system

Abstract

Provide a system. [Solution] means for storing user information based on characteristics and preferences; A means for generating an optimal conversation scenario based on the stored user information; a means for converting the generated conversation scenario into voice data; means for receiving voice input from a user and converting it into text data; A means for analyzing the content of a user's utterance and generating an appropriate response; means for converting the generated response back into voice data and outputting it to the user; A system that includes a means for storing the dialogue content in a database and using it as future learning data.

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] Current speech recognition and dialogue systems have the problem that they can only provide general responses to users and are unable to facilitate personalized coaching based on individual personalities and preferences. Furthermore, conventional systems rely on text-based interfaces, making it difficult to encourage self-reflection through natural conversation. As a result, they are unable to provide effective support that will encourage users to continue using them. [Means for solving the problem]

[0005] The system of the present invention solves the above-mentioned problems by including the following means.

[0006] A way to store user information based on personality and preferences

[0007] A method for generating optimal conversation scenarios based on saved user information

[0008] A means of converting the generated conversation scenario into voice data

[0009] A means of receiving voice input from the user and converting it into text data

[0010] A means of analyzing what users say and generating appropriate responses

[0011] A means for converting the generated response back into voice data and outputting it to the user

[0012] A means of storing dialogue content in a database and using it as learning data for the future

[0013] This makes it possible to provide personalized voice coaching to users and encourage self-reflection through a natural conversational format. Furthermore, by providing optimized voice based on user information, it is possible to provide a more individualized and engaging experience for users. Furthermore, by analyzing the user's voice in real time and providing feedback, it is possible to provide effective support for achieving the user's goals.

[0014] The "means for storing user information based on personality and preferences" refers to a method and device for acquiring individual information such as a user's personality, preferences, areas of interest, etc., and storing it in a database.

[0015] "Means for generating optimal conversation scenarios based on stored user information" refers to a method and device for automatically generating conversation content and scenarios that match the user's needs and goals based on stored user information.

[0016] The "means for converting the generated conversation scenario into voice data" refers to a method and apparatus for converting the generated conversation scenario from text format to voice format and providing a user with natural voice interaction.

[0017] The "means for receiving speech input from a user and converting it into text data" refers to a method and apparatus for receiving speech uttered by a user and converting it into text form.

[0018] The "means for analyzing the content of a user's utterances and generating an appropriate response" refers to a method and device for analyzing the content of a user's utterances converted into text using natural language processing technology and generating an optimal response to it.

[0019] The "means for converting the generated response back into voice data and outputting it to the user" refers to a method and apparatus for converting the generated response back from text format to voice format and playing back the voice to the user.

[0020] "Means for storing dialogue content in a database and using it as future learning data" refers to a method and device for storing all dialogue content in a database and using that data as learning data for an AI model in subsequent dialogues.

[0021] "Means for optimizing voice based on user information" refers to a method and device for adjusting the characteristics of the voice used (for example, tone and speed) according to the user's personality and preferences.

[0022] The "means for analyzing voice interaction in real time and providing appropriate feedback" refers to a method and apparatus for analyzing a user's voice input in real time and providing appropriate feedback immediately based on the analysis results. [Brief explanation of the drawings]

[0023] [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

[0024] 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.

[0025] First, the terms used in the following description will be explained.

[0026] 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).

[0027] 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.

[0028] 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.

[0029] 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.

[0030] 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."

[0031] [First embodiment]

[0032] FIG. 1 shows an example of the configuration of a data processing system 10 according to the first embodiment.

[0033] 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.

[0034] 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).

[0035] 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.

[0036] 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.

[0037] 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.

[0038] 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.

[0039] FIG. 2 shows an example of the main functions of the data processing device 12 and the smart device 14.

[0040] 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.

[0041] 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.

[0042] 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.

[0043] 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."

[0044] The system of the present invention provides personalized voice interactive coaching based on individual characteristics and preferences. The following description will explain the overall flow of the system and the program's processing in detail with specific examples.

[0045] 1. User Registration

[0046] To use the system, a user launches the application and enters the required information, such as name, age, interests, and goals.

[0047] The terminal receives this information and transmits it to the server.

[0048] The server stores the submitted information in a database and creates a personalized profile for each user.

[0049] 2. Conversation scenario generation

[0050] The server generates optimal conversation scenarios based on registered user information. These scenarios are created using AI models based on the user's goals and interests.

[0051] For example, if a user is looking to "advance their career," the server might generate the question, "What was particularly challenging about your recent project?"

[0052] 3. Speech Synthesis

[0053] The server passes the generated text scenario to a speech synthesis engine, which converts the text into speech.

[0054] At this time, the voice characteristics (e.g., youthful voice, calm voice) are optimized according to the user's preferences.

[0055] The synthesized voice data is stored in a cache for the user ID.

[0056] 4. Starting a voice conversation

[0057] The user presses the "Start voice interaction" button within the application to start the voice interaction.

[0058] The device activates the microphone and begins receiving voice input from the user.

[0059] When the user speaks to the coach, the terminal collects the voice data and sends it to the server.

[0060] 5. Real-time processing and feedback

[0061] The server analyzes the received voice data in real time and converts it into text using a voice recognition engine.

[0062] The server analyzes this text using natural language processing (NLP) technology to understand the user's intention.

[0063] For example, if a user says, "I'd like to talk about the difficulties I had in a recent project," the server generates an appropriate response: "What specifically were the difficulties?"

[0064] The server converts this response into voice using a voice synthesis engine and sends the voice data to the terminal.

[0065] The terminal plays the audio data to the user and waits for the next audio input.

[0066] 6. Data feedback and learning

[0067] After the conversation is over, the server stores all conversation content (voice, text data, and NLP analysis results) in a database.

[0068] The saved data is used as training data for future AI models. This continuous learning allows the system to provide more accurate coaching in the next interaction.

[0069] As a concrete example, if a user sets a goal of "I want to be successful as the leader of the next project," the system will use this information to generate questions that delve deeper into the user's current situation and challenges, and provide these questions via voice. If the user says, "I'd like to talk about the difficulties I had in today's meeting," a response such as "What were the difficulties? Please tell us the specific situation" will be generated in real time and returned to the user via voice. This process allows the user to organize their own challenges and promote introspection.

[0070] The above is a specific embodiment for carrying out the present invention. This system makes it possible to provide natural, personalized, and interactive voice coaching that goes beyond conventional text-based interfaces.

[0071] The processing flow will be explained below.

[0072] Step 1:

[0073] To use the system, a user launches the application and enters required information such as name, age, areas of interest, and goals.

[0074] Step 2:

[0075] The terminal obtains the information entered by the user and sends it to the server.

[0076] Step 3:

[0077] The server stores the received user information in a database, which creates a user profile.

[0078] Step 4:

[0079] The server uses an AI model based on the saved user information to generate optimal conversation scenarios. For example, if a user is interested in career advancement, it generates a scenario such as, "What particular challenges did you face in your recent project?"

[0080] Step 5:

[0081] The server passes the generated conversation scenario to a speech synthesis engine, which converts the text into speech data, optimizing the voice characteristics (e.g., youthful voice, calm voice) based on the user's preferences.

[0082] Step 6:

[0083] When the user presses the "Start Voice Dialogue" button, the terminal activates the microphone and starts voice input.

[0084] Step 7:

[0085] When the user speaks to the coach, the device collects and temporarily stores the voice data, and then transmits the stored voice data to the server.

[0086] Step 8:

[0087] The server analyzes the received voice data using a voice recognition engine and converts it into text data.

[0088] Step 9:

[0089] The server analyzes the text data using natural language processing (NLP) technology to understand the user's intent. Based on the analysis results, it generates an appropriate response. For example, if a user says, "I'd like to talk about the difficulties I faced in a recent project," it generates a response such as, "What specifically were the difficulties you faced?"

[0090] Step 10:

[0091] The server passes the generated response to a speech synthesis engine, converts the text into voice data, and transmits the voice data to the terminal.

[0092] Step 11:

[0093] The terminal reproduces the voice data received from the server and allows the user to hear the response.

[0094] Step 12:

[0095] The user listens to the audio playback and, if necessary, speaks again, and the process repeats.

[0096] Step 13:

[0097] After the conversation is over, the server stores all of the conversation content (voice, text data, and NLP analysis results) in a database. This not only serves as a reference for future conversations, but also serves as training data for the AI ​​model.

[0098] By repeating each of the above steps, it is possible to provide individually optimized conversations for each user and achieve coaching that encourages self-reflection.

[0099] Example 1

[0100] 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."

[0101] Conventional voice dialogue systems provide uniform responses to users, making it difficult to provide personalized responses that reflect individual personalities and preferences. Furthermore, they lacked a mechanism for continuously accumulating and learning from dialogue data with users to provide more appropriate feedback for the next dialogue. This limited users' opportunities to receive truly useful coaching.

[0102] 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.

[0103] In this invention, the server includes means for storing user information based on personality and preferences, means for generating an optimal conversation scenario based on the stored user information, and means for converting the generated conversation scenario into voice data. This makes it possible to provide personalized voice dialogue and coaching to each user and support their continuous growth.

[0104] "Means of saving user information based on personality and preferences" refers to the function of saving information entered by the user, such as name, age, areas of interest, and goals, and creating a profile for each user.

[0105] "Means for generating an optimal conversation scenario based on stored user information" refers to a function for generating an optimal conversation scenario that corresponds to the user's goals and interests based on stored user information.

[0106] The "means for converting the generated conversation scenario into voice data" refers to a voice synthesis function that converts the generated text-format conversation scenario into voice data.

[0107] "Means for receiving voice input from the user and converting it into text data" refers to a voice recognition function that converts the voice spoken by the user into text data.

[0108] "Means for analyzing the content of user comments and generating appropriate responses" refers to a natural language processing function that analyzes the content of user comments and generates appropriate responses based on that content.

[0109] "Means for converting the generated response back into voice data and outputting it to the user" refers to a voice output function that converts the generated text response into voice data and provides it to the user.

[0110] "Means of saving the content of the dialogue in a database and using it as future learning data" refers to the function of saving records of dialogue with users in a database and using that data as learning data for the AI ​​model.

[0111] "Means for optimizing voice characteristics based on user information" refers to a function that adjusts the characteristics of synthesized voice (e.g., voice pitch and speed) according to the user's preferences.

[0112] "Means for improving model accuracy by continuously saving and learning from dialogue content" refers to a function that continuously accumulates dialogue data with users and uses that data to retrain the AI ​​model, thereby improving the accuracy of the model.

[0113] "Means for analyzing voice dialogue in real time and providing appropriate feedback" refers to a function for analyzing voice dialogue in real time and quickly providing appropriate feedback in response to user comments.

[0114] "Means for understanding the intention of a user's speech using natural language processing technology" refers to a function that uses natural language processing technology to analyze the content of a user's speech and accurately understand their intention.

[0115] The system of the present invention provides personalized voice interactive coaching based on an individual's personality and preferences. Detailed embodiments of the system are described below.

[0116] 1. User Registration

[0117] The user launches a dedicated application and enters the necessary information, such as their name, age, areas of interest, and goals. The entered information is sent to the server by the device. The server stores the received information in a database and creates a personalized profile for each user. For example, MySQL (registered trademark) is used as the database, and user information is stored in a "Users" table.

[0118] 2. Conversation scenario generation

[0119] The server retrieves user information from a database and generates an optimal conversation scenario. This generation uses a generative AI model (e.g., GPT-3 (registered trademark)). If the user's goal is "career advancement," the server generates questions such as, "What was particularly challenging about your recent project?"

[0120] 3. Speech Synthesis

[0121] The server passes the generated text scenario to a speech synthesis engine (e.g., Google® Text-to-Speech API) to convert the text into speech data. The server optimizes the voice characteristics, such as a youthful voice or a calm voice, according to the user's preferences. The synthesized speech data is stored in a cache system (e.g., Redis).

[0122] 4. Starting a voice conversation

[0123] The user presses the "Start voice interaction" button in the application to start the voice interaction. The device activates the microphone and starts the user's voice input. As the user speaks, the voice data is sent from the device to the server.

[0124] 5. Real-time processing and feedback

[0125] The server analyzes the received voice data in real time and converts it into text using a voice recognition engine (e.g., IBM Watson (registered trademark) Speech to Text). The converted text data is analyzed using natural language processing (NLP) technology (e.g., Google Dialogflow) to understand the user's intention. For example, if the user says, "I'd like to talk about the difficulties I had in a recent project," the server generates an appropriate response such as, "What specifically were the difficulties you had?" This response is again converted into speech using a speech synthesis engine and sent to the device. The device plays the voice data to the user and waits for the next voice input.

[0126] 6. Data feedback and learning

[0127] Once the conversation is over, the server stores all conversation content (voice, text, NLP analysis results, etc.) in a database. This data is used as training data for future AI models. Continuous learning allows the system to provide more accurate coaching in the next conversation.

[0128] As a concrete example, if a user sets a goal of "I want to be successful as the leader of the next project," the system can use this information to generate questions that delve deeper into the user's current situation and challenges, and provide these questions via voice. If the user says, "I'd like to talk about the difficulties I had in today's meeting," a response such as "What were the difficulties you had? Please tell us the specific situation" is generated in real time and returned as voice. This process allows the user to organize their own challenges and promote introspection.

[0129] An example of a prompt for a generative AI model is:

[0130] "Generate an appropriate response when a user says, 'I'd like to talk about something I struggled with in today's meeting.'"

[0131] The above is a specific embodiment for carrying out the present invention. This system makes it possible to provide natural, personalized, and interactive voice coaching that goes beyond conventional text-based interfaces.

[0132] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0133] Step 1: Collect user information

[0134] The user starts the dedicated application and enters information such as their name, age, areas of interest, and goals.

[0135] Input: Information entered by the user, such as name, age, interests, goals, etc.

[0136] The terminal receives the input information and stores it in temporary memory for state maintenance.

[0137] Output: The terminal sends the input information to the server as an HTTP request.

[0138] Step 2: Save user information

[0139] The server stores the received user information in a database.

[0140] Input: User information sent from the device.

[0141] For example, the server uses a MySQL database to store information in a "Users" table.

[0142] Output: User information recorded in a database.

[0143] Step 3: Generate conversation scenarios

[0144] The server acquires user information from a database and generates an optimal conversation scenario.

[0145] Input: Database user information.

[0146] The server uses a generative AI model (e.g., GPT-3) to generate optimal scenarios based on the user's goals and interests.

[0147] Output: The generated conversation scenario in text format.

[0148] Example: If a user's goal is to "advance their career," generate the following question scenario: "What was particularly challenging about your recent project?"

[0149] Step 4: Converting to audio data

[0150] The server passes the conversation scenario (text) to a speech synthesis engine and converts it into voice data.

[0151] Input: Text data of the generated conversation scenario.

[0152] The server converts the text to speech using, for example, the Google Text-to-Speech API.

[0153] Output: Audio data.

[0154] The server stores the audio data in a cache system (e.g., Redis).

[0155] Step 5: Initiating a voice interaction

[0156] The user presses the "Start Voice Dialogue" button in the application to start the voice dialogue.

[0157] Input: The user presses the "Start voice interaction" button.

[0158] The device detects the button press event, activates the microphone, and starts voice input.

[0159] Output: The audio data recorded by the device.

[0160] Step 6: Send and convert audio data

[0161] The terminal transmits the recorded voice data to the server.

[0162] Input: The audio data spoken by the user.

[0163] The server converts the received voice data into text data using a voice recognition engine (e.g., IBM Watson Speech to Text).

[0164] Output: Text data.

[0165] Step 7: Analyzing the content of the comment and generating a response

[0166] The server analyzes the text data using natural language processing (NLP) technology (e.g., Google Dialogflow) to understand the user's intention in speaking.

[0167] Input: Text data generated by speech recognition.

[0168] The server generates an appropriate response based on the analysis results.

[0169] Output: The generated response text.

[0170] Example: If a user says, "I'd like to talk about a challenge I had on a recent project," generate a response of, "What specifically were the challenges?"

[0171] Step 8: Convert the response text to audio data

[0172] The server passes the response text to the speech synthesis engine again and converts it into voice data.

[0173] Input: The generated response text.

[0174] Output: The converted audio data.

[0175] Step 9: Send and play responses

[0176] The server transmits the audio data to the terminal.

[0177] The terminal plays back the received voice data and waits for voice input of the next follow-up question.

[0178] Input: Audio data sent from the server.

[0179] Output: The audio data to be played.

[0180] Step 10: Storing and Learning Dialogue Data

[0181] After the dialogue is completed, the server stores all dialogue content (voice data, text data, and NLP analysis results) in a database.

[0182] Input: Full historical data of the interaction.

[0183] The saved data is used as training data for the AI ​​model to provide more accurate coaching in the next interaction.

[0184] Output: Dialogue history stored in a database.

[0185] The above is the specific processing flow of the program for this system. This system makes it possible to provide personalized voice-interactive coaching to each user.

[0186] (Application example 1)

[0187] 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."

[0188] Conventional food delivery systems have difficulty providing personalized menu suggestions because they do not adequately consider the user's individual preferences and dietary restrictions. Furthermore, even voice-based interactive systems have faced many technical challenges in achieving natural dialogue with the user. The present invention aims to solve these challenges and provide users with more personalized menu suggestions and natural voice dialogue.

[0189] 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.

[0190] In this invention, the server includes means for saving user information based on the user's personality and preferences, means for generating an optimal conversation scenario based on the saved user information, means for converting the generated conversation scenario into voice data, means for receiving voice input from the user and converting it into text data, means for analyzing the user's utterances and generating an appropriate response, means for converting the generated response back into voice data and outputting it to the user, means for saving the dialogue content and using it as future learning data, means for generating personalized menu suggestions based on the user's food preferences and past order history, and means for audibly confirming the user's order details and optimizing the suggestions in real time, thereby enabling natural and personalized voice dialogue and menu suggestions that accommodate the user's individual preferences and dietary restrictions.

[0191] The "means for storing user information based on characteristics and preferences" refers to a device or program that has the function of collecting information about users' characteristics and individual preferences and storing it in a database.

[0192] "Means for generating an optimal dialogue scenario based on stored user information" refers to a device or program that has the function of automatically generating the most appropriate dialogue scenario for a user based on stored user information.

[0193] The "means for converting the generated conversation scenario into voice data" refers to a device or program that has the function of converting the generated text-format conversation scenario into voice data.

[0194] The "means for receiving voice input from a user and converting it into text data" refers to a device or program that has the function of converting the user's speech into text using voice recognition technology.

[0195] The "means for analyzing the content of a user's comments and generating an appropriate response" refers to a device or program that has the function of analyzing a user's comments converted into text format and generating an appropriate response based on the content.

[0196] The "means for converting the generated response back into voice data and outputting it to the user" refers to a device or program that has the function of converting the generated text response back into voice data and outputting it to the user.

[0197] The "means for saving the content of the dialogue and using it as future learning data" refers to a device or program that has the function of saving the content of the dialogue with the user in a database and using it as future learning data.

[0198] "Means for generating personalized menu suggestions based on a user's food preferences and past ordering history" refers to a device or program that has the function of automatically generating individually customized menu suggestions based on a user's food preferences and past ordering history.

[0199] The "means for confirming the user's order details by voice and optimizing suggestions in real time" refers to a device or program that has the function of confirming the user's order details by voice and updating them to the optimal suggestions on the spot.

[0200] This invention provides a voice-based interactive food delivery system based on user characteristics and preferences, which can assist users in the interactive ordering process and provide more personalized menu suggestions.

[0201] Hardware and software used

[0202] The following hardware and software are used as the main components of the system:

[0203] Hardware: Smartphone (microphone, speaker), server (database)

[0204] Software: AI models, speech recognition engines, speech synthesis engines, natural language processing engines (NLP)

[0205] System Components

[0206] 1. User Registration

[0207] First, a user launches the application on their smartphone and enters their name, age, food preferences (e.g., Japanese food, Western food, vegan, etc.), past order history, and allergy information. The smartphone receives this information and sends it to the server. The server stores the information in a database and creates a personalized profile for each user.

[0208] 2. Proposed scenario generation

[0209] The server generates an optimal menu recommendation scenario based on registered user information. This scenario is created using an AI model. For example, if the user is vegan, the recommendation scenario will include vegan menu items.

[0210] 3. Speech Synthesis

[0211] The server passes the generated text scenario to a speech synthesis engine, which converts the text into speech data. The voice characteristics (e.g., youthful voice, calm voice) are optimized according to the user's preferences. The synthesized speech data is stored in a cache.

[0212] 4. Starting a voice conversation

[0213] The user presses the "Start Voice Interaction" button in the application to activate the microphone and start the voice interaction. The smartphone receives the user's voice input and sends the voice data to the server.

[0214] 5. Real-time processing and feedback

[0215] The server analyzes the received voice data in real time and converts it into text using a speech recognition engine. This text is then analyzed using natural language processing (NLP) technology to understand the user's intent. For example, in response to a question such as "What's your recommendation today?", a response such as "Today's recommendations are salmon sushi and Margherita pizza" is generated. The generated response is then converted back into voice data using a speech synthesis engine and sent to the smartphone. The smartphone then plays the response back to the user.

[0216] 6. Data feedback and learning

[0217] After the dialogue with the user is completed, the server stores all dialogue content (voice, text data, and NLP analysis results) in a database. This data is used as training data for future AI models, enabling more accurate menu suggestions to be provided in the next dialogue.

[0218] Examples of specific examples and prompts

[0219] For example, if a user registers in the app that they like "Japanese food" and "pizza," the server will use this information to generate a menu scenario that suggests "salmon sushi" and "Margherita pizza" as today's recommendations. As a specific example of a prompt, a scenario will be generated that answers the question, "What's your recommendation today?" with an appropriate menu item.

[0220] Examples of prompts:

[0221] What's your recommendation today?

[0222] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0223] Step 1:

[0224] Users launch the application on their smartphone and enter their name, age, food preferences (Japanese, Western, vegan, etc.), past order history, and allergy information. The device receives this information and sends it to the server. The entered data is stored in a database, creating a personalized profile for each user.

[0225] Step 2:

[0226] The server generates an optimal menu suggestion scenario based on the saved user information. This is where the AI ​​model comes into play. It performs calculations to generate menu suggestions based on the user's input data (food preferences, past order history, allergy information), and selects a menu that is suitable for the user.

[0227] Step 3:

[0228] The server passes the generated text-format proposed scenario to a speech synthesis engine, which converts the text into speech data. The speech synthesis engine sets the voice characteristics (e.g., youthful voice, calm voice) according to the user's preferences. The generated speech data is saved in a cache.

[0229] Step 4:

[0230] The user presses the "Start Voice Dialogue" button in the application to start a voice dialogue. The device activates the microphone and receives the user's voice input. The collected voice data is sent to the server.

[0231] Step 5:

[0232] The server analyzes the received voice data in real time and converts it into text data using a speech recognition engine. The converted text data is then used to analyze the user's intention using natural language processing (NLP) technology. For example, if a user asks, "What's recommended today?", the intention of the speech is analyzed.

[0233] Step 6:

[0234] The server generates an appropriate response based on the analysis results. For example, it generates a response such as "Today's recommendations are salmon sushi and Margherita pizza," and converts it into voice data using a speech synthesis engine. The generated voice data is then sent to the device.

[0235] Step 7:

[0236] The device plays the voice data sent from the server to the user, who then listens to the response and makes the next voice input (e.g., "I'd like to order salmon sushi"), allowing the conversation to continue and receiving menu suggestions updated in real time.

[0237] Step 8:

[0238] After the dialogue is completed, the server stores all dialogue content (voice, text data, and NLP analysis results) in a database. This adds new information about the user and uses it as learning data for the AI ​​model from the next time onwards, improving the accuracy of suggestions.

[0239] 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.

[0240] This invention provides more effective coaching by combining a personalized voice dialogue coaching system based on the user's personality and preferences with an emotion engine that recognizes the user's emotions. The following explanation will explain the overall processing flow of the system and the program processing in detail with concrete examples.

[0241] 1. User Registration

[0242] To use the system, a user launches the application and enters required information such as name, age, areas of interest, and goals.

[0243] The terminal acquires the information entered by the user and transmits it to the server.

[0244] The server stores the transmitted user information in a database and creates a personalized profile for each user.

[0245] 2. Conversation scenario generation

[0246] The server uses an AI model based on the saved user information to generate optimal conversation scenarios. For example, if a user is interested in career advancement, it generates a scenario such as, "What particular challenges did you face in your recent project?"

[0247] 3. Speech Synthesis

[0248] The server passes the generated text scenario to a speech synthesis engine to convert the text into speech data, optimizing the voice characteristics (e.g., youthful voice, calm voice) based on the user's preferences.

[0249] 4. User Emotion Recognition

[0250] When a user presses the "Start voice interaction" button in the application, the device activates the microphone and begins voice input.

[0251] When the user speaks, the device collects the voice data, temporarily stores it, and then sends it to the server.

[0252] The server analyzes the received voice data using a voice recognition engine and converts it into text, while at the same time recognizing the user's emotions using an emotion engine.

[0253] 5. Real-time processing and feedback

[0254] The server analyzes the text data and the recognized emotions using natural language processing (NLP) technology to understand the user's intention and generate an appropriate response based on the emotion.

[0255] For example, if a user says, "I'd like to talk about the difficulties I had in a recent project," and the emotion engine recognizes "stress," it will generate responses that take emotions into account, such as, "What specifically were the difficulties?" or "That must have been difficult. How did you deal with it?"

[0256] The server converts the generated response into voice using a voice synthesis engine and transmits the voice data to the terminal.

[0257] 6. Audio output and re-input

[0258] The terminal reproduces the voice data received from the server and allows the user to hear the response.

[0259] The user listens to the audio playback and, if necessary, speaks again, and the process repeats.

[0260] 7. Data feedback and learning

[0261] After the dialogue is completed, the server stores all of the dialogue content (voice, text data, emotion data, and NLP analysis results) in a database.

[0262] The stored data will be used as training data for future AI models, improving the accuracy of the system.

[0263] As a concrete example, if a user sets a goal of "I want to be successful as the leader of the next project," the system will use this information to generate questions that delve deeper into the user's current situation and challenges, and provide them via voice. If the user says, "I'd like to talk about the difficulties I had in today's meeting," and the emotion engine recognizes "anxiety," a response based on the emotion, such as "That's difficult. What specifically were you worried about?", will be generated in real time and returned to the user via voice. This process allows the user to organize their own emotions and deepen their introspection.

[0264] The above is a concrete example of how to implement a system that combines an emotion engine that recognizes the user's emotions. This system enables detailed responses based on the user's emotions, and can provide more effective personalized coaching.

[0265] The processing flow will be explained below.

[0266] Step 1:

[0267] To use the system, a user launches the application and enters required information such as name, age, areas of interest, and goals.

[0268] Step 2:

[0269] The terminal obtains the information entered by the user and sends it to the server.

[0270] Step 3:

[0271] The server stores the received user information in a database, creating a personalized profile for each user.

[0272] Step 4:

[0273] The server uses an AI model based on the saved user information to generate optimal conversation scenarios. For example, if a user is interested in career advancement, it generates a scenario such as, "What particular challenges did you face in your recent project?"

[0274] Step 5:

[0275] The server passes the generated text scenario to a speech synthesis engine and converts it from text to speech data. During this process, the voice characteristics (e.g., youthful voice, calm voice) are optimized based on the user's preferences. The synthesized speech data is stored in a cache for the user ID.

[0276] Step 6:

[0277] When a user presses the "Start voice interaction" button in the application, the device activates the microphone and starts voice input.

[0278] Step 7:

[0279] When a user speaks, the device collects and temporarily stores the voice data, which is then sent to the server.

[0280] Step 8:

[0281] The server analyzes the received voice data using a voice recognition engine and converts it into text data.

[0282] Step 9:

[0283] The server uses an emotion engine to analyze the voice data received at the same time as the text data and recognize the user's emotions (e.g., joy, sadness, anger, surprise, etc.). For example, when a user says, "I had a hard time with a recent project," the emotion engine recognizes "stress."

[0284] Step 10:

[0285] The server uses natural language processing (NLP) technology to analyze the text data and the recognized emotional data to understand the user's intention. Based on the results of this analysis, it generates an appropriate response based on the user's emotions. For example, it generates a response that takes emotions into consideration, such as, "That must have been difficult. How did you deal with it?"

[0286] Step 11:

[0287] The server passes the generated response to a speech synthesis engine, converts the text into voice data, and transmits the voice data to the terminal.

[0288] Step 12:

[0289] The terminal reproduces the voice data received from the server and allows the user to hear the response.

[0290] Step 13:

[0291] The user listens to the audio playback and, if necessary, speaks again, and the process repeats.

[0292] Step 14:

[0293] After the dialogue is completed, the server stores all of the dialogue content (voice, text data, emotion data, and NLP analysis results) in a database.

[0294] Step 15:

[0295] The saved data will be used as training data for future AI models, improving the accuracy of the system and enabling more precise and personalized responses in subsequent interactions.

[0296] Through each of these steps, users are provided with conversations that include individually optimized emotion recognition, enabling effective coaching that encourages self-reflection.

[0297] Example 2

[0298] 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."

[0299] Conventional voice dialogue systems have difficulty recognizing and responding to changes in a user's emotions, as well as their personality and preferences, in real time. As a result, responses to users are uniform, making it impossible to provide effective personalized coaching. Furthermore, feedback tailored to the user's emotions is lacking, resulting in a poor user experience.

[0300] The specific processing by the specific processing unit 290 of the data processing device 12 in the second embodiment is realized by the following means.

[0301] In this invention, the server includes: [means for saving user information based on the user's personality and preferences;] [means for generating an optimal conversation scenario based on the saved user information;] [means for converting the generated conversation scenario into voice data;] [means for receiving voice input from the user and converting it into text data;] [means for analyzing the user's utterances and emotions and generating an appropriate response;] [means for converting the generated response back into voice data and outputting it to the user;] [means for saving the dialogue content in a database and using it as future learning data; and [means for recognizing the user's emotions.] This makes it possible to recognize the user's emotions in real time and provide a detailed response. Therefore, more effective personalized coaching can be provided, improving the quality of the user experience.

[0302] "User Information" refers to personal information about a User, such as their characteristics, preferences, interests, and goals.

[0303] The "conversation scenario" refers to a scenario such as a dialogue progress plan and question content generated based on information input by the user.

[0304] "Voice data" refers to audio data obtained by converting text information using a speech synthesis engine.

[0305] "Text data" refers to data in the form of a character string that is generated by converting a user's voice input using a voice recognition engine.

[0306] "Emotions" refer to the psychological state or feelings expressed by a user during a voice interaction.

[0307] "Analysis" refers to the process of analyzing and understanding what users say and their emotions.

[0308] A "reply" refers to an appropriate response that is generated based on what the user says.

[0309] "Database" refers to a data management system for storing information about interactions and users.

[0310] "Real-time" refers to the process of instantly analyzing and responding to a user's voice input.

[0311] This invention is a voice-interactive coaching system that is personalized based on the user's personality and preferences, and by combining it with an emotion engine that recognizes the user's emotions, it provides more effective coaching. The processing flow of the entire system and specific examples are described in detail below.

[0312] This system consists of three main elements: a server, a terminal, and a user.

[0313] 1. User Registration

[0314] A user launches an application and enters personal information such as name, age, interests, and goals.

[0315] The device acquires the input information and sends it to the server using the HTTP or HTTPS communication protocol.

[0316] The server stores the received information in a database (e.g., MySQL or MongoDB) and creates a personalized profile for each user.

[0317] 2. Conversation scenario generation

[0318] The server uses a generative AI model (e.g., OpenAI® GPT-4®) to generate optimal conversation scenarios based on the saved user information. Specifically, if the user is interested in "career advancement," the server generates a scenario such as, "What particular challenges did you face in your recent project?"

[0319] 3. Speech Synthesis

[0320] The server passes the generated text scenario to a speech synthesis engine (e.g., Google Cloud Text-to-Speech) to convert the text into voice data. The voice characteristics (e.g., youthful voice, calm voice) are optimized based on the user's preferences.

[0321] 4. User Emotion Recognition

[0322] When the user presses the "Start voice interaction" button, the device activates the microphone and begins voice input.

[0323] When a user speaks, the device collects and temporarily stores the voice data, which is then sent to the server in a streaming or batch process.

[0324] The server converts the voice data into text using a speech recognition engine (e.g., Google Cloud Speech-to-Text) and recognizes the user's emotions using an emotion engine (e.g., Azure® Emotion API).

[0325] 5. Real-time processing and feedback

[0326] The server analyzes the text data and emotions using natural language processing (NLP) technology (such as spaCy or AllenNLP), understands the user's intention, and generates an appropriate response. For example, if a user says, "I'd like to talk about the difficulties I faced in a recent project," and the emotion engine recognizes this as "stress," it will generate responses such as, "What specifically were the difficulties you faced?" or "That must have been difficult. How did you deal with it?"

[0327] The server converts the generated response into speech using a speech synthesis engine and sends the speech data to the terminal.

[0328] 6. Audio output and re-input

[0329] The terminal reproduces the voice data received from the server and allows the user to hear the response.

[0330] The user listens to the playback and, if necessary, speaks again, and the process repeats.

[0331] 7. Data feedback and learning

[0332] After the dialogue is completed, the server stores all of the dialogue content (voice, text data, emotion data, and NLP analysis results) in a database.

[0333] The stored data will be used as training data for future AI models, improving the accuracy of the system.

[0334] Specific examples

[0335] For example, if a user sets a goal of "I want to be successful as the leader of the next project," the system can use this information to generate questions that delve deeper into the user's current situation and challenges, and provide them via voice.As another example, if a user says, "I'd like to talk about the difficulties I had in today's meeting," and the emotion engine recognizes "anxiety," a response based on the emotion, such as "That's difficult. What specifically were you worried about?", is generated in real time and returned to the user via voice.

[0336] This system enables more detailed responses that take into account the user's emotions, enabling more effective personalized coaching.

[0337] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0338] Step 1:

[0339] Registering Users

[0340] Input: A user launches an application and enters personal information such as name, age, interests, and goals.

[0341] How it works: The device takes the information entered by the user and converts it into JSON format.

[0342] Output: User information in JSON format is generated.

[0343] Next step: Send the user information in JSON format to the server.

[0344] Step 2:

[0345] Data storage

[0346] Input: User information in JSON format.

[0347] What happens: The server parses the received JSON data and stores it in the database.

[0348] Output: User information is saved in the database.

[0349] Next: Create a personalized profile for each user based on the stored user information.

[0350] Step 3:

[0351] Conversation scenario generation

[0352] Input: User information stored in the database.

[0353] How it works: The server uses a generative AI model (e.g., OpenAI GPT-4) to generate an optimal conversation scenario. Specifically, it inputs user information into a prompt sentence and generates a scenario such as, "What were the particular challenges you faced in your recent project?"

[0354] Output: Generated text data of the conversation scenario.

[0355] Next process: Convert the text scenario into audio data.

[0356] Step 4:

[0357] Speech synthesis

[0358] Input: Text data of the generated conversation scenario.

[0359] How it works: The server uses a speech synthesis engine (e.g., Google Cloud Text-to-Speech) to convert text data into voice data, optimizing voice characteristics (e.g., youthful voice, calm voice) based on the user's preferences.

[0360] Output: Audio file (e.g. MP3 format).

[0361] Next step: Send the audio data to the device.

[0362] Step 5:

[0363] Start a voice interaction

[0364] Input: The audio file sent from the server.

[0365] How it works: When a user presses the "Start voice interaction" button in an application, the device activates the microphone and plays an audio file.

[0366] Output: The user hears the start of the dialogue.

[0367] Next: Receive voice input from the user.

[0368] Step 6:

[0369] Audio data collection

[0370] Input: Speech input from the user.

[0371] How it works: The device collects and temporarily stores the user's voice data.

[0372] Output: Temporarily saved audio data.

[0373] Next step: Send the audio data to the server.

[0374] Step 7:

[0375] Analysis of audio data

[0376] Input: Audio data sent from the device.

[0377] How it works: The server converts the voice data into text using a speech recognition engine (e.g., Google Cloud Speech-to-Text) and recognizes the user's emotions using an emotion engine (e.g., Azure Emotion API).

[0378] Output: Text data and emotion data.

[0379] Next step: Analyze the text and sentiment data and generate an appropriate response.

[0380] Step 8:

[0381] Response Generation

[0382] Input: Text data and emotion data.

[0383] How it works: The server uses natural language processing (NLP) technology (such as spaCy or AllenNLP) to analyze text and sentiment data and generate appropriate responses to the user. For example, if a user says, "I'd like to talk about the difficulties I faced in a recent project," the server generates a response such as, "What specifically were the difficulties?"

[0384] Output: Text data of the response.

[0385] Next process: Convert the generated response into audio data.

[0386] Step 9:

[0387] Voiced responses

[0388] Input: Text data of the response.

[0389] How it works: The server uses a speech synthesis engine (e.g., Google Cloud Text-to-Speech) to convert the text data into audio data.

[0390] Output: Audio file.

[0391] Next step: Send the audio data to the device.

[0392] Step 10:

[0393] Playing audio data

[0394] Input: Audio data sent from the server.

[0395] Operation: The device plays the audio data received from the server, allowing the user to hear the response.

[0396] Output: A spoken response to the user.

[0397] Next step: Retry voice input if necessary.

[0398] Step 11:

[0399] Data feedback and learning

[0400] Input: All content of the dialogue (voice, text data, emotion data, and NLP analysis results).

[0401] How it works: The server stores the conversation in a database and uses it as learning data for future projects. The stored data is used to improve the generative AI model and increase the accuracy of the system.

[0402] Output: Training data stored in a database.

[0403] Next: Retrain and improve the AI ​​model to improve the system's accuracy.

[0404] The above is the specific processing flow of this system, and details of the specific operations and inputs / outputs at each step. This makes it possible to provide personalized coaching according to the user's emotions.

[0405] (Application example 2)

[0406] 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."

[0407] The objective of this invention is to provide personalized voice dialogue coaching based on the user's emotions and preferences, and in particular to support the user's mental and emotional well-being by recognizing the user's emotional state in real time and providing appropriate feedback. Conventional voice dialogue systems have difficulty recognizing the user's emotions and immediately reflecting them in responses, so more effective coaching is required.

[0408] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 2 is realized by the following means.

[0409] In this invention, the server includes means for saving user information based on personality and preferences, means for generating an optimal conversation scenario based on the saved user information, and means for converting the generated conversation scenario into voice data. This makes it possible to provide personalized coaching in real time according to the user's emotions and state.

[0410] "User information" refers to information about a user, such as their personality, preferences, areas of interest, and goals.

[0411] A "conversation scenario" refers to text data that is generated based on user information and that plans the flow of a conversation with a user.

[0412] "Emotional state" refers to data for determining the emotional state a user exhibits during a dialogue.

[0413] "Voice data" refers to an audio file converted from the generated conversation scenario by a voice synthesis engine.

[0414] "Speech recognition" refers to the technology that converts voice input from a user into text data.

[0415] "Appropriate reply" refers to analyzing the content of a user's speech and emotional state and generating a response that is deemed appropriate.

[0416] "Personalized coaching messages" refer to coaching messages that are individually optimized based on the user's personality, preferences, and emotional state.

[0417] "Database" refers to data storage that stores user information, dialogue content, emotional data, etc., and is used as future learning data.

[0418] A "natural language processing engine" refers to technology that analyzes user statements and text and generates appropriate responses.

[0419] "Real-time processing" refers to processing that analyzes data and generates responses immediately during a user interaction.

[0420] This invention is a system that provides personalized voice-interactive coaching based on a user's emotional state and individual preferences. The entire system is mainly composed of a server, a terminal, and a user. Specific embodiments for implementing this system are described below.

[0421] User registration and information storage

[0422] To use the system, a user launches the application and enters necessary information such as name, age, areas of interest, goals, etc. This information is sent to the server via the terminal, and the server stores the user information in a database and creates a personalized profile for each user.

[0423] Conversation scenario generation

[0424] The server uses an AI model (natural language processing engine) based on the stored user information to generate a conversation scenario suited to the user. For example, if the user is interested in "stress management," this scenario can include questions such as, "What has caused you stress recently?"

[0425] Generate audio data

[0426] The generated conversation scenario is converted into voice data using the server's voice synthesis engine, with the tone and pitch of the voice adjusted based on the user's preferences.

[0427] User voice input and emotion recognition

[0428] When a user initiates a dialogue, the device's microphone collects voice input, which is then sent to a server that uses a speech recognition engine to convert the speech into text data and an emotion engine to recognize the user's emotional state.

[0429] Real-time response and feedback

[0430] The server uses a natural language processing engine based on the recognized text data and emotion data to generate an appropriate response according to the user's comment and emotional state. The generated response is then converted into voice data by a speech synthesis engine and output to the user via the terminal.

[0431] Data storage and training

[0432] After the dialogue is completed, the server stores all dialogue data (voice data, text data, emotion data, and analysis results) in a database, which will be used as training data for future AI models, improving the accuracy and performance of the system.

[0433] For example, if a user says, "I'm feeling really stressed today," the emotion engine will detect "stress" and generate a response like this: "That's tough. Is there a specific reason why?"

[0434] Prompt Sentence Examples

[0435] If a user says something that suggests they are under stress, generate an appropriate coaching message. For example, if a user says, "I'm feeling really stressed today," generate a message like, "That sounds tough. Is there a specific reason for that?"

[0436] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[0437] Step 1:

[0438] A user launches the application and enters the required information, such as name, age, interests, and goals.

[0439] Input: User's personal information (name, age, interests, goals, etc.)

[0440] Output: Dataset as user information

[0441] The terminal collects information entered by the user and sends it to a server for analysis.

[0442] Step 2:

[0443] The server stores the transmitted user information in a database and creates a personalized profile for each user.

[0444] Input: User information data from the terminal

[0445] Output: User profile in the database

[0446] The server analyzes the input information and creates and saves a profile for each user.

[0447] Step 3:

[0448] Based on the user information stored on the server, a conversation scenario is generated using an AI model (natural language processing engine).

[0449] Input: User profile in database

[0450] Output: Conversation scenario

[0451] The server generates an appropriate conversation scenario based on the user's interests and goals.

[0452] Step 4:

[0453] The server passes the generated conversation scenario to a speech synthesis engine and converts it into voice data.

[0454] Input: Generated conversation scenario (text data)

[0455] Output: Audio data

[0456] The server converts the text data into speech and adjusts the tone and pitch of the speech based on the user's preferences.

[0457] Step 5:

[0458] When the user presses the "Start Voice Interaction" button, the device activates the microphone and receives voice input from the user.

[0459] Input: User's voice

[0460] Output: Temporarily saved audio data

[0461] The device collects the user's voice and temporarily stores it for analysis.

[0462] Step 6:

[0463] The device sends the temporarily saved voice data to the server, which then analyzes it with a voice recognition engine, converts it into text data, and recognizes the user's emotions using an emotion engine.

[0464] Input: Audio data sent from the device

[0465] Output: Text data and emotion recognition data

[0466] The server converts the voice data into text and also recognizes emotions.

[0467] Step 7:

[0468] The server uses a natural language processing engine to generate an appropriate response based on the text data and emotional data it recognizes.

[0469] Input: Text data, emotion recognition data

[0470] Output: Response (text data)

[0471] The server analyzes the user's comments and emotional state and generates an appropriate response.

[0472] Step 8:

[0473] The response generated by the server is passed back to the speech synthesis engine, converted into voice data, and then sent to the terminal.

[0474] Input: Generated response (text data)

[0475] Output: Response audio data

[0476] The server converts the text response into audio data and sends it to the device.

[0477] Step 9:

[0478] The terminal plays back the voice data from the server and lets the user hear the response. The user listens to the played back voice and makes further voice input as necessary.

[0479] Input: Audio data from the server

[0480] Output: The audio the user hears

[0481] The terminal plays the audio data and provides a response to the user.

[0482] Step 10:

[0483] After the dialogue is completed, the server stores all of the dialogue content (voice, text data, emotion data, and NLP analysis results) in a database.

[0484] Input: All dialogue data (voice, text, emotion data, analysis results)

[0485] Output: Interaction data stored in a database

[0486] The server stores all collected data in a database and uses it as learning data for the future.

[0487] 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.

[0488] 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.

[0489] 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.

[0490] [Second embodiment]

[0491] FIG. 3 shows an example of the configuration of a data processing system 210 according to the second embodiment.

[0492] 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.

[0493] 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).

[0494] 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.

[0495] 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.

[0496] 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).

[0497] 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.

[0498] 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.

[0499] 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.

[0500] 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.

[0501] In the smart glasses 214, the processor 46 performs the reception output process. A reception output program 60 is stored in the storage 50. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output process is realized by the processor 46 operating as the control unit 46A in accordance with the reception output program 60 executed on the RAM 48.

[0502] 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."

[0503] The system of the present invention provides personalized voice interactive coaching based on individual characteristics and preferences. The following description will explain the overall flow of the system and the program's processing in detail with specific examples.

[0504] 1. User Registration

[0505] To use the system, a user launches the application and enters the required information, such as name, age, interests, and goals.

[0506] The terminal receives this information and transmits it to the server.

[0507] The server stores the submitted information in a database and creates a personalized profile for each user.

[0508] 2. Conversation scenario generation

[0509] The server generates optimal conversation scenarios based on registered user information. These scenarios are created using AI models based on the user's goals and interests.

[0510] For example, if a user is looking to "advance their career," the server might generate the question, "What was particularly challenging about your recent project?"

[0511] 3. Speech Synthesis

[0512] The server passes the generated text scenario to a speech synthesis engine, which converts the text into speech.

[0513] At this time, the voice characteristics (e.g., youthful voice, calm voice) are optimized according to the user's preferences.

[0514] The synthesized voice data is stored in a cache for the user ID.

[0515] 4. Starting a voice conversation

[0516] The user presses the "Start voice interaction" button within the application to start the voice interaction.

[0517] The device activates the microphone and begins receiving voice input from the user.

[0518] When the user speaks to the coach, the terminal collects the voice data and sends it to the server.

[0519] 5. Real-time processing and feedback

[0520] The server analyzes the received voice data in real time and converts it into text using a voice recognition engine.

[0521] The server analyzes this text using natural language processing (NLP) technology to understand the user's intention.

[0522] For example, if a user says, "I'd like to talk about the difficulties I had in a recent project," the server generates an appropriate response: "What specifically were the difficulties?"

[0523] The server converts this response into voice using a voice synthesis engine and sends the voice data to the terminal.

[0524] The terminal plays the audio data to the user and waits for the next audio input.

[0525] 6. Data feedback and learning

[0526] After the conversation is over, the server stores all conversation content (voice, text data, and NLP analysis results) in a database.

[0527] The saved data is used as training data for future AI models. This continuous learning allows the system to provide more accurate coaching in the next interaction.

[0528] As a concrete example, if a user sets a goal of "I want to be successful as the leader of the next project," the system will use this information to generate questions that delve deeper into the user's current situation and challenges, and provide these questions via voice. If the user says, "I'd like to talk about the difficulties I had in today's meeting," a response such as "What were the difficulties? Please tell us the specific situation" will be generated in real time and returned to the user via voice. This process allows the user to organize their own challenges and promote introspection.

[0529] The above is a specific embodiment for carrying out the present invention. This system makes it possible to provide natural, personalized, and interactive voice coaching that goes beyond conventional text-based interfaces.

[0530] The processing flow will be explained below.

[0531] Step 1:

[0532] To use the system, a user launches the application and enters required information such as name, age, areas of interest, and goals.

[0533] Step 2:

[0534] The terminal obtains the information entered by the user and sends it to the server.

[0535] Step 3:

[0536] The server stores the received user information in a database, which creates a user profile.

[0537] Step 4:

[0538] The server uses an AI model based on the saved user information to generate optimal conversation scenarios. For example, if a user is interested in career advancement, it generates a scenario such as, "What particular challenges did you face in your recent project?"

[0539] Step 5:

[0540] The server passes the generated conversation scenario to a speech synthesis engine, which converts the text into speech data, optimizing the voice characteristics (e.g., youthful voice, calm voice) based on the user's preferences.

[0541] Step 6:

[0542] When the user presses the "Start Voice Dialogue" button, the terminal activates the microphone and starts voice input.

[0543] Step 7:

[0544] When the user speaks to the coach, the device collects and temporarily stores the voice data, and then transmits the stored voice data to the server.

[0545] Step 8:

[0546] The server analyzes the received voice data using a voice recognition engine and converts it into text data.

[0547] Step 9:

[0548] The server analyzes the text data using natural language processing (NLP) technology to understand the user's intent. Based on the analysis results, it generates an appropriate response. For example, if a user says, "I'd like to talk about the difficulties I faced in a recent project," it generates a response such as, "What specifically were the difficulties you faced?"

[0549] Step 10:

[0550] The server passes the generated response to a speech synthesis engine, converts the text into voice data, and transmits the voice data to the terminal.

[0551] Step 11:

[0552] The terminal reproduces the voice data received from the server and allows the user to hear the response.

[0553] Step 12:

[0554] The user listens to the audio playback and, if necessary, speaks again, and the process repeats.

[0555] Step 13:

[0556] After the conversation is over, the server stores all of the conversation content (voice, text data, and NLP analysis results) in a database. This not only serves as a reference for future conversations, but also serves as training data for the AI ​​model.

[0557] By repeating each of the above steps, it is possible to provide individually optimized conversations for each user and achieve coaching that encourages self-reflection.

[0558] Example 1

[0559] 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."

[0560] Conventional voice dialogue systems provide uniform responses to users, making it difficult to provide personalized responses that reflect individual personalities and preferences. Furthermore, they lacked a mechanism for continuously accumulating and learning from dialogue data with users to provide more appropriate feedback for the next dialogue. This limited users' opportunities to receive truly useful coaching.

[0561] 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.

[0562] In this invention, the server includes means for storing user information based on personality and preferences, means for generating an optimal conversation scenario based on the stored user information, and means for converting the generated conversation scenario into voice data. This makes it possible to provide personalized voice dialogue and coaching to each user and support their continuous growth.

[0563] "Means of saving user information based on personality and preferences" refers to the function of saving information entered by the user, such as name, age, areas of interest, and goals, and creating a profile for each user.

[0564] "Means for generating an optimal conversation scenario based on stored user information" refers to a function for generating an optimal conversation scenario that corresponds to the user's goals and interests based on stored user information.

[0565] The "means for converting the generated conversation scenario into voice data" refers to a voice synthesis function that converts the generated text-format conversation scenario into voice data.

[0566] "Means for receiving voice input from the user and converting it into text data" refers to a voice recognition function that converts the voice spoken by the user into text data.

[0567] "Means for analyzing the content of user comments and generating appropriate responses" refers to a natural language processing function that analyzes the content of user comments and generates appropriate responses based on that content.

[0568] "Means for converting the generated response back into voice data and outputting it to the user" refers to a voice output function that converts the generated text response into voice data and provides it to the user.

[0569] "Means of saving the content of the dialogue in a database and using it as future learning data" refers to the function of saving records of dialogue with users in a database and using that data as learning data for the AI ​​model.

[0570] "Means for optimizing voice characteristics based on user information" refers to a function that adjusts the characteristics of synthesized voice (e.g., voice pitch and speed) according to the user's preferences.

[0571] "Means for improving model accuracy by continuously saving and learning from dialogue content" refers to a function that continuously accumulates dialogue data with users and uses that data to retrain the AI ​​model, thereby improving the accuracy of the model.

[0572] "Means for analyzing voice dialogue in real time and providing appropriate feedback" refers to a function for analyzing voice dialogue in real time and quickly providing appropriate feedback in response to user comments.

[0573] "Means for understanding the intention of a user's speech using natural language processing technology" refers to a function that uses natural language processing technology to analyze the content of a user's speech and accurately understand their intention.

[0574] The system of the present invention provides personalized voice interactive coaching based on an individual's personality and preferences. Detailed embodiments of the system are described below.

[0575] 1. User Registration

[0576] The user launches a dedicated application and enters the necessary information, such as their name, age, areas of interest, and goals. The entered information is sent by the device to the server. The server stores the received information in a database and creates a personalized profile for each user. For example, MySQL is used as the database, and user information is stored in a "Users" table.

[0577] 2. Conversation scenario generation

[0578] The server retrieves user information from the database and generates an optimal conversation scenario. This generation uses a generative AI model (e.g., GPT-3). If the user's goal is "career advancement," the server generates questions such as, "What was particularly challenging about your recent project?"

[0579] 3. Speech Synthesis

[0580] The server passes the generated text scenario to a speech synthesis engine (e.g., Google Text-to-Speech API) and converts the text into speech data. The server optimizes the voice characteristics, such as a youthful voice or a calm voice, according to the user's preferences. The synthesized speech data is stored in a cache system (e.g., Redis).

[0581] 4. Starting a voice conversation

[0582] The user presses the "Start voice interaction" button in the application to start the voice interaction. The device activates the microphone and starts the user's voice input. As the user speaks, the voice data is sent from the device to the server.

[0583] 5. Real-time processing and feedback

[0584] The server analyzes the received voice data in real time and converts it into text using a speech recognition engine (for example, IBM Watson Speech to Text). The converted text data is then analyzed using natural language processing (NLP) technology (for example, Google Dialogflow) to understand the user's intention. For example, if the user says, "I'd like to talk about the difficulties I had in a recent project," the server generates an appropriate response such as, "What specifically were the difficulties you had?" This response is again converted into speech using a speech synthesis engine and sent to the device. The device plays the voice data to the user and waits for the next voice input.

[0585] 6. Data feedback and learning

[0586] Once the conversation is over, the server stores all conversation content (voice, text, NLP analysis results, etc.) in a database. This data is used as training data for future AI models. Continuous learning allows the system to provide more accurate coaching in the next conversation.

[0587] As a concrete example, if a user sets a goal of "I want to be successful as the leader of the next project," the system can use this information to generate questions that delve deeper into the user's current situation and challenges, and provide these questions via voice. If the user says, "I'd like to talk about the difficulties I had in today's meeting," a response such as "What were the difficulties you had? Please tell us the specific situation" is generated in real time and returned as voice. This process allows the user to organize their own challenges and promote introspection.

[0588] An example of a prompt for a generative AI model is:

[0589] "Generate an appropriate response when a user says, 'I'd like to talk about something I struggled with in today's meeting.'"

[0590] The above is a specific embodiment for carrying out the present invention. This system makes it possible to provide natural, personalized, and interactive voice coaching that goes beyond conventional text-based interfaces.

[0591] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0592] Step 1: Collect user information

[0593] The user starts the dedicated application and enters information such as their name, age, areas of interest, and goals.

[0594] Input: Information entered by the user, such as name, age, interests, goals, etc.

[0595] The terminal receives the input information and stores it in temporary memory for state maintenance.

[0596] Output: The terminal sends the input information to the server as an HTTP request.

[0597] Step 2: Save user information

[0598] The server stores the received user information in a database.

[0599] Input: User information sent from the device.

[0600] For example, the server uses a MySQL database to store information in a "Users" table.

[0601] Output: User information recorded in a database.

[0602] Step 3: Generate conversation scenarios

[0603] The server acquires user information from a database and generates an optimal conversation scenario.

[0604] Input: Database user information.

[0605] The server uses a generative AI model (e.g., GPT-3) to generate optimal scenarios based on the user's goals and interests.

[0606] Output: The generated conversation scenario in text format.

[0607] Example: If a user's goal is to "advance their career," generate the following question scenario: "What was particularly challenging about your recent project?"

[0608] Step 4: Converting to audio data

[0609] The server passes the conversation scenario (text) to a speech synthesis engine and converts it into voice data.

[0610] Input: Text data of the generated conversation scenario.

[0611] The server converts the text to speech using, for example, the Google Text-to-Speech API.

[0612] Output: Audio data.

[0613] The server stores the audio data in a cache system (e.g., Redis).

[0614] Step 5: Initiating a voice interaction

[0615] The user presses the "Start Voice Dialogue" button in the application to start the voice dialogue.

[0616] Input: The user presses the "Start voice interaction" button.

[0617] The device detects the button press event, activates the microphone, and starts voice input.

[0618] Output: The audio data recorded by the device.

[0619] Step 6: Send and convert audio data

[0620] The terminal transmits the recorded voice data to the server.

[0621] Input: The audio data spoken by the user.

[0622] The server converts the received voice data into text data using a voice recognition engine (e.g., IBM Watson Speech to Text).

[0623] Output: Text data.

[0624] Step 7: Analyzing the content of the comment and generating a response

[0625] The server analyzes the text data using natural language processing (NLP) technology (e.g., Google Dialogflow) to understand the user's intention in speaking.

[0626] Input: Text data generated by speech recognition.

[0627] The server generates an appropriate response based on the analysis results.

[0628] Output: The generated response text.

[0629] Example: If a user says, "I'd like to talk about a challenge I had on a recent project," generate a response of, "What specifically were the challenges?"

[0630] Step 8: Convert the response text to audio data

[0631] The server passes the response text to the speech synthesis engine again and converts it into voice data.

[0632] Input: The generated response text.

[0633] Output: The converted audio data.

[0634] Step 9: Send and play responses

[0635] The server transmits the audio data to the terminal.

[0636] The terminal plays back the received voice data and waits for voice input of the next follow-up question.

[0637] Input: Audio data sent from the server.

[0638] Output: The audio data to be played.

[0639] Step 10: Storing and Learning Dialogue Data

[0640] After the dialogue is completed, the server stores all dialogue content (voice data, text data, and NLP analysis results) in a database.

[0641] Input: Full historical data of the interaction.

[0642] The saved data is used as training data for the AI ​​model to provide more accurate coaching in the next interaction.

[0643] Output: Dialogue history stored in a database.

[0644] The above is the specific processing flow of the program for this system. This system makes it possible to provide personalized voice-interactive coaching to each user.

[0645] (Application example 1)

[0646] 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."

[0647] Conventional food delivery systems have difficulty providing personalized menu suggestions because they do not adequately consider the user's individual preferences and dietary restrictions. Furthermore, even voice-based interactive systems have faced many technical challenges in achieving natural dialogue with the user. The present invention aims to solve these challenges and provide users with more personalized menu suggestions and natural voice dialogue.

[0648] 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.

[0649] In this invention, the server includes means for saving user information based on the user's personality and preferences, means for generating an optimal conversation scenario based on the saved user information, means for converting the generated conversation scenario into voice data, means for receiving voice input from the user and converting it into text data, means for analyzing the user's utterances and generating an appropriate response, means for converting the generated response back into voice data and outputting it to the user, means for saving the dialogue content and using it as future learning data, means for generating personalized menu suggestions based on the user's food preferences and past order history, and means for audibly confirming the user's order details and optimizing the suggestions in real time, thereby enabling natural and personalized voice dialogue and menu suggestions that accommodate the user's individual preferences and dietary restrictions.

[0650] The "means for storing user information based on characteristics and preferences" refers to a device or program that has the function of collecting information about users' characteristics and individual preferences and storing it in a database.

[0651] "Means for generating an optimal dialogue scenario based on stored user information" refers to a device or program that has the function of automatically generating the most appropriate dialogue scenario for a user based on stored user information.

[0652] The "means for converting the generated conversation scenario into voice data" refers to a device or program that has the function of converting the generated text-format conversation scenario into voice data.

[0653] The "means for receiving voice input from a user and converting it into text data" refers to a device or program that has the function of converting the user's speech into text using voice recognition technology.

[0654] The "means for analyzing the content of a user's comments and generating an appropriate response" refers to a device or program that has the function of analyzing a user's comments converted into text format and generating an appropriate response based on the content.

[0655] The "means for converting the generated response back into voice data and outputting it to the user" refers to a device or program that has the function of converting the generated text response back into voice data and outputting it to the user.

[0656] The "means for saving the content of the dialogue and using it as future learning data" refers to a device or program that has the function of saving the content of the dialogue with the user in a database and using it as future learning data.

[0657] "Means for generating personalized menu suggestions based on a user's food preferences and past ordering history" refers to a device or program that has the function of automatically generating individually customized menu suggestions based on a user's food preferences and past ordering history.

[0658] The "means for confirming the user's order details by voice and optimizing suggestions in real time" refers to a device or program that has the function of confirming the user's order details by voice and updating them to the optimal suggestions on the spot.

[0659] This invention provides a voice-based interactive food delivery system based on user characteristics and preferences, which can assist users in the interactive ordering process and provide more personalized menu suggestions.

[0660] Hardware and software used

[0661] The following hardware and software are used as the main components of the system:

[0662] Hardware: Smartphone (microphone, speaker), server (database)

[0663] Software: AI models, speech recognition engines, speech synthesis engines, natural language processing engines (NLP)

[0664] System Components

[0665] 1. User Registration

[0666] First, a user launches the application on their smartphone and enters their name, age, food preferences (e.g., Japanese food, Western food, vegan, etc.), past order history, and allergy information. The smartphone receives this information and sends it to the server. The server stores the information in a database and creates a personalized profile for each user.

[0667] 2. Proposed scenario generation

[0668] The server generates an optimal menu recommendation scenario based on registered user information. This scenario is created using an AI model. For example, if the user is vegan, the recommendation scenario will include vegan menu items.

[0669] 3. Speech Synthesis

[0670] The server passes the generated text scenario to a speech synthesis engine, which converts the text into speech data. The voice characteristics (e.g., youthful voice, calm voice) are optimized according to the user's preferences. The synthesized speech data is stored in a cache.

[0671] 4. Starting a voice conversation

[0672] The user presses the "Start Voice Interaction" button in the application to activate the microphone and start the voice interaction. The smartphone receives the user's voice input and sends the voice data to the server.

[0673] 5. Real-time processing and feedback

[0674] The server analyzes the received voice data in real time and converts it into text using a speech recognition engine. This text is then analyzed using natural language processing (NLP) technology to understand the user's intent. For example, in response to a question such as "What's your recommendation today?", a response such as "Today's recommendations are salmon sushi and Margherita pizza" is generated. The generated response is then converted back into voice data using a speech synthesis engine and sent to the smartphone. The smartphone then plays the response back to the user.

[0675] 6. Data feedback and learning

[0676] After the dialogue with the user is completed, the server stores all dialogue content (voice, text data, and NLP analysis results) in a database. This data is used as training data for future AI models, enabling more accurate menu suggestions to be provided in the next dialogue.

[0677] Examples of specific examples and prompts

[0678] For example, if a user registers in the app that they like "Japanese food" and "pizza," the server will use this information to generate a menu scenario that suggests "salmon sushi" and "Margherita pizza" as today's recommendations. As a specific example of a prompt, a scenario will be generated that answers the question, "What's your recommendation today?" with an appropriate menu item.

[0679] Examples of prompts:

[0680] What's your recommendation today?

[0681] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0682] Step 1:

[0683] Users launch the application on their smartphone and enter their name, age, food preferences (Japanese, Western, vegan, etc.), past order history, and allergy information. The device receives this information and sends it to the server. The entered data is stored in a database, creating a personalized profile for each user.

[0684] Step 2:

[0685] The server generates an optimal menu suggestion scenario based on the saved user information. This is where the AI ​​model comes into play. It performs calculations to generate menu suggestions based on the user's input data (food preferences, past order history, allergy information), and selects a menu that is suitable for the user.

[0686] Step 3:

[0687] The server passes the generated text-format proposed scenario to a speech synthesis engine, which converts the text into speech data. The speech synthesis engine sets the voice characteristics (e.g., youthful voice, calm voice) according to the user's preferences. The generated speech data is saved in a cache.

[0688] Step 4:

[0689] The user presses the "Start Voice Dialogue" button in the application to start a voice dialogue. The device activates the microphone and receives the user's voice input. The collected voice data is sent to the server.

[0690] Step 5:

[0691] The server analyzes the received voice data in real time and converts it into text data using a speech recognition engine. The converted text data is then used to analyze the user's intention using natural language processing (NLP) technology. For example, if a user asks, "What's recommended today?", the intention of the speech is analyzed.

[0692] Step 6:

[0693] The server generates an appropriate response based on the analysis results. For example, it generates a response such as "Today's recommendations are salmon sushi and Margherita pizza," and converts it into voice data using a speech synthesis engine. The generated voice data is then sent to the device.

[0694] Step 7:

[0695] The device plays the voice data sent from the server to the user, who then listens to the response and makes the next voice input (e.g., "I'd like to order salmon sushi"), allowing the conversation to continue and receiving menu suggestions updated in real time.

[0696] Step 8:

[0697] After the dialogue is completed, the server stores all dialogue content (voice, text data, and NLP analysis results) in a database. This adds new information about the user and uses it as learning data for the AI ​​model from the next time onwards, improving the accuracy of suggestions.

[0698] 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.

[0699] This invention provides more effective coaching by combining a personalized voice dialogue coaching system based on the user's personality and preferences with an emotion engine that recognizes the user's emotions. The following explanation will explain the overall processing flow of the system and the program processing in detail with concrete examples.

[0700] 1. User Registration

[0701] To use the system, a user launches the application and enters required information such as name, age, areas of interest, and goals.

[0702] The terminal acquires the information entered by the user and transmits it to the server.

[0703] The server stores the transmitted user information in a database and creates a personalized profile for each user.

[0704] 2. Conversation scenario generation

[0705] The server uses an AI model based on the saved user information to generate optimal conversation scenarios. For example, if a user is interested in career advancement, it generates a scenario such as, "What particular challenges did you face in your recent project?"

[0706] 3. Speech Synthesis

[0707] The server passes the generated text scenario to a speech synthesis engine to convert the text into speech data, optimizing the voice characteristics (e.g., youthful voice, calm voice) based on the user's preferences.

[0708] 4. User Emotion Recognition

[0709] When a user presses the "Start voice interaction" button in the application, the device activates the microphone and begins voice input.

[0710] When the user speaks, the device collects the voice data, temporarily stores it, and then sends it to the server.

[0711] The server analyzes the received voice data using a voice recognition engine and converts it into text, while at the same time recognizing the user's emotions using an emotion engine.

[0712] 5. Real-time processing and feedback

[0713] The server analyzes the text data and the recognized emotions using natural language processing (NLP) technology to understand the user's intention and generate an appropriate response based on the emotion.

[0714] For example, if a user says, "I'd like to talk about the difficulties I had in a recent project," and the emotion engine recognizes "stress," it will generate responses that take emotions into account, such as, "What specifically were the difficulties?" or "That must have been difficult. How did you deal with it?"

[0715] The server converts the generated response into voice using a voice synthesis engine and transmits the voice data to the terminal.

[0716] 6. Audio output and re-input

[0717] The terminal reproduces the voice data received from the server and allows the user to hear the response.

[0718] The user listens to the audio playback and, if necessary, speaks again, and the process repeats.

[0719] 7. Data feedback and learning

[0720] After the dialogue is completed, the server stores all of the dialogue content (voice, text data, emotion data, and NLP analysis results) in a database.

[0721] The stored data will be used as training data for future AI models, improving the accuracy of the system.

[0722] As a concrete example, if a user sets a goal of "I want to be successful as the leader of the next project," the system will use this information to generate questions that delve deeper into the user's current situation and challenges, and provide them via voice. If the user says, "I'd like to talk about the difficulties I had in today's meeting," and the emotion engine recognizes "anxiety," a response based on the emotion, such as "That's difficult. What specifically were you worried about?", will be generated in real time and returned to the user via voice. This process allows the user to organize their own emotions and deepen their introspection.

[0723] The above is a concrete example of how to implement a system that combines an emotion engine that recognizes the user's emotions. This system enables detailed responses based on the user's emotions, and can provide more effective personalized coaching.

[0724] The processing flow will be explained below.

[0725] Step 1:

[0726] To use the system, a user launches the application and enters required information such as name, age, areas of interest, and goals.

[0727] Step 2:

[0728] The terminal obtains the information entered by the user and sends it to the server.

[0729] Step 3:

[0730] The server stores the received user information in a database, creating a personalized profile for each user.

[0731] Step 4:

[0732] The server uses an AI model based on the saved user information to generate optimal conversation scenarios. For example, if a user is interested in career advancement, it generates a scenario such as, "What particular challenges did you face in your recent project?"

[0733] Step 5:

[0734] The server passes the generated text scenario to a speech synthesis engine and converts it from text to speech data. During this process, the voice characteristics (e.g., youthful voice, calm voice) are optimized based on the user's preferences. The synthesized speech data is stored in a cache for the user ID.

[0735] Step 6:

[0736] When a user presses the "Start voice interaction" button in the application, the device activates the microphone and starts voice input.

[0737] Step 7:

[0738] When a user speaks, the device collects and temporarily stores the voice data, which is then sent to the server.

[0739] Step 8:

[0740] The server analyzes the received voice data using a voice recognition engine and converts it into text data.

[0741] Step 9:

[0742] The server uses an emotion engine to analyze the voice data received at the same time as the text data and recognize the user's emotions (e.g., joy, sadness, anger, surprise, etc.). For example, when a user says, "I had a hard time with a recent project," the emotion engine recognizes "stress."

[0743] Step 10:

[0744] The server uses natural language processing (NLP) technology to analyze the text data and the recognized emotional data to understand the user's intention. Based on the results of this analysis, it generates an appropriate response based on the user's emotions. For example, it generates a response that takes emotions into consideration, such as, "That must have been difficult. How did you deal with it?"

[0745] Step 11:

[0746] The server passes the generated response to a speech synthesis engine, converts the text into voice data, and transmits the voice data to the terminal.

[0747] Step 12:

[0748] The terminal reproduces the voice data received from the server and allows the user to hear the response.

[0749] Step 13:

[0750] The user listens to the audio playback and, if necessary, speaks again, and the process repeats.

[0751] Step 14:

[0752] After the dialogue is completed, the server stores all of the dialogue content (voice, text data, emotion data, and NLP analysis results) in a database.

[0753] Step 15:

[0754] The saved data will be used as training data for future AI models, improving the accuracy of the system and enabling more precise and personalized responses in subsequent interactions.

[0755] Through each of these steps, users are provided with conversations that include individually optimized emotion recognition, enabling effective coaching that encourages self-reflection.

[0756] Example 2

[0757] 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."

[0758] Conventional voice dialogue systems have difficulty recognizing and responding to changes in a user's emotions, as well as their personality and preferences, in real time. As a result, responses to users are uniform, making it impossible to provide effective personalized coaching. Furthermore, feedback tailored to the user's emotions is lacking, resulting in a poor user experience.

[0759] The specific processing by the specific processing unit 290 of the data processing device 12 in the second embodiment is realized by the following means.

[0760] In this invention, the server includes: [means for saving user information based on the user's personality and preferences;] [means for generating an optimal conversation scenario based on the saved user information;] [means for converting the generated conversation scenario into voice data;] [means for receiving voice input from the user and converting it into text data;] [means for analyzing the user's utterances and emotions and generating an appropriate response;] [means for converting the generated response back into voice data and outputting it to the user;] [means for saving the dialogue content in a database and using it as future learning data; and [means for recognizing the user's emotions.] This makes it possible to recognize the user's emotions in real time and provide a detailed response. Therefore, more effective personalized coaching can be provided, improving the quality of the user experience.

[0761] "User Information" refers to personal information about a User, such as their characteristics, preferences, interests, and goals.

[0762] The "conversation scenario" refers to a scenario such as a dialogue progress plan and question content generated based on information input by the user.

[0763] "Voice data" refers to audio data obtained by converting text information using a speech synthesis engine.

[0764] "Text data" refers to data in the form of a character string that is generated by converting a user's voice input using a voice recognition engine.

[0765] "Emotions" refer to the psychological state or feelings expressed by a user during a voice interaction.

[0766] "Analysis" refers to the process of analyzing and understanding what users say and their emotions.

[0767] A "reply" refers to an appropriate response that is generated based on what the user says.

[0768] "Database" refers to a data management system for storing information about interactions and users.

[0769] "Real-time" refers to the process of instantly analyzing and responding to a user's voice input.

[0770] This invention is a voice-interactive coaching system that is personalized based on the user's personality and preferences, and by combining it with an emotion engine that recognizes the user's emotions, it provides more effective coaching. The processing flow of the entire system and specific examples are described in detail below.

[0771] This system consists of three main elements: a server, a terminal, and a user.

[0772] 1. User Registration

[0773] A user launches an application and enters personal information such as name, age, interests, and goals.

[0774] The device acquires the input information and sends it to the server using the HTTP or HTTPS communication protocol.

[0775] The server stores the received information in a database (e.g., MySQL or MongoDB) and creates a personalized profile for each user.

[0776] 2. Conversation scenario generation

[0777] The server uses a generative AI model (e.g., OpenAI GPT-4) to generate optimal conversation scenarios based on the saved user information. Specifically, if the user is interested in "career advancement," it generates a scenario such as "What particular challenges did you face in your recent project?"

[0778] 3. Speech Synthesis

[0779] The server passes the generated text scenario to a speech synthesis engine (e.g., Google Cloud Text-to-Speech) to convert the text into voice data. The voice characteristics (e.g., youthful voice, calm voice) are optimized based on the user's preferences.

[0780] 4. User Emotion Recognition

[0781] When the user presses the "Start voice interaction" button, the device activates the microphone and begins voice input.

[0782] When a user speaks, the device collects and temporarily stores the voice data, which is then sent to the server in a streaming or batch process.

[0783] The server converts the voice data into text using a speech recognition engine (e.g., Google Cloud Speech-to-Text) and recognizes the user's emotions using an emotion engine (e.g., Azure Emotion API).

[0784] 5. Real-time processing and feedback

[0785] The server analyzes the text data and emotions using natural language processing (NLP) technology (such as spaCy or AllenNLP), understands the user's intention, and generates an appropriate response. For example, if a user says, "I'd like to talk about the difficulties I faced in a recent project," and the emotion engine recognizes this as "stress," it will generate responses such as, "What specifically were the difficulties you faced?" or "That must have been difficult. How did you deal with it?"

[0786] The server converts the generated response into speech using a speech synthesis engine and sends the speech data to the terminal.

[0787] 6. Audio output and re-input

[0788] The terminal reproduces the voice data received from the server and allows the user to hear the response.

[0789] The user listens to the playback and, if necessary, speaks again, and the process repeats.

[0790] 7. Data feedback and learning

[0791] After the dialogue is completed, the server stores all of the dialogue content (voice, text data, emotion data, and NLP analysis results) in a database.

[0792] The stored data will be used as training data for future AI models, improving the accuracy of the system.

[0793] Specific examples

[0794] For example, if a user sets a goal of "I want to be successful as the leader of the next project," the system can use this information to generate questions that delve deeper into the user's current situation and challenges, and provide them via voice.As another example, if a user says, "I'd like to talk about the difficulties I had in today's meeting," and the emotion engine recognizes "anxiety," a response based on the emotion, such as "That's difficult. What specifically were you worried about?", is generated in real time and returned to the user via voice.

[0795] This system enables more detailed responses that take into account the user's emotions, enabling more effective personalized coaching.

[0796] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0797] Step 1:

[0798] Registering Users

[0799] Input: A user launches an application and enters personal information such as name, age, interests, and goals.

[0800] How it works: The device takes the information entered by the user and converts it into JSON format.

[0801] Output: User information in JSON format is generated.

[0802] Next step: Send the user information in JSON format to the server.

[0803] Step 2:

[0804] Data storage

[0805] Input: User information in JSON format.

[0806] What happens: The server parses the received JSON data and stores it in the database.

[0807] Output: User information is saved in the database.

[0808] Next: Create a personalized profile for each user based on the stored user information.

[0809] Step 3:

[0810] Conversation scenario generation

[0811] Input: User information stored in the database.

[0812] How it works: The server uses a generative AI model (e.g., OpenAI GPT-4) to generate an optimal conversation scenario. Specifically, it inputs user information into a prompt sentence and generates a scenario such as, "What were the particular challenges you faced in your recent project?"

[0813] Output: Generated text data of the conversation scenario.

[0814] Next process: Convert the text scenario into audio data.

[0815] Step 4:

[0816] Speech synthesis

[0817] Input: Text data of the generated conversation scenario.

[0818] How it works: The server uses a speech synthesis engine (e.g., Google Cloud Text-to-Speech) to convert text data into voice data, optimizing voice characteristics (e.g., youthful voice, calm voice) based on the user's preferences.

[0819] Output: Audio file (e.g. MP3 format).

[0820] Next step: Send the audio data to the device.

[0821] Step 5:

[0822] Start a voice interaction

[0823] Input: The audio file sent from the server.

[0824] How it works: When a user presses the "Start voice interaction" button in an application, the device activates the microphone and plays an audio file.

[0825] Output: The user hears the start of the dialogue.

[0826] Next: Receive voice input from the user.

[0827] Step 6:

[0828] Audio data collection

[0829] Input: Speech input from the user.

[0830] How it works: The device collects and temporarily stores the user's voice data.

[0831] Output: Temporarily saved audio data.

[0832] Next step: Send the audio data to the server.

[0833] Step 7:

[0834] Analysis of audio data

[0835] Input: Audio data sent from the device.

[0836] How it works: The server converts the voice data into text using a speech recognition engine (e.g., Google Cloud Speech-to-Text) and recognizes the user's emotions using an emotion engine (e.g., Azure Emotion API).

[0837] Output: Text data and emotion data.

[0838] Next step: Analyze the text and sentiment data and generate an appropriate response.

[0839] Step 8:

[0840] Response Generation

[0841] Input: Text data and emotion data.

[0842] How it works: The server uses natural language processing (NLP) technology (such as spaCy or AllenNLP) to analyze text and sentiment data and generate appropriate responses to the user. For example, if a user says, "I'd like to talk about the difficulties I faced in a recent project," the server generates a response such as, "What specifically were the difficulties?"

[0843] Output: Text data of the response.

[0844] Next process: Convert the generated response into audio data.

[0845] Step 9:

[0846] Voiced responses

[0847] Input: Text data of the response.

[0848] How it works: The server uses a speech synthesis engine (e.g., Google Cloud Text-to-Speech) to convert the text data into audio data.

[0849] Output: Audio file.

[0850] Next step: Send the audio data to the device.

[0851] Step 10:

[0852] Playing audio data

[0853] Input: Audio data sent from the server.

[0854] Operation: The device plays the audio data received from the server, allowing the user to hear the response.

[0855] Output: A spoken response to the user.

[0856] Next step: Retry voice input if necessary.

[0857] Step 11:

[0858] Data feedback and learning

[0859] Input: All content of the dialogue (voice, text data, emotion data, and NLP analysis results).

[0860] How it works: The server stores the conversation in a database and uses it as learning data for future projects. The stored data is used to improve the generative AI model and increase the accuracy of the system.

[0861] Output: Training data stored in a database.

[0862] Next: Retrain and improve the AI ​​model to improve the system's accuracy.

[0863] The above is the specific processing flow of this system, and details of the specific operations and inputs / outputs at each step. This makes it possible to provide personalized coaching according to the user's emotions.

[0864] (Application example 2)

[0865] 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."

[0866] The objective of this invention is to provide personalized voice dialogue coaching based on the user's emotions and preferences, and in particular to support the user's mental and emotional well-being by recognizing the user's emotional state in real time and providing appropriate feedback. Conventional voice dialogue systems have difficulty recognizing the user's emotions and immediately reflecting them in responses, so more effective coaching is required.

[0867] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 2 is realized by the following means.

[0868] In this invention, the server includes means for saving user information based on personality and preferences, means for generating an optimal conversation scenario based on the saved user information, and means for converting the generated conversation scenario into voice data. This makes it possible to provide personalized coaching in real time according to the user's emotions and state.

[0869] "User information" refers to information about a user, such as their personality, preferences, areas of interest, and goals.

[0870] A "conversation scenario" refers to text data that is generated based on user information and that plans the flow of a conversation with a user.

[0871] "Emotional state" refers to data for determining the emotional state a user exhibits during a dialogue.

[0872] "Voice data" refers to an audio file converted from the generated conversation scenario by a voice synthesis engine.

[0873] "Speech recognition" refers to the technology that converts voice input from a user into text data.

[0874] "Appropriate reply" refers to analyzing the content of a user's speech and emotional state and generating a response that is deemed appropriate.

[0875] "Personalized coaching messages" refer to coaching messages that are individually optimized based on the user's personality, preferences, and emotional state.

[0876] "Database" refers to data storage that stores user information, dialogue content, emotional data, etc., and is used as future learning data.

[0877] A "natural language processing engine" refers to technology that analyzes user statements and text and generates appropriate responses.

[0878] "Real-time processing" refers to processing that analyzes data and generates responses immediately during a user interaction.

[0879] This invention is a system that provides personalized voice-interactive coaching based on a user's emotional state and individual preferences. The entire system is mainly composed of a server, a terminal, and a user. Specific embodiments for implementing this system are described below.

[0880] User registration and information storage

[0881] To use the system, a user launches the application and enters necessary information such as name, age, areas of interest, goals, etc. This information is sent to the server via the terminal, and the server stores the user information in a database and creates a personalized profile for each user.

[0882] Conversation scenario generation

[0883] The server uses an AI model (natural language processing engine) based on the stored user information to generate a conversation scenario suited to the user. For example, if the user is interested in "stress management," this scenario can include questions such as, "What has caused you stress recently?"

[0884] Generate audio data

[0885] The generated conversation scenario is converted into voice data using the server's voice synthesis engine, with the tone and pitch of the voice adjusted based on the user's preferences.

[0886] User voice input and emotion recognition

[0887] When a user initiates a dialogue, the device's microphone collects voice input, which is then sent to a server that uses a speech recognition engine to convert the speech into text data and an emotion engine to recognize the user's emotional state.

[0888] Real-time response and feedback

[0889] The server uses a natural language processing engine based on the recognized text data and emotion data to generate an appropriate response according to the user's comment and emotional state. The generated response is then converted into voice data by a speech synthesis engine and output to the user via the terminal.

[0890] Data storage and training

[0891] After the dialogue is completed, the server stores all dialogue data (voice data, text data, emotion data, and analysis results) in a database, which will be used as training data for future AI models, improving the accuracy and performance of the system.

[0892] For example, if a user says, "I'm feeling really stressed today," the emotion engine will detect "stress" and generate a response like this: "That's tough. Is there a specific reason why?"

[0893] Prompt Sentence Examples

[0894] If a user says something that suggests they are under stress, generate an appropriate coaching message. For example, if a user says, "I'm feeling really stressed today," generate a message like, "That sounds tough. Is there a specific reason for that?"

[0895] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[0896] Step 1:

[0897] A user launches the application and enters the required information, such as name, age, interests, and goals.

[0898] Input: User's personal information (name, age, interests, goals, etc.)

[0899] Output: Dataset as user information

[0900] The terminal collects information entered by the user and sends it to a server for analysis.

[0901] Step 2:

[0902] The server stores the transmitted user information in a database and creates a personalized profile for each user.

[0903] Input: User information data from the terminal

[0904] Output: User profile in the database

[0905] The server analyzes the input information and creates and saves a profile for each user.

[0906] Step 3:

[0907] Based on the user information stored on the server, a conversation scenario is generated using an AI model (natural language processing engine).

[0908] Input: User profile in database

[0909] Output: Conversation scenario

[0910] The server generates an appropriate conversation scenario based on the user's interests and goals.

[0911] Step 4:

[0912] The server passes the generated conversation scenario to a speech synthesis engine and converts it into voice data.

[0913] Input: Generated conversation scenario (text data)

[0914] Output: Audio data

[0915] The server converts the text data into speech and adjusts the tone and pitch of the speech based on the user's preferences.

[0916] Step 5:

[0917] When the user presses the "Start Voice Interaction" button, the device activates the microphone and receives voice input from the user.

[0918] Input: User's voice

[0919] Output: Temporarily saved audio data

[0920] The device collects the user's voice and temporarily stores it for analysis.

[0921] Step 6:

[0922] The device sends the temporarily saved voice data to the server, which then analyzes it with a voice recognition engine, converts it into text data, and recognizes the user's emotions using an emotion engine.

[0923] Input: Audio data sent from the device

[0924] Output: Text data and emotion recognition data

[0925] The server converts the voice data into text and also recognizes emotions.

[0926] Step 7:

[0927] The server uses a natural language processing engine to generate an appropriate response based on the text data and emotional data it recognizes.

[0928] Input: Text data, emotion recognition data

[0929] Output: Response (text data)

[0930] The server analyzes the user's comments and emotional state and generates an appropriate response.

[0931] Step 8:

[0932] The response generated by the server is passed back to the speech synthesis engine, converted into voice data, and then sent to the terminal.

[0933] Input: Generated response (text data)

[0934] Output: Response audio data

[0935] The server converts the text response into audio data and sends it to the device.

[0936] Step 9:

[0937] The terminal plays back the voice data from the server and lets the user hear the response. The user listens to the played back voice and makes further voice input as necessary.

[0938] Input: Audio data from the server

[0939] Output: The audio the user hears

[0940] The terminal plays the audio data and provides a response to the user.

[0941] Step 10:

[0942] After the dialogue is completed, the server stores all of the dialogue content (voice, text data, emotion data, and NLP analysis results) in a database.

[0943] Input: All dialogue data (voice, text, emotion data, analysis results)

[0944] Output: Interaction data stored in a database

[0945] The server stores all collected data in a database and uses it as learning data for the future.

[0946] 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.

[0947] 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.

[0948] 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.

[0949] [Third embodiment]

[0950] FIG. 5 shows an example of the configuration of a data processing system 310 according to the third embodiment.

[0951] 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.

[0952] 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).

[0953] 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.

[0954] 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.

[0955] 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).

[0956] 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.

[0957] 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.

[0958] 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.

[0959] 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.

[0960] 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.

[0961] 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."

[0962] The system of the present invention provides personalized voice interactive coaching based on individual characteristics and preferences. The following description will explain the overall flow of the system and the program's processing in detail with specific examples.

[0963] 1. User Registration

[0964] To use the system, a user launches the application and enters the required information, such as name, age, interests, and goals.

[0965] The terminal receives this information and transmits it to the server.

[0966] The server stores the submitted information in a database and creates a personalized profile for each user.

[0967] 2. Conversation scenario generation

[0968] The server generates optimal conversation scenarios based on registered user information. These scenarios are created using AI models based on the user's goals and interests.

[0969] For example, if a user is looking to "advance their career," the server might generate the question, "What was particularly challenging about your recent project?"

[0970] 3. Speech Synthesis

[0971] The server passes the generated text scenario to a speech synthesis engine, which converts the text into speech.

[0972] At this time, the voice characteristics (e.g., youthful voice, calm voice) are optimized according to the user's preferences.

[0973] The synthesized voice data is stored in a cache for the user ID.

[0974] 4. Starting a voice conversation

[0975] The user presses the "Start voice interaction" button within the application to start the voice interaction.

[0976] The device activates the microphone and begins receiving voice input from the user.

[0977] When the user speaks to the coach, the terminal collects the voice data and sends it to the server.

[0978] 5. Real-time processing and feedback

[0979] The server analyzes the received voice data in real time and converts it into text using a voice recognition engine.

[0980] The server analyzes this text using natural language processing (NLP) technology to understand the user's intention.

[0981] For example, if a user says, "I'd like to talk about the difficulties I had in a recent project," the server generates an appropriate response: "What specifically were the difficulties?"

[0982] The server converts this response into voice using a voice synthesis engine and sends the voice data to the terminal.

[0983] The terminal plays the audio data to the user and waits for the next audio input.

[0984] 6. Data feedback and learning

[0985] After the conversation is over, the server stores all conversation content (voice, text data, and NLP analysis results) in a database.

[0986] The saved data is used as training data for future AI models. This continuous learning allows the system to provide more accurate coaching in the next interaction.

[0987] As a concrete example, if a user sets a goal of "I want to be successful as the leader of the next project," the system will use this information to generate questions that delve deeper into the user's current situation and challenges, and provide these questions via voice. If the user says, "I'd like to talk about the difficulties I had in today's meeting," a response such as "What were the difficulties? Please tell us the specific situation" will be generated in real time and returned to the user via voice. This process allows the user to organize their own challenges and promote introspection.

[0988] The above is a specific embodiment for carrying out the present invention. This system makes it possible to provide natural, personalized, and interactive voice coaching that goes beyond conventional text-based interfaces.

[0989] The processing flow will be explained below.

[0990] Step 1:

[0991] To use the system, a user launches the application and enters required information such as name, age, areas of interest, and goals.

[0992] Step 2:

[0993] The terminal obtains the information entered by the user and sends it to the server.

[0994] Step 3:

[0995] The server stores the received user information in a database, which creates a user profile.

[0996] Step 4:

[0997] The server uses an AI model based on the saved user information to generate optimal conversation scenarios. For example, if a user is interested in career advancement, it generates a scenario such as, "What particular challenges did you face in your recent project?"

[0998] Step 5:

[0999] The server passes the generated conversation scenario to a speech synthesis engine, which converts the text into speech data, optimizing the voice characteristics (e.g., youthful voice, calm voice) based on the user's preferences.

[1000] Step 6:

[1001] When the user presses the "Start Voice Dialogue" button, the terminal activates the microphone and starts voice input.

[1002] Step 7:

[1003] When the user speaks to the coach, the device collects and temporarily stores the voice data, and then transmits the stored voice data to the server.

[1004] Step 8:

[1005] The server analyzes the received voice data using a voice recognition engine and converts it into text data.

[1006] Step 9:

[1007] The server analyzes the text data using natural language processing (NLP) technology to understand the user's intent. Based on the analysis results, it generates an appropriate response. For example, if a user says, "I'd like to talk about the difficulties I faced in a recent project," it generates a response such as, "What specifically were the difficulties you faced?"

[1008] Step 10:

[1009] The server passes the generated response to a speech synthesis engine, converts the text into voice data, and transmits the voice data to the terminal.

[1010] Step 11:

[1011] The terminal reproduces the voice data received from the server and allows the user to hear the response.

[1012] Step 12:

[1013] The user listens to the audio playback and, if necessary, speaks again, and the process repeats.

[1014] Step 13:

[1015] After the conversation is over, the server stores all of the conversation content (voice, text data, and NLP analysis results) in a database. This not only serves as a reference for future conversations, but also serves as training data for the AI ​​model.

[1016] By repeating each of the above steps, it is possible to provide individually optimized conversations for each user and achieve coaching that encourages self-reflection.

[1017] Example 1

[1018] 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."

[1019] Conventional voice dialogue systems provide uniform responses to users, making it difficult to provide personalized responses that reflect individual personalities and preferences. Furthermore, they lacked a mechanism for continuously accumulating and learning from dialogue data with users to provide more appropriate feedback for the next dialogue. This limited users' opportunities to receive truly useful coaching.

[1020] 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.

[1021] In this invention, the server includes means for storing user information based on personality and preferences, means for generating an optimal conversation scenario based on the stored user information, and means for converting the generated conversation scenario into voice data. This makes it possible to provide personalized voice dialogue and coaching to each user and support their continuous growth.

[1022] "Means of saving user information based on personality and preferences" refers to the function of saving information entered by the user, such as name, age, areas of interest, and goals, and creating a profile for each user.

[1023] "Means for generating an optimal conversation scenario based on stored user information" refers to a function for generating an optimal conversation scenario that corresponds to the user's goals and interests based on stored user information.

[1024] The "means for converting the generated conversation scenario into voice data" refers to a voice synthesis function that converts the generated text-format conversation scenario into voice data.

[1025] "Means for receiving voice input from the user and converting it into text data" refers to a voice recognition function that converts the voice spoken by the user into text data.

[1026] "Means for analyzing the content of user comments and generating appropriate responses" refers to a natural language processing function that analyzes the content of user comments and generates appropriate responses based on that content.

[1027] "Means for converting the generated response back into voice data and outputting it to the user" refers to a voice output function that converts the generated text response into voice data and provides it to the user.

[1028] "Means of saving the content of the dialogue in a database and using it as future learning data" refers to the function of saving records of dialogue with users in a database and using that data as learning data for the AI ​​model.

[1029] "Means for optimizing voice characteristics based on user information" refers to a function that adjusts the characteristics of synthesized voice (e.g., voice pitch and speed) according to the user's preferences.

[1030] "Means for improving model accuracy by continuously saving and learning from dialogue content" refers to a function that continuously accumulates dialogue data with users and uses that data to retrain the AI ​​model, thereby improving the accuracy of the model.

[1031] "Means for analyzing voice dialogue in real time and providing appropriate feedback" refers to a function for analyzing voice dialogue in real time and quickly providing appropriate feedback in response to user comments.

[1032] "Means for understanding the intention of a user's speech using natural language processing technology" refers to a function that uses natural language processing technology to analyze the content of a user's speech and accurately understand their intention.

[1033] The system of the present invention provides personalized voice interactive coaching based on an individual's personality and preferences. Detailed embodiments of the system are described below.

[1034] 1. User Registration

[1035] The user launches a dedicated application and enters the necessary information, such as their name, age, areas of interest, and goals. The entered information is sent by the device to the server. The server stores the received information in a database and creates a personalized profile for each user. For example, MySQL is used as the database, and user information is stored in a "Users" table.

[1036] 2. Conversation scenario generation

[1037] The server retrieves user information from the database and generates an optimal conversation scenario. This generation uses a generative AI model (e.g., GPT-3). If the user's goal is "career advancement," the server generates questions such as, "What was particularly challenging about your recent project?"

[1038] 3. Speech Synthesis

[1039] The server passes the generated text scenario to a speech synthesis engine (e.g., Google Text-to-Speech API) and converts the text into speech data. The server optimizes the voice characteristics, such as a youthful voice or a calm voice, according to the user's preferences. The synthesized speech data is stored in a cache system (e.g., Redis).

[1040] 4. Starting a voice conversation

[1041] The user presses the "Start voice interaction" button in the application to start the voice interaction. The device activates the microphone and starts the user's voice input. As the user speaks, the voice data is sent from the device to the server.

[1042] 5. Real-time processing and feedback

[1043] The server analyzes the received voice data in real time and converts it into text using a speech recognition engine (for example, IBM Watson Speech to Text). The converted text data is then analyzed using natural language processing (NLP) technology (for example, Google Dialogflow) to understand the user's intention. For example, if the user says, "I'd like to talk about the difficulties I had in a recent project," the server generates an appropriate response such as, "What specifically were the difficulties you had?" This response is again converted into speech using a speech synthesis engine and sent to the device. The device plays the voice data to the user and waits for the next voice input.

[1044] 6. Data feedback and learning

[1045] Once the conversation is over, the server stores all conversation content (voice, text, NLP analysis results, etc.) in a database. This data is used as training data for future AI models. Continuous learning allows the system to provide more accurate coaching in the next conversation.

[1046] As a concrete example, if a user sets a goal of "I want to be successful as the leader of the next project," the system can use this information to generate questions that delve deeper into the user's current situation and challenges, and provide these questions via voice. If the user says, "I'd like to talk about the difficulties I had in today's meeting," a response such as "What were the difficulties you had? Please tell us the specific situation" is generated in real time and returned as voice. This process allows the user to organize their own challenges and promote introspection.

[1047] An example of a prompt for a generative AI model is:

[1048] "Generate an appropriate response when a user says, 'I'd like to talk about something I struggled with in today's meeting.'"

[1049] The above is a specific embodiment for carrying out the present invention. This system makes it possible to provide natural, personalized, and interactive voice coaching that goes beyond conventional text-based interfaces.

[1050] The flow of the identification process in the first embodiment will be described with reference to FIG.

[1051] Step 1: Collect user information

[1052] The user starts the dedicated application and enters information such as their name, age, areas of interest, and goals.

[1053] Input: Information entered by the user, such as name, age, interests, goals, etc.

[1054] The terminal receives the input information and stores it in temporary memory for state maintenance.

[1055] Output: The terminal sends the input information to the server as an HTTP request.

[1056] Step 2: Save user information

[1057] The server stores the received user information in a database.

[1058] Input: User information sent from the device.

[1059] For example, the server uses a MySQL database to store information in a "Users" table.

[1060] Output: User information recorded in a database.

[1061] Step 3: Generate conversation scenarios

[1062] The server acquires user information from a database and generates an optimal conversation scenario.

[1063] Input: Database user information.

[1064] The server uses a generative AI model (e.g., GPT-3) to generate optimal scenarios based on the user's goals and interests.

[1065] Output: The generated conversation scenario in text format.

[1066] Example: If a user's goal is to "advance their career," generate the following question scenario: "What was particularly challenging about your recent project?"

[1067] Step 4: Converting to audio data

[1068] The server passes the conversation scenario (text) to a speech synthesis engine and converts it into voice data.

[1069] Input: Text data of the generated conversation scenario.

[1070] The server converts the text to speech using, for example, the Google Text-to-Speech API.

[1071] Output: Audio data.

[1072] The server stores the audio data in a cache system (e.g., Redis).

[1073] Step 5: Initiating a voice interaction

[1074] The user presses the "Start Voice Dialogue" button in the application to start the voice dialogue.

[1075] Input: The user presses the "Start voice interaction" button.

[1076] The device detects the button press event, activates the microphone, and starts voice input.

[1077] Output: The audio data recorded by the device.

[1078] Step 6: Send and convert audio data

[1079] The terminal transmits the recorded voice data to the server.

[1080] Input: The audio data spoken by the user.

[1081] The server converts the received voice data into text data using a voice recognition engine (e.g., IBM Watson Speech to Text).

[1082] Output: Text data.

[1083] Step 7: Analyzing the content of the comment and generating a response

[1084] The server analyzes the text data using natural language processing (NLP) technology (e.g., Google Dialogflow) to understand the user's intention in speaking.

[1085] Input: Text data generated by speech recognition.

[1086] The server generates an appropriate response based on the analysis results.

[1087] Output: The generated response text.

[1088] Example: If a user says, "I'd like to talk about a challenge I had on a recent project," generate a response of, "What specifically were the challenges?"

[1089] Step 8: Convert the response text to audio data

[1090] The server passes the response text to the speech synthesis engine again and converts it into voice data.

[1091] Input: The generated response text.

[1092] Output: The converted audio data.

[1093] Step 9: Send and play responses

[1094] The server transmits the audio data to the terminal.

[1095] The terminal plays back the received voice data and waits for voice input of the next follow-up question.

[1096] Input: Audio data sent from the server.

[1097] Output: The audio data to be played.

[1098] Step 10: Storing and Learning Dialogue Data

[1099] After the dialogue is completed, the server stores all dialogue content (voice data, text data, and NLP analysis results) in a database.

[1100] Input: Full historical data of the interaction.

[1101] The saved data is used as training data for the AI ​​model to provide more accurate coaching in the next interaction.

[1102] Output: Dialogue history stored in a database.

[1103] The above is the specific processing flow of the program for this system. This system makes it possible to provide personalized voice-interactive coaching to each user.

[1104] (Application example 1)

[1105] 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."

[1106] Conventional food delivery systems have difficulty providing personalized menu suggestions because they do not adequately consider the user's individual preferences and dietary restrictions. Furthermore, even voice-based interactive systems have faced many technical challenges in achieving natural dialogue with the user. The present invention aims to solve these challenges and provide users with more personalized menu suggestions and natural voice dialogue.

[1107] 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.

[1108] In this invention, the server includes means for saving user information based on the user's personality and preferences, means for generating an optimal conversation scenario based on the saved user information, means for converting the generated conversation scenario into voice data, means for receiving voice input from the user and converting it into text data, means for analyzing the user's utterances and generating an appropriate response, means for converting the generated response back into voice data and outputting it to the user, means for saving the dialogue content and using it as future learning data, means for generating personalized menu suggestions based on the user's food preferences and past order history, and means for audibly confirming the user's order details and optimizing the suggestions in real time, thereby enabling natural and personalized voice dialogue and menu suggestions that accommodate the user's individual preferences and dietary restrictions.

[1109] The "means for storing user information based on characteristics and preferences" refers to a device or program that has the function of collecting information about users' characteristics and individual preferences and storing it in a database.

[1110] "Means for generating an optimal dialogue scenario based on stored user information" refers to a device or program that has the function of automatically generating the most appropriate dialogue scenario for a user based on stored user information.

[1111] The "means for converting the generated conversation scenario into voice data" refers to a device or program that has the function of converting the generated text-format conversation scenario into voice data.

[1112] The "means for receiving voice input from a user and converting it into text data" refers to a device or program that has the function of converting the user's speech into text using voice recognition technology.

[1113] The "means for analyzing the content of a user's comments and generating an appropriate response" refers to a device or program that has the function of analyzing a user's comments converted into text format and generating an appropriate response based on the content.

[1114] The "means for converting the generated response back into voice data and outputting it to the user" refers to a device or program that has the function of converting the generated text response back into voice data and outputting it to the user.

[1115] The "means for saving the content of the dialogue and using it as future learning data" refers to a device or program that has the function of saving the content of the dialogue with the user in a database and using it as future learning data.

[1116] "Means for generating personalized menu suggestions based on a user's food preferences and past ordering history" refers to a device or program that has the function of automatically generating individually customized menu suggestions based on a user's food preferences and past ordering history.

[1117] The "means for confirming the user's order details by voice and optimizing suggestions in real time" refers to a device or program that has the function of confirming the user's order details by voice and updating them to the optimal suggestions on the spot.

[1118] This invention provides a voice-based interactive food delivery system based on user characteristics and preferences, which can assist users in the interactive ordering process and provide more personalized menu suggestions.

[1119] Hardware and software used

[1120] The following hardware and software are used as the main components of the system:

[1121] Hardware: Smartphone (microphone, speaker), server (database)

[1122] Software: AI models, speech recognition engines, speech synthesis engines, natural language processing engines (NLP)

[1123] System Components

[1124] 1. User Registration

[1125] First, a user launches the application on their smartphone and enters their name, age, food preferences (e.g., Japanese food, Western food, vegan, etc.), past order history, and allergy information. The smartphone receives this information and sends it to the server. The server stores the information in a database and creates a personalized profile for each user.

[1126] 2. Proposed scenario generation

[1127] The server generates an optimal menu recommendation scenario based on registered user information. This scenario is created using an AI model. For example, if the user is vegan, the recommendation scenario will include vegan menu items.

[1128] 3. Speech Synthesis

[1129] The server passes the generated text scenario to a speech synthesis engine, which converts the text into speech data. The voice characteristics (e.g., youthful voice, calm voice) are optimized according to the user's preferences. The synthesized speech data is stored in a cache.

[1130] 4. Starting a voice conversation

[1131] The user presses the "Start Voice Interaction" button in the application to activate the microphone and start the voice interaction. The smartphone receives the user's voice input and sends the voice data to the server.

[1132] 5. Real-time processing and feedback

[1133] The server analyzes the received voice data in real time and converts it into text using a speech recognition engine. This text is then analyzed using natural language processing (NLP) technology to understand the user's intent. For example, in response to a question such as "What's your recommendation today?", a response such as "Today's recommendations are salmon sushi and Margherita pizza" is generated. The generated response is then converted back into voice data using a speech synthesis engine and sent to the smartphone. The smartphone then plays the response back to the user.

[1134] 6. Data feedback and learning

[1135] After the dialogue with the user is completed, the server stores all dialogue content (voice, text data, and NLP analysis results) in a database. This data is used as training data for future AI models, enabling more accurate menu suggestions to be provided in the next dialogue.

[1136] Examples of specific examples and prompts

[1137] For example, if a user registers in the app that they like "Japanese food" and "pizza," the server will use this information to generate a menu scenario that suggests "salmon sushi" and "Margherita pizza" as today's recommendations. As a specific example of a prompt, a scenario will be generated that answers the question, "What's your recommendation today?" with an appropriate menu item.

[1138] Examples of prompts:

[1139] What's your recommendation today?

[1140] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[1141] Step 1:

[1142] Users launch the application on their smartphone and enter their name, age, food preferences (Japanese, Western, vegan, etc.), past order history, and allergy information. The device receives this information and sends it to the server. The entered data is stored in a database, creating a personalized profile for each user.

[1143] Step 2:

[1144] The server generates an optimal menu suggestion scenario based on the saved user information. This is where the AI ​​model comes into play. It performs calculations to generate menu suggestions based on the user's input data (food preferences, past order history, allergy information), and selects a menu that is suitable for the user.

[1145] Step 3:

[1146] The server passes the generated text-format proposed scenario to a speech synthesis engine, which converts the text into speech data. The speech synthesis engine sets the voice characteristics (e.g., youthful voice, calm voice) according to the user's preferences. The generated speech data is saved in a cache.

[1147] Step 4:

[1148] The user presses the "Start Voice Dialogue" button in the application to start a voice dialogue. The device activates the microphone and receives the user's voice input. The collected voice data is sent to the server.

[1149] Step 5:

[1150] The server analyzes the received voice data in real time and converts it into text data using a speech recognition engine. The converted text data is then used to analyze the user's intention using natural language processing (NLP) technology. For example, if a user asks, "What's recommended today?", the intention of the speech is analyzed.

[1151] Step 6:

[1152] The server generates an appropriate response based on the analysis results. For example, it generates a response such as "Today's recommendations are salmon sushi and Margherita pizza," and converts it into voice data using a speech synthesis engine. The generated voice data is then sent to the device.

[1153] Step 7:

[1154] The device plays the voice data sent from the server to the user, who then listens to the response and makes the next voice input (e.g., "I'd like to order salmon sushi"), allowing the conversation to continue and receiving menu suggestions updated in real time.

[1155] Step 8:

[1156] After the dialogue is completed, the server stores all dialogue content (voice, text data, and NLP analysis results) in a database. This adds new information about the user and uses it as learning data for the AI ​​model from the next time onwards, improving the accuracy of suggestions.

[1157] 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.

[1158] This invention provides more effective coaching by combining a personalized voice dialogue coaching system based on the user's personality and preferences with an emotion engine that recognizes the user's emotions. The following explanation will explain the overall processing flow of the system and the program processing in detail with concrete examples.

[1159] 1. User Registration

[1160] To use the system, a user launches the application and enters required information such as name, age, areas of interest, and goals.

[1161] The terminal acquires the information entered by the user and transmits it to the server.

[1162] The server stores the transmitted user information in a database and creates a personalized profile for each user.

[1163] 2. Conversation scenario generation

[1164] The server uses an AI model based on the saved user information to generate optimal conversation scenarios. For example, if a user is interested in career advancement, it generates a scenario such as, "What particular challenges did you face in your recent project?"

[1165] 3. Speech Synthesis

[1166] The server passes the generated text scenario to a speech synthesis engine to convert the text into speech data, optimizing the voice characteristics (e.g., youthful voice, calm voice) based on the user's preferences.

[1167] 4. User Emotion Recognition

[1168] When a user presses the "Start voice interaction" button in the application, the device activates the microphone and begins voice input.

[1169] When the user speaks, the device collects the voice data, temporarily stores it, and then sends it to the server.

[1170] The server analyzes the received voice data using a voice recognition engine and converts it into text, while at the same time recognizing the user's emotions using an emotion engine.

[1171] 5. Real-time processing and feedback

[1172] The server analyzes the text data and the recognized emotions using natural language processing (NLP) technology to understand the user's intention and generate an appropriate response based on the emotion.

[1173] For example, if a user says, "I'd like to talk about the difficulties I had in a recent project," and the emotion engine recognizes "stress," it will generate responses that take emotions into account, such as, "What specifically were the difficulties?" or "That must have been difficult. How did you deal with it?"

[1174] The server converts the generated response into voice using a voice synthesis engine and transmits the voice data to the terminal.

[1175] 6. Audio output and re-input

[1176] The terminal reproduces the voice data received from the server and allows the user to hear the response.

[1177] The user listens to the audio playback and, if necessary, speaks again, and the process repeats.

[1178] 7. Data feedback and learning

[1179] After the dialogue is completed, the server stores all of the dialogue content (voice, text data, emotion data, and NLP analysis results) in a database.

[1180] The stored data will be used as training data for future AI models, improving the accuracy of the system.

[1181] As a concrete example, if a user sets a goal of "I want to be successful as the leader of the next project," the system will use this information to generate questions that delve deeper into the user's current situation and challenges, and provide them via voice. If the user says, "I'd like to talk about the difficulties I had in today's meeting," and the emotion engine recognizes "anxiety," a response based on the emotion, such as "That's difficult. What specifically were you worried about?", will be generated in real time and returned to the user via voice. This process allows the user to organize their own emotions and deepen their introspection.

[1182] The above is a concrete example of how to implement a system that combines an emotion engine that recognizes the user's emotions. This system enables detailed responses based on the user's emotions, and can provide more effective personalized coaching.

[1183] The processing flow will be explained below.

[1184] Step 1:

[1185] To use the system, a user launches the application and enters required information such as name, age, areas of interest, and goals.

[1186] Step 2:

[1187] The terminal obtains the information entered by the user and sends it to the server.

[1188] Step 3:

[1189] The server stores the received user information in a database, creating a personalized profile for each user.

[1190] Step 4:

[1191] The server uses an AI model based on the saved user information to generate optimal conversation scenarios. For example, if a user is interested in career advancement, it generates a scenario such as, "What particular challenges did you face in your recent project?"

[1192] Step 5:

[1193] The server passes the generated text scenario to a speech synthesis engine and converts it from text to speech data. During this process, the voice characteristics (e.g., youthful voice, calm voice) are optimized based on the user's preferences. The synthesized speech data is stored in a cache for the user ID.

[1194] Step 6:

[1195] When a user presses the "Start voice interaction" button in the application, the device activates the microphone and starts voice input.

[1196] Step 7:

[1197] When a user speaks, the device collects and temporarily stores the voice data, which is then sent to the server.

[1198] Step 8:

[1199] The server analyzes the received voice data using a voice recognition engine and converts it into text data.

[1200] Step 9:

[1201] The server uses an emotion engine to analyze the voice data received at the same time as the text data and recognize the user's emotions (e.g., joy, sadness, anger, surprise, etc.). For example, when a user says, "I had a hard time with a recent project," the emotion engine recognizes "stress."

[1202] Step 10:

[1203] The server uses natural language processing (NLP) technology to analyze the text data and the recognized emotional data to understand the user's intention. Based on the results of this analysis, it generates an appropriate response based on the user's emotions. For example, it generates a response that takes emotions into consideration, such as, "That must have been difficult. How did you deal with it?"

[1204] Step 11:

[1205] The server passes the generated response to a speech synthesis engine, converts the text into voice data, and transmits the voice data to the terminal.

[1206] Step 12:

[1207] The terminal reproduces the voice data received from the server and allows the user to hear the response.

[1208] Step 13:

[1209] The user listens to the audio playback and, if necessary, speaks again, and the process repeats.

[1210] Step 14:

[1211] After the dialogue is completed, the server stores all of the dialogue content (voice, text data, emotion data, and NLP analysis results) in a database.

[1212] Step 15:

[1213] The saved data will be used as training data for future AI models, improving the accuracy of the system and enabling more precise and personalized responses in subsequent interactions.

[1214] Through each of these steps, users are provided with conversations that include individually optimized emotion recognition, enabling effective coaching that encourages self-reflection.

[1215] Example 2

[1216] 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."

[1217] Conventional voice dialogue systems have difficulty recognizing and responding to changes in a user's emotions, as well as their personality and preferences, in real time. As a result, responses to users are uniform, making it impossible to provide effective personalized coaching. Furthermore, feedback tailored to the user's emotions is lacking, resulting in a poor user experience.

[1218] The specific processing by the specific processing unit 290 of the data processing device 12 in the second embodiment is realized by the following means.

[1219] In this invention, the server includes: [means for saving user information based on the user's personality and preferences;] [means for generating an optimal conversation scenario based on the saved user information;] [means for converting the generated conversation scenario into voice data;] [means for receiving voice input from the user and converting it into text data;] [means for analyzing the user's utterances and emotions and generating an appropriate response;] [means for converting the generated response back into voice data and outputting it to the user;] [means for saving the dialogue content in a database and using it as future learning data; and [means for recognizing the user's emotions.] This makes it possible to recognize the user's emotions in real time and provide a detailed response. Therefore, more effective personalized coaching can be provided, improving the quality of the user experience.

[1220] "User Information" refers to personal information about a User, such as their characteristics, preferences, interests, and goals.

[1221] The "conversation scenario" refers to a scenario such as a dialogue progress plan and question content generated based on information input by the user.

[1222] "Voice data" refers to audio data obtained by converting text information using a speech synthesis engine.

[1223] "Text data" refers to data in the form of a character string that is generated by converting a user's voice input using a voice recognition engine.

[1224] "Emotions" refer to the psychological state or feelings expressed by a user during a voice interaction.

[1225] "Analysis" refers to the process of analyzing and understanding what users say and their emotions.

[1226] A "reply" refers to an appropriate response that is generated based on what the user says.

[1227] "Database" refers to a data management system for storing information about interactions and users.

[1228] "Real-time" refers to the process of instantly analyzing and responding to a user's voice input.

[1229] This invention is a voice-interactive coaching system that is personalized based on the user's personality and preferences, and by combining it with an emotion engine that recognizes the user's emotions, it provides more effective coaching. The processing flow of the entire system and specific examples are described in detail below.

[1230] This system consists of three main elements: a server, a terminal, and a user.

[1231] 1. User Registration

[1232] A user launches an application and enters personal information such as name, age, interests, and goals.

[1233] The device acquires the input information and sends it to the server using the HTTP or HTTPS communication protocol.

[1234] The server stores the received information in a database (e.g., MySQL or MongoDB) and creates a personalized profile for each user.

[1235] 2. Conversation scenario generation

[1236] The server uses a generative AI model (e.g., OpenAI GPT-4) to generate optimal conversation scenarios based on the saved user information. Specifically, if the user is interested in "career advancement," it generates a scenario such as "What particular challenges did you face in your recent project?"

[1237] 3. Speech Synthesis

[1238] The server passes the generated text scenario to a speech synthesis engine (e.g., Google Cloud Text-to-Speech) to convert the text into voice data. The voice characteristics (e.g., youthful voice, calm voice) are optimized based on the user's preferences.

[1239] 4. User Emotion Recognition

[1240] When the user presses the "Start voice interaction" button, the device activates the microphone and begins voice input.

[1241] When a user speaks, the device collects and temporarily stores the voice data, which is then sent to the server in a streaming or batch process.

[1242] The server converts the voice data into text using a speech recognition engine (e.g., Google Cloud Speech-to-Text) and recognizes the user's emotions using an emotion engine (e.g., Azure Emotion API).

[1243] 5. Real-time processing and feedback

[1244] The server analyzes the text data and emotions using natural language processing (NLP) technology (such as spaCy or AllenNLP), understands the user's intention, and generates an appropriate response. For example, if a user says, "I'd like to talk about the difficulties I faced in a recent project," and the emotion engine recognizes this as "stress," it will generate responses such as, "What specifically were the difficulties you faced?" or "That must have been difficult. How did you deal with it?"

[1245] The server converts the generated response into speech using a speech synthesis engine and sends the speech data to the terminal.

[1246] 6. Audio output and re-input

[1247] The terminal reproduces the voice data received from the server and allows the user to hear the response.

[1248] The user listens to the playback and, if necessary, speaks again, and the process repeats.

[1249] 7. Data feedback and learning

[1250] After the dialogue is completed, the server stores all of the dialogue content (voice, text data, emotion data, and NLP analysis results) in a database.

[1251] The stored data will be used as training data for future AI models, improving the accuracy of the system.

[1252] Specific examples

[1253] For example, if a user sets a goal of "I want to be successful as the leader of the next project," the system can use this information to generate questions that delve deeper into the user's current situation and challenges, and provide them via voice.As another example, if a user says, "I'd like to talk about the difficulties I had in today's meeting," and the emotion engine recognizes "anxiety," a response based on the emotion, such as "That's difficult. What specifically were you worried about?", is generated in real time and returned to the user via voice.

[1254] This system enables more detailed responses that take into account the user's emotions, enabling more effective personalized coaching.

[1255] The flow of the identification process in the second embodiment will be described with reference to FIG.

[1256] Step 1:

[1257] Registering Users

[1258] Input: A user launches an application and enters personal information such as name, age, interests, and goals.

[1259] How it works: The device takes the information entered by the user and converts it into JSON format.

[1260] Output: User information in JSON format is generated.

[1261] Next step: Send the user information in JSON format to the server.

[1262] Step 2:

[1263] Data storage

[1264] Input: User information in JSON format.

[1265] What happens: The server parses the received JSON data and stores it in the database.

[1266] Output: User information is saved in the database.

[1267] Next: Create a personalized profile for each user based on the stored user information.

[1268] Step 3:

[1269] Conversation scenario generation

[1270] Input: User information stored in the database.

[1271] How it works: The server uses a generative AI model (e.g., OpenAI GPT-4) to generate an optimal conversation scenario. Specifically, it inputs user information into a prompt sentence and generates a scenario such as, "What were the particular challenges you faced in your recent project?"

[1272] Output: Generated text data of the conversation scenario.

[1273] Next process: Convert the text scenario into audio data.

[1274] Step 4:

[1275] Speech synthesis

[1276] Input: Text data of the generated conversation scenario.

[1277] How it works: The server uses a speech synthesis engine (e.g., Google Cloud Text-to-Speech) to convert text data into voice data, optimizing voice characteristics (e.g., youthful voice, calm voice) based on the user's preferences.

[1278] Output: Audio file (e.g. MP3 format).

[1279] Next step: Send the audio data to the device.

[1280] Step 5:

[1281] Start a voice interaction

[1282] Input: The audio file sent from the server.

[1283] How it works: When a user presses the "Start voice interaction" button in an application, the device activates the microphone and plays an audio file.

[1284] Output: The user hears the start of the dialogue.

[1285] Next: Receive voice input from the user.

[1286] Step 6:

[1287] Audio data collection

[1288] Input: Speech input from the user.

[1289] How it works: The device collects and temporarily stores the user's voice data.

[1290] Output: Temporarily saved audio data.

[1291] Next step: Send the audio data to the server.

[1292] Step 7:

[1293] Analysis of audio data

[1294] Input: Audio data sent from the device.

[1295] How it works: The server converts the voice data into text using a speech recognition engine (e.g., Google Cloud Speech-to-Text) and recognizes the user's emotions using an emotion engine (e.g., Azure Emotion API).

[1296] Output: Text data and emotion data.

[1297] Next step: Analyze the text and sentiment data and generate an appropriate response.

[1298] Step 8:

[1299] Response Generation

[1300] Input: Text data and emotion data.

[1301] How it works: The server uses natural language processing (NLP) technology (such as spaCy or AllenNLP) to analyze text and sentiment data and generate appropriate responses to the user. For example, if a user says, "I'd like to talk about the difficulties I faced in a recent project," the server generates a response such as, "What specifically were the difficulties?"

[1302] Output: Text data of the response.

[1303] Next process: Convert the generated response into audio data.

[1304] Step 9:

[1305] Voiced responses

[1306] Input: Text data of the response.

[1307] How it works: The server uses a speech synthesis engine (e.g., Google Cloud Text-to-Speech) to convert the text data into audio data.

[1308] Output: Audio file.

[1309] Next step: Send the audio data to the device.

[1310] Step 10:

[1311] Playing audio data

[1312] Input: Audio data sent from the server.

[1313] Operation: The device plays the audio data received from the server, allowing the user to hear the response.

[1314] Output: A spoken response to the user.

[1315] Next step: Retry voice input if necessary.

[1316] Step 11:

[1317] Data feedback and learning

[1318] Input: All content of the dialogue (voice, text data, emotion data, and NLP analysis results).

[1319] How it works: The server stores the conversation in a database and uses it as learning data for future projects. The stored data is used to improve the generative AI model and increase the accuracy of the system.

[1320] Output: Training data stored in a database.

[1321] Next: Retrain and improve the AI ​​model to improve the system's accuracy.

[1322] The above is the specific processing flow of this system, and details of the specific operations and inputs / outputs at each step. This makes it possible to provide personalized coaching according to the user's emotions.

[1323] (Application example 2)

[1324] 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."

[1325] The objective of this invention is to provide personalized voice dialogue coaching based on the user's emotions and preferences, and in particular to support the user's mental and emotional well-being by recognizing the user's emotional state in real time and providing appropriate feedback. Conventional voice dialogue systems have difficulty recognizing the user's emotions and immediately reflecting them in responses, so more effective coaching is required.

[1326] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 2 is realized by the following means.

[1327] In this invention, the server includes means for saving user information based on personality and preferences, means for generating an optimal conversation scenario based on the saved user information, and means for converting the generated conversation scenario into voice data. This makes it possible to provide personalized coaching in real time according to the user's emotions and state.

[1328] "User information" refers to information about a user, such as their personality, preferences, areas of interest, and goals.

[1329] A "conversation scenario" refers to text data that is generated based on user information and that plans the flow of a conversation with a user.

[1330] "Emotional state" refers to data for determining the emotional state a user exhibits during a dialogue.

[1331] "Voice data" refers to an audio file converted from the generated conversation scenario by a voice synthesis engine.

[1332] "Speech recognition" refers to the technology that converts voice input from a user into text data.

[1333] "Appropriate reply" refers to analyzing the content of a user's speech and emotional state and generating a response that is deemed appropriate.

[1334] "Personalized coaching messages" refer to coaching messages that are individually optimized based on the user's personality, preferences, and emotional state.

[1335] "Database" refers to data storage that stores user information, dialogue content, emotional data, etc., and is used as future learning data.

[1336] A "natural language processing engine" refers to technology that analyzes user statements and text and generates appropriate responses.

[1337] "Real-time processing" refers to processing that analyzes data and generates responses immediately during a user interaction.

[1338] This invention is a system that provides personalized voice-interactive coaching based on a user's emotional state and individual preferences. The entire system is mainly composed of a server, a terminal, and a user. Specific embodiments for implementing this system are described below.

[1339] User registration and information storage

[1340] To use the system, a user launches the application and enters necessary information such as name, age, areas of interest, goals, etc. This information is sent to the server via the terminal, and the server stores the user information in a database and creates a personalized profile for each user.

[1341] Conversation scenario generation

[1342] The server uses an AI model (natural language processing engine) based on the stored user information to generate a conversation scenario suited to the user. For example, if the user is interested in "stress management," this scenario can include questions such as, "What has caused you stress recently?"

[1343] Generate audio data

[1344] The generated conversation scenario is converted into voice data using the server's voice synthesis engine, with the tone and pitch of the voice adjusted based on the user's preferences.

[1345] User voice input and emotion recognition

[1346] When a user initiates a dialogue, the device's microphone collects voice input, which is then sent to a server that uses a speech recognition engine to convert the speech into text data and an emotion engine to recognize the user's emotional state.

[1347] Real-time response and feedback

[1348] The server uses a natural language processing engine based on the recognized text data and emotion data to generate an appropriate response according to the user's comment and emotional state. The generated response is then converted into voice data by a speech synthesis engine and output to the user via the terminal.

[1349] Data storage and training

[1350] After the dialogue is completed, the server stores all dialogue data (voice data, text data, emotion data, and analysis results) in a database, which will be used as training data for future AI models, improving the accuracy and performance of the system.

[1351] For example, if a user says, "I'm feeling really stressed today," the emotion engine will detect "stress" and generate a response like this: "That's tough. Is there a specific reason why?"

[1352] Prompt Sentence Examples

[1353] If a user says something that suggests they are under stress, generate an appropriate coaching message. For example, if a user says, "I'm feeling really stressed today," generate a message like, "That sounds tough. Is there a specific reason for that?"

[1354] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[1355] Step 1:

[1356] A user launches the application and enters the required information, such as name, age, interests, and goals.

[1357] Input: User's personal information (name, age, interests, goals, etc.)

[1358] Output: Dataset as user information

[1359] The terminal collects information entered by the user and sends it to a server for analysis.

[1360] Step 2:

[1361] The server stores the transmitted user information in a database and creates a personalized profile for each user.

[1362] Input: User information data from the terminal

[1363] Output: User profile in the database

[1364] The server analyzes the input information and creates and saves a profile for each user.

[1365] Step 3:

[1366] Based on the user information stored on the server, a conversation scenario is generated using an AI model (natural language processing engine).

[1367] Input: User profile in database

[1368] Output: Conversation scenario

[1369] The server generates an appropriate conversation scenario based on the user's interests and goals.

[1370] Step 4:

[1371] The server passes the generated conversation scenario to a speech synthesis engine and converts it into voice data.

[1372] Input: Generated conversation scenario (text data)

[1373] Output: Audio data

[1374] The server converts the text data into speech and adjusts the tone and pitch of the speech based on the user's preferences.

[1375] Step 5:

[1376] When the user presses the "Start Voice Interaction" button, the device activates the microphone and receives voice input from the user.

[1377] Input: User's voice

[1378] Output: Temporarily saved audio data

[1379] The device collects the user's voice and temporarily stores it for analysis.

[1380] Step 6:

[1381] The device sends the temporarily saved voice data to the server, which then analyzes it with a voice recognition engine, converts it into text data, and recognizes the user's emotions using an emotion engine.

[1382] Input: Audio data sent from the device

[1383] Output: Text data and emotion recognition data

[1384] The server converts the voice data into text and also recognizes emotions.

[1385] Step 7:

[1386] The server uses a natural language processing engine to generate an appropriate response based on the text data and emotional data it recognizes.

[1387] Input: Text data, emotion recognition data

[1388] Output: Response (text data)

[1389] The server analyzes the user's comments and emotional state and generates an appropriate response.

[1390] Step 8:

[1391] The response generated by the server is passed back to the speech synthesis engine, converted into voice data, and then sent to the terminal.

[1392] Input: Generated response (text data)

[1393] Output: Response audio data

[1394] The server converts the text response into audio data and sends it to the device.

[1395] Step 9:

[1396] The terminal plays back the voice data from the server and lets the user hear the response. The user listens to the played back voice and makes further voice input as necessary.

[1397] Input: Audio data from the server

[1398] Output: The audio the user hears

[1399] The terminal plays the audio data and provides a response to the user.

[1400] Step 10:

[1401] After the dialogue is completed, the server stores all of the dialogue content (voice, text data, emotion data, and NLP analysis results) in a database.

[1402] Input: All dialogue data (voice, text, emotion data, analysis results)

[1403] Output: Interaction data stored in a database

[1404] The server stores all collected data in a database and uses it as learning data for the future.

[1405] 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.

[1406] 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.

[1407] 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.

[1408] [Fourth embodiment]

[1409] FIG. 7 shows an example of the configuration of a data processing system 410 according to the fourth embodiment.

[1410] 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.

[1411] 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).

[1412] 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.

[1413] 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.

[1414] 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).

[1415] 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.

[1416] 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.

[1417] 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.

[1418] 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.

[1419] 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.

[1420] 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.

[1421] 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."

[1422] The system of the present invention provides personalized voice interactive coaching based on individual characteristics and preferences. The following description will explain the overall flow of the system and the program's processing in detail with specific examples.

[1423] 1. User Registration

[1424] To use the system, a user launches the application and enters the required information, such as name, age, interests, and goals.

[1425] The terminal receives this information and transmits it to the server.

[1426] The server stores the submitted information in a database and creates a personalized profile for each user.

[1427] 2. Conversation scenario generation

[1428] The server generates optimal conversation scenarios based on registered user information. These scenarios are created using AI models based on the user's goals and interests.

[1429] For example, if a user is looking to "advance their career," the server might generate the question, "What was particularly challenging about your recent project?"

[1430] 3. Speech Synthesis

[1431] The server passes the generated text scenario to a speech synthesis engine, which converts the text into speech.

[1432] At this time, the voice characteristics (e.g., youthful voice, calm voice) are optimized according to the user's preferences.

[1433] The synthesized voice data is stored in a cache for the user ID.

[1434] 4. Starting a voice conversation

[1435] The user presses the "Start voice interaction" button within the application to start the voice interaction.

[1436] The device activates the microphone and begins receiving voice input from the user.

[1437] When the user speaks to the coach, the terminal collects the voice data and sends it to the server.

[1438] 5. Real-time processing and feedback

[1439] The server analyzes the received voice data in real time and converts it into text using a voice recognition engine.

[1440] The server analyzes this text using natural language processing (NLP) technology to understand the user's intention.

[1441] For example, if a user says, "I'd like to talk about the difficulties I had in a recent project," the server generates an appropriate response: "What specifically were the difficulties?"

[1442] The server converts this response into voice using a voice synthesis engine and sends the voice data to the terminal.

[1443] The terminal plays the audio data to the user and waits for the next audio input.

[1444] 6. Data feedback and learning

[1445] After the conversation is over, the server stores all conversation content (voice, text data, and NLP analysis results) in a database.

[1446] The saved data is used as training data for future AI models. This continuous learning allows the system to provide more accurate coaching in the next interaction.

[1447] As a concrete example, if a user sets a goal of "I want to be successful as the leader of the next project," the system will use this information to generate questions that delve deeper into the user's current situation and challenges, and provide these questions via voice. If the user says, "I'd like to talk about the difficulties I had in today's meeting," a response such as "What were the difficulties? Please tell us the specific situation" will be generated in real time and returned to the user via voice. This process allows the user to organize their own challenges and promote introspection.

[1448] The above is a specific embodiment for carrying out the present invention. This system makes it possible to provide natural, personalized, and interactive voice coaching that goes beyond conventional text-based interfaces.

[1449] The processing flow will be explained below.

[1450] Step 1:

[1451] To use the system, a user launches the application and enters required information such as name, age, areas of interest, and goals.

[1452] Step 2:

[1453] The terminal obtains the information entered by the user and sends it to the server.

[1454] Step 3:

[1455] The server stores the received user information in a database, which creates a user profile.

[1456] Step 4:

[1457] The server uses an AI model based on the saved user information to generate optimal conversation scenarios. For example, if a user is interested in career advancement, it generates a scenario such as, "What particular challenges did you face in your recent project?"

[1458] Step 5:

[1459] The server passes the generated conversation scenario to a speech synthesis engine, which converts the text into speech data, optimizing the voice characteristics (e.g., youthful voice, calm voice) based on the user's preferences.

[1460] Step 6:

[1461] When the user presses the "Start Voice Dialogue" button, the terminal activates the microphone and starts voice input.

[1462] Step 7:

[1463] When the user speaks to the coach, the device collects and temporarily stores the voice data, and then transmits the stored voice data to the server.

[1464] Step 8:

[1465] The server analyzes the received voice data using a voice recognition engine and converts it into text data.

[1466] Step 9:

[1467] The server analyzes the text data using natural language processing (NLP) technology to understand the user's intent. Based on the analysis results, it generates an appropriate response. For example, if a user says, "I'd like to talk about the difficulties I faced in a recent project," it generates a response such as, "What specifically were the difficulties you faced?"

[1468] Step 10:

[1469] The server passes the generated response to a speech synthesis engine, converts the text into voice data, and transmits the voice data to the terminal.

[1470] Step 11:

[1471] The terminal reproduces the voice data received from the server and allows the user to hear the response.

[1472] Step 12:

[1473] The user listens to the audio playback and, if necessary, speaks again, and the process repeats.

[1474] Step 13:

[1475] After the conversation is over, the server stores all of the conversation content (voice, text data, and NLP analysis results) in a database. This not only serves as a reference for future conversations, but also serves as training data for the AI ​​model.

[1476] By repeating each of the above steps, it is possible to provide individually optimized conversations for each user and achieve coaching that encourages self-reflection.

[1477] Example 1

[1478] 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."

[1479] Conventional voice dialogue systems provide uniform responses to users, making it difficult to provide personalized responses that reflect individual personalities and preferences. Furthermore, they lacked a mechanism for continuously accumulating and learning from dialogue data with users to provide more appropriate feedback for the next dialogue. This limited users' opportunities to receive truly useful coaching.

[1480] 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.

[1481] In this invention, the server includes means for storing user information based on personality and preferences, means for generating an optimal conversation scenario based on the stored user information, and means for converting the generated conversation scenario into voice data. This makes it possible to provide personalized voice dialogue and coaching to each user and support their continuous growth.

[1482] "Means of saving user information based on personality and preferences" refers to the function of saving information entered by the user, such as name, age, areas of interest, and goals, and creating a profile for each user.

[1483] "Means for generating an optimal conversation scenario based on stored user information" refers to a function for generating an optimal conversation scenario that corresponds to the user's goals and interests based on stored user information.

[1484] The "means for converting the generated conversation scenario into voice data" refers to a voice synthesis function that converts the generated text-format conversation scenario into voice data.

[1485] "Means for receiving voice input from the user and converting it into text data" refers to a voice recognition function that converts the voice spoken by the user into text data.

[1486] "Means for analyzing the content of user comments and generating appropriate responses" refers to a natural language processing function that analyzes the content of user comments and generates appropriate responses based on that content.

[1487] "Means for converting the generated response back into voice data and outputting it to the user" refers to a voice output function that converts the generated text response into voice data and provides it to the user.

[1488] "Means of saving the content of the dialogue in a database and using it as future learning data" refers to the function of saving records of dialogue with users in a database and using that data as learning data for the AI ​​model.

[1489] "Means for optimizing voice characteristics based on user information" refers to a function that adjusts the characteristics of synthesized voice (e.g., voice pitch and speed) according to the user's preferences.

[1490] "Means for improving model accuracy by continuously saving and learning from dialogue content" refers to a function that continuously accumulates dialogue data with users and uses that data to retrain the AI ​​model, thereby improving the accuracy of the model.

[1491] "Means for analyzing voice dialogue in real time and providing appropriate feedback" refers to a function for analyzing voice dialogue in real time and quickly providing appropriate feedback in response to user comments.

[1492] "Means for understanding the intention of a user's speech using natural language processing technology" refers to a function that uses natural language processing technology to analyze the content of a user's speech and accurately understand their intention.

[1493] The system of the present invention provides personalized voice interactive coaching based on an individual's personality and preferences. Detailed embodiments of the system are described below.

[1494] 1. User Registration

[1495] The user launches a dedicated application and enters the necessary information, such as their name, age, areas of interest, and goals. The entered information is sent by the device to the server. The server stores the received information in a database and creates a personalized profile for each user. For example, MySQL is used as the database, and user information is stored in a "Users" table.

[1496] 2. Conversation scenario generation

[1497] The server retrieves user information from the database and generates an optimal conversation scenario. This generation uses a generative AI model (e.g., GPT-3). If the user's goal is "career advancement," the server generates questions such as, "What was particularly challenging about your recent project?"

[1498] 3. Speech Synthesis

[1499] The server passes the generated text scenario to a speech synthesis engine (e.g., Google Text-to-Speech API) and converts the text into speech data. The server optimizes the voice characteristics, such as a youthful voice or a calm voice, according to the user's preferences. The synthesized speech data is stored in a cache system (e.g., Redis).

[1500] 4. Starting a voice conversation

[1501] The user presses the "Start voice interaction" button in the application to start the voice interaction. The device activates the microphone and starts the user's voice input. As the user speaks, the voice data is sent from the device to the server.

[1502] 5. Real-time processing and feedback

[1503] The server analyzes the received voice data in real time and converts it into text using a speech recognition engine (for example, IBM Watson Speech to Text). The converted text data is then analyzed using natural language processing (NLP) technology (for example, Google Dialogflow) to understand the user's intention. For example, if the user says, "I'd like to talk about the difficulties I had in a recent project," the server generates an appropriate response such as, "What specifically were the difficulties you had?" This response is again converted into speech using a speech synthesis engine and sent to the device. The device plays the voice data to the user and waits for the next voice input.

[1504] 6. Data feedback and learning

[1505] Once the conversation is over, the server stores all conversation content (voice, text, NLP analysis results, etc.) in a database. This data is used as training data for future AI models. Continuous learning allows the system to provide more accurate coaching in the next conversation.

[1506] As a concrete example, if a user sets a goal of "I want to be successful as the leader of the next project," the system will use this information to generate questions that delve deeper into the user's current situation and challenges, and provide these questions via voice. If the user says, "I'd like to talk about the difficulties I had in today's meeting," a response such as "What were the difficulties you had? Please tell us the specific situation" will be generated in real time and returned as voice. This process allows the user to organize their own challenges and promote introspection.

[1507] An example of a prompt for a generative AI model is:

[1508] "Generate an appropriate response when a user says, 'I'd like to talk about something I struggled with in today's meeting.'"

[1509] The above is a specific embodiment for carrying out the present invention. This system makes it possible to provide natural, personalized, and interactive voice coaching that goes beyond conventional text-based interfaces.

[1510] The flow of the identification process in the first embodiment will be described with reference to FIG.

[1511] Step 1: Collect user information

[1512] The user starts the dedicated application and enters information such as their name, age, areas of interest, and goals.

[1513] Input: Information entered by the user, such as name, age, interests, goals, etc.

[1514] The terminal receives the input information and stores it in temporary memory for state maintenance.

[1515] Output: The terminal sends the input information to the server as an HTTP request.

[1516] Step 2: Save user information

[1517] The server stores the received user information in a database.

[1518] Input: User information sent from the device.

[1519] For example, the server uses a MySQL database to store information in a "Users" table.

[1520] Output: User information recorded in a database.

[1521] Step 3: Generate conversation scenarios

[1522] The server acquires user information from a database and generates an optimal conversation scenario.

[1523] Input: Database user information.

[1524] The server uses a generative AI model (e.g., GPT-3) to generate optimal scenarios based on the user's goals and interests.

[1525] Output: The generated conversation scenario in text format.

[1526] Example: If a user's goal is to "advance their career," generate the following question scenario: "What was particularly challenging about your recent project?"

[1527] Step 4: Converting to audio data

[1528] The server passes the conversation scenario (text) to a speech synthesis engine and converts it into voice data.

[1529] Input: Text data of the generated conversation scenario.

[1530] The server converts the text to speech using, for example, the Google Text-to-Speech API.

[1531] Output: Audio data.

[1532] The server stores the audio data in a cache system (e.g., Redis).

[1533] Step 5: Initiating a voice interaction

[1534] The user presses the "Start Voice Dialogue" button in the application to start the voice dialogue.

[1535] Input: The user presses the "Start voice interaction" button.

[1536] The device detects the button press event, activates the microphone, and starts voice input.

[1537] Output: The audio data recorded by the device.

[1538] Step 6: Send and convert audio data

[1539] The terminal transmits the recorded voice data to the server.

[1540] Input: The audio data spoken by the user.

[1541] The server converts the received voice data into text data using a voice recognition engine (e.g., IBM Watson Speech to Text).

[1542] Output: Text data.

[1543] Step 7: Analyzing the content of the comment and generating a response

[1544] The server analyzes the text data using natural language processing (NLP) technology (e.g., Google Dialogflow) to understand the user's intention in speaking.

[1545] Input: Text data generated by speech recognition.

[1546] The server generates an appropriate response based on the analysis results.

[1547] Output: The generated response text.

[1548] Example: If a user says, "I'd like to talk about a challenge I had on a recent project," generate a response of, "What specifically were the challenges?"

[1549] Step 8: Convert the response text to audio data

[1550] The server passes the response text to the speech synthesis engine again and converts it into voice data.

[1551] Input: The generated response text.

[1552] Output: The converted audio data.

[1553] Step 9: Send and play responses

[1554] The server transmits the audio data to the terminal.

[1555] The terminal plays back the received voice data and waits for voice input of the next follow-up question.

[1556] Input: Audio data sent from the server.

[1557] Output: The audio data to be played.

[1558] Step 10: Storing and Learning Dialogue Data

[1559] After the dialogue is completed, the server stores all dialogue content (voice data, text data, and NLP analysis results) in a database.

[1560] Input: Full historical data of the interaction.

[1561] The saved data is used as training data for the AI ​​model to provide more accurate coaching in the next interaction.

[1562] Output: Dialogue history stored in a database.

[1563] The above is the specific processing flow of the program for this system. This system makes it possible to provide personalized voice-interactive coaching to each user.

[1564] (Application example 1)

[1565] 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."

[1566] Conventional food delivery systems have difficulty providing personalized menu suggestions because they do not adequately consider the user's individual preferences and dietary restrictions. Furthermore, even voice-based interactive systems have faced many technical challenges in achieving natural dialogue with the user. The present invention aims to solve these challenges and provide users with more personalized menu suggestions and natural voice dialogue.

[1567] 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.

[1568] In this invention, the server includes means for saving user information based on the user's personality and preferences, means for generating an optimal conversation scenario based on the saved user information, means for converting the generated conversation scenario into voice data, means for receiving voice input from the user and converting it into text data, means for analyzing the user's utterances and generating an appropriate response, means for converting the generated response back into voice data and outputting it to the user, means for saving the dialogue content and using it as future learning data, means for generating personalized menu suggestions based on the user's food preferences and past order history, and means for audibly confirming the user's order details and optimizing the suggestions in real time, thereby enabling natural and personalized voice dialogue and menu suggestions that accommodate the user's individual preferences and dietary restrictions.

[1569] The "means for storing user information based on characteristics and preferences" refers to a device or program that has the function of collecting information about users' characteristics and individual preferences and storing it in a database.

[1570] "Means for generating an optimal dialogue scenario based on stored user information" refers to a device or program that has the function of automatically generating the most appropriate dialogue scenario for a user based on stored user information.

[1571] The "means for converting the generated conversation scenario into voice data" refers to a device or program that has the function of converting the generated text-format conversation scenario into voice data.

[1572] The "means for receiving voice input from a user and converting it into text data" refers to a device or program that has the function of converting the user's speech into text using voice recognition technology.

[1573] The "means for analyzing the content of a user's comments and generating an appropriate response" refers to a device or program that has the function of analyzing a user's comments converted into text format and generating an appropriate response based on the content.

[1574] The "means for converting the generated response back into voice data and outputting it to the user" refers to a device or program that has the function of converting the generated text response back into voice data and outputting it to the user.

[1575] The "means for saving the content of the dialogue and using it as future learning data" refers to a device or program that has the function of saving the content of the dialogue with the user in a database and using it as future learning data.

[1576] "Means for generating personalized menu suggestions based on a user's food preferences and past ordering history" refers to a device or program that has the function of automatically generating individually customized menu suggestions based on a user's food preferences and past ordering history.

[1577] The "means for confirming the user's order details by voice and optimizing suggestions in real time" refers to a device or program that has the function of confirming the user's order details by voice and updating them to the optimal suggestions on the spot.

[1578] This invention provides a voice-based interactive food delivery system based on user characteristics and preferences, which can assist users in the interactive ordering process and provide more personalized menu suggestions.

[1579] Hardware and software used

[1580] The following hardware and software are used as the main components of the system:

[1581] Hardware: Smartphone (microphone, speaker), server (database)

[1582] Software: AI models, speech recognition engines, speech synthesis engines, natural language processing engines (NLP)

[1583] System Components

[1584] 1. User Registration

[1585] First, a user launches the application on their smartphone and enters their name, age, food preferences (e.g., Japanese food, Western food, vegan, etc.), past order history, and allergy information. The smartphone receives this information and sends it to the server. The server stores the information in a database and creates a personalized profile for each user.

[1586] 2. Proposed scenario generation

[1587] The server generates an optimal menu recommendation scenario based on registered user information. This scenario is created using an AI model. For example, if the user is vegan, the recommendation scenario will include vegan menu items.

[1588] 3. Speech Synthesis

[1589] The server passes the generated text scenario to a speech synthesis engine, which converts the text into speech data. The voice characteristics (e.g., youthful voice, calm voice) are optimized according to the user's preferences. The synthesized speech data is stored in a cache.

[1590] 4. Starting a voice conversation

[1591] The user presses the "Start Voice Interaction" button in the application to activate the microphone and start the voice interaction. The smartphone receives the user's voice input and sends the voice data to the server.

[1592] 5. Real-time processing and feedback

[1593] The server analyzes the received voice data in real time and converts it into text using a speech recognition engine. This text is then analyzed using natural language processing (NLP) technology to understand the user's intent. For example, in response to a question such as "What's your recommendation today?", a response such as "Today's recommendations are salmon sushi and Margherita pizza" is generated. The generated response is then converted back into voice data using a speech synthesis engine and sent to the smartphone. The smartphone then plays the response back to the user.

[1594] 6. Data feedback and learning

[1595] After the dialogue with the user is completed, the server stores all dialogue content (voice, text data, and NLP analysis results) in a database. This data is used as training data for future AI models, enabling more accurate menu suggestions to be provided in the next dialogue.

[1596] Examples of specific examples and prompts

[1597] For example, if a user registers in the app that they like "Japanese food" and "pizza," the server will use this information to generate a menu scenario that suggests "salmon sushi" and "Margherita pizza" as today's recommendations. As a specific example of a prompt, a scenario will be generated that answers the question, "What's your recommendation today?" with an appropriate menu item.

[1598] Examples of prompts:

[1599] What's your recommendation today?

[1600] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[1601] Step 1:

[1602] Users launch the application on their smartphone and enter their name, age, food preferences (Japanese, Western, vegan, etc.), past order history, and allergy information. The device receives this information and sends it to the server. The entered data is stored in a database, creating a personalized profile for each user.

[1603] Step 2:

[1604] The server generates an optimal menu suggestion scenario based on the saved user information. This is where the AI ​​model comes into play. It performs calculations to generate menu suggestions based on the user's input data (food preferences, past order history, allergy information), and selects a menu that is suitable for the user.

[1605] Step 3:

[1606] The server passes the generated text-format proposed scenario to a speech synthesis engine, which converts the text into speech data. The speech synthesis engine sets the voice characteristics (e.g., youthful voice, calm voice) according to the user's preferences. The generated speech data is saved in a cache.

[1607] Step 4:

[1608] The user presses the "Start Voice Dialogue" button in the application to start a voice dialogue. The device activates the microphone and receives the user's voice input. The collected voice data is sent to the server.

[1609] Step 5:

[1610] The server analyzes the received voice data in real time and converts it into text data using a speech recognition engine. The converted text data is then used to analyze the user's intention using natural language processing (NLP) technology. For example, if a user asks, "What's recommended today?", the intention of the speech is analyzed.

[1611] Step 6:

[1612] The server generates an appropriate response based on the analysis results. For example, it generates a response such as "Today's recommendations are salmon sushi and Margherita pizza," and converts it into voice data using a speech synthesis engine. The generated voice data is then sent to the device.

[1613] Step 7:

[1614] The device plays the voice data sent from the server to the user, who then listens to the response and makes the next voice input (e.g., "I'd like to order salmon sushi"), allowing the conversation to continue and receiving menu suggestions updated in real time.

[1615] Step 8:

[1616] After the dialogue is completed, the server stores all dialogue content (voice, text data, and NLP analysis results) in a database. This adds new information about the user and uses it as learning data for the AI ​​model from the next time onwards, improving the accuracy of suggestions.

[1617] 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.

[1618] This invention provides more effective coaching by combining a personalized voice dialogue coaching system based on the user's personality and preferences with an emotion engine that recognizes the user's emotions. The following explanation will explain the overall processing flow of the system and the program processing in detail with concrete examples.

[1619] 1. User Registration

[1620] To use the system, a user launches the application and enters required information such as name, age, areas of interest, and goals.

[1621] The terminal acquires the information entered by the user and transmits it to the server.

[1622] The server stores the transmitted user information in a database and creates a personalized profile for each user.

[1623] 2. Conversation scenario generation

[1624] The server uses an AI model based on the saved user information to generate optimal conversation scenarios. For example, if a user is interested in career advancement, it generates a scenario such as, "What particular challenges did you face in your recent project?"

[1625] 3. Speech Synthesis

[1626] The server passes the generated text scenario to a speech synthesis engine to convert the text into speech data, optimizing the voice characteristics (e.g., youthful voice, calm voice) based on the user's preferences.

[1627] 4. User Emotion Recognition

[1628] When a user presses the "Start voice interaction" button in the application, the device activates the microphone and begins voice input.

[1629] When the user speaks, the device collects the voice data, temporarily stores it, and then sends it to the server.

[1630] The server analyzes the received voice data using a voice recognition engine and converts it into text, while at the same time recognizing the user's emotions using an emotion engine.

[1631] 5. Real-time processing and feedback

[1632] The server analyzes the text data and the recognized emotions using natural language processing (NLP) technology to understand the user's intention and generate an appropriate response based on the emotion.

[1633] For example, if a user says, "I'd like to talk about the difficulties I had in a recent project," and the emotion engine recognizes "stress," it will generate responses that take emotions into account, such as, "What specifically were the difficulties?" or "That must have been difficult. How did you deal with it?"

[1634] The server converts the generated response into voice using a voice synthesis engine and transmits the voice data to the terminal.

[1635] 6. Audio output and re-input

[1636] The terminal reproduces the voice data received from the server and allows the user to hear the response.

[1637] The user listens to the audio playback and, if necessary, speaks again, and the process repeats.

[1638] 7. Data feedback and learning

[1639] After the dialogue is completed, the server stores all of the dialogue content (voice, text data, emotion data, and NLP analysis results) in a database.

[1640] The stored data will be used as training data for future AI models, improving the accuracy of the system.

[1641] As a concrete example, if a user sets a goal of "I want to be successful as the leader of the next project," the system will use this information to generate questions that delve deeper into the user's current situation and challenges, and provide them via voice. If the user says, "I'd like to talk about the difficulties I had in today's meeting," and the emotion engine recognizes "anxiety," a response based on the emotion, such as "That's difficult. What specifically were you worried about?", will be generated in real time and returned to the user via voice. This process allows the user to organize their own emotions and deepen their introspection.

[1642] The above is a concrete example of how to implement a system that combines an emotion engine that recognizes the user's emotions. This system enables detailed responses based on the user's emotions, and can provide more effective personalized coaching.

[1643] The processing flow will be explained below.

[1644] Step 1:

[1645] To use the system, a user launches the application and enters required information such as name, age, areas of interest, and goals.

[1646] Step 2:

[1647] The terminal obtains the information entered by the user and sends it to the server.

[1648] Step 3:

[1649] The server stores the received user information in a database, creating a personalized profile for each user.

[1650] Step 4:

[1651] The server uses an AI model based on the saved user information to generate optimal conversation scenarios. For example, if a user is interested in career advancement, it generates a scenario such as, "What particular challenges did you face in your recent project?"

[1652] Step 5:

[1653] The server passes the generated text scenario to a speech synthesis engine and converts it from text to speech data. During this process, the voice characteristics (e.g., youthful voice, calm voice) are optimized based on the user's preferences. The synthesized speech data is stored in a cache for the user ID.

[1654] Step 6:

[1655] When a user presses the "Start voice interaction" button in the application, the device activates the microphone and starts voice input.

[1656] Step 7:

[1657] When a user speaks, the device collects and temporarily stores the voice data, which is then sent to the server.

[1658] Step 8:

[1659] The server analyzes the received voice data using a voice recognition engine and converts it into text data.

[1660] Step 9:

[1661] The server uses an emotion engine to analyze the voice data received at the same time as the text data and recognize the user's emotions (e.g., joy, sadness, anger, surprise, etc.). For example, when a user says, "I had a hard time with a recent project," the emotion engine recognizes "stress."

[1662] Step 10:

[1663] The server uses natural language processing (NLP) technology to analyze the text data and the recognized emotional data to understand the user's intention. Based on the results of this analysis, it generates an appropriate response based on the user's emotions. For example, it generates a response that takes emotions into consideration, such as, "That must have been difficult. How did you deal with it?"

[1664] Step 11:

[1665] The server passes the generated response to a speech synthesis engine, converts the text into voice data, and transmits the voice data to the terminal.

[1666] Step 12:

[1667] The terminal reproduces the voice data received from the server and allows the user to hear the response.

[1668] Step 13:

[1669] The user listens to the audio playback and, if necessary, speaks again, and the process repeats.

[1670] Step 14:

[1671] After the dialogue is completed, the server stores all of the dialogue content (voice, text data, emotion data, and NLP analysis results) in a database.

[1672] Step 15:

[1673] The saved data will be used as training data for future AI models, improving the accuracy of the system and enabling more precise and personalized responses in subsequent interactions.

[1674] Through each of these steps, users are provided with conversations that include individually optimized emotion recognition, enabling effective coaching that encourages self-reflection.

[1675] Example 2

[1676] 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."

[1677] Conventional voice dialogue systems have difficulty recognizing and responding to changes in a user's emotions, as well as their personality and preferences, in real time. As a result, responses to users are uniform, making it impossible to provide effective personalized coaching. Furthermore, feedback tailored to the user's emotions is lacking, resulting in a poor user experience.

[1678] The specific processing by the specific processing unit 290 of the data processing device 12 in the second embodiment is realized by the following means.

[1679] In this invention, the server includes: [means for saving user information based on the user's personality and preferences;] [means for generating an optimal conversation scenario based on the saved user information;] [means for converting the generated conversation scenario into voice data;] [means for receiving voice input from the user and converting it into text data;] [means for analyzing the user's utterances and emotions and generating an appropriate response;] [means for converting the generated response back into voice data and outputting it to the user;] [means for saving the dialogue content in a database and using it as future learning data; and [means for recognizing the user's emotions.] This makes it possible to recognize the user's emotions in real time and provide a detailed response. Therefore, more effective personalized coaching can be provided, improving the quality of the user experience.

[1680] "User Information" refers to personal information about a User, such as their characteristics, preferences, interests, and goals.

[1681] The "conversation scenario" refers to a scenario such as a dialogue progress plan and question content generated based on information input by the user.

[1682] "Voice data" refers to audio data obtained by converting text information using a speech synthesis engine.

[1683] "Text data" refers to data in the form of a character string that is generated by converting a user's voice input using a voice recognition engine.

[1684] "Emotions" refer to the psychological state or feelings expressed by a user during a voice interaction.

[1685] "Analysis" refers to the process of analyzing and understanding what users say and their emotions.

[1686] A "reply" refers to an appropriate response that is generated based on what the user says.

[1687] "Database" refers to a data management system for storing information about interactions and users.

[1688] "Real-time" refers to the process of instantly analyzing and responding to a user's voice input.

[1689] This invention is a voice-interactive coaching system that is personalized based on the user's personality and preferences, and by combining it with an emotion engine that recognizes the user's emotions, it provides more effective coaching. The processing flow of the entire system and specific examples are described in detail below.

[1690] This system consists of three main elements: a server, a terminal, and a user.

[1691] 1. User Registration

[1692] A user launches an application and enters personal information such as name, age, interests, and goals.

[1693] The device acquires the input information and sends it to the server using the HTTP or HTTPS communication protocol.

[1694] The server stores the received information in a database (e.g., MySQL or MongoDB) and creates a personalized profile for each user.

[1695] 2. Conversation scenario generation

[1696] The server uses a generative AI model (e.g., OpenAI GPT-4) to generate optimal conversation scenarios based on the saved user information. Specifically, if the user is interested in "career advancement," it generates a scenario such as "What particular challenges did you face in your recent project?"

[1697] 3. Speech Synthesis

[1698] The server passes the generated text scenario to a speech synthesis engine (e.g., Google Cloud Text-to-Speech) to convert the text into voice data. The voice characteristics (e.g., youthful voice, calm voice) are optimized based on the user's preferences.

[1699] 4. User Emotion Recognition

[1700] When the user presses the "Start voice interaction" button, the device activates the microphone and begins voice input.

[1701] When a user speaks, the device collects and temporarily stores the voice data, which is then sent to the server in a streaming or batch process.

[1702] The server converts the voice data into text using a speech recognition engine (e.g., Google Cloud Speech-to-Text) and recognizes the user's emotions using an emotion engine (e.g., Azure Emotion API).

[1703] 5. Real-time processing and feedback

[1704] The server analyzes the text data and emotions using natural language processing (NLP) technology (such as spaCy or AllenNLP), understands the user's intention, and generates an appropriate response. For example, if a user says, "I'd like to talk about the difficulties I faced in a recent project," and the emotion engine recognizes this as "stress," it will generate responses such as, "What specifically were the difficulties you faced?" or "That must have been difficult. How did you deal with it?"

[1705] The server converts the generated response into speech using a speech synthesis engine and sends the speech data to the terminal.

[1706] 6. Audio output and re-input

[1707] The terminal reproduces the voice data received from the server and allows the user to hear the response.

[1708] The user listens to the playback and, if necessary, speaks again, and the process repeats.

[1709] 7. Data feedback and learning

[1710] After the dialogue is completed, the server stores all of the dialogue content (voice, text data, emotion data, and NLP analysis results) in a database.

[1711] The stored data will be used as training data for future AI models, improving the accuracy of the system.

[1712] Specific examples

[1713] For example, if a user sets a goal of "I want to be successful as the leader of the next project," the system can use this information to generate questions that delve deeper into the user's current situation and challenges, and provide them via voice.As another example, if a user says, "I'd like to talk about the difficulties I had in today's meeting," and the emotion engine recognizes "anxiety," a response based on the emotion, such as "That's difficult. What specifically were you worried about?", is generated in real time and returned to the user via voice.

[1714] This system enables more detailed responses that take into account the user's emotions, enabling more effective personalized coaching.

[1715] The flow of the identification process in the second embodiment will be described with reference to FIG.

[1716] Step 1:

[1717] Registering Users

[1718] Input: A user launches an application and enters personal information such as name, age, interests, and goals.

[1719] How it works: The device takes the information entered by the user and converts it into JSON format.

[1720] Output: User information in JSON format is generated.

[1721] Next step: Send the user information in JSON format to the server.

[1722] Step 2:

[1723] Data storage

[1724] Input: User information in JSON format.

[1725] What happens: The server parses the received JSON data and stores it in the database.

[1726] Output: User information is saved in the database.

[1727] Next: Create a personalized profile for each user based on the stored user information.

[1728] Step 3:

[1729] Conversation scenario generation

[1730] Input: User information stored in the database.

[1731] How it works: The server uses a generative AI model (e.g., OpenAI GPT-4) to generate an optimal conversation scenario. Specifically, it inputs user information into a prompt sentence and generates a scenario such as, "What were the particular challenges you faced in your recent project?"

[1732] Output: Generated text data of the conversation scenario.

[1733] Next process: Convert the text scenario into audio data.

[1734] Step 4:

[1735] Speech synthesis

[1736] Input: Text data of the generated conversation scenario.

[1737] How it works: The server uses a speech synthesis engine (e.g., Google Cloud Text-to-Speech) to convert text data into voice data, optimizing voice characteristics (e.g., youthful voice, calm voice) based on the user's preferences.

[1738] Output: Audio file (e.g. MP3 format).

[1739] Next step: Send the audio data to the device.

[1740] Step 5:

[1741] Start a voice interaction

[1742] Input: The audio file sent from the server.

[1743] How it works: When a user presses the "Start voice interaction" button in an application, the device activates the microphone and plays an audio file.

[1744] Output: The user hears the start of the dialogue.

[1745] Next: Receive voice input from the user.

[1746] Step 6:

[1747] Audio data collection

[1748] Input: Speech input from the user.

[1749] How it works: The device collects and temporarily stores the user's voice data.

[1750] Output: Temporarily saved audio data.

[1751] Next step: Send the audio data to the server.

[1752] Step 7:

[1753] Analysis of audio data

[1754] Input: Audio data sent from the device.

[1755] How it works: The server converts the voice data into text using a speech recognition engine (e.g., Google Cloud Speech-to-Text) and recognizes the user's emotions using an emotion engine (e.g., Azure Emotion API).

[1756] Output: Text data and emotion data.

[1757] Next step: Analyze the text and sentiment data and generate an appropriate response.

[1758] Step 8:

[1759] Response Generation

[1760] Input: Text data and emotion data.

[1761] How it works: The server uses natural language processing (NLP) technology (such as spaCy or AllenNLP) to analyze text and sentiment data and generate appropriate responses to the user. For example, if a user says, "I'd like to talk about the difficulties I faced in a recent project," the server generates a response such as, "What specifically were the difficulties?"

[1762] Output: Text data of the response.

[1763] Next process: Convert the generated response into audio data.

[1764] Step 9:

[1765] Voiced responses

[1766] Input: Text data of the response.

[1767] How it works: The server uses a speech synthesis engine (e.g., Google Cloud Text-to-Speech) to convert the text data into audio data.

[1768] Output: Audio file.

[1769] Next step: Send the audio data to the device.

[1770] Step 10:

[1771] Playing audio data

[1772] Input: Audio data sent from the server.

[1773] Operation: The device plays the audio data received from the server, allowing the user to hear the response.

[1774] Output: A spoken response to the user.

[1775] Next step: Retry voice input if necessary.

[1776] Step 11:

[1777] Data feedback and learning

[1778] Input: All content of the dialogue (voice, text data, emotion data, and NLP analysis results).

[1779] How it works: The server stores the conversation in a database and uses it as learning data for future projects. The stored data is used to improve the generative AI model and increase the accuracy of the system.

[1780] Output: Training data stored in a database.

[1781] Next: Retrain and improve the AI ​​model to improve the system's accuracy.

[1782] The above is the specific processing flow of this system, and details of the specific operations and inputs / outputs at each step. This makes it possible to provide personalized coaching according to the user's emotions.

[1783] (Application example 2)

[1784] 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."

[1785] The objective of this invention is to provide personalized voice dialogue coaching based on the user's emotions and preferences, and in particular to support the user's mental and emotional well-being by recognizing the user's emotional state in real time and providing appropriate feedback. Conventional voice dialogue systems have difficulty recognizing the user's emotions and immediately reflecting them in responses, so more effective coaching is required.

[1786] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 2 is realized by the following means.

[1787] In this invention, the server includes means for saving user information based on personality and preferences, means for generating an optimal conversation scenario based on the saved user information, and means for converting the generated conversation scenario into voice data. This makes it possible to provide personalized coaching in real time according to the user's emotions and state.

[1788] "User information" refers to information about a user, such as their personality, preferences, areas of interest, and goals.

[1789] A "conversation scenario" refers to text data that is generated based on user information and that plans the flow of a conversation with a user.

[1790] "Emotional state" refers to data for determining the emotional state a user exhibits during a dialogue.

[1791] "Voice data" refers to an audio file converted from the generated conversation scenario by a voice synthesis engine.

[1792] "Speech recognition" refers to the technology that converts voice input from a user into text data.

[1793] "Appropriate reply" refers to analyzing the content of a user's speech and emotional state and generating a response that is deemed appropriate.

[1794] "Personalized coaching messages" refer to coaching messages that are individually optimized based on the user's personality, preferences, and emotional state.

[1795] "Database" refers to data storage that stores user information, dialogue content, emotional data, etc., and is used as future learning data.

[1796] A "natural language processing engine" refers to technology that analyzes user statements and text and generates appropriate responses.

[1797] "Real-time processing" refers to processing that analyzes data and generates responses immediately during a user interaction.

[1798] This invention is a system that provides personalized voice-interactive coaching based on a user's emotional state and individual preferences. The entire system is mainly composed of a server, a terminal, and a user. Specific embodiments for implementing this system are described below.

[1799] User registration and information storage

[1800] To use the system, a user launches the application and enters necessary information such as name, age, areas of interest, goals, etc. This information is sent to the server via the terminal, and the server stores the user information in a database and creates a personalized profile for each user.

[1801] Conversation scenario generation

[1802] The server uses an AI model (natural language processing engine) based on the stored user information to generate a conversation scenario suited to the user. For example, if the user is interested in "stress management," this scenario can include questions such as, "What has caused you stress recently?"

[1803] Generate audio data

[1804] The generated conversation scenario is converted into voice data using the server's voice synthesis engine, with the tone and pitch of the voice adjusted based on the user's preferences.

[1805] User voice input and emotion recognition

[1806] When a user initiates a dialogue, the device's microphone collects voice input, which is then sent to a server that uses a speech recognition engine to convert the speech into text data and an emotion engine to recognize the user's emotional state.

[1807] Real-time response and feedback

[1808] The server uses a natural language processing engine based on the recognized text data and emotion data to generate an appropriate response according to the user's comment and emotional state. The generated response is then converted into voice data by a speech synthesis engine and output to the user via the terminal.

[1809] Data storage and training

[1810] After the dialogue is completed, the server stores all dialogue data (voice data, text data, emotion data, and analysis results) in a database, which will be used as training data for future AI models, improving the accuracy and performance of the system.

[1811] For example, if a user says, "I'm feeling really stressed today," the emotion engine will detect "stress" and generate a response like this: "That's tough. Is there a specific reason why?"

[1812] Prompt Sentence Examples

[1813] If a user says something that suggests they are under stress, generate an appropriate coaching message. For example, if a user says, "I'm feeling really stressed today," generate a message like, "That sounds tough. Is there a specific reason for that?"

[1814] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[1815] Step 1:

[1816] A user launches the application and enters the required information, such as name, age, interests, and goals.

[1817] Input: User's personal information (name, age, interests, goals, etc.)

[1818] Output: Dataset as user information

[1819] The terminal collects information entered by the user and sends it to a server for analysis.

[1820] Step 2:

[1821] The server stores the transmitted user information in a database and creates a personalized profile for each user.

[1822] Input: User information data from the terminal

[1823] Output: User profile in the database

[1824] The server analyzes the input information and creates and saves a profile for each user.

[1825] Step 3:

[1826] Based on the user information stored on the server, a conversation scenario is generated using an AI model (natural language processing engine).

[1827] Input: User profile in database

[1828] Output: Conversation scenario

[1829] The server generates an appropriate conversation scenario based on the user's interests and goals.

[1830] Step 4:

[1831] The server passes the generated conversation scenario to a speech synthesis engine and converts it into voice data.

[1832] Input: Generated conversation scenario (text data)

[1833] Output: Audio data

[1834] The server converts the text data into speech and adjusts the tone and pitch of the speech based on the user's preferences.

[1835] Step 5:

[1836] When the user presses the "Start Voice Interaction" button, the device activates the microphone and receives voice input from the user.

[1837] Input: User's voice

[1838] Output: Temporarily saved audio data

[1839] The device collects the user's voice and temporarily stores it for analysis.

[1840] Step 6:

[1841] The device sends the temporarily saved voice data to the server, which then analyzes it with a voice recognition engine, converts it into text data, and recognizes the user's emotions using an emotion engine.

[1842] Input: Audio data sent from the device

[1843] Output: Text data and emotion recognition data

[1844] The server converts the voice data into text and also recognizes emotions.

[1845] Step 7:

[1846] The server uses a natural language processing engine to generate an appropriate response based on the text data and emotional data it recognizes.

[1847] Input: Text data, emotion recognition data

[1848] Output: Response (text data)

[1849] The server analyzes the user's comments and emotional state and generates an appropriate response.

[1850] Step 8:

[1851] The response generated by the server is passed back to the speech synthesis engine, converted into voice data, and then sent to the terminal.

[1852] Input: Generated response (text data)

[1853] Output: Response audio data

[1854] The server converts the text response into audio data and sends it to the device.

[1855] Step 9:

[1856] The terminal plays back the voice data from the server and lets the user hear the response. The user listens to the played back voice and makes further voice input as necessary.

[1857] Input: Audio data from the server

[1858] Output: The audio the user hears

[1859] The terminal plays the audio data and provides a response to the user.

[1860] Step 10:

[1861] After the dialogue is completed, the server stores all of the dialogue content (voice, text data, emotion data, and NLP analysis results) in a database.

[1862] Input: All dialogue data (voice, text, emotion data, analysis results)

[1863] Output: Interaction data stored in a database

[1864] The server stores all collected data in a database and uses it as learning data for the future.

[1865] 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.

[1866] 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.

[1867] In the above embodiment, an example in which the specific processing is performed by the data processing device 12 has been given, but the technology of the present disclosure is not limited to this, and the specific processing may be performed by the robot 414.

[1868] 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.

[1869] FIG. 9 illustrates 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 behaviors 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.

[1870] 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.

[1871] 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).

[1872] 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.

[1873] 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."

[1874] 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.

[1875] 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).

[1876] 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.

[1877] 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.

[1878] 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.

[1879] 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.

[1880] 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.

[1881] 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.

[1882] 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.

[1883] 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.

[1884] 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.

[1885] 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.

[1886] The following is further disclosed regarding the above embodiment.

[1887] (Claim 1)

[1888] [Means for storing user information based on personality and preferences;

[1889] [Means for generating optimal conversation scenarios based on stored user information;

[1890] [Means for converting the generated conversation scenario into voice data;

[1891] [means for receiving voice input from a user and converting it into text data;

[1892] [Means for analyzing user comments and generating appropriate responses;

[1893] [Means for converting the generated response back into voice data and outputting it to the user;

[1894] [A system including a means for storing the dialogue content in a database and using it as future learning data.

[1895] (Claim 2)

[1896] The system of claim 1, further comprising: means for optimizing audio based on user information.

[1897] (Claim 3)

[1898] The system of claim 1, further comprising means for analyzing the voice dialogue in real time and providing appropriate feedback.

[1899] "Example 1"

[1900] (Claim 1)

[1901] [Means of storing user information based on characteristics and preferences;

[1902] [Means for generating optimal conversation scenarios based on stored user information;

[1903] [Means for converting the generated conversation scenario into voice data;

[1904] [means for receiving voice input from a user and converting it into text data;

[1905] [Means for analyzing the content of user comments and generating appropriate responses;

[1906] [Means for converting the generated response back into voice data and outputting it to the user;

[1907] [Means to save the dialogue content in a database and use it as future learning data,

[1908] [means for optimizing voice characteristics based on user information;

[1909] [A system that includes a means for continuously saving dialogue content and improving model accuracy through learning.

[1910] (Claim 2)

[1911] [The system according to claim 1, which analyzes voice dialogue in real time and provides appropriate feedback.

[1912] (Claim 3)

[1913] [The system according to claim 1 uses natural language processing technology to understand the intention of a user's speech.

[1914] "Application Example 1"

[1915] (Claim 1)

[1916] [Means for storing user information based on personality and preferences;

[1917] [Means for generating optimal conversation scenarios based on stored user information;

[1918] [Means for converting the generated conversation scenario into voice data;

[1919] [means for receiving voice input from a user and converting it into text data;

[1920] [Means for analyzing user comments and generating appropriate responses;

[1921] [Means for converting the generated response back into voice data and outputting it to the user;

[1922] [Means for saving the dialogue content and using it as future learning data,

[1923] [means for generating personalized menu suggestions based on a user's food preferences and past ordering history; and

[1924] [A system including a means for confirming the user's order via voice and optimizing suggestions in real time.

[1925] (Claim 2)

[1926] The system of claim 1, further comprising: means for optimizing audio based on user information.

[1927] (Claim 3)

[1928] The system of claim 1, further comprising means for analyzing the voice dialogue in real time and providing appropriate feedback.

[1929] "Example 2: Combining Emotion Engines"

[1930] (Claim 1)

[1931] [Means for storing user information based on user characteristics and preferences;

[1932] [Means for generating optimal conversation scenarios based on stored user information;

[1933] [Means for converting the generated conversation scenario into voice data;

[1934] [means for receiving voice input from a user and converting it into text data;

[1935] [Means for analyzing user comments and emotions and generating appropriate responses;

[1936] [Means for converting the generated response back into voice data and outputting it to the user;

[1937] [Means to save the dialogue content in a database and use it as future learning data,

[1938] [A system including a means for recognizing a user's emotion.

[1939] (Claim 2)

[1940] The system of claim 1, further comprising: means for optimizing audio based on user information.

[1941] (Claim 3)

[1942] The system of claim 1, further comprising means for analyzing the voice dialogue in real time and providing appropriate feedback.

[1943] "Application example 2 when combining emotion engines"

[1944] (Claim 1)

[1945] [Means for storing user information based on personality and preferences;

[1946] [Means for generating optimal conversation scenarios based on stored user information;

[1947] [Means for converting the generated conversation scenario into voice data;

[1948] [means for receiving voice input from a user and converting it into text data;

[1949] [Means for analyzing the user's speech content and emotional state to generate an appropriate response;

[1950] [Means for converting the generated response back into voice data and outputting it to the user;

[1951] [A system including a means for storing dialogue content and emotion data in a database and using it as future learning data.]

[1952] (Claim 2)

[1953] The system of claim 1, further comprising: means for optimizing audio based on user information.

[1954] (Claim 3)

[1955] [Means for analyzing voice dialogue in real time and providing appropriate feedback;

[1956] The system of claim 1, further comprising means for providing personalized coaching messages according to the user's emotional state. [Explanation of symbols]

[1957] 10, 210, 310, 410 Data Processing Systems 12 Data Processing Device 14 Smart Devices 214 Smart Glasses 314 Headset-type terminal 414 Robot< / url:> < / url:> < / url:> < / url:>

Claims

1. means for storing user information based on characteristics and preferences; A means for generating an optimal conversation scenario based on the stored user information; a means for converting the generated conversation scenario into voice data; means for receiving voice input from a user and converting it into text data; A means for analyzing the content of a user's utterance and generating an appropriate response; means for converting the generated response back into voice data and outputting it to the user; A system that includes a means for storing the dialogue content in a database and using it as future learning data.

2. 10. The system of claim 1, further comprising means for optimizing audio based on user information.

3. 10. The system of claim 1, further comprising means for analyzing the voice interaction in real time and providing appropriate feedback.

Images