according to the present disclosure may be implemented as a general information processing system. The present disclosure may be implemented, for example, as a software program running on a personal computer or an application running on a smartphone, etc. The method according to the present disclosure may be provided to users in the form of SaaS (Software as a Service).

[1967] In the above embodiment, an example was given in which the specific processing is performed by one computer 22, but the technology of the present disclosure is not limited to this, and the specific processing may be distributed and performed by a plurality of computers including the computer 22. For example, the data generation model 58 may be provided in an external device of the data processing device 12, and data may be generated in the external device in accordance with input data.

[1968] In the above embodiment, an example in which the specific processing program 56 is stored in the storage 32 has been described, but the technology of the present disclosure is not limited to this. For example, the specific processing program 56 may be stored in a portable, computer-readable, non-transitory storage medium such as a USB (Universal Serial Bus) memory. The specific processing program 56 stored in the non-transitory storage medium is installed in the computer 22 of the data processing device 12. The processor 28 executes the specific processing in accordance with the specific processing program 56.

[1969] 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.

[1970] It is not necessary to store all of the specific processing program 56 in a storage device such as a server connected to the data processing device 12 via the network 54, or to store all of the specific processing program 56 in the storage 32; only a portion of the specific processing program 56 may be stored.

[1971] The hardware resource for executing a specific process can be any of the following processors: An example of a processor is a CPU, which is a general-purpose processor that functions as a hardware resource for executing a specific process by executing software, i.e., a program. Another example of a processor is a dedicated electrical circuit, such as an FPGA (Field-Programmable Gate Array), a PLD (Programmable Logic Device), or an ASIC (Application Specific Integrated Circuit), which is a processor with a circuit configuration designed specifically for executing a specific process. Each processor has built-in or connected memory, and each processor uses the memory to execute the specific process.

[1972] The hardware resource that executes the specific processing may be configured with one of these various processors, or may be configured with a combination of two or more processors of the same or different types (for example, a combination of multiple FPGAs, or a combination of a CPU and an FPGA). Also, the hardware resource that executes the specific processing may be a single processor.

[1973] As an example of a system configured with a single processor, first, one processor is configured by combining one or more CPUs and software, and this processor functions as a hardware resource that executes a specific process. Second, there is a system that uses a processor that realizes the functions of an entire system including multiple hardware resources that execute a specific process on a single IC chip, as typified by SoC (System-on-a-chip). In this way, a specific process is realized using one or more of the above-mentioned various processors as hardware resources.

[1974] Furthermore, the hardware structure of these various processors can be, more specifically, an electric circuit that combines circuit elements such as semiconductor devices. The specific processing described above is merely an example. Therefore, it goes without saying that unnecessary steps may be deleted, new steps may be added, or the processing order may be rearranged, without departing from the spirit of the invention.

[1975] The above-described description and illustrations are a detailed explanation of the parts related to the technology of the present disclosure and are merely an example of the technology of the present disclosure. For example, the above description of the configuration, functions, actions, and effects is an explanation of an example of the configuration, functions, actions, and effects of the parts related to the technology of the present disclosure. Therefore, it goes without saying that unnecessary parts may be deleted, new elements may be added, or replacements may be made to the above-described description and illustrations within the scope of the gist of the technology of the present disclosure. Furthermore, to avoid confusion and facilitate understanding of the parts related to the technology of the present disclosure, the above-described description and illustrations omit explanations of common technical knowledge that do not require particular explanation to enable the implementation of the technology of the present disclosure.

[1976] All publications, patent applications, and technical standards mentioned in this specification are herein incorporated by reference to the same extent as if each individual publication, patent application, or technical standard was specifically and individually indicated to be incorporated by reference.

[1977] The following is further disclosed regarding the above embodiment.

[1978] (Claim 1)

[1979] A user authentication means;

[1980] a character voice selection means;

[1981] A voice input means;

[1982] audio data transmitting means;

[1983] a voice recognition means;

[1984] A conversation generation means based on text data;

[1985] A means for converting the generated conversation content into character voice;

[1986] means for playing the converted audio data;

[1987] A system including:

[1988] (Claim 2)

[1989] 2. The system according to claim 1, wherein the means for converting the generated conversation content into character voice utilizes voice data of a selected character.

[1990] (Claim 3)

[1991] 10. The system of claim 1, wherein the audio input means includes a microphone.

[1992] "Example 1"

[1993] (Claim 1)

[1994] A user authentication means;

[1995] a character voice selection means;

[1996] A voice input means;

[1997] audio data transmitting means;

[1998] a voice recognition means;

[1999] A conversation generation means based on text data;

[2000] A means for converting the generated conversation content into character voice;

[2001] means for playing the converted audio data;

[2002] A means of loading required resources and establishing database connections at system startup;

[2003] means for generating a session and transmitting a message of successful authentication to the terminal if the authentication is successful;

[2004] A means for the terminal to acquire and load voice data of the corresponding character from the server;

[2005] a means for generating conversational content for a generative AI model using the prompt sentence;

[2006] A system including:

[2007] (Claim 2)

[2008] 2. The system according to claim 1, wherein the means for converting the generated conversation content into character voice utilizes voice data of a selected character.

[2009] (Claim 3)

[2010] 10. The system of claim 1, wherein the audio input means includes a microphone.

[2011] "Application Example 1"

[2012] (Claim 1)

[2013] A user authentication means;

[2014] a character voice selection means;

[2015] A voice input means;

[2016] audio data transmitting means;

[2017] a voice recognition means;

[2018] A conversation generation means based on text data;

[2019] A means for converting the generated conversation content into character voice;

[2020] means for playing the converted audio data;

[2021] Interactive learning support tools to effectively learn the content,

[2022] A system including:

[2023] (Claim 2)

[2024] 2. The system according to claim 1, wherein the means for converting the generated conversation content into character voice utilizes voice data of a selected character.

[2025] (Claim 3)

[2026] 10. The system of claim 1, wherein the audio input means includes a microphone.

[2027] (Claim 4)

[2028] 2. The system according to claim 1, wherein the interactive learning support means for effectively learning the learning content converts the voice input by the user into text data and generates an appropriate response.

[2029] (Claim 5)

[2030] 2. The system according to claim 1, wherein said interactive learning support means reproduces audio data in the voice of a character.

[2031] (Claim 6)

[2032] 2. The system according to claim 1, wherein the interactive learning support means provides an environment in which the user can learn in an enjoyable and interactive manner based on conversation content generated using a natural language generation model.

[2033] "Example 2: Combining Emotion Engines"

[2034] (Claim 1)

[2035] A user authentication means;

[2036] a character voice selection means;

[2037] A voice input means;

[2038] audio data transmitting means;

[2039] a voice recognition means;

[2040] A conversation generation means based on text data;

[2041] A means for converting the generated conversation content into character voice;

[2042] means for playing the converted audio data;

[2043] The system includes an emotion engine that recognizes the user's emotions.

[2044] (Claim 2)

[2045] 2. The system according to claim 1, wherein the means for converting the generated conversation content into character voice utilizes voice data of a selected character.

[2046] (Claim 3)

[2047] 10. The system of claim 1, wherein the audio input means includes a microphone.

[2048] "Application example 2 when combining emotion engines"

[2049] (Claim 1)

[2050] A user authentication means;

[2051] a character voice selection means;

[2052] A voice input means;

[2053] audio data transmitting means;

[2054] a voice recognition means;

[2055] A conversation generation means based on text data;

[2056] A means for converting the generated conversation content into character voice;

[2057] means for playing the converted audio data;

[2058] emotion recognition means for recognizing an emotional state of a user;

[2059] means for adjusting the content of the conversation based on the perceived emotional state;

[2060] a display means of the smart device;

[2061] A system including:

[2062] (Claim 2)

[2063] 2. The system according to claim 1, wherein the means for converting the generated conversation content into character voice utilizes voice data of a selected character.

[2064] (Claim 3)

[2065] 10. The system of claim 1, wherein the audio input means includes a microphone. [Explanation of symbols]

[2066] 10, 210, 310, 410 Data Processing Systems 12 Data Processing Device 14 Smart Devices 214 Smart Glasses 314 Headset-type terminal 414 Robot< / url:> < / url:> < / url:> < / url:>

Claims

1. A user authentication means; a character voice selection means; A voice input means; audio data transmitting means; a speech recognition means; A conversation generation means based on text data; A means for converting the generated conversation content into character voice; means for playing the converted audio data; A system including:

2. 2. The system according to claim 1, wherein the means for converting the generated conversation content into character voice utilizes voice data of a selected character.

3. 2. The system of claim 1, wherein said audio input means includes a microphone.

Images