System

Abstract

A system is provided.SOLUTION: A system comprising: means for generating a virtual personality based on setting information input by a user; means for recognizing a voice input of the user and converting the voice input into a text; means for generating an answer to a question of the user by the generated virtual personality; means for speech synthesis and reproducing the generated answer; means for storing interview contents as proceedings; and means for storing interview voice information.SELECTED DRAWING: Figure 1

Description

[Technical Field]

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

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

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

[0004] Current user interview methods have challenges, such as the time and cost required to secure interviewees and the effort required to prepare for the interviews, making them difficult to use efficiently. Furthermore, opportunities to practice interviews and to gain new ideas and insights are limited, making it difficult to quickly obtain answers to specific questions. To address these challenges, a system is needed that allows users to generate virtual personalities based on their own settings and conduct interviews. [Means for solving the problem]

[0005] The present invention solves the above-mentioned problems with a system that includes: means for generating a virtual personality based on setting information entered by a user; means for recognizing the user's voice input and converting it into text; means for the generated virtual personality to generate answers to the user's questions; means for synthesizing and playing back the generated answers; means for saving the interview content as minutes; and means for saving the interview audio data. The present invention allows users to easily conduct interviews with virtual personalities, enabling effective interview and training while saving time and cost. Furthermore, the ease of saving and reviewing interview content allows for efficient acquisition of new ideas and insights.

[0006] "User" refers to a human being who uses the system to conduct an interview with a virtual persona.

[0007] "Setting information" refers to data entered by the user to generate a virtual personality, such as occupation, personality, and characteristics.

[0008] "Virtual personality" refers to a fictional personality created using a generative AI model based on user preferences.

[0009] "Means of generation" refers to the methods and techniques for creating a virtual personality based on the setting information entered by the user.

[0010] "Voice input" refers to the act of a user providing questions or instructions to a system by voice.

[0011] "Speech recognition" refers to the technology that converts a user's voice input into text data.

[0012] A "question" refers to an inquiry that a user poses to a virtual personality.

[0013] "Answer" refers to the answer generated by the virtual personality in response to the user's question.

[0014] "Speech synthesis" refers to the technology of converting text data into voice data.

[0015] "Interview content" refers to the entire question and answer session between the user and the virtual personality.

[0016] "Minutes" refers to a textual record of the interview contents.

[0017] "Audio data" refers to audio files of voice-synthesized answers and interview content.

[0018] "System" refers to a set of programs and hardware that includes all of the above elements and enables interviews with virtual personalities. [Brief explanation of the drawings]

[0019] [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

[0020] 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.

[0021] First, the terms used in the following description will be explained.

[0022] 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).

[0023] 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.

[0024] 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.

[0025] 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.

[0026] 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."

[0027] [First embodiment]

[0028] FIG. 1 shows an example of the configuration of a data processing system 10 according to the first embodiment.

[0029] 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.

[0030] 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).

[0031] 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.

[0032] 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.

[0033] 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.

[0034] 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.

[0035] FIG. 2 shows an example of the main functions of the data processing device 12 and the smart device 14.

[0036] 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.

[0037] 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.

[0038] 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.

[0039] 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."

[0040] The present invention relates to a system for generating a virtual personality based on setting information input by a user and conducting an audio interview with the virtual personality. Specific embodiments for carrying out the present invention will be described below.

[0041] 1. User setting input

[0042] The user inputs the virtual persona's configuration information, including occupation, personality, characteristics, etc., using a terminal application or a web interface. The input configuration information is then sent to the server in an appropriate format.

[0043] 2. Virtual personality generation

[0044] The server receives the setting information sent by the user and generates a virtual personality using a generative AI model. The generated virtual personality data is stored on the server until the interview begins.

[0045] 3. Start of interview

[0046] The user speaks questions to the virtual persona through the device, which uses a speech recognition engine to convert the user's voice input into text in real time, and this text data is sent to the server.

[0047] 4. Answer generation and voice output

[0048] The server analyzes the received question text and generates an answer as a virtual personality. The generated answer is passed to a speech synthesis engine and generated as voice data. The voice data is sent to the device and played back to the user.

[0049] 5. Recording of interviews

[0050] The server stores the interview contents as a text record in the form of minutes, and also stores the audio data so that users can review the interview contents later.

[0051] Specific examples

[0052] 1. Example of user preference input

[0053] Examples of setting information input by the user include the following:

[0054] json

[0055] {

[0056] "Occupation": "Engineer",

[0057] "Personality": "Logical",

[0058] "Characteristics": "Tech-savvy"

[0059] }

[0060] 2. Virtual personality generation

[0061] Based on the above setting information, the server uses a generative AI model to generate a virtual personality. For example, a personality with characteristics such as "engineer," "logical," and "tech-savvy" is generated.

[0062] 3. Example user questions

[0063] A user verbally asks the question, "What do you think about the latest AI technology?"

[0064] 4. Example of answer generation and speech output

[0065] The server receives the question and generates an answer such as, "The latest AI technology is very interesting." This answer is then synthesized into voice, which the device plays back to the user.

[0066] 5. Examples of interview recording

[0067] The server saves the entire interview as a transcript in a text file, and also saves the audio data in MP3 format.

[0068] The present invention can be implemented in the above manner. By using this system, users can efficiently and effectively conduct interviews with virtual personalities and gain new insights and ideas.

[0069] The processing flow will be explained below.

[0070] Step 1:

[0071] The user opens the application or web interface on their device and enters configuration information for their virtual personality, including their occupation, personality, and characteristics.

[0072] Step 2:

[0073] The terminal formats the configuration information entered by the user and transmits it to the server in the appropriate data format.

[0074] Step 3:

[0075] The server receives the setting information sent from the terminal and checks its contents.

[0076] Step 4:

[0077] The server uses a generative AI model to generate a virtual personality based on the user's settings, and the generated virtual personality data is stored on the server.

[0078] Step 5:

[0079] The user verbally asks a question to the device.

[0080] Step 6:

[0081] The device uses a speech recognition engine to convert the user's voice input into text data in real time.

[0082] Step 7:

[0083] The terminal transmits the converted question text data to the server.

[0084] Step 8:

[0085] The server analyzes the question text data received from the terminal and generates an answer as a virtual personality.

[0086] Step 9:

[0087] The generated answer text is passed to a speech synthesis engine to generate speech data.

[0088] Step 10:

[0089] The server transmits the generated voice data to the terminal.

[0090] Step 11:

[0091] The device plays back the received audio data and provides the user with a response.

[0092] Step 12:

[0093] The server generates and stores a text record of the interview contents as a transcript.

[0094] Step 13:

[0095] The server stores the audio data of the interview.

[0096] Step 14:

[0097] After the interview, users can review the saved transcript and audio data.

[0098] Example 1

[0099] 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."

[0100] A method is needed to generate a virtual personality based on user-entered settings and enable natural dialogue when the user interviews the virtual personality. Another challenge is to efficiently convert the user's voice input into text, generate appropriate responses based on the text, and then respond in voice. It is also important to keep a record of the interview content so that it can be referenced later.

[0101] 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.

[0102] In this invention, the server includes means for generating a virtual personality based on setting information input by a user, means for recognizing a user's voice input and converting it into text, means for generating a virtual personality using a generative AI model, means for the generated virtual personality to generate answers to the user's questions, means for synthesizing and playing back the generated answers, means for saving the interview content as minutes, and means for saving the interview audio data, which enables a user to input setting information, realize natural conversations with a virtual personality, and record and save the content.

[0103] "User" refers to any individual or entity that uses the System.

[0104] "Setting information" refers to information about a specific occupation, personality, and characteristics that a user inputs to generate a virtual personality.

[0105] A "virtual personality" is a virtual entity generated based on the user's settings, and refers to a pseudo-personality that can interact with the user.

[0106] "Voice input" refers to input made by a user to a system using voice.

[0107] "Text conversion" refers to the process of analyzing voice input and expressing it as a string of characters.

[0108] A "generative AI model" refers to an algorithm that uses machine learning techniques to generate a virtual personality from a user's settings.

[0109] "Answer generation" refers to the process by which a virtual personality constructs an appropriate response to a question posed by a user.

[0110] "Speech synthesis" refers to the process of converting generated text data into speech data.

[0111] "Playback" refers to the process of playing back the synthesized voice data to the user.

[0112] "Minutes" refers to data that records the contents of an interview in written form.

[0113] "Voice data" refers to voice-synthesized responses and user voice input data.

[0114] The present invention is a system for generating a virtual personality based on setting information input by a user and conducting an audio interview with the virtual personality. Specific embodiments of the present invention will be described below.

[0115] User preference input

[0116] The user inputs configuration information for the virtual persona using a device application or web interface, including occupation, personality, and characteristics. For example, the user might input the following information:

[0117] Occupation: Engineer

[0118] Personality: Logical

[0119] Specialty: Technology savvy

[0120] Once these entries are complete, the device sends this information to the server in JSON format.

[0121] Virtual personality generation

[0122] The server receives the setting information sent by the user. Then, it generates a virtual personality using a generative AI model (e.g., GPT-3). The generated virtual personality data is stored on the server until the interview begins. For example, the following prompt sentences are used to input to the generative AI model:

[0123] Prompt: "You are an engineer, a logical, tech-savvy person."

[0124] Interview begins

[0125] The user asks the virtual persona a question by voice through the device, such as, "What do you think about the latest AI technology?" The device uses a speech recognition engine (e.g., Google Speech-to-Text API) to convert the user's voice into text in real time and sends this text data to the server.

[0126] Answer generation and voice output

[0127] The server analyzes the received question text and generates an answer as a virtual personality using a generative AI model. For example, it generates an answer such as "The latest AI technology is very interesting." The generated answer is passed to a speech synthesis engine (e.g., Amazon Polly) and generated as audio data. This audio data is sent to the device and played back to the user.

[0128] Interview recording

[0129] The server stores the interview contents as text records in minutes format. Audio data is also stored in the same way. Users can review the interview contents later. The recordings are generally stored in text files and MP3 format.

[0130] This embodiment allows users to efficiently and effectively interview virtual personalities, and gain new insights and ideas.

[0131] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0132] Program processing flow and specific explanation

[0133] Step 1: User Settings Input

[0134] The user inputs the virtual personality's configuration information using a terminal application or web interface. This configuration information includes occupation, personality, characteristics, etc. For example, the user inputs information such as "Occupation: Engineer," "Personality: Logical," and "Characteristics: Knowledgeable about technology."

[0135] Input: Setting information about occupation, personality, and characteristics

[0136] Output: JSON data containing configuration information

[0137] Specific behavior: The user enters the setting information into the input form and clicks the "Submit" button.

[0138] Step 2: Sending configuration information

[0139] The device sends the configuration information entered by the user to the server in an appropriate format (JSON format).

[0140] Input: JSON data generated in step 1

[0141] Output: Configuration information sent to the server

[0142] Specific operation: JSON data containing configuration information is sent to the server via an HTTP request.

[0143] Step 3: Receiving configuration information

[0144] The server receives the setting information sent from the device, and this data is stored and analyzed within the server.

[0145] Input: Setting information sent from the device

[0146] Output: Configuration information saved on the server

[0147] Specific operation: The server receives the HTTP request and saves the configuration information in the database.

[0148] Step 4: Virtual personality generation

[0149] The server generates a virtual personality using a generative AI model (e.g., GPT-3) based on the received configuration information. For example, it creates a prompt sentence like the following based on the configuration information: "Occupation: Engineer," "Personality: Logical," and "Characteristics: Knowledgeable about technology."

[0150] Prompt: "You are an engineer, a logical, tech-savvy person."

[0151] Input: Configuration information stored on the server

[0152] Output: Generated virtual personality data

[0153] Specific operation: A prompt sentence is input into the generative AI model, and the resulting virtual personality data is analyzed and saved.

[0154] Step 5: Start the interview

[0155] The user uses the device to ask the virtual persona questions by voice, such as, "What do you think about the latest AI technology?"

[0156] Input: User voice input

[0157] Output: Speech-to-text data

[0158] Specific operation: Using a speech recognition engine (e.g., Google Speech-to-Text API), the speech is converted into text in real time and this text is sent to the server.

[0159] Step 6: Receiving and parsing the question text

[0160] The server receives and analyzes the question text sent by the user.

[0161] Input: User's question text

[0162] Output: Parsed question data

[0163] What it does: The server receives the text data, parses it, and converts it into a format that can be fed into the appropriate generative AI model.

[0164] Step 7: Generate answers using virtual personalities

[0165] The server uses the generative AI model to generate an appropriate answer to the user's question, for example, "The latest AI technology is very interesting."

[0166] Input: Parsed question data

[0167] Output: Generated answer text

[0168] Specific operation: Question data is input into the generative AI model and the resulting answer text is obtained.

[0169] Step 8: Generate audio data

[0170] The server passes the generated answer text to a speech synthesis engine (e.g., Amazon Polly) to generate voice data.

[0171] Input: Generated answer text

[0172] Output: Audio data

[0173] Specific operation: Input text into the speech synthesis engine and send the generated audio file to the device.

[0174] Step 9: Sending and Playing Audio Data

[0175] The server sends the generated audio data to the terminal, which then plays the audio data and lets the user hear it.

[0176] Input: Audio data

[0177] Output: The audio played to the user

[0178] What it does: Plays audio files in streaming or download format.

[0179] Step 10: Record the interview

[0180] The server stores the entire interview as text data in the form of minutes, along with the audio data.

[0181] Input: Interview content (text and audio data)

[0182] Output: Saved minutes text and audio data

[0183] Specific operation: The server saves the minutes in text format and the audio data in an appropriate format (e.g., mp3).

[0184] By performing these steps sequentially, the system of the present invention can facilitate an interview with a virtual personality.

[0185] (Application example 1)

[0186] 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."

[0187] In conventional online shopping systems, users often struggle with product selection, and the systems that can provide appropriate support are limited. Furthermore, there is a lack of mechanisms to generate a personal assistant based on the user's settings information to support product selection. As a result, users are unable to receive appropriate advice, resulting in a poor purchasing experience.

[0188] 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.

[0189] In this invention, the server includes means for generating a virtual personality based on setting information input by the user, means for recognizing the user's voice input and converting it into text, means for the generated virtual personality to generate answers to the user's questions, means for synthesizing and playing back the generated answers, means for saving the interview content as minutes, means for saving the interview audio data, means for generating a shopping assistant based on the user's settings and providing audio support for product selection, means for generating product recommendation information based on the inquiry content, and means for outputting the generated recommendation information by voice. This allows the user to receive appropriate recommendations through the shopping assistant, providing a new purchasing experience.

[0190] "Means for generating a virtual personality based on user-entered setting information" refers to a system that uses a generative AI model to create a virtual personality based on user-entered setting information (e.g., occupation, personality, characteristics).

[0191] The "means for recognizing a user's voice input and converting it into text" is a system that uses a voice recognition engine to convert a user's voice into text data in real time.

[0192] "Means for a generated virtual personality to generate answers to a user's questions" refers to a system in which a virtual personality uses a generative AI model to create appropriate answers to a user's questions.

[0193] The "means for synthesizing and reproducing the generated answer" is a system that uses a speech synthesis engine to convert the generated answer from text to speech and reproduce it aloud to the user.

[0194] "Means for saving interview content as minutes" refers to a storage system that stores the content of conversations during interviews as text data and makes it available for later viewing.

[0195] "Means for storing audio data of an interview" refers to a system for recording and storing audio data during an interview.

[0196] "A means for generating a shopping assistant based on user settings and providing voice support for product selection" is a system that creates a virtual shopping assistant based on information set by the user and provides voice support for the user's shopping through that assistant.

[0197] The "means for generating product recommendation information based on the inquiry content" is a system that analyzes the inquiry content of the user and generates information that recommends appropriate products based on the analysis.

[0198] The "means for outputting generated recommendation information by voice" is a system that converts the generated recommendation information into voice data and provides it to the user by voice.

[0199] The present invention is a system for generating a virtual personality based on setting information input by a user and conducting an audio interview with the virtual personality. Specific embodiments for carrying out the present invention will be described below.

[0200] System configuration

[0201] This system mainly consists of the following components:

[0202] 1. User setting input interface

[0203] Users input their preferences via a smartphone or web interface, including their occupation, personality, and characteristics. For example, they might enter preferences such as "occupation: fashion consultant, personality: friendly, characteristics: sensitive to trends."

[0204] 2. Virtual personality generation

[0205] The server receives the configuration information and generates a virtual personality using a generative AI model (e.g., GPT-3.5-Turbo). The generated virtual personality data is stored on the server and awaits the start of the interview.

[0206] 3. Start of interview

[0207] Users ask questions by voice using a smartphone or other device, and the device's built-in speech recognition engine (e.g., Google Speech Recognition API) converts the voice into text data and sends it to the server.

[0208] 4. Answer Generation and Speech Synthesis

[0209] The server analyzes the text data of the question and generates an appropriate answer as a virtual personality. The generated answer is converted into voice data by a speech synthesis engine (e.g., pyttsx3) and sent to the device.

[0210] 5. Recording of interviews

[0211] The server stores the entire interview as a transcript in text format, along with the audio data, which can be accessed by the user later.

[0212] Hardware and software used

[0213] Hardware: smartphones, tablets, servers, etc.

[0214] software:

[0215] Generative AI model: GPT-3.5-Turbo

[0216] Speech recognition engine: Google Speech Recognition API

[0217] Speech synthesis engine: pyttsx3

[0218] Web Interface: Any web browser

[0219] Specific examples

[0220] For example, if a user asks, "What is a recommended outfit for spring?" the system will act as follows:

[0221] 1. User's question is entered by voice

[0222] 2. The speech recognition engine converts speech to text

[0223] 3. The server analyzes the text and generates an answer as a virtual personality.

[0224] 4. The answer is converted into speech using a speech synthesis engine and played back to the user.

[0225] Prompt Sentence Examples

[0226] What is your recommended outfit for spring?

[0227] This allows users to receive appropriate advice and enjoy a more personalized shopping experience.

[0228] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0229] Step 1:

[0230] The user inputs configuration information such as occupation, personality, and characteristics via a smartphone or web interface. The input data is sent to the server.

[0231] Step 2:

[0232] The server generates a virtual personality. Based on the received setting information, a generative AI model (e.g., GPT-3.5-Turbo) is used to generate the virtual personality. This virtual personality data is stored on the server and waits until the interview begins.

[0233] Step 3:

[0234] The user asks a question by voice. The user asks a question by voice to the virtual personality using a smartphone or another device. The voice recognition engine (e.g., Google Speech Recognition API) installed on the device converts the voice into text data and sends the text data to the server.

[0235] Step 4:

[0236] The server analyzes the question and generates an answer as a virtual personality. The server analyzes the text data of the received question and generates an appropriate answer using a generative AI model. The generated answer is stored as text data on the server.

[0237] Step 5:

[0238] The server passes the generated answer to a speech synthesis engine (e.g., pyttsx3), which converts the text data of the answer into audio data, which is then sent to the device and played back to the user.

[0239] Step 6:

[0240] The server stores the interviews. The server saves the entire interview in text format as a transcript. The server also saves the audio of the interviews for the user to refer to later.

[0241] Step 7:

[0242] Generate a shopping assistant based on user settings. The server uses the settings to create a virtual persona as a shopping assistant. This virtual persona generates recommendation information based on the user's product inquiries.

[0243] Step 8:

[0244] Recommendation information is generated based on the query content. The server uses the generative AI model to generate product recommendation information. This recommendation information is saved as text data.

[0245] Step 9:

[0246] The generated recommendation information is output as voice data. The server passes the recommendation information to a voice synthesis engine and converts it into voice data. This voice data is sent to the device and played back to the user.

[0247] Through these steps, the system effectively acts as a shopping assistant for users, enabling a more personalized purchasing experience.

[0248] 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.

[0249] The present invention combines a system that generates a virtual personality based on setting information entered by a user and conducts an audio interview with that virtual personality with an emotion engine that recognizes the user's emotions. Specific embodiments for carrying out the present invention will be described below.

[0250] 1. User setting input

[0251] The user inputs configuration information for the virtual persona using a terminal application or a web interface, including occupation, personality, characteristics, etc. The configuration information is then sent to the server in an appropriate format.

[0252] 2. Virtual personality generation

[0253] The server receives the setting information sent by the user and generates a virtual personality using the generative AI model. The generated virtual personality data is stored on the server.

[0254] 3. Start of interview

[0255] The user asks questions to the virtual persona by voice through the device, which uses a voice recognition engine to convert the user's voice input into text in real time and transmits this text data to the server.

[0256] 4. Emotion recognition

[0257] The server uses an emotion engine to recognize emotions from the user's voice input in addition to the voice-recognized text data. The emotion engine analyzes the user's voice tone, speed, and other parameters to generate emotion data.

[0258] 5. Answer generation and voice output

[0259] The server generates answers from the virtual personality based on the received question text and the recognized emotion data, using a natural language processing algorithm to generate answers that include appropriate tone and content according to the emotion recognized.

[0260] The generated answer is passed to a speech synthesis engine, which generates audio data, which is then sent to the device and played back to the user.

[0261] 6. Recording of interviews

[0262] The server stores the interview contents as a text record in the form of minutes, and emotional data can also be included in the minutes. Audio data is also stored, so users can review the interview contents later.

[0263] Specific examples

[0264] 1. Example of user preference input

[0265] Examples of setting information input by the user include the following:

[0266] json

[0267] {

[0268] "Occupation": "Psychologist",

[0269] "Personality": "Friendly",

[0270] "Characteristics": "Emotionally sensitive"

[0271] }

[0272] 2. Virtual personality generation

[0273] Based on the above settings, the server uses a generative AI model to generate a virtual personality, such as a "psychologist," "friendly," or "sensitive to emotions."

[0274] 3. Example user questions

[0275] The user verbally asks, "Tell me how you deal with stress."

[0276] 4. Emotion Recognition Example

[0277] The server analyzes the user's voice input and uses an emotion engine to recognize the emotion that the user is feeling slightly anxious.

[0278] 5. Example of answer generation and speech output

[0279] Based on the question and the sense of anxiety recognized, the server generates an answer such as, "When you feel stressed, it's important to first take a deep breath and calm yourself down." This answer is synthesized into voice and sent to the device to be played back to the user.

[0280] 6. Examples of interview recording

[0281] The server saves the entire interview as a text file containing transcripts, including emotional data. The audio data is also saved in MP3 format.

[0282] The present invention can be implemented using the above method. By using this system, users can efficiently and effectively conduct interviews with virtual personalities and obtain appropriate responses and answers that take emotions into consideration. This allows users to gain new insights and a deeper understanding based on emotions.

[0283] The processing flow will be explained below.

[0284] Step 1:

[0285] The user opens the application or web interface on their device and enters configuration information for their virtual personality, including their occupation, personality, and characteristics.

[0286] Step 2:

[0287] The terminal formats the setting information entered by the user into an appropriate data format and sends it to the server.

[0288] Step 3:

[0289] The server receives the setting information sent from the terminal and analyzes its contents.

[0290] Step 4:

[0291] The server uses the generative AI model to generate a virtual personality based on the setting information, and the generated virtual personality data is stored on the server.

[0292] Step 5:

[0293] The user verbally asks a question to the device.

[0294] Step 6:

[0295] The device uses a speech recognition engine to convert the user's voice input into text data in real time, which is then sent to the server.

[0296] Step 7:

[0297] The server analyzes the received question text data and simultaneously generates emotion data from the user's voice input using an emotion engine.

[0298] Step 8:

[0299] The server combines the question text data with the emotion data to generate an appropriate answer for the virtual personality, using a natural language processing algorithm.

[0300] Step 9:

[0301] The generated answer text is passed to a speech synthesis engine and generated as voice data.

[0302] Step 10:

[0303] The server transmits the generated voice data to the terminal.

[0304] Step 11:

[0305] The device plays back the received audio data and provides the user with a response.

[0306] Step 12:

[0307] The server stores the interview contents as a text record in the form of a transcript, which also contains the recognized emotion data.

[0308] Step 13:

[0309] The server stores the audio data of the interview.

[0310] Step 14:

[0311] After the interview, users can review the saved transcript and audio data.

[0312] The following is an explanation using a specific example.

[0313] 1. Example of user preference input

[0314] Examples of setting information that the user inputs include the following:

[0315] json

[0316] {

[0317] "Occupation": "Psychologist",

[0318] "Personality": "Friendly",

[0319] "Characteristics": "Emotionally sensitive"

[0320] }

[0321] 2. Virtual personality generation

[0322] The server uses the AI ​​model to generate a virtual personality based on the above settings. The virtual personality has characteristics such as "psychologist," "friendly," and "sensitive to emotions."

[0323] 3. Example user questions

[0324] The user verbally asks, "Tell me how you deal with stress."

[0325] 4. Emotion Recognition Example

[0326] The server analyzes the user's voice input and uses an emotion engine to recognize that the user is feeling a little anxious.

[0327] 5. Example of answer generation and speech output

[0328] Based on the question and the recognized emotional data, the server generates an answer such as, "When you feel stressed, it's important to first take a deep breath and calm yourself down." This answer is synthesized into voice and sent to the device to be played back to the user.

[0329] 6. Examples of interview recording

[0330] The server saves the entire interview as a transcript in a text file, including emotional data, and also saves the audio data in an appropriate format.

[0331] Example 2

[0332] 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."

[0333] Conventional virtual personality interview systems generate answers without considering the user's emotions, making it difficult to provide appropriate answers tailored to individual needs. Furthermore, the recording of interview content and audio data is often insufficient, resulting in insufficient information for later reference. Furthermore, when generating answers using natural language processing algorithms, the lack of emotion recognition can lead to poor answer quality.

[0334] 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.

[0335] In this invention, the server includes means for generating a virtual personality based on setting information input by the user, means for recognizing the user's voice input and converting it into text, means for the generated virtual personality to generate answers to the user's questions, means for synthesizing the generated answers and playing them back, means for saving the interview content as minutes, means for saving the interview voice data, means for recognizing emotions from the user's voice input, and means for the virtual personality to generate answers based on the recognized emotion data. This makes it possible to provide appropriate answers according to the user's emotions in real time and to record and save the interview content and voice data in detail.

[0336] "Setting information" refers to information that a user inputs when creating a virtual personality, and includes data such as occupation, personality, and characteristics.

[0337] A "virtual personality" is an interactive character generated by the server based on configuration information, and has the ability to answer users' questions in real time.

[0338] "User voice input" refers to the voice that the user makes through the terminal, including interview questions and conversation content.

[0339] "Convert to text" refers to the process of converting audio data into text using speech recognition technology.

[0340] "Generating an answer" refers to the process by which the virtual personality creates an appropriate response to the user's question, which may use natural language processing algorithms.

[0341] "Speech synthesis" refers to a technique for outputting generated text responses as speech, converting text data into speech data.

[0342] "Saving as minutes" means recording the interview contents in text format so that they can be referenced at a later date.

[0343] "Storing audio data" refers to recording the audio data of an interview in digital form so that it can be played back and analyzed at a later date.

[0344] "Emotion recognition" refers to the process of extracting emotional data from a user's voice input by analyzing the tone, speed, and word choice of the voice.

[0345] "Emotional data" refers to data that indicates the user's emotional state using emotion recognition technology and is used by the virtual personality to generate responses.

[0346] This invention is a system that generates a virtual personality based on setting information entered by a user and conducts an audio interview with that virtual personality, and further combines it with an emotion engine that recognizes the user's emotions. Specific embodiments for implementing this system are described below.

[0347] First, the user inputs the virtual persona's configuration information, including occupation, personality, characteristics, etc., using a terminal application or web interface. This configuration information is then sent to the server in an appropriate format.

[0348] The server receives the setting information sent by the user and generates a virtual personality using a generative AI model (e.g., GPT-4). The generated virtual personality data is stored on the server.

[0349] Next, the user asks the virtual persona a question by voice through the device. The user's voice input is converted into text in real time by a speech recognition engine (e.g., Google Speech-to-Text) within the device, and this text data is sent to the server.

[0350] The server uses an emotion engine (e.g., IBM Watson Tone Analyzer) to recognize emotions from the user's voice input in addition to the transmitted text data. The emotion engine analyzes the tone, rate, and other parameters of the user's voice to generate emotion data.

[0351] Based on the submitted question text and emotion data, the server uses a generative AI model to generate an answer from the virtual personality. For example, it utilizes a natural language processing algorithm. The generated answer is passed to a speech synthesis engine (e.g., Amazon Polly) and generated as audio data. This audio data is sent to the device and played back to the user.

[0352] The server also stores the interview content as a text record in the form of minutes, including emotional data, and audio data, so users can review the interview content later.

[0353] Specific examples

[0354] 1. Example of user preference input

[0355] An example of the setting information entered by the user is as follows:

[0356] Occupation: Psychologist

[0357] Personality: Friendly

[0358] Traits: Emotionally sensitive

[0359] 2. Virtual personality generation

[0360] Based on the above configuration information, the server uses a generative AI model (e.g., GPT-4) to generate a virtual personality. For example, a personality with characteristics such as "psychologist," "friendly," and "sensitive to emotions" is generated.

[0361] 3. Example user questions

[0362] The user verbally asks, "Tell me how you deal with stress."

[0363] 4. Emotion Recognition Example

[0364] The server analyzes the user's voice input and uses an emotion engine (e.g., IBM Watson Tone Analyzer) to recognize the user's emotion, which indicates slight anxiety.

[0365] 5. Example of answer generation and speech output

[0366] The server generates an answer based on the question and the perceived anxiety level. For example, "When you feel stressed, it's important to first take a deep breath and calm yourself down." The generated answer is synthesized into voice and sent to the device.

[0367] 6. Examples of interview recording

[0368] The server saves the entire interview as a text file containing transcripts, including emotional data. The audio data is also saved in MP3 format.

[0369] Prompt Sentence Examples

[0370] The following is an example of a prompt sentence:

[0371] Role: Virtual Psychologist

[0372] Occupation: Psychologist

[0373] Personality: Friendly

[0374] Traits: Emotionally sensitive

[0375] User Question: What do you do when you feel stressed?

[0376] Recognized emotion: Anxiety

[0377] By implementing the invention in accordance with the above aspects, users can efficiently and effectively interview virtual personalities and obtain appropriate responses and answers that take emotions into account, thereby gaining new insights and deeper understanding based on emotions.

[0378] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0379] Step 1: User Settings Input

[0380] The user uses a terminal application or a web interface to input configuration information for the virtual personality, including occupation, personality, and characteristics. For example, the user might input information such as "Occupation: Psychologist, Personality: Friendly, Characteristics: Sensitive to Emotions."

[0381] Input: The user enters the configuration information.

[0382] Output: The device converts the input configuration information into the appropriate format, checks for errors, and sends the converted configuration information to the server.

[0383] Step 2: Virtual personality generation

[0384] The server receives the setting information sent by the user.

[0385] Based on the received information, the server invokes a generative AI model (e.g., GPT-4) to generate a virtual personality that reflects the user's specified occupation, personality, and characteristics.

[0386] Input: The server receives user configuration information.

[0387] Data processing: The server calls the generative AI model and generates a virtual personality based on the setting information.

[0388] Output: The server stores the generated virtual personality data in its own database.

[0389] Step 3: Start the interview

[0390] The user uses the device to ask the virtual personality a question by voice. The user types the question into the device's microphone. For example, the user might ask, "Tell me how to deal with stress."

[0391] The device uses a speech recognition engine such as Google Speech-to-Text to convert the user's speech into text.

[0392] Input: User's voice input.

[0393] Data processing: The device uses a speech recognition engine to convert the user's speech into text.

[0394] Output: The converted text data is sent to the server.

[0395] Step 4: Emotion Recognition

[0396] The server receives the transmitted text data and, if necessary, also analyzes the user's voice data.

[0397] The server uses emotion engines such as IBM Watson Tone Analyzer to recognize the user's emotions from text and audio data, including tone of voice, speaking rate and word choice.

[0398] Input: Text and audio data.

[0399] Data processing: The server uses the emotion engine to generate emotion data.

[0400] Output: Add the recognized emotion data to the prompt sentence.

[0401] Step 5: Answer generation and speech output

[0402] The server generates an appropriate answer using a generative AI model (e.g., GPT-4) based on the user's question text and emotion data. For example, if the server recognizes anxiety in response to the question, "Please tell me how to deal with stress," it will generate an answer such as, "When you feel stressed, it's important to take a deep breath and calm yourself down first."

[0403] The server passes the generated answer to a speech synthesis engine such as Amazon Polly to generate voice data.

[0404] Input: Question text and sentiment data.

[0405] Data processing: The server uses the generative AI model to generate an appropriate answer, which is then converted into voice data using a speech synthesis engine.

[0406] Output: The generated audio data is sent to the device.

[0407] The terminal plays the received audio data so that it reaches the user.

[0408] Step 6: Record the interview

[0409] The server stores all the conversations in the interview as transcripts in text format, including emotional data.

[0410] The server also stores the audio data for later reference, for example in mp3 format.

[0411] Users can log in later to check the minutes and audio data.

[0412] Input: Interview audio and text data.

[0413] Data processing: The server stores the minutes and audio data in a database.

[0414] Output: Saved transcripts and audio data.

[0415] (Application example 2)

[0416] 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."

[0417] In modern society, users have more opportunities to access a variety of content, but finding content that is optimized for their emotional state and interests remains a difficult challenge. Furthermore, there is a lack of easy ways for users to obtain recommended content tailored to their emotions and circumstances. To address this issue, there is a need for a method to provide optimal content based on the user's input information and emotional state.

[0418] The specific processing by the specific processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means. In this invention, the server includes means for generating a virtual personality based on setting information entered by the user, means for recognizing the user's voice input and converting it into text, means for the generated virtual personality to recommend content, means for analyzing the user's emotions using an emotion engine, and means for audibly outputting emotion-based content recommendations based on this data. This makes it possible to recommend personalized content that is optimized for the user's emotional state and interests.

[0419] "User preference input" is the process by which a user inputs information required for a virtual personality or recommendation system.

[0420] A "virtual personality" is a virtual agent with specific characteristics, occupations, and personalities that is generated based on the user's settings.

[0421] "Speech recognition" is a technology that converts a user's voice input into text data.

[0422] An "emotion engine" is an algorithm or software that analyzes voice and text data to recognize the user's emotions.

[0423] A "natural language processing algorithm" is a technology that analyzes the meaning of text data and is used to generate content and answers.

[0424] "Content recommendation" is the process of suggesting the most suitable content, such as movies, music, or books, based on a user's interests and emotional state.

[0425] "Emotion analysis" is a technology that uses a user's voice and text data to identify their emotional state at that time.

[0426] "Speech synthesis" is a technology that generates synthetic speech based on text data.

[0427] "Minutes" are the contents of interviews or conversations recorded as text data.

[0428] "Audio data preservation" is the process of storing recorded audio in digital form.

[0429] By "operating on a smartphone" it is meant that the present invention is executable on a smartphone device.

[0430] A specific embodiment of the present invention will now be described in detail. The present invention provides a system that generates a virtual personality based on setting information input by a user and recommends content that is optimized for the user's emotions through interaction with the virtual personality.

[0431] First, a user launches the application through their device and enters their personal settings, including their interests, favorite actors and music genres, and other characteristics. This information is then sent to the server and used to generate a unique virtual personality for the user.

[0432] The server uses a generative AI model based on the received settings to generate a virtual personality that matches the user's interests and characteristics. This virtual personality acts as an agent that recommends content through dialogue with the user.

[0433] Next, the user speaks a question to the virtual agent, such as, "What movies are good to watch today?" The device uses a speech recognition engine (e.g., Google Speech-to-Text) to convert the user's voice into text in real time and send it to the server.

[0434] The server analyzes the received text data and uses an emotion engine (e.g., IBM Watson Tone Analyzer) to recognize the user's emotion. For example, if it recognizes that the user is tired, it will use this information to suggest the most appropriate content.

[0435] The generated answer is adjusted based on emotion recognition and is generated in the form of, for example, "You seem tired today. How about a relaxing comedy movie?" This answer is passed to a speech synthesis engine (e.g., Amazon Polly) and generated as synthetic speech. The generated speech data is sent to the device and played back to the user.

[0436] The server also stores the interview as a text transcript, including the questions asked, emotional data, and the virtual agent's responses, as well as audio data, so the user can review the interview later.

[0437] As a concrete example, consider a scenario where a user asks a question by voice, "What are the latest action movies starring Will Smith?" In this case, the system works to recommend the most suitable movie, taking into account the user's emotional state.

[0438] Example prompt sentence:

[0439] User: Want to watch a relaxing movie today?

[0440] Virtual Agent: You seem tired today. How about a relaxing comedy movie?

[0441] This enables personalized content recommendations that are optimized for the user's emotional state and interests.

[0442] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[0443] Step 1:

[0444] The user launches the application through their device and enters their personal settings, including their interests, favorite actors and music genres, and other characteristics. This data is sent to the server in an appropriate format, in JSON format, and is saved as the user's profile information on the server side.

[0445] Step 2:

[0446] The server uses a generative AI model based on the received configuration information to generate a virtual personality. A generative AI model (e.g., GPT-3) is used to create a virtual agent tailored to the user's interests and characteristics. This virtual personality data is stored on the server and used in subsequent interactions and recommendation processes. Specifically, the generative AI model generates text data and stores it as a virtual personality profile.

[0447] Step 3:

[0448] The user asks a question to the virtual agent by voice. The device uses a speech recognition engine (e.g., Google Speech-to-Text) to convert the user's voice into text in real time and send it to the server. The input voice data is digitized at a sample rate and converted into text by the speech recognition engine. The converted text is sent to the server in JSON format.

[0449] Step 4:

[0450] The server analyzes the received text data and recognizes the user's emotions using an emotion engine (e.g., IBM Watson Tone Analyzer). Specifically, the emotion engine extracts emotion parameters (e.g., happiness, sadness, anger, etc.) from the text data and saves them as emotion analysis results. This emotion data is saved in JSON format as metadata such as the intensity and type of emotion.

[0451] Step 5:

[0452] The server uses the user's question text and emotional data to generate the best answer from the generated virtual personality. It uses a natural language processing algorithm to generate an answer optimized for the user's emotional state. For example, if the user is tired, it will recommend a relaxing movie. A generative AI model is used in this answer generation process.

[0453] Step 6:

[0454] The generated answer is passed to a speech synthesis engine (e.g., Amazon Polly) to generate synthetic speech. This generated speech data is sent to the device and played back to the user. The speech synthesis engine converts the text data into speech waveforms and sends the speech data to the device.

[0455] Step 7:

[0456] The server saves the entire interview as a text file containing the questions asked, emotional data, and the virtual agent's responses. The audio data is also saved digitally so that it can be played back later if necessary. The server then saves this data in a suitable format on the file system, making it accessible to the user.

[0457] 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.

[0458] 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.

[0459] 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.

[0460] [Second embodiment]

[0461] FIG. 3 shows an example of the configuration of a data processing system 210 according to the second embodiment.

[0462] 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.

[0463] 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).

[0464] 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.

[0465] 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.

[0466] 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).

[0467] 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.

[0468] 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.

[0469] 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.

[0470] 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.

[0471] In the smart glasses 214, the reception output process is performed by the processor 46. A reception output program 60 is stored in the storage 50. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output process is realized by the processor 46 operating as the control unit 46A in accordance with the reception output program 60 executed on the RAM 48.

[0472] 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."

[0473] The present invention relates to a system for generating a virtual personality based on setting information input by a user and conducting an audio interview with the virtual personality. Specific embodiments for carrying out the present invention will be described below.

[0474] 1. User setting input

[0475] The user inputs the virtual persona's configuration information, including occupation, personality, characteristics, etc., using a terminal application or a web interface. The input configuration information is then sent to the server in an appropriate format.

[0476] 2. Virtual personality generation

[0477] The server receives the setting information sent by the user and generates a virtual personality using a generative AI model. The generated virtual personality data is stored on the server until the interview begins.

[0478] 3. Start of interview

[0479] The user speaks questions to the virtual persona through the device, which uses a speech recognition engine to convert the user's voice input into text in real time, and this text data is sent to the server.

[0480] 4. Answer generation and voice output

[0481] The server analyzes the received question text and generates an answer as a virtual personality. The generated answer is passed to a speech synthesis engine and generated as voice data. The voice data is sent to the device and played back to the user.

[0482] 5. Recording of interviews

[0483] The server stores the interview contents as a text record in the form of minutes, and also stores the audio data so that users can review the interview contents later.

[0484] Specific examples

[0485] 1. Example of user preference input

[0486] Examples of setting information input by the user include the following:

[0487] json

[0488] {

[0489] "Occupation": "Engineer",

[0490] "Personality": "Logical",

[0491] "Characteristics": "Tech-savvy"

[0492] }

[0493] 2. Virtual personality generation

[0494] Based on the above setting information, the server uses a generative AI model to generate a virtual personality. For example, a personality with characteristics such as "engineer," "logical," and "tech-savvy" is generated.

[0495] 3. Example user questions

[0496] A user verbally asks the question, "What do you think about the latest AI technology?"

[0497] 4. Example of answer generation and speech output

[0498] The server receives the question and generates an answer such as, "The latest AI technology is very interesting." This answer is then synthesized into voice, which the device plays back to the user.

[0499] 5. Examples of interview recording

[0500] The server saves the entire interview as a transcript in a text file, and also saves the audio data in MP3 format.

[0501] The present invention can be implemented in the above manner. By using this system, users can efficiently and effectively conduct interviews with virtual personalities and gain new insights and ideas.

[0502] The processing flow will be explained below.

[0503] Step 1:

[0504] The user opens the application or web interface on their device and enters configuration information for their virtual personality, including their occupation, personality, and characteristics.

[0505] Step 2:

[0506] The terminal formats the configuration information entered by the user and transmits it to the server in the appropriate data format.

[0507] Step 3:

[0508] The server receives the setting information sent from the terminal and checks its contents.

[0509] Step 4:

[0510] The server uses a generative AI model to generate a virtual personality based on the user's settings, and the generated virtual personality data is stored on the server.

[0511] Step 5:

[0512] The user verbally asks a question to the device.

[0513] Step 6:

[0514] The device uses a speech recognition engine to convert the user's voice input into text data in real time.

[0515] Step 7:

[0516] The terminal transmits the converted question text data to the server.

[0517] Step 8:

[0518] The server analyzes the question text data received from the terminal and generates an answer as a virtual personality.

[0519] Step 9:

[0520] The generated answer text is passed to a speech synthesis engine to generate speech data.

[0521] Step 10:

[0522] The server transmits the generated voice data to the terminal.

[0523] Step 11:

[0524] The device plays back the received audio data and provides the user with a response.

[0525] Step 12:

[0526] The server generates and stores a text record of the interview contents as a transcript.

[0527] Step 13:

[0528] The server stores the audio data of the interview.

[0529] Step 14:

[0530] After the interview, users can review the saved transcript and audio data.

[0531] Example 1

[0532] 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."

[0533] A method is needed to generate a virtual personality based on user-entered settings and enable natural dialogue when the user interviews the virtual personality. Another challenge is to efficiently convert the user's voice input into text, generate appropriate responses based on the text, and then respond in voice. It is also important to keep a record of the interview content so that it can be referenced later.

[0534] 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.

[0535] In this invention, the server includes means for generating a virtual personality based on setting information input by a user, means for recognizing a user's voice input and converting it into text, means for generating a virtual personality using a generative AI model, means for the generated virtual personality to generate answers to the user's questions, means for synthesizing and playing back the generated answers, means for saving the interview content as minutes, and means for saving the interview audio data, which enables a user to input setting information, realize natural conversations with a virtual personality, and record and save the content.

[0536] "User" refers to any individual or entity that uses the System.

[0537] "Setting information" refers to information about a specific occupation, personality, and characteristics that a user inputs to generate a virtual personality.

[0538] A "virtual personality" is a virtual entity generated based on the user's settings, and refers to a pseudo-personality that can interact with the user.

[0539] "Voice input" refers to input made by a user to a system using voice.

[0540] "Text conversion" refers to the process of analyzing voice input and expressing it as a string of characters.

[0541] A "generative AI model" refers to an algorithm that uses machine learning techniques to generate a virtual personality from a user's settings.

[0542] "Answer generation" refers to the process by which a virtual personality constructs an appropriate response to a question posed by a user.

[0543] "Speech synthesis" refers to the process of converting generated text data into speech data.

[0544] "Playback" refers to the process of playing back the synthesized voice data to the user.

[0545] "Minutes" refers to data that records the contents of an interview in written form.

[0546] "Voice data" refers to voice-synthesized responses and user voice input data.

[0547] The present invention is a system for generating a virtual personality based on setting information input by a user and conducting an audio interview with the virtual personality. Specific embodiments of the present invention will be described below.

[0548] User preference input

[0549] The user inputs configuration information for the virtual persona using a device application or web interface, including occupation, personality, and characteristics. For example, the user might input the following information:

[0550] Occupation: Engineer

[0551] Personality: Logical

[0552] Specialty: Technology savvy

[0553] Once these entries are complete, the device sends this information to the server in JSON format.

[0554] Virtual personality generation

[0555] The server receives the setting information sent by the user. Then, it generates a virtual personality using a generative AI model (e.g., GPT-3). The generated virtual personality data is stored on the server until the interview begins. For example, the following prompt sentences are used to input to the generative AI model:

[0556] Prompt: "You are an engineer, a logical, tech-savvy person."

[0557] Interview begins

[0558] The user asks the virtual persona a question by voice through the device, such as, "What do you think about the latest AI technology?" The device uses a speech recognition engine (e.g., Google Speech-to-Text API) to convert the user's voice into text in real time and sends this text data to the server.

[0559] Answer generation and voice output

[0560] The server analyzes the received question text and generates an answer as a virtual personality using a generative AI model. For example, it generates an answer such as "The latest AI technology is very interesting." The generated answer is passed to a speech synthesis engine (e.g., Amazon Polly) and generated as audio data. This audio data is sent to the device and played back to the user.

[0561] Interview recording

[0562] The server stores the interview contents as text records in minutes format. Audio data is also stored in the same way. Users can review the interview contents later. The recordings are generally stored in text files and MP3 format.

[0563] This embodiment allows users to efficiently and effectively interview virtual personalities, and gain new insights and ideas.

[0564] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0565] Program processing flow and specific explanation

[0566] Step 1: User Settings Input

[0567] The user inputs the virtual personality's configuration information using a terminal application or web interface. This configuration information includes occupation, personality, characteristics, etc. For example, the user inputs information such as "Occupation: Engineer," "Personality: Logical," and "Characteristics: Knowledgeable about technology."

[0568] Input: Setting information about occupation, personality, and characteristics

[0569] Output: JSON data containing configuration information

[0570] Specific behavior: The user enters the setting information into the input form and clicks the "Submit" button.

[0571] Step 2: Sending configuration information

[0572] The device sends the configuration information entered by the user to the server in an appropriate format (JSON format).

[0573] Input: JSON data generated in step 1

[0574] Output: Configuration information sent to the server

[0575] Specific operation: JSON data containing configuration information is sent to the server via an HTTP request.

[0576] Step 3: Receiving configuration information

[0577] The server receives the setting information sent from the device, and this data is stored and analyzed within the server.

[0578] Input: Setting information sent from the device

[0579] Output: Configuration information saved on the server

[0580] Specific operation: The server receives the HTTP request and saves the configuration information in the database.

[0581] Step 4: Virtual personality generation

[0582] The server generates a virtual personality using a generative AI model (e.g., GPT-3) based on the received configuration information. For example, it creates a prompt sentence like the following based on the configuration information: "Occupation: Engineer," "Personality: Logical," and "Characteristics: Knowledgeable about technology."

[0583] Prompt: "You are an engineer, a logical, tech-savvy person."

[0584] Input: Configuration information stored on the server

[0585] Output: Generated virtual personality data

[0586] Specific operation: A prompt sentence is input into the generative AI model, and the resulting virtual personality data is analyzed and saved.

[0587] Step 5: Start the interview

[0588] The user uses the device to ask the virtual persona questions by voice, such as, "What do you think about the latest AI technology?"

[0589] Input: User voice input

[0590] Output: Speech-to-text data

[0591] Specific operation: Using a speech recognition engine (e.g., Google Speech-to-Text API), the speech is converted into text in real time and this text is sent to the server.

[0592] Step 6: Receiving and parsing the question text

[0593] The server receives and analyzes the question text sent by the user.

[0594] Input: User's question text

[0595] Output: Parsed question data

[0596] What it does: The server receives the text data, parses it, and converts it into a format that can be fed into the appropriate generative AI model.

[0597] Step 7: Generate answers using virtual personalities

[0598] The server uses the generative AI model to generate an appropriate answer to the user's question, for example, "The latest AI technology is very interesting."

[0599] Input: Parsed question data

[0600] Output: Generated answer text

[0601] Specific operation: Question data is input into the generative AI model and the resulting answer text is obtained.

[0602] Step 8: Generate audio data

[0603] The server passes the generated answer text to a speech synthesis engine (e.g., Amazon Polly) to generate voice data.

[0604] Input: Generated answer text

[0605] Output: Audio data

[0606] Specific operation: Input text into the speech synthesis engine and send the generated audio file to the device.

[0607] Step 9: Sending and Playing Audio Data

[0608] The server sends the generated audio data to the terminal, which then plays the audio data and lets the user hear it.

[0609] Input: Audio data

[0610] Output: The audio played to the user

[0611] What it does: Plays audio files in streaming or download format.

[0612] Step 10: Record the interview

[0613] The server stores the entire interview as text data in the form of minutes, along with the audio data.

[0614] Input: Interview content (text and audio data)

[0615] Output: Saved minutes text and audio data

[0616] Specific operation: The server saves the minutes in text format and the audio data in an appropriate format (e.g., mp3).

[0617] By performing these steps sequentially, the system of the present invention can facilitate an interview with a virtual personality.

[0618] (Application example 1)

[0619] 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."

[0620] In conventional online shopping systems, users often struggle with product selection, and the systems that can provide appropriate support are limited. Furthermore, there is a lack of mechanisms to generate a personal assistant based on the user's settings information to support product selection. As a result, users are unable to receive appropriate advice, resulting in a poor purchasing experience.

[0621] 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.

[0622] In this invention, the server includes means for generating a virtual personality based on setting information input by the user, means for recognizing the user's voice input and converting it into text, means for the generated virtual personality to generate answers to the user's questions, means for synthesizing and playing back the generated answers, means for saving the interview content as minutes, means for saving the interview audio data, means for generating a shopping assistant based on the user's settings and providing audio support for product selection, means for generating product recommendation information based on the inquiry content, and means for outputting the generated recommendation information by voice. This allows the user to receive appropriate recommendations through the shopping assistant, providing a new purchasing experience.

[0623] "Means for generating a virtual personality based on user-entered setting information" refers to a system that uses a generative AI model to create a virtual personality based on user-entered setting information (e.g., occupation, personality, characteristics).

[0624] The "means for recognizing a user's voice input and converting it into text" is a system that uses a voice recognition engine to convert a user's voice into text data in real time.

[0625] "Means for a generated virtual personality to generate answers to a user's questions" refers to a system in which a virtual personality uses a generative AI model to create appropriate answers to a user's questions.

[0626] The "means for synthesizing and reproducing the generated answer" is a system that uses a speech synthesis engine to convert the generated answer from text to speech and reproduce it aloud to the user.

[0627] "Means for saving interview content as minutes" refers to a storage system that stores the content of conversations during interviews as text data and makes it available for later viewing.

[0628] "Means for storing audio data of an interview" refers to a system for recording and storing audio data during an interview.

[0629] "A means for generating a shopping assistant based on user settings and providing voice support for product selection" is a system that creates a virtual shopping assistant based on information set by the user and provides voice support for the user's shopping through that assistant.

[0630] The "means for generating product recommendation information based on the inquiry content" is a system that analyzes the inquiry content of the user and generates information that recommends appropriate products based on the analysis.

[0631] The "means for outputting generated recommendation information by voice" is a system that converts the generated recommendation information into voice data and provides it to the user by voice.

[0632] The present invention is a system for generating a virtual personality based on setting information input by a user and conducting an audio interview with the virtual personality. Specific embodiments for carrying out the present invention will be described below.

[0633] System configuration

[0634] This system mainly consists of the following components:

[0635] 1. User setting input interface

[0636] Users input their preferences via a smartphone or web interface, including their occupation, personality, and characteristics. For example, they might enter preferences such as "occupation: fashion consultant, personality: friendly, characteristics: sensitive to trends."

[0637] 2. Virtual personality generation

[0638] The server receives the configuration information and generates a virtual personality using a generative AI model (e.g., GPT-3.5-Turbo). The generated virtual personality data is stored on the server and awaits the start of the interview.

[0639] 3. Start of interview

[0640] Users ask questions by voice using a smartphone or other device, and the device's built-in speech recognition engine (e.g., Google Speech Recognition API) converts the voice into text data and sends it to the server.

[0641] 4. Answer Generation and Speech Synthesis

[0642] The server analyzes the text data of the question and generates an appropriate answer as a virtual personality. The generated answer is converted into voice data by a speech synthesis engine (e.g., pyttsx3) and sent to the device.

[0643] 5. Recording of interviews

[0644] The server stores the entire interview as a transcript in text format, along with the audio data, which can be accessed by the user later.

[0645] Hardware and software used

[0646] Hardware: smartphones, tablets, servers, etc.

[0647] software:

[0648] Generative AI model: GPT-3.5-Turbo

[0649] Speech recognition engine: Google Speech Recognition API

[0650] Speech synthesis engine: pyttsx3

[0651] Web Interface: Any web browser

[0652] Specific examples

[0653] For example, if a user asks, "What is a recommended outfit for spring?" the system will act as follows:

[0654] 1. User's question is entered by voice

[0655] 2. The speech recognition engine converts speech to text

[0656] 3. The server analyzes the text and generates an answer as a virtual personality.

[0657] 4. The answer is converted into speech using a speech synthesis engine and played back to the user.

[0658] Prompt Sentence Examples

[0659] What is your recommended outfit for spring?

[0660] This allows users to receive appropriate advice and enjoy a more personalized shopping experience.

[0661] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0662] Step 1:

[0663] The user inputs configuration information such as occupation, personality, and characteristics via a smartphone or web interface. The input data is sent to the server.

[0664] Step 2:

[0665] The server generates a virtual personality. Based on the received setting information, a generative AI model (e.g., GPT-3.5-Turbo) is used to generate the virtual personality. This virtual personality data is stored on the server and waits until the interview begins.

[0666] Step 3:

[0667] The user asks a question by voice. The user asks a question by voice to the virtual personality using a smartphone or another device. The voice recognition engine (e.g., Google Speech Recognition API) installed on the device converts the voice into text data and sends the text data to the server.

[0668] Step 4:

[0669] The server analyzes the question and generates an answer as a virtual personality. The server analyzes the text data of the received question and generates an appropriate answer using a generative AI model. The generated answer is stored as text data on the server.

[0670] Step 5:

[0671] The server passes the generated answer to a speech synthesis engine (e.g., pyttsx3), which converts the text data of the answer into audio data, which is then sent to the device and played back to the user.

[0672] Step 6:

[0673] The server stores the interviews. The server saves the entire interview in text format as a transcript. The server also saves the audio of the interviews for the user to refer to later.

[0674] Step 7:

[0675] Generate a shopping assistant based on user settings. The server uses the settings to create a virtual persona as a shopping assistant. This virtual persona generates recommendation information based on the user's product inquiries.

[0676] Step 8:

[0677] Recommendation information is generated based on the query content. The server uses the generative AI model to generate product recommendation information. This recommendation information is saved as text data.

[0678] Step 9:

[0679] The generated recommendation information is output as voice data. The server passes the recommendation information to a voice synthesis engine and converts it into voice data. This voice data is sent to the device and played back to the user.

[0680] Through these steps, the system effectively acts as a shopping assistant for users, enabling a more personalized purchasing experience.

[0681] 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.

[0682] The present invention combines a system that generates a virtual personality based on setting information entered by a user and conducts an audio interview with that virtual personality with an emotion engine that recognizes the user's emotions. Specific embodiments for carrying out the present invention will be described below.

[0683] 1. User setting input

[0684] The user inputs configuration information for the virtual persona using a terminal application or a web interface, including occupation, personality, characteristics, etc. The configuration information is then sent to the server in an appropriate format.

[0685] 2. Virtual personality generation

[0686] The server receives the setting information sent by the user and generates a virtual personality using the generative AI model. The generated virtual personality data is stored on the server.

[0687] 3. Start of interview

[0688] The user asks questions to the virtual persona by voice through the device, which uses a voice recognition engine to convert the user's voice input into text in real time and transmits this text data to the server.

[0689] 4. Emotion recognition

[0690] The server uses an emotion engine to recognize emotions from the user's voice input in addition to the voice-recognized text data. The emotion engine analyzes the user's voice tone, speed, and other parameters to generate emotion data.

[0691] 5. Answer generation and voice output

[0692] The server generates answers from the virtual personality based on the received question text and the recognized emotion data, using a natural language processing algorithm to generate answers that include appropriate tone and content according to the emotion recognized.

[0693] The generated answer is passed to a speech synthesis engine, which generates audio data, which is then sent to the device and played back to the user.

[0694] 6. Recording of interviews

[0695] The server stores the interview contents as a text record in the form of minutes, and emotional data can also be included in the minutes. Audio data is also stored, so users can review the interview contents later.

[0696] Specific examples

[0697] 1. Example of user preference input

[0698] Examples of setting information input by the user include the following:

[0699] json

[0700] {

[0701] "Occupation": "Psychologist",

[0702] "Personality": "Friendly",

[0703] "Characteristics": "Emotionally sensitive"

[0704] }

[0705] 2. Virtual personality generation

[0706] Based on the above settings, the server uses a generative AI model to generate a virtual personality, such as a "psychologist," "friendly," or "sensitive to emotions."

[0707] 3. Example user questions

[0708] The user verbally asks, "Tell me how you deal with stress."

[0709] 4. Emotion Recognition Example

[0710] The server analyzes the user's voice input and uses an emotion engine to recognize the emotion that the user is feeling slightly anxious.

[0711] 5. Example of answer generation and speech output

[0712] Based on the question and the sense of anxiety recognized, the server generates an answer such as, "When you feel stressed, it's important to first take a deep breath and calm yourself down." This answer is synthesized into voice and sent to the device to be played back to the user.

[0713] 6. Examples of interview recording

[0714] The server saves the entire interview as a text file containing transcripts, including emotional data. The audio data is also saved in MP3 format.

[0715] The present invention can be implemented using the above method. By using this system, users can efficiently and effectively conduct interviews with virtual personalities and obtain appropriate responses and answers that take emotions into consideration. This allows users to gain new insights and a deeper understanding based on emotions.

[0716] The processing flow will be explained below.

[0717] Step 1:

[0718] The user opens the application or web interface on their device and enters configuration information for their virtual personality, including their occupation, personality, and characteristics.

[0719] Step 2:

[0720] The terminal formats the setting information entered by the user into an appropriate data format and sends it to the server.

[0721] Step 3:

[0722] The server receives the setting information sent from the terminal and analyzes its contents.

[0723] Step 4:

[0724] The server uses the generative AI model to generate a virtual personality based on the setting information, and the generated virtual personality data is stored on the server.

[0725] Step 5:

[0726] The user verbally asks a question to the device.

[0727] Step 6:

[0728] The device uses a speech recognition engine to convert the user's voice input into text data in real time, which is then sent to the server.

[0729] Step 7:

[0730] The server analyzes the received question text data and simultaneously generates emotion data from the user's voice input using an emotion engine.

[0731] Step 8:

[0732] The server combines the question text data with the emotion data to generate an appropriate answer for the virtual personality, using a natural language processing algorithm.

[0733] Step 9:

[0734] The generated answer text is passed to a speech synthesis engine and generated as voice data.

[0735] Step 10:

[0736] The server transmits the generated voice data to the terminal.

[0737] Step 11:

[0738] The device plays back the received audio data and provides the user with a response.

[0739] Step 12:

[0740] The server stores the interview contents as a text record in the form of a transcript, which also contains the recognized emotion data.

[0741] Step 13:

[0742] The server stores the audio data of the interview.

[0743] Step 14:

[0744] After the interview, users can review the saved transcript and audio data.

[0745] The following is an explanation using a specific example.

[0746] 1. Example of user preference input

[0747] Examples of setting information that the user inputs include the following:

[0748] json

[0749] {

[0750] "Occupation": "Psychologist",

[0751] "Personality": "Friendly",

[0752] "Characteristics": "Emotionally sensitive"

[0753] }

[0754] 2. Virtual personality generation

[0755] The server uses the AI ​​model to generate a virtual personality based on the above settings. The virtual personality has characteristics such as "psychologist," "friendly," and "sensitive to emotions."

[0756] 3. Example user questions

[0757] The user verbally asks, "Tell me how you deal with stress."

[0758] 4. Emotion Recognition Example

[0759] The server analyzes the user's voice input and uses an emotion engine to recognize that the user is feeling a little anxious.

[0760] 5. Example of answer generation and speech output

[0761] Based on the question and the recognized emotional data, the server generates an answer such as, "When you feel stressed, it's important to first take a deep breath and calm yourself down." This answer is synthesized into voice and sent to the device to be played back to the user.

[0762] 6. Examples of interview recording

[0763] The server saves the entire interview as a transcript in a text file, including emotional data, and also saves the audio data in an appropriate format.

[0764] Example 2

[0765] 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."

[0766] Conventional virtual personality interview systems generate answers without considering the user's emotions, making it difficult to provide appropriate answers tailored to individual needs. Furthermore, the recording of interview content and audio data is often insufficient, resulting in insufficient information for later reference. Furthermore, when generating answers using natural language processing algorithms, the lack of emotion recognition can lead to poor answer quality.

[0767] 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.

[0768] In this invention, the server includes means for generating a virtual personality based on setting information input by the user, means for recognizing the user's voice input and converting it into text, means for the generated virtual personality to generate answers to the user's questions, means for synthesizing the generated answers and playing them back, means for saving the interview content as minutes, means for saving the interview voice data, means for recognizing emotions from the user's voice input, and means for the virtual personality to generate answers based on the recognized emotion data. This makes it possible to provide appropriate answers according to the user's emotions in real time and to record and save the interview content and voice data in detail.

[0769] "Setting information" refers to information that a user inputs when creating a virtual personality, and includes data such as occupation, personality, and characteristics.

[0770] A "virtual personality" is an interactive character generated by the server based on configuration information, and has the ability to answer users' questions in real time.

[0771] "User voice input" refers to the voice that the user makes through the terminal, including interview questions and conversation content.

[0772] "Convert to text" refers to the process of converting audio data into text using speech recognition technology.

[0773] "Generating an answer" refers to the process by which the virtual personality creates an appropriate response to the user's question, which may use natural language processing algorithms.

[0774] "Speech synthesis" refers to a technique for outputting generated text responses as speech, converting text data into speech data.

[0775] "Saving as minutes" means recording the interview contents in text format so that they can be referenced at a later date.

[0776] "Storing audio data" refers to recording the audio data of an interview in digital form so that it can be played back and analyzed at a later date.

[0777] "Emotion recognition" refers to the process of extracting emotional data from a user's voice input by analyzing the tone, speed, and word choice of the voice.

[0778] "Emotional data" refers to data that indicates the user's emotional state using emotion recognition technology and is used by the virtual personality to generate responses.

[0779] This invention is a system that generates a virtual personality based on setting information entered by a user and conducts an audio interview with that virtual personality, and further combines it with an emotion engine that recognizes the user's emotions. Specific embodiments for implementing this system are described below.

[0780] First, the user inputs the virtual persona's configuration information, including occupation, personality, characteristics, etc., using a terminal application or web interface. This configuration information is then sent to the server in an appropriate format.

[0781] The server receives the setting information sent by the user and generates a virtual personality using a generative AI model (e.g., GPT-4). The generated virtual personality data is stored on the server.

[0782] Next, the user asks the virtual persona a question by voice through the device. The user's voice input is converted into text in real time by a speech recognition engine (e.g., Google Speech-to-Text) within the device, and this text data is sent to the server.

[0783] The server uses an emotion engine (e.g., IBM Watson Tone Analyzer) to recognize emotions from the user's voice input in addition to the transmitted text data. The emotion engine analyzes the tone, rate, and other parameters of the user's voice to generate emotion data.

[0784] Based on the submitted question text and emotion data, the server uses a generative AI model to generate an answer from the virtual personality. For example, it utilizes a natural language processing algorithm. The generated answer is passed to a speech synthesis engine (e.g., Amazon Polly) and generated as audio data. This audio data is sent to the device and played back to the user.

[0785] The server also stores the interview content as a text record in the form of minutes, including emotional data, and audio data, so users can review the interview content later.

[0786] Specific examples

[0787] 1. Example of user preference input

[0788] An example of the setting information entered by the user is as follows:

[0789] Occupation: Psychologist

[0790] Personality: Friendly

[0791] Traits: Emotionally sensitive

[0792] 2. Virtual personality generation

[0793] Based on the above configuration information, the server uses a generative AI model (e.g., GPT-4) to generate a virtual personality. For example, a personality with characteristics such as "psychologist," "friendly," and "sensitive to emotions" is generated.

[0794] 3. Example user questions

[0795] The user verbally asks, "Tell me how you deal with stress."

[0796] 4. Emotion Recognition Example

[0797] The server analyzes the user's voice input and uses an emotion engine (e.g., IBM Watson Tone Analyzer) to recognize the user's emotion, which indicates slight anxiety.

[0798] 5. Example of answer generation and speech output

[0799] The server generates an answer based on the question and the perceived anxiety level. For example, "When you feel stressed, it's important to first take a deep breath and calm yourself down." The generated answer is synthesized into voice and sent to the device.

[0800] 6. Examples of interview recording

[0801] The server saves the entire interview as a text file containing transcripts, including emotional data. The audio data is also saved in MP3 format.

[0802] Prompt Sentence Examples

[0803] The following is an example of a prompt sentence:

[0804] Role: Virtual Psychologist

[0805] Occupation: Psychologist

[0806] Personality: Friendly

[0807] Traits: Emotionally sensitive

[0808] User Question: What do you do when you feel stressed?

[0809] Recognized emotion: Anxiety

[0810] By implementing the invention in accordance with the above aspects, users can efficiently and effectively interview virtual personalities and obtain appropriate responses and answers that take emotions into account, thereby gaining new insights and deeper understanding based on emotions.

[0811] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0812] Step 1: User Settings Input

[0813] The user uses a terminal application or a web interface to input configuration information for the virtual personality, including occupation, personality, and characteristics. For example, the user might input information such as "Occupation: Psychologist, Personality: Friendly, Characteristics: Sensitive to Emotions."

[0814] Input: The user enters the configuration information.

[0815] Output: The device converts the input configuration information into the appropriate format, checks for errors, and sends the converted configuration information to the server.

[0816] Step 2: Virtual personality generation

[0817] The server receives the setting information sent by the user.

[0818] Based on the received information, the server invokes a generative AI model (e.g., GPT-4) to generate a virtual personality that reflects the user's specified occupation, personality, and characteristics.

[0819] Input: The server receives user configuration information.

[0820] Data processing: The server calls the generative AI model and generates a virtual personality based on the setting information.

[0821] Output: The server stores the generated virtual personality data in its own database.

[0822] Step 3: Start the interview

[0823] The user uses the device to ask the virtual personality a question by voice. The user types the question into the device's microphone. For example, the user might ask, "Tell me how to deal with stress."

[0824] The device uses a speech recognition engine such as Google Speech-to-Text to convert the user's speech into text.

[0825] Input: User's voice input.

[0826] Data processing: The device uses a speech recognition engine to convert the user's speech into text.

[0827] Output: The converted text data is sent to the server.

[0828] Step 4: Emotion Recognition

[0829] The server receives the transmitted text data and, if necessary, also analyzes the user's voice data.

[0830] The server uses emotion engines such as IBM Watson Tone Analyzer to recognize the user's emotions from text and audio data, including tone of voice, speaking rate and word choice.

[0831] Input: Text and audio data.

[0832] Data processing: The server uses the emotion engine to generate emotion data.

[0833] Output: Add the recognized emotion data to the prompt sentence.

[0834] Step 5: Answer generation and speech output

[0835] The server generates an appropriate answer using a generative AI model (e.g., GPT-4) based on the user's question text and emotion data. For example, if the server recognizes anxiety in response to the question, "Please tell me how to deal with stress," it will generate an answer such as, "When you feel stressed, it's important to take a deep breath and calm yourself down first."

[0836] The server passes the generated answer to a speech synthesis engine such as Amazon Polly to generate voice data.

[0837] Input: Question text and sentiment data.

[0838] Data processing: The server uses the generative AI model to generate an appropriate answer, which is then converted into voice data using a speech synthesis engine.

[0839] Output: The generated audio data is sent to the device.

[0840] The terminal plays the received audio data so that it reaches the user.

[0841] Step 6: Record the interview

[0842] The server stores all the conversations in the interview as transcripts in text format, including emotional data.

[0843] The server also stores the audio data for later reference, for example in mp3 format.

[0844] Users can log in later to check the minutes and audio data.

[0845] Input: Interview audio and text data.

[0846] Data processing: The server stores the minutes and audio data in a database.

[0847] Output: Saved transcripts and audio data.

[0848] (Application example 2)

[0849] 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."

[0850] In modern society, users have more opportunities to access a variety of content, but finding content that is optimized for their emotional state and interests remains a difficult challenge. Furthermore, there is a lack of easy ways for users to obtain recommended content tailored to their emotions and circumstances. To address this issue, there is a need for a method to provide optimal content based on the user's input information and emotional state.

[0851] The specific processing by the specific processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means. In this invention, the server includes means for generating a virtual personality based on setting information entered by the user, means for recognizing the user's voice input and converting it into text, means for the generated virtual personality to recommend content, means for analyzing the user's emotions using an emotion engine, and means for audibly outputting emotion-based content recommendations based on this data. This makes it possible to recommend personalized content that is optimized for the user's emotional state and interests.

[0852] "User preference input" is the process by which a user inputs information required for a virtual personality or recommendation system.

[0853] A "virtual personality" is a virtual agent with specific characteristics, occupations, and personalities that is generated based on the user's settings.

[0854] "Speech recognition" is a technology that converts a user's voice input into text data.

[0855] An "emotion engine" is an algorithm or software that analyzes voice and text data to recognize the user's emotions.

[0856] A "natural language processing algorithm" is a technology that analyzes the meaning of text data and is used to generate content and answers.

[0857] "Content recommendation" is the process of suggesting the most suitable content, such as movies, music, or books, based on a user's interests and emotional state.

[0858] "Emotion analysis" is a technology that uses a user's voice and text data to identify their emotional state at that time.

[0859] "Speech synthesis" is a technology that generates synthetic speech based on text data.

[0860] "Minutes" are the contents of interviews or conversations recorded as text data.

[0861] "Audio data preservation" is the process of storing recorded audio in digital form.

[0862] By "operating on a smartphone" it is meant that the present invention is executable on a smartphone device.

[0863] A specific embodiment of the present invention will now be described in detail. The present invention provides a system that generates a virtual personality based on setting information input by a user and recommends content that is optimized for the user's emotions through interaction with the virtual personality.

[0864] First, a user launches the application through their device and enters their personal settings, including their interests, favorite actors and music genres, and other characteristics. This information is then sent to the server and used to generate a unique virtual personality for the user.

[0865] The server uses a generative AI model based on the received settings to generate a virtual personality that matches the user's interests and characteristics. This virtual personality acts as an agent that recommends content through dialogue with the user.

[0866] Next, the user speaks a question to the virtual agent, such as, "What movies are good to watch today?" The device uses a speech recognition engine (e.g., Google Speech-to-Text) to convert the user's voice into text in real time and send it to the server.

[0867] The server analyzes the received text data and uses an emotion engine (e.g., IBM Watson Tone Analyzer) to recognize the user's emotion. For example, if it recognizes that the user is tired, it will use this information to suggest the most appropriate content.

[0868] The generated answer is adjusted based on emotion recognition and is generated in the form of, for example, "You seem tired today. How about a relaxing comedy movie?" This answer is passed to a speech synthesis engine (e.g., Amazon Polly) and generated as synthetic speech. The generated speech data is sent to the device and played back to the user.

[0869] The server also stores the interview as a text transcript, including the questions asked, emotional data, and the virtual agent's responses, as well as audio data, so the user can review the interview later.

[0870] As a concrete example, consider a scenario where a user asks a question by voice, "What are the latest action movies starring Will Smith?" In this case, the system works to recommend the most suitable movie, taking into account the user's emotional state.

[0871] Example prompt sentence:

[0872] User: Want to watch a relaxing movie today?

[0873] Virtual Agent: You seem tired today. How about a relaxing comedy movie?

[0874] This enables personalized content recommendations that are optimized for the user's emotional state and interests.

[0875] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[0876] Step 1:

[0877] The user launches the application through their device and enters their personal settings, including their interests, favorite actors and music genres, and other characteristics. This data is sent to the server in an appropriate format, in JSON format, and is saved as the user's profile information on the server side.

[0878] Step 2:

[0879] The server uses a generative AI model based on the received configuration information to generate a virtual personality. A generative AI model (e.g., GPT-3) is used to create a virtual agent tailored to the user's interests and characteristics. This virtual personality data is stored on the server and used in subsequent interactions and recommendation processes. Specifically, the generative AI model generates text data and stores it as a virtual personality profile.

[0880] Step 3:

[0881] The user asks a question to the virtual agent by voice. The device uses a speech recognition engine (e.g., Google Speech-to-Text) to convert the user's voice into text in real time and send it to the server. The input voice data is digitized at a sample rate and converted into text by the speech recognition engine. The converted text is sent to the server in JSON format.

[0882] Step 4:

[0883] The server analyzes the received text data and recognizes the user's emotions using an emotion engine (e.g., IBM Watson Tone Analyzer). Specifically, the emotion engine extracts emotion parameters (e.g., happiness, sadness, anger, etc.) from the text data and saves them as emotion analysis results. This emotion data is saved in JSON format as metadata such as the intensity and type of emotion.

[0884] Step 5:

[0885] The server uses the user's question text and emotional data to generate the best answer from the generated virtual personality. It uses a natural language processing algorithm to generate an answer optimized for the user's emotional state. For example, if the user is tired, it will recommend a relaxing movie. A generative AI model is used in this answer generation process.

[0886] Step 6:

[0887] The generated answer is passed to a speech synthesis engine (e.g., Amazon Polly) to generate synthetic speech. This generated speech data is sent to the device and played back to the user. The speech synthesis engine converts the text data into speech waveforms and sends the speech data to the device.

[0888] Step 7:

[0889] The server saves the entire interview as a text file containing the questions asked, emotional data, and the virtual agent's responses. The audio data is also saved digitally so that it can be played back later if necessary. The server then saves this data in a suitable format on the file system, making it accessible to the user.

[0890] 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.

[0891] 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.

[0892] 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.

[0893] [Third embodiment]

[0894] FIG. 5 shows an example of the configuration of a data processing system 310 according to the third embodiment.

[0895] 5, the data processing system 310 includes the data processing device 12 and a headset terminal 314. An example of the data processing device 12 is a server.

[0896] 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).

[0897] 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.

[0898] 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.

[0899] 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).

[0900] 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.

[0901] 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.

[0902] 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.

[0903] 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.

[0904] 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.

[0905] 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."

[0906] The present invention relates to a system for generating a virtual personality based on setting information input by a user and conducting an audio interview with the virtual personality. Specific embodiments for carrying out the present invention will be described below.

[0907] 1. User setting input

[0908] The user inputs the virtual persona's configuration information, including occupation, personality, characteristics, etc., using a terminal application or a web interface. The input configuration information is then sent to the server in an appropriate format.

[0909] 2. Virtual personality generation

[0910] The server receives the setting information sent by the user and generates a virtual personality using a generative AI model. The generated virtual personality data is stored on the server until the interview begins.

[0911] 3. Start of interview

[0912] The user speaks questions to the virtual persona through the device, which uses a speech recognition engine to convert the user's voice input into text in real time, and this text data is sent to the server.

[0913] 4. Answer generation and voice output

[0914] The server analyzes the received question text and generates an answer as a virtual personality. The generated answer is passed to a speech synthesis engine and generated as voice data. The voice data is sent to the device and played back to the user.

[0915] 5. Recording of interviews

[0916] The server stores the interview contents as a text record in the form of minutes, and also stores the audio data so that users can review the interview contents later.

[0917] Specific examples

[0918] 1. Example of user preference input

[0919] Examples of setting information input by the user include the following:

[0920] json

[0921] {

[0922] "Occupation": "Engineer",

[0923] "Personality": "Logical",

[0924] "Characteristics": "Tech-savvy"

[0925] }

[0926] 2. Virtual personality generation

[0927] Based on the above setting information, the server uses a generative AI model to generate a virtual personality. For example, a personality with characteristics such as "engineer," "logical," and "tech-savvy" is generated.

[0928] 3. Example user questions

[0929] A user verbally asks the question, "What do you think about the latest AI technology?"

[0930] 4. Example of answer generation and speech output

[0931] The server receives the question and generates an answer such as, "The latest AI technology is very interesting." This answer is then synthesized into voice, which the device plays back to the user.

[0932] 5. Examples of interview recording

[0933] The server saves the entire interview as a transcript in a text file, and also saves the audio data in MP3 format.

[0934] The present invention can be implemented in the above manner. By using this system, users can efficiently and effectively conduct interviews with virtual personalities and gain new insights and ideas.

[0935] The processing flow will be explained below.

[0936] Step 1:

[0937] The user opens the application or web interface on their device and enters configuration information for their virtual personality, including their occupation, personality, and characteristics.

[0938] Step 2:

[0939] The terminal formats the configuration information entered by the user and transmits it to the server in the appropriate data format.

[0940] Step 3:

[0941] The server receives the setting information sent from the terminal and checks its contents.

[0942] Step 4:

[0943] The server uses a generative AI model to generate a virtual personality based on the user's settings, and the generated virtual personality data is stored on the server.

[0944] Step 5:

[0945] The user verbally asks a question to the device.

[0946] Step 6:

[0947] The device uses a speech recognition engine to convert the user's voice input into text data in real time.

[0948] Step 7:

[0949] The terminal transmits the converted question text data to the server.

[0950] Step 8:

[0951] The server analyzes the question text data received from the terminal and generates an answer as a virtual personality.

[0952] Step 9:

[0953] The generated answer text is passed to a speech synthesis engine to generate speech data.

[0954] Step 10:

[0955] The server transmits the generated voice data to the terminal.

[0956] Step 11:

[0957] The device plays back the received audio data and provides the user with a response.

[0958] Step 12:

[0959] The server generates and stores a text record of the interview contents as a transcript.

[0960] Step 13:

[0961] The server stores the audio data of the interview.

[0962] Step 14:

[0963] After the interview, users can review the saved transcript and audio data.

[0964] Example 1

[0965] 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."

[0966] A method is needed to generate a virtual personality based on user-entered settings and enable natural dialogue when the user interviews the virtual personality. Another challenge is to efficiently convert the user's voice input into text, generate appropriate responses based on the text, and then respond in voice. It is also important to keep a record of the interview content so that it can be referenced later.

[0967] 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.

[0968] In this invention, the server includes means for generating a virtual personality based on setting information input by a user, means for recognizing a user's voice input and converting it into text, means for generating a virtual personality using a generative AI model, means for the generated virtual personality to generate answers to the user's questions, means for synthesizing and playing back the generated answers, means for saving the interview content as minutes, and means for saving the interview audio data, which enables a user to input setting information, realize natural conversations with a virtual personality, and record and save the content.

[0969] "User" refers to any individual or entity that uses the System.

[0970] "Setting information" refers to information about a specific occupation, personality, and characteristics that a user inputs to generate a virtual personality.

[0971] A "virtual personality" is a virtual entity generated based on the user's settings, and refers to a pseudo-personality that can interact with the user.

[0972] "Voice input" refers to input made by a user to a system using voice.

[0973] "Text conversion" refers to the process of analyzing voice input and expressing it as a string of characters.

[0974] A "generative AI model" refers to an algorithm that uses machine learning techniques to generate a virtual personality from a user's settings.

[0975] "Answer generation" refers to the process by which a virtual personality constructs an appropriate response to a question posed by a user.

[0976] "Speech synthesis" refers to the process of converting generated text data into speech data.

[0977] "Playback" refers to the process of playing back the synthesized voice data to the user.

[0978] "Minutes" refers to data that records the contents of an interview in written form.

[0979] "Voice data" refers to voice-synthesized responses and user voice input data.

[0980] The present invention is a system for generating a virtual personality based on setting information input by a user and conducting an audio interview with the virtual personality. Specific embodiments of the present invention will be described below.

[0981] User preference input

[0982] The user inputs configuration information for the virtual persona using a device application or web interface, including occupation, personality, and characteristics. For example, the user might input the following information:

[0983] Occupation: Engineer

[0984] Personality: Logical

[0985] Specialty: Technology savvy

[0986] Once these entries are complete, the device sends this information to the server in JSON format.

[0987] Virtual personality generation

[0988] The server receives the setting information sent by the user. Then, it generates a virtual personality using a generative AI model (e.g., GPT-3). The generated virtual personality data is stored on the server until the interview begins. For example, the following prompt sentences are used to input to the generative AI model:

[0989] Prompt: "You are an engineer, a logical, tech-savvy person."

[0990] Interview begins

[0991] The user asks the virtual persona a question by voice through the device, such as, "What do you think about the latest AI technology?" The device uses a speech recognition engine (e.g., Google Speech-to-Text API) to convert the user's voice into text in real time and sends this text data to the server.

[0992] Answer generation and voice output

[0993] The server analyzes the received question text and generates an answer as a virtual personality using a generative AI model. For example, it generates an answer such as "The latest AI technology is very interesting." The generated answer is passed to a speech synthesis engine (e.g., Amazon Polly) and generated as audio data. This audio data is sent to the device and played back to the user.

[0994] Interview recording

[0995] The server stores the interview contents as text records in minutes format. Audio data is also stored in the same way. Users can review the interview contents later. The recordings are generally stored in text files and MP3 format.

[0996] This embodiment allows users to efficiently and effectively interview virtual personalities, and gain new insights and ideas.

[0997] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0998] Program processing flow and specific explanation

[0999] Step 1: User Settings Input

[1000] The user inputs the virtual personality's configuration information using a terminal application or web interface. This configuration information includes occupation, personality, characteristics, etc. For example, the user inputs information such as "Occupation: Engineer," "Personality: Logical," and "Characteristics: Knowledgeable about technology."

[1001] Input: Setting information about occupation, personality, and characteristics

[1002] Output: JSON data containing configuration information

[1003] Specific behavior: The user enters the setting information into the input form and clicks the "Submit" button.

[1004] Step 2: Sending configuration information

[1005] The device sends the configuration information entered by the user to the server in an appropriate format (JSON format).

[1006] Input: JSON data generated in step 1

[1007] Output: Configuration information sent to the server

[1008] Specific operation: JSON data containing configuration information is sent to the server via an HTTP request.

[1009] Step 3: Receiving configuration information

[1010] The server receives the setting information sent from the device, and this data is stored and analyzed within the server.

[1011] Input: Setting information sent from the device

[1012] Output: Configuration information saved on the server

[1013] Specific operation: The server receives the HTTP request and saves the configuration information in the database.

[1014] Step 4: Virtual personality generation

[1015] The server generates a virtual personality using a generative AI model (e.g., GPT-3) based on the received configuration information. For example, it creates a prompt sentence like the following based on the configuration information: "Occupation: Engineer," "Personality: Logical," and "Characteristics: Knowledgeable about technology."

[1016] Prompt: "You are an engineer, a logical, tech-savvy person."

[1017] Input: Configuration information stored on the server

[1018] Output: Generated virtual personality data

[1019] Specific operation: A prompt sentence is input into the generative AI model, and the resulting virtual personality data is analyzed and saved.

[1020] Step 5: Start the interview

[1021] The user uses the device to ask the virtual persona questions by voice, such as, "What do you think about the latest AI technology?"

[1022] Input: User voice input

[1023] Output: Speech-to-text data

[1024] Specific operation: Using a speech recognition engine (e.g., Google Speech-to-Text API), the speech is converted into text in real time and this text is sent to the server.

[1025] Step 6: Receiving and parsing the question text

[1026] The server receives and analyzes the question text sent by the user.

[1027] Input: User's question text

[1028] Output: Parsed question data

[1029] What it does: The server receives the text data, parses it, and converts it into a format that can be fed into the appropriate generative AI model.

[1030] Step 7: Generate answers using virtual personalities

[1031] The server uses the generative AI model to generate an appropriate answer to the user's question, for example, "The latest AI technology is very interesting."

[1032] Input: Parsed question data

[1033] Output: Generated answer text

[1034] Specific operation: Question data is input into the generative AI model and the resulting answer text is obtained.

[1035] Step 8: Generate audio data

[1036] The server passes the generated answer text to a speech synthesis engine (e.g., Amazon Polly) to generate voice data.

[1037] Input: Generated answer text

[1038] Output: Audio data

[1039] Specific operation: Input text into the speech synthesis engine and send the generated audio file to the device.

[1040] Step 9: Sending and Playing Audio Data

[1041] The server sends the generated audio data to the terminal, which then plays the audio data and lets the user hear it.

[1042] Input: Audio data

[1043] Output: The audio played to the user

[1044] What it does: Plays audio files in streaming or download format.

[1045] Step 10: Record the interview

[1046] The server stores the entire interview as text data in the form of minutes, along with the audio data.

[1047] Input: Interview content (text and audio data)

[1048] Output: Saved minutes text and audio data

[1049] Specific operation: The server saves the minutes in text format and the audio data in an appropriate format (e.g., mp3).

[1050] By performing these steps sequentially, the system of the present invention can facilitate an interview with a virtual personality.

[1051] (Application example 1)

[1052] 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."

[1053] In conventional online shopping systems, users often struggle with product selection, and the systems that can provide appropriate support are limited. Furthermore, there is a lack of mechanisms to generate a personal assistant based on the user's settings information to support product selection. As a result, users are unable to receive appropriate advice, resulting in a poor purchasing experience.

[1054] 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.

[1055] In this invention, the server includes means for generating a virtual personality based on setting information input by the user, means for recognizing the user's voice input and converting it into text, means for the generated virtual personality to generate answers to the user's questions, means for synthesizing and playing back the generated answers, means for saving the interview content as minutes, means for saving the interview audio data, means for generating a shopping assistant based on the user's settings and providing audio support for product selection, means for generating product recommendation information based on the inquiry content, and means for outputting the generated recommendation information by voice. This allows the user to receive appropriate recommendations through the shopping assistant, providing a new purchasing experience.

[1056] "Means for generating a virtual personality based on user-entered setting information" refers to a system that uses a generative AI model to create a virtual personality based on user-entered setting information (e.g., occupation, personality, characteristics).

[1057] The "means for recognizing a user's voice input and converting it into text" is a system that uses a voice recognition engine to convert a user's voice into text data in real time.

[1058] "Means for a generated virtual personality to generate answers to a user's questions" refers to a system in which a virtual personality uses a generative AI model to create appropriate answers to a user's questions.

[1059] The "means for synthesizing and reproducing the generated answer" is a system that uses a speech synthesis engine to convert the generated answer from text to speech and reproduce it aloud to the user.

[1060] "Means for saving interview content as minutes" refers to a storage system that stores the content of conversations during interviews as text data and makes it available for later viewing.

[1061] "Means for storing audio data of an interview" refers to a system for recording and storing audio data during an interview.

[1062] "A means for generating a shopping assistant based on user settings and providing voice support for product selection" is a system that creates a virtual shopping assistant based on information set by the user and provides voice support for the user's shopping through that assistant.

[1063] The "means for generating product recommendation information based on the inquiry content" is a system that analyzes the inquiry content of the user and generates information that recommends appropriate products based on the analysis.

[1064] The "means for outputting generated recommendation information by voice" is a system that converts the generated recommendation information into voice data and provides it to the user by voice.

[1065] The present invention is a system for generating a virtual personality based on setting information input by a user and conducting an audio interview with the virtual personality. Specific embodiments for carrying out the present invention will be described below.

[1066] System configuration

[1067] This system mainly consists of the following components:

[1068] 1. User setting input interface

[1069] Users input their preferences via a smartphone or web interface, including their occupation, personality, and characteristics. For example, they might enter preferences such as "occupation: fashion consultant, personality: friendly, characteristics: sensitive to trends."

[1070] 2. Virtual personality generation

[1071] The server receives the configuration information and generates a virtual personality using a generative AI model (e.g., GPT-3.5-Turbo). The generated virtual personality data is stored on the server and awaits the start of the interview.

[1072] 3. Start of interview

[1073] Users ask questions by voice using a smartphone or other device, and the device's built-in speech recognition engine (e.g., Google Speech Recognition API) converts the voice into text data and sends it to the server.

[1074] 4. Answer Generation and Speech Synthesis

[1075] The server analyzes the text data of the question and generates an appropriate answer as a virtual personality. The generated answer is converted into voice data by a speech synthesis engine (e.g., pyttsx3) and sent to the device.

[1076] 5. Recording of interviews

[1077] The server stores the entire interview as a transcript in text format, along with the audio data, which can be accessed by the user later.

[1078] Hardware and software used

[1079] Hardware: smartphones, tablets, servers, etc.

[1080] software:

[1081] Generative AI model: GPT-3.5-Turbo

[1082] Speech recognition engine: Google Speech Recognition API

[1083] Speech synthesis engine: pyttsx3

[1084] Web Interface: Any web browser

[1085] Specific examples

[1086] For example, if a user asks, "What is a recommended outfit for spring?" the system will act as follows:

[1087] 1. User's question is entered by voice

[1088] 2. The speech recognition engine converts speech to text

[1089] 3. The server analyzes the text and generates an answer as a virtual personality.

[1090] 4. The answer is converted into speech using a speech synthesis engine and played back to the user.

[1091] Prompt Sentence Examples

[1092] What is your recommended outfit for spring?

[1093] This allows users to receive appropriate advice and enjoy a more personalized shopping experience.

[1094] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[1095] Step 1:

[1096] The user inputs configuration information such as occupation, personality, and characteristics via a smartphone or web interface. The input data is sent to the server.

[1097] Step 2:

[1098] The server generates a virtual personality. Based on the received setting information, a generative AI model (e.g., GPT-3.5-Turbo) is used to generate the virtual personality. This virtual personality data is stored on the server and waits until the interview begins.

[1099] Step 3:

[1100] The user asks a question by voice. The user asks a question by voice to the virtual personality using a smartphone or another device. The voice recognition engine (e.g., Google Speech Recognition API) installed on the device converts the voice into text data and sends the text data to the server.

[1101] Step 4:

[1102] The server analyzes the question and generates an answer as a virtual personality. The server analyzes the text data of the received question and generates an appropriate answer using a generative AI model. The generated answer is stored as text data on the server.

[1103] Step 5:

[1104] The server passes the generated answer to a speech synthesis engine (e.g., pyttsx3), which converts the text data of the answer into audio data, which is then sent to the device and played back to the user.

[1105] Step 6:

[1106] The server stores the interviews. The server saves the entire interview in text format as a transcript. The server also saves the audio of the interviews for the user to refer to later.

[1107] Step 7:

[1108] Generate a shopping assistant based on user settings. The server uses the settings to create a virtual persona as a shopping assistant. This virtual persona generates recommendation information based on the user's product inquiries.

[1109] Step 8:

[1110] Recommendation information is generated based on the query content. The server uses the generative AI model to generate product recommendation information. This recommendation information is saved as text data.

[1111] Step 9:

[1112] The generated recommendation information is output as voice data. The server passes the recommendation information to a voice synthesis engine and converts it into voice data. This voice data is sent to the device and played back to the user.

[1113] Through these steps, the system effectively acts as a shopping assistant for users, enabling a more personalized purchasing experience.

[1114] 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.

[1115] The present invention combines a system that generates a virtual personality based on setting information entered by a user and conducts an audio interview with that virtual personality with an emotion engine that recognizes the user's emotions. Specific embodiments for carrying out the present invention will be described below.

[1116] 1. User setting input

[1117] The user inputs configuration information for the virtual persona using a terminal application or a web interface, including occupation, personality, characteristics, etc. The configuration information is then sent to the server in an appropriate format.

[1118] 2. Virtual personality generation

[1119] The server receives the setting information sent by the user and generates a virtual personality using the generative AI model. The generated virtual personality data is stored on the server.

[1120] 3. Start of interview

[1121] The user asks questions to the virtual persona by voice through the device, which uses a voice recognition engine to convert the user's voice input into text in real time and transmits this text data to the server.

[1122] 4. Emotion recognition

[1123] The server uses an emotion engine to recognize emotions from the user's voice input in addition to the voice-recognized text data. The emotion engine analyzes the user's voice tone, speed, and other parameters to generate emotion data.

[1124] 5. Answer generation and voice output

[1125] The server generates answers from the virtual personality based on the received question text and the recognized emotion data, using a natural language processing algorithm to generate answers that include appropriate tone and content according to the emotion recognized.

[1126] The generated answer is passed to a speech synthesis engine, which generates audio data, which is then sent to the device and played back to the user.

[1127] 6. Recording of interviews

[1128] The server stores the interview contents as a text record in the form of minutes, and emotional data can also be included in the minutes. Audio data is also stored, so users can review the interview contents later.

[1129] Specific examples

[1130] 1. Example of user preference input

[1131] Examples of setting information input by the user include the following:

[1132] json

[1133] {

[1134] "Occupation": "Psychologist",

[1135] "Personality": "Friendly",

[1136] "Characteristics": "Emotionally sensitive"

[1137] }

[1138] 2. Virtual personality generation

[1139] Based on the above settings, the server uses a generative AI model to generate a virtual personality, such as a "psychologist," "friendly," or "sensitive to emotions."

[1140] 3. Example user questions

[1141] The user verbally asks, "Tell me how you deal with stress."

[1142] 4. Emotion Recognition Example

[1143] The server analyzes the user's voice input and uses an emotion engine to recognize the emotion that the user is feeling slightly anxious.

[1144] 5. Example of answer generation and speech output

[1145] Based on the question and the sense of anxiety recognized, the server generates an answer such as, "When you feel stressed, it's important to first take a deep breath and calm yourself down." This answer is synthesized into voice and sent to the device to be played back to the user.

[1146] 6. Examples of interview recording

[1147] The server saves the entire interview as a text file containing transcripts, including emotional data. The audio data is also saved in MP3 format.

[1148] The present invention can be implemented using the above method. By using this system, users can efficiently and effectively conduct interviews with virtual personalities and obtain appropriate responses and answers that take emotions into consideration. This allows users to gain new insights and a deeper understanding based on emotions.

[1149] The processing flow will be explained below.

[1150] Step 1:

[1151] The user opens the application or web interface on their device and enters configuration information for their virtual personality, including their occupation, personality, and characteristics.

[1152] Step 2:

[1153] The terminal formats the setting information entered by the user into an appropriate data format and sends it to the server.

[1154] Step 3:

[1155] The server receives the setting information sent from the terminal and analyzes its contents.

[1156] Step 4:

[1157] The server uses the generative AI model to generate a virtual personality based on the setting information, and the generated virtual personality data is stored on the server.

[1158] Step 5:

[1159] The user verbally asks a question to the device.

[1160] Step 6:

[1161] The device uses a speech recognition engine to convert the user's voice input into text data in real time, which is then sent to the server.

[1162] Step 7:

[1163] The server analyzes the received question text data and simultaneously generates emotion data from the user's voice input using an emotion engine.

[1164] Step 8:

[1165] The server combines the question text data with the emotion data to generate an appropriate answer for the virtual personality, using a natural language processing algorithm.

[1166] Step 9:

[1167] The generated answer text is passed to a speech synthesis engine and generated as voice data.

[1168] Step 10:

[1169] The server transmits the generated voice data to the terminal.

[1170] Step 11:

[1171] The device plays back the received audio data and provides the user with a response.

[1172] Step 12:

[1173] The server stores the interview contents as a text record in the form of a transcript, which also contains the recognized emotion data.

[1174] Step 13:

[1175] The server stores the audio data of the interview.

[1176] Step 14:

[1177] After the interview, users can review the saved transcript and audio data.

[1178] The following is an explanation using a specific example.

[1179] 1. Example of user preference input

[1180] Examples of setting information that the user inputs include the following:

[1181] json

[1182] {

[1183] "Occupation": "Psychologist",

[1184] "Personality": "Friendly",

[1185] "Characteristics": "Emotionally sensitive"

[1186] }

[1187] 2. Virtual personality generation

[1188] The server uses the AI ​​model to generate a virtual personality based on the above settings. The virtual personality has characteristics such as "psychologist," "friendly," and "sensitive to emotions."

[1189] 3. Example user questions

[1190] The user verbally asks, "Tell me how you deal with stress."

[1191] 4. Emotion Recognition Example

[1192] The server analyzes the user's voice input and uses an emotion engine to recognize that the user is feeling a little anxious.

[1193] 5. Example of answer generation and speech output

[1194] Based on the question and the recognized emotional data, the server generates an answer such as, "When you feel stressed, it's important to first take a deep breath and calm yourself down." This answer is synthesized into voice and sent to the device to be played back to the user.

[1195] 6. Examples of interview recording

[1196] The server saves the entire interview as a transcript in a text file, including emotional data, and also saves the audio data in an appropriate format.

[1197] Example 2

[1198] 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."

[1199] Conventional virtual personality interview systems generate answers without considering the user's emotions, making it difficult to provide appropriate answers tailored to individual needs. Furthermore, the recording of interview content and audio data is often insufficient, resulting in insufficient information for later reference. Furthermore, when generating answers using natural language processing algorithms, the lack of emotion recognition can lead to poor answer quality.

[1200] 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.

[1201] In this invention, the server includes means for generating a virtual personality based on setting information input by the user, means for recognizing the user's voice input and converting it into text, means for the generated virtual personality to generate answers to the user's questions, means for synthesizing the generated answers and playing them back, means for saving the interview content as minutes, means for saving the interview voice data, means for recognizing emotions from the user's voice input, and means for the virtual personality to generate answers based on the recognized emotion data. This makes it possible to provide appropriate answers according to the user's emotions in real time and to record and save the interview content and voice data in detail.

[1202] "Setting information" refers to information that a user inputs when creating a virtual personality, and includes data such as occupation, personality, and characteristics.

[1203] A "virtual personality" is an interactive character generated by the server based on configuration information, and has the ability to answer users' questions in real time.

[1204] "User voice input" refers to the voice that the user makes through the terminal, including interview questions and conversation content.

[1205] "Convert to text" refers to the process of converting audio data into text using speech recognition technology.

[1206] "Generating an answer" refers to the process by which the virtual personality creates an appropriate response to the user's question, which may use natural language processing algorithms.

[1207] "Speech synthesis" refers to a technique for outputting generated text responses as speech, converting text data into speech data.

[1208] "Saving as minutes" means recording the interview contents in text format so that they can be referenced at a later date.

[1209] "Storing audio data" refers to recording the audio data of an interview in digital form so that it can be played back and analyzed at a later date.

[1210] "Emotion recognition" refers to the process of extracting emotional data from a user's voice input by analyzing the tone, speed, and word choice of the voice.

[1211] "Emotional data" refers to data that indicates the user's emotional state using emotion recognition technology and is used by the virtual personality to generate responses.

[1212] This invention is a system that generates a virtual personality based on setting information entered by a user and conducts an audio interview with that virtual personality, and further combines it with an emotion engine that recognizes the user's emotions. Specific embodiments for implementing this system are described below.

[1213] First, the user inputs the virtual persona's configuration information, including occupation, personality, characteristics, etc., using a terminal application or web interface. This configuration information is then sent to the server in an appropriate format.

[1214] The server receives the setting information sent by the user and generates a virtual personality using a generative AI model (e.g., GPT-4). The generated virtual personality data is stored on the server.

[1215] Next, the user asks the virtual persona a question by voice through the device. The user's voice input is converted into text in real time by a speech recognition engine (e.g., Google Speech-to-Text) within the device, and this text data is sent to the server.

[1216] The server uses an emotion engine (e.g., IBM Watson Tone Analyzer) to recognize emotions from the user's voice input in addition to the transmitted text data. The emotion engine analyzes the tone, rate, and other parameters of the user's voice to generate emotion data.

[1217] Based on the submitted question text and emotion data, the server uses a generative AI model to generate an answer from the virtual personality. For example, it utilizes a natural language processing algorithm. The generated answer is passed to a speech synthesis engine (e.g., Amazon Polly) and generated as audio data. This audio data is sent to the device and played back to the user.

[1218] The server also stores the interview content as a text record in the form of minutes, including emotional data, and audio data, so users can review the interview content later.

[1219] Specific examples

[1220] 1. Example of user preference input

[1221] An example of the setting information entered by the user is as follows:

[1222] Occupation: Psychologist

[1223] Personality: Friendly

[1224] Traits: Emotionally sensitive

[1225] 2. Virtual personality generation

[1226] Based on the above configuration information, the server uses a generative AI model (e.g., GPT-4) to generate a virtual personality. For example, a personality with characteristics such as "psychologist," "friendly," and "sensitive to emotions" is generated.

[1227] 3. Example user questions

[1228] The user verbally asks, "Tell me how you deal with stress."

[1229] 4. Emotion Recognition Example

[1230] The server analyzes the user's voice input and uses an emotion engine (e.g., IBM Watson Tone Analyzer) to recognize the user's emotion, which indicates slight anxiety.

[1231] 5. Example of answer generation and speech output

[1232] The server generates an answer based on the question and the perceived anxiety level. For example, "When you feel stressed, it's important to first take a deep breath and calm yourself down." The generated answer is synthesized into voice and sent to the device.

[1233] 6. Examples of interview recording

[1234] The server saves the entire interview as a text file containing transcripts, including emotional data. The audio data is also saved in MP3 format.

[1235] Prompt Sentence Examples

[1236] The following is an example of a prompt sentence:

[1237] Role: Virtual Psychologist

[1238] Occupation: Psychologist

[1239] Personality: Friendly

[1240] Traits: Emotionally sensitive

[1241] User Question: What do you do when you feel stressed?

[1242] Recognized emotion: Anxiety

[1243] By implementing the invention in accordance with the above aspects, users can efficiently and effectively interview virtual personalities and obtain appropriate responses and answers that take emotions into account, thereby gaining new insights and deeper understanding based on emotions.

[1244] The flow of the identification process in the second embodiment will be described with reference to FIG.

[1245] Step 1: User Settings Input

[1246] The user uses a terminal application or a web interface to input configuration information for the virtual personality, including occupation, personality, and characteristics. For example, the user might input information such as "Occupation: Psychologist, Personality: Friendly, Characteristics: Sensitive to Emotions."

[1247] Input: The user enters the configuration information.

[1248] Output: The device converts the input configuration information into the appropriate format, checks for errors, and sends the converted configuration information to the server.

[1249] Step 2: Virtual personality generation

[1250] The server receives the setting information sent by the user.

[1251] Based on the received information, the server invokes a generative AI model (e.g., GPT-4) to generate a virtual personality that reflects the user's specified occupation, personality, and characteristics.

[1252] Input: The server receives user configuration information.

[1253] Data processing: The server calls the generative AI model and generates a virtual personality based on the setting information.

[1254] Output: The server stores the generated virtual personality data in its own database.

[1255] Step 3: Start the interview

[1256] The user uses the device to ask the virtual personality a question by voice. The user types the question into the device's microphone. For example, the user might ask, "Tell me how to deal with stress."

[1257] The device uses a speech recognition engine such as Google Speech-to-Text to convert the user's speech into text.

[1258] Input: User's voice input.

[1259] Data processing: The device uses a speech recognition engine to convert the user's speech into text.

[1260] Output: The converted text data is sent to the server.

[1261] Step 4: Emotion Recognition

[1262] The server receives the transmitted text data and, if necessary, also analyzes the user's voice data.

[1263] The server uses emotion engines such as IBM Watson Tone Analyzer to recognize the user's emotions from text and audio data, including tone of voice, speaking rate and word choice.

[1264] Input: Text and audio data.

[1265] Data processing: The server uses the emotion engine to generate emotion data.

[1266] Output: Add the recognized emotion data to the prompt sentence.

[1267] Step 5: Answer generation and speech output

[1268] The server generates an appropriate answer using a generative AI model (e.g., GPT-4) based on the user's question text and emotion data. For example, if the server recognizes anxiety in response to the question, "Please tell me how to deal with stress," it will generate an answer such as, "When you feel stressed, it's important to take a deep breath and calm yourself down first."

[1269] The server passes the generated answer to a speech synthesis engine such as Amazon Polly to generate voice data.

[1270] Input: Question text and sentiment data.

[1271] Data processing: The server uses the generative AI model to generate an appropriate answer, which is then converted into voice data using a speech synthesis engine.

[1272] Output: The generated audio data is sent to the device.

[1273] The terminal plays the received audio data so that it reaches the user.

[1274] Step 6: Record the interview

[1275] The server stores all the conversations in the interview as transcripts in text format, including emotional data.

[1276] The server also stores the audio data for later reference, for example in mp3 format.

[1277] Users can log in later to check the minutes and audio data.

[1278] Input: Interview audio and text data.

[1279] Data processing: The server stores the minutes and audio data in a database.

[1280] Output: Saved transcripts and audio data.

[1281] (Application example 2)

[1282] 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."

[1283] In modern society, users have more opportunities to access a variety of content, but finding content that is optimized for their emotional state and interests remains a difficult challenge. Furthermore, there is a lack of easy ways for users to obtain recommended content tailored to their emotions and circumstances. To address this issue, there is a need for a method to provide optimal content based on the user's input information and emotional state.

[1284] The specific processing by the specific processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means. In this invention, the server includes means for generating a virtual personality based on setting information entered by the user, means for recognizing the user's voice input and converting it into text, means for the generated virtual personality to recommend content, means for analyzing the user's emotions using an emotion engine, and means for audibly outputting emotion-based content recommendations based on this data. This makes it possible to recommend personalized content that is optimized for the user's emotional state and interests.

[1285] "User preference input" is the process by which a user inputs information required for a virtual personality or recommendation system.

[1286] A "virtual personality" is a virtual agent with specific characteristics, occupations, and personalities that is generated based on the user's settings.

[1287] "Speech recognition" is a technology that converts a user's voice input into text data.

[1288] An "emotion engine" is an algorithm or software that analyzes voice and text data to recognize the user's emotions.

[1289] A "natural language processing algorithm" is a technology that analyzes the meaning of text data and is used to generate content and answers.

[1290] "Content recommendation" is the process of suggesting the most suitable content, such as movies, music, or books, based on a user's interests and emotional state.

[1291] "Emotion analysis" is a technology that uses a user's voice and text data to identify their emotional state at that time.

[1292] "Speech synthesis" is a technology that generates synthetic speech based on text data.

[1293] "Minutes" are the contents of interviews or conversations recorded as text data.

[1294] "Audio data preservation" is the process of storing recorded audio in digital form.

[1295] By "operating on a smartphone" it is meant that the present invention is executable on a smartphone device.

[1296] A specific embodiment of the present invention will now be described in detail. The present invention provides a system that generates a virtual personality based on setting information input by a user and recommends content that is optimized for the user's emotions through interaction with the virtual personality.

[1297] First, a user launches the application through their device and enters their personal settings, including their interests, favorite actors and music genres, and other characteristics. This information is then sent to the server and used to generate a unique virtual personality for the user.

[1298] The server uses a generative AI model based on the received settings to generate a virtual personality that matches the user's interests and characteristics. This virtual personality acts as an agent that recommends content through dialogue with the user.

[1299] Next, the user speaks a question to the virtual agent, such as, "What movies are good to watch today?" The device uses a speech recognition engine (e.g., Google Speech-to-Text) to convert the user's voice into text in real time and send it to the server.

[1300] The server analyzes the received text data and uses an emotion engine (e.g., IBM Watson Tone Analyzer) to recognize the user's emotion. For example, if it recognizes that the user is tired, it will use this information to suggest the most appropriate content.

[1301] The generated answer is adjusted based on emotion recognition and is generated in the form of, for example, "You seem tired today. How about a relaxing comedy movie?" This answer is passed to a speech synthesis engine (e.g., Amazon Polly) and generated as synthetic speech. The generated speech data is sent to the device and played back to the user.

[1302] The server also stores the interview as a text transcript, including the questions asked, emotional data, and the virtual agent's responses, as well as audio data, so the user can review the interview later.

[1303] As a concrete example, consider a scenario where a user asks a question by voice, "What are the latest action movies starring Will Smith?" In this case, the system works to recommend the most suitable movie, taking into account the user's emotional state.

[1304] Example prompt sentence:

[1305] User: Want to watch a relaxing movie today?

[1306] Virtual Agent: You seem tired today. How about a relaxing comedy movie?

[1307] This enables personalized content recommendations that are optimized for the user's emotional state and interests.

[1308] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[1309] Step 1:

[1310] The user launches the application through their device and enters their personal settings, including their interests, favorite actors and music genres, and other characteristics. This data is sent to the server in an appropriate format, in JSON format, and is saved as the user's profile information on the server side.

[1311] Step 2:

[1312] The server uses a generative AI model based on the received configuration information to generate a virtual personality. A generative AI model (e.g., GPT-3) is used to create a virtual agent tailored to the user's interests and characteristics. This virtual personality data is stored on the server and used in subsequent interactions and recommendation processes. Specifically, the generative AI model generates text data and stores it as a virtual personality profile.

[1313] Step 3:

[1314] The user asks a question to the virtual agent by voice. The device uses a speech recognition engine (e.g., Google Speech-to-Text) to convert the user's voice into text in real time and send it to the server. The input voice data is digitized at a sample rate and converted into text by the speech recognition engine. The converted text is sent to the server in JSON format.

[1315] Step 4:

[1316] The server analyzes the received text data and recognizes the user's emotions using an emotion engine (e.g., IBM Watson Tone Analyzer). Specifically, the emotion engine extracts emotion parameters (e.g., happiness, sadness, anger, etc.) from the text data and saves them as emotion analysis results. This emotion data is saved in JSON format as metadata such as the intensity and type of emotion.

[1317] Step 5:

[1318] The server uses the user's question text and emotional data to generate the best answer from the generated virtual personality. It uses a natural language processing algorithm to generate an answer optimized for the user's emotional state. For example, if the user is tired, it will recommend a relaxing movie. A generative AI model is used in this answer generation process.

[1319] Step 6:

[1320] The generated answer is passed to a speech synthesis engine (e.g., Amazon Polly) to generate synthetic speech. This generated speech data is sent to the device and played back to the user. The speech synthesis engine converts the text data into speech waveforms and sends the speech data to the device.

[1321] Step 7:

[1322] The server saves the entire interview as a text file containing the questions asked, emotional data, and the virtual agent's responses. The audio data is also saved digitally so that it can be played back later if necessary. The server then saves this data in a suitable format on the file system, making it accessible to the user.

[1323] 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.

[1324] 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.

[1325] 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.

[1326] [Fourth embodiment]

[1327] FIG. 7 shows an example of the configuration of a data processing system 410 according to the fourth embodiment.

[1328] 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.

[1329] 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).

[1330] 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.

[1331] 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.

[1332] 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).

[1333] 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.

[1334] 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.

[1335] 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.

[1336] 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.

[1337] 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.

[1338] 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.

[1339] 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."

[1340] The present invention relates to a system for generating a virtual personality based on setting information input by a user and conducting an audio interview with the virtual personality. Specific embodiments for carrying out the present invention will be described below.

[1341] 1. User setting input

[1342] The user inputs the virtual persona's configuration information, including occupation, personality, characteristics, etc., using a terminal application or a web interface. The input configuration information is then sent to the server in an appropriate format.

[1343] 2. Virtual personality generation

[1344] The server receives the setting information sent by the user and generates a virtual personality using a generative AI model. The generated virtual personality data is stored on the server until the interview begins.

[1345] 3. Start of interview

[1346] The user speaks questions to the virtual persona through the device, which uses a speech recognition engine to convert the user's voice input into text in real time, and this text data is sent to the server.

[1347] 4. Answer generation and voice output

[1348] The server analyzes the received question text and generates an answer as a virtual personality. The generated answer is passed to a speech synthesis engine and generated as voice data. The voice data is sent to the device and played back to the user.

[1349] 5. Recording of interviews

[1350] The server stores the interview contents as a text record in the form of minutes, and also stores the audio data so that users can review the interview contents later.

[1351] Specific examples

[1352] 1. Example of user preference input

[1353] Examples of setting information input by the user include the following:

[1354] json

[1355] {

[1356] "Occupation": "Engineer",

[1357] "Personality": "Logical",

[1358] "Characteristics": "Tech-savvy"

[1359] }

[1360] 2. Virtual personality generation

[1361] Based on the above setting information, the server uses a generative AI model to generate a virtual personality. For example, a personality with characteristics such as "engineer," "logical," and "tech-savvy" is generated.

[1362] 3. Example user questions

[1363] A user verbally asks the question, "What do you think about the latest AI technology?"

[1364] 4. Example of answer generation and speech output

[1365] The server receives the question and generates an answer such as, "The latest AI technology is very interesting." This answer is then synthesized into voice, which the device plays back to the user.

[1366] 5. Examples of interview recording

[1367] The server saves the entire interview as a transcript in a text file, and also saves the audio data in MP3 format.

[1368] The present invention can be implemented in the above manner. By using this system, users can efficiently and effectively conduct interviews with virtual personalities and gain new insights and ideas.

[1369] The processing flow will be explained below.

[1370] Step 1:

[1371] The user opens the application or web interface on their device and enters configuration information for their virtual personality, including their occupation, personality, and characteristics.

[1372] Step 2:

[1373] The terminal formats the configuration information entered by the user and transmits it to the server in the appropriate data format.

[1374] Step 3:

[1375] The server receives the setting information sent from the terminal and checks its contents.

[1376] Step 4:

[1377] The server uses a generative AI model to generate a virtual personality based on the user's settings, and the generated virtual personality data is stored on the server.

[1378] Step 5:

[1379] The user verbally asks a question to the device.

[1380] Step 6:

[1381] The device uses a speech recognition engine to convert the user's voice input into text data in real time.

[1382] Step 7:

[1383] The terminal transmits the converted question text data to the server.

[1384] Step 8:

[1385] The server analyzes the question text data received from the terminal and generates an answer as a virtual personality.

[1386] Step 9:

[1387] The generated answer text is passed to a speech synthesis engine to generate speech data.

[1388] Step 10:

[1389] The server transmits the generated voice data to the terminal.

[1390] Step 11:

[1391] The device plays back the received audio data and provides the user with a response.

[1392] Step 12:

[1393] The server generates and stores a text record of the interview contents as a transcript.

[1394] Step 13:

[1395] The server stores the audio data of the interview.

[1396] Step 14:

[1397] After the interview, users can review the saved transcript and audio data.

[1398] Example 1

[1399] 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."

[1400] A method is needed to generate a virtual personality based on user-entered settings and enable natural dialogue when the user interviews the virtual personality. Another challenge is to efficiently convert the user's voice input into text, generate appropriate responses based on the text, and then respond in voice. It is also important to keep a record of the interview content so that it can be referenced later.

[1401] 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.

[1402] In this invention, the server includes means for generating a virtual personality based on setting information input by a user, means for recognizing a user's voice input and converting it into text, means for generating a virtual personality using a generative AI model, means for the generated virtual personality to generate answers to the user's questions, means for synthesizing and playing back the generated answers, means for saving the interview content as minutes, and means for saving the interview audio data, which enables a user to input setting information, realize natural conversations with a virtual personality, and record and save the content.

[1403] "User" refers to any individual or entity that uses the System.

[1404] "Setting information" refers to information about a specific occupation, personality, and characteristics that a user inputs to generate a virtual personality.

[1405] A "virtual personality" is a virtual entity generated based on the user's settings, and refers to a pseudo-personality that can interact with the user.

[1406] "Voice input" refers to input made by a user to a system using voice.

[1407] "Text conversion" refers to the process of analyzing voice input and expressing it as a string of characters.

[1408] A "generative AI model" refers to an algorithm that uses machine learning techniques to generate a virtual personality from a user's settings.

[1409] "Answer generation" refers to the process by which a virtual personality constructs an appropriate response to a question posed by a user.

[1410] "Speech synthesis" refers to the process of converting generated text data into speech data.

[1411] "Playback" refers to the process of playing back the synthesized voice data to the user.

[1412] "Minutes" refers to data that records the contents of an interview in written form.

[1413] "Voice data" refers to voice-synthesized responses and user voice input data.

[1414] The present invention is a system for generating a virtual personality based on setting information input by a user and conducting an audio interview with the virtual personality. Specific embodiments of the present invention will be described below.

[1415] User preference input

[1416] The user inputs configuration information for the virtual persona using a device application or web interface, including occupation, personality, and characteristics. For example, the user might input the following information:

[1417] Occupation: Engineer

[1418] Personality: Logical

[1419] Specialty: Technology savvy

[1420] Once these entries are complete, the device sends this information to the server in JSON format.

[1421] Virtual personality generation

[1422] The server receives the setting information sent by the user. Then, it generates a virtual personality using a generative AI model (e.g., GPT-3). The generated virtual personality data is stored on the server until the interview begins. For example, the following prompt sentences are used to input to the generative AI model:

[1423] Prompt: "You are an engineer, a logical, tech-savvy person."

[1424] Interview begins

[1425] The user asks the virtual persona a question by voice through the device, such as, "What do you think about the latest AI technology?" The device uses a speech recognition engine (e.g., Google Speech-to-Text API) to convert the user's voice into text in real time and sends this text data to the server.

[1426] Answer generation and voice output

[1427] The server analyzes the received question text and generates an answer as a virtual personality using a generative AI model. For example, it generates an answer such as "The latest AI technology is very interesting." The generated answer is passed to a speech synthesis engine (e.g., Amazon Polly) and generated as audio data. This audio data is sent to the device and played back to the user.

[1428] Interview recording

[1429] The server stores the interview contents as text records in minutes format. Audio data is also stored in the same way. Users can review the interview contents later. The recordings are generally stored in text files and MP3 format.

[1430] This embodiment allows users to efficiently and effectively interview virtual personalities, and gain new insights and ideas.

[1431] The flow of the identification process in the first embodiment will be described with reference to FIG.

[1432] Program processing flow and specific explanation

[1433] Step 1: User Settings Input

[1434] The user inputs the virtual personality's configuration information using a terminal application or web interface. This configuration information includes occupation, personality, characteristics, etc. For example, the user inputs information such as "Occupation: Engineer," "Personality: Logical," and "Characteristics: Knowledgeable about technology."

[1435] Input: Setting information about occupation, personality, and characteristics

[1436] Output: JSON data containing configuration information

[1437] Specific behavior: The user enters the setting information into the input form and clicks the "Submit" button.

[1438] Step 2: Sending configuration information

[1439] The device sends the configuration information entered by the user to the server in an appropriate format (JSON format).

[1440] Input: JSON data generated in step 1

[1441] Output: Configuration information sent to the server

[1442] Specific operation: JSON data containing configuration information is sent to the server via an HTTP request.

[1443] Step 3: Receiving configuration information

[1444] The server receives the setting information sent from the device, and this data is stored and analyzed within the server.

[1445] Input: Setting information sent from the device

[1446] Output: Configuration information saved on the server

[1447] Specific operation: The server receives the HTTP request and saves the configuration information in the database.

[1448] Step 4: Virtual personality generation

[1449] The server generates a virtual personality using a generative AI model (e.g., GPT-3) based on the received configuration information. For example, it creates a prompt sentence like the following based on the configuration information: "Occupation: Engineer," "Personality: Logical," and "Characteristics: Knowledgeable about technology."

[1450] Prompt: "You are an engineer, a logical, tech-savvy person."

[1451] Input: Configuration information stored on the server

[1452] Output: Generated virtual personality data

[1453] Specific operation: A prompt sentence is input into the generative AI model, and the resulting virtual personality data is analyzed and saved.

[1454] Step 5: Start the interview

[1455] The user uses the device to ask the virtual persona questions by voice, such as, "What do you think about the latest AI technology?"

[1456] Input: User voice input

[1457] Output: Speech-to-text data

[1458] Specific operation: Using a speech recognition engine (e.g., Google Speech-to-Text API), the speech is converted into text in real time and this text is sent to the server.

[1459] Step 6: Receiving and parsing the question text

[1460] The server receives and analyzes the question text sent by the user.

[1461] Input: User's question text

[1462] Output: Parsed question data

[1463] What it does: The server receives the text data, parses it, and converts it into a format that can be fed into the appropriate generative AI model.

[1464] Step 7: Generate answers using virtual personalities

[1465] The server uses the generative AI model to generate an appropriate answer to the user's question, for example, "The latest AI technology is very interesting."

[1466] Input: Parsed question data

[1467] Output: Generated answer text

[1468] Specific operation: Question data is input into the generative AI model and the resulting answer text is obtained.

[1469] Step 8: Generate audio data

[1470] The server passes the generated answer text to a speech synthesis engine (e.g., Amazon Polly) to generate voice data.

[1471] Input: Generated answer text

[1472] Output: Audio data

[1473] Specific operation: Input text into the speech synthesis engine and send the generated audio file to the device.

[1474] Step 9: Sending and Playing Audio Data

[1475] The server sends the generated audio data to the terminal, which then plays the audio data and lets the user hear it.

[1476] Input: Audio data

[1477] Output: The audio played to the user

[1478] What it does: Plays audio files in streaming or download format.

[1479] Step 10: Record the interview

[1480] The server stores the entire interview as text data in the form of minutes, along with the audio data.

[1481] Input: Interview content (text and audio data)

[1482] Output: Saved minutes text and audio data

[1483] Specific operation: The server saves the minutes in text format and the audio data in an appropriate format (e.g., mp3).

[1484] By performing these steps sequentially, the system of the present invention can facilitate an interview with a virtual personality.

[1485] (Application example 1)

[1486] 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."

[1487] In conventional online shopping systems, users often struggle with product selection, and the systems that can provide appropriate support are limited. Furthermore, there is a lack of mechanisms to generate a personal assistant based on the user's settings information to support product selection. As a result, users are unable to receive appropriate advice, resulting in a poor purchasing experience.

[1488] 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.

[1489] In this invention, the server includes means for generating a virtual personality based on setting information input by the user, means for recognizing the user's voice input and converting it into text, means for the generated virtual personality to generate answers to the user's questions, means for synthesizing and playing back the generated answers, means for saving the interview content as minutes, means for saving the interview audio data, means for generating a shopping assistant based on the user's settings and providing audio support for product selection, means for generating product recommendation information based on the inquiry content, and means for outputting the generated recommendation information by voice. This allows the user to receive appropriate recommendations through the shopping assistant, providing a new purchasing experience.

[1490] "Means for generating a virtual personality based on user-entered setting information" refers to a system that uses a generative AI model to create a virtual personality based on user-entered setting information (e.g., occupation, personality, characteristics).

[1491] The "means for recognizing a user's voice input and converting it into text" is a system that uses a voice recognition engine to convert a user's voice into text data in real time.

[1492] "Means for a generated virtual personality to generate answers to a user's questions" refers to a system in which a virtual personality uses a generative AI model to create appropriate answers to a user's questions.

[1493] The "means for synthesizing and reproducing the generated answer" is a system that uses a speech synthesis engine to convert the generated answer from text to speech and reproduce it aloud to the user.

[1494] "Means for saving interview content as minutes" refers to a storage system that stores the content of conversations during interviews as text data and makes it available for later viewing.

[1495] "Means for storing audio data of an interview" refers to a system for recording and storing audio data during an interview.

[1496] "A means for generating a shopping assistant based on user settings and providing voice support for product selection" is a system that creates a virtual shopping assistant based on information set by the user and provides voice support for the user's shopping through that assistant.

[1497] The "means for generating product recommendation information based on the inquiry content" is a system that analyzes the inquiry content of the user and generates information that recommends appropriate products based on the analysis.

[1498] The "means for outputting generated recommendation information by voice" is a system that converts the generated recommendation information into voice data and provides it to the user by voice.

[1499] The present invention is a system for generating a virtual personality based on setting information input by a user and conducting an audio interview with the virtual personality. Specific embodiments for carrying out the present invention will be described below.

[1500] System configuration

[1501] This system mainly consists of the following components:

[1502] 1. User setting input interface

[1503] Users input their preferences via a smartphone or web interface, including their occupation, personality, and characteristics. For example, they might enter preferences such as "occupation: fashion consultant, personality: friendly, characteristics: sensitive to trends."

[1504] 2. Virtual personality generation

[1505] The server receives the configuration information and generates a virtual personality using a generative AI model (e.g., GPT-3.5-Turbo). The generated virtual personality data is stored on the server and awaits the start of the interview.

[1506] 3. Start of interview

[1507] Users ask questions by voice using a smartphone or other device, and the device's built-in speech recognition engine (e.g., Google Speech Recognition API) converts the voice into text data and sends it to the server.

[1508] 4. Answer Generation and Speech Synthesis

[1509] The server analyzes the text data of the question and generates an appropriate answer as a virtual personality. The generated answer is converted into voice data by a speech synthesis engine (e.g., pyttsx3) and sent to the device.

[1510] 5. Recording of interviews

[1511] The server stores the entire interview as a transcript in text format, along with the audio data, which can be accessed by the user later.

[1512] Hardware and software used

[1513] Hardware: smartphones, tablets, servers, etc.

[1514] software:

[1515] Generative AI model: GPT-3.5-Turbo

[1516] Speech recognition engine: Google Speech Recognition API

[1517] Speech synthesis engine: pyttsx3

[1518] Web Interface: Any web browser

[1519] Specific examples

[1520] For example, if a user asks, "What is a recommended outfit for spring?" the system will act as follows:

[1521] 1. User's question is entered by voice

[1522] 2. The speech recognition engine converts speech to text

[1523] 3. The server analyzes the text and generates an answer as a virtual personality.

[1524] 4. The answer is converted into speech using a speech synthesis engine and played back to the user.

[1525] Prompt Sentence Examples

[1526] What is your recommended outfit for spring?

[1527] This allows users to receive appropriate advice and enjoy a more personalized shopping experience.

[1528] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[1529] Step 1:

[1530] The user inputs configuration information such as occupation, personality, and characteristics via a smartphone or web interface. The input data is sent to the server.

[1531] Step 2:

[1532] The server generates a virtual personality. Based on the received setting information, a generative AI model (e.g., GPT-3.5-Turbo) is used to generate the virtual personality. This virtual personality data is stored on the server and waits until the interview begins.

[1533] Step 3:

[1534] The user asks a question by voice. The user asks a question by voice to the virtual personality using a smartphone or another device. The voice recognition engine (e.g., Google Speech Recognition API) installed on the device converts the voice into text data and sends the text data to the server.

[1535] Step 4:

[1536] The server analyzes the question and generates an answer as a virtual personality. The server analyzes the text data of the received question and generates an appropriate answer using a generative AI model. The generated answer is stored as text data on the server.

[1537] Step 5:

[1538] The server passes the generated answer to a speech synthesis engine (e.g., pyttsx3), which converts the text data of the answer into audio data, which is then sent to the device and played back to the user.

[1539] Step 6:

[1540] The server stores the interviews. The server saves the entire interview in text format as a transcript. The server also saves the audio of the interviews for the user to refer to later.

[1541] Step 7:

[1542] Generate a shopping assistant based on user settings. The server uses the settings to create a virtual persona as a shopping assistant. This virtual persona generates recommendation information based on the user's product inquiries.

[1543] Step 8:

[1544] Recommendation information is generated based on the query content. The server uses the generative AI model to generate product recommendation information. This recommendation information is saved as text data.

[1545] Step 9:

[1546] The generated recommendation information is output as voice data. The server passes the recommendation information to a voice synthesis engine and converts it into voice data. This voice data is sent to the device and played back to the user.

[1547] Through these steps, the system effectively acts as a shopping assistant for users, enabling a more personalized purchasing experience.

[1548] 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.

[1549] The present invention combines a system that generates a virtual personality based on setting information entered by a user and conducts an audio interview with that virtual personality with an emotion engine that recognizes the user's emotions. Specific embodiments for carrying out the present invention will be described below.

[1550] 1. User setting input

[1551] The user inputs configuration information for the virtual persona using a terminal application or a web interface, including occupation, personality, characteristics, etc. The configuration information is then sent to the server in an appropriate format.

[1552] 2. Virtual personality generation

[1553] The server receives the setting information sent by the user and generates a virtual personality using the generative AI model. The generated virtual personality data is stored on the server.

[1554] 3. Start of interview

[1555] The user asks questions to the virtual persona by voice through the device, which uses a voice recognition engine to convert the user's voice input into text in real time and transmits this text data to the server.

[1556] 4. Emotion recognition

[1557] The server uses an emotion engine to recognize emotions from the user's voice input in addition to the voice-recognized text data. The emotion engine analyzes the user's voice tone, speed, and other parameters to generate emotion data.

[1558] 5. Answer generation and voice output

[1559] The server generates answers from the virtual personality based on the received question text and the recognized emotion data, using a natural language processing algorithm to generate answers that include appropriate tone and content according to the emotion recognized.

[1560] The generated answer is passed to a speech synthesis engine, which generates audio data, which is then sent to the device and played back to the user.

[1561] 6. Recording of interviews

[1562] The server stores the interview contents as a text record in the form of minutes, and emotional data can also be included in the minutes. Audio data is also stored, so users can review the interview contents later.

[1563] Specific examples

[1564] 1. Example of user preference input

[1565] Examples of setting information input by the user include the following:

[1566] json

[1567] {

[1568] "Occupation": "Psychologist",

[1569] "Personality": "Friendly",

[1570] "Characteristics": "Emotionally sensitive"

[1571] }

[1572] 2. Virtual personality generation

[1573] Based on the above settings, the server uses a generative AI model to generate a virtual personality, such as a "psychologist," "friendly," or "sensitive to emotions."

[1574] 3. Example user questions

[1575] The user verbally asks, "Tell me how you deal with stress."

[1576] 4. Emotion Recognition Example

[1577] The server analyzes the user's voice input and uses an emotion engine to recognize the emotion that the user is feeling slightly anxious.

[1578] 5. Example of answer generation and speech output

[1579] Based on the question and the sense of anxiety recognized, the server generates an answer such as, "When you feel stressed, it's important to first take a deep breath and calm yourself down." This answer is synthesized into voice and sent to the device to be played back to the user.

[1580] 6. Examples of interview recording

[1581] The server saves the entire interview as a text file containing transcripts, including emotional data. The audio data is also saved in MP3 format.

[1582] The present invention can be implemented using the above method. By using this system, users can efficiently and effectively conduct interviews with virtual personalities and obtain appropriate responses and answers that take emotions into consideration. This allows users to gain new insights and a deeper understanding based on emotions.

[1583] The processing flow will be explained below.

[1584] Step 1:

[1585] The user opens the application or web interface on their device and enters configuration information for their virtual personality, including their occupation, personality, and characteristics.

[1586] Step 2:

[1587] The terminal formats the setting information entered by the user into an appropriate data format and sends it to the server.

[1588] Step 3:

[1589] The server receives the setting information sent from the terminal and analyzes its contents.

[1590] Step 4:

[1591] The server uses the generative AI model to generate a virtual personality based on the setting information, and the generated virtual personality data is stored on the server.

[1592] Step 5:

[1593] The user verbally asks a question to the device.

[1594] Step 6:

[1595] The device uses a speech recognition engine to convert the user's voice input into text data in real time, which is then sent to the server.

[1596] Step 7:

[1597] The server analyzes the received question text data and simultaneously generates emotion data from the user's voice input using an emotion engine.

[1598] Step 8:

[1599] The server combines the question text data with the emotion data to generate an appropriate answer for the virtual personality, using a natural language processing algorithm.

[1600] Step 9:

[1601] The generated answer text is passed to a speech synthesis engine and generated as voice data.

[1602] Step 10:

[1603] The server transmits the generated voice data to the terminal.

[1604] Step 11:

[1605] The device plays back the received audio data and provides the user with a response.

[1606] Step 12:

[1607] The server stores the interview contents as a text record in the form of a transcript, which also contains the recognized emotion data.

[1608] Step 13:

[1609] The server stores the audio data of the interview.

[1610] Step 14:

[1611] After the interview, users can review the saved transcript and audio data.

[1612] The following is an explanation using a specific example.

[1613] 1. Example of user preference input

[1614] Examples of setting information that the user inputs include the following:

[1615] json

[1616] {

[1617] "Occupation": "Psychologist",

[1618] "Personality": "Friendly",

[1619] "Characteristics": "Emotionally sensitive"

[1620] }

[1621] 2. Virtual personality generation

[1622] The server uses the AI ​​model to generate a virtual personality based on the above settings. The virtual personality has characteristics such as "psychologist," "friendly," and "sensitive to emotions."

[1623] 3. Example user questions

[1624] The user verbally asks, "Tell me how you deal with stress."

[1625] 4. Emotion Recognition Example

[1626] The server analyzes the user's voice input and uses an emotion engine to recognize that the user is feeling a little anxious.

[1627] 5. Example of answer generation and speech output

[1628] Based on the question and the recognized emotional data, the server generates an answer such as, "When you feel stressed, it's important to first take a deep breath and calm yourself down." This answer is synthesized into voice and sent to the device to be played back to the user.

[1629] 6. Examples of interview recording

[1630] The server saves the entire interview as a transcript in a text file, including emotional data, and also saves the audio data in an appropriate format.

[1631] Example 2

[1632] 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."

[1633] Conventional virtual personality interview systems generate answers without considering the user's emotions, making it difficult to provide appropriate answers tailored to individual needs. Furthermore, the recording of interview content and audio data is often insufficient, resulting in insufficient information for later reference. Furthermore, when generating answers using natural language processing algorithms, the lack of emotion recognition can lead to poor answer quality.

[1634] 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.

[1635] In this invention, the server includes means for generating a virtual personality based on setting information input by the user, means for recognizing the user's voice input and converting it into text, means for the generated virtual personality to generate answers to the user's questions, means for synthesizing the generated answers and playing them back, means for saving the interview content as minutes, means for saving the interview voice data, means for recognizing emotions from the user's voice input, and means for the virtual personality to generate answers based on the recognized emotion data. This makes it possible to provide appropriate answers according to the user's emotions in real time and to record and save the interview content and voice data in detail.

[1636] "Setting information" refers to information that a user inputs when creating a virtual personality, and includes data such as occupation, personality, and characteristics.

[1637] A "virtual personality" is an interactive character generated by the server based on configuration information, and has the ability to answer users' questions in real time.

[1638] "User voice input" refers to the voice that the user makes through the terminal, including interview questions and conversation content.

[1639] "Convert to text" refers to the process of converting audio data into text using speech recognition technology.

[1640] "Generating an answer" refers to the process by which the virtual personality creates an appropriate response to the user's question, which may use natural language processing algorithms.

[1641] "Speech synthesis" refers to a technique for outputting generated text responses as speech, converting text data into speech data.

[1642] "Saving as minutes" means recording the interview contents in text format so that they can be referenced at a later date.

[1643] "Storing audio data" refers to recording the audio data of an interview in digital form so that it can be played back and analyzed at a later date.

[1644] "Emotion recognition" refers to the process of extracting emotional data from a user's voice input by analyzing the tone, speed, and word choice of the voice.

[1645] "Emotional data" refers to data that indicates the user's emotional state using emotion recognition technology and is used by the virtual personality to generate responses.

[1646] This invention is a system that generates a virtual personality based on setting information entered by a user and conducts an audio interview with that virtual personality, and further combines it with an emotion engine that recognizes the user's emotions. Specific embodiments for implementing this system are described below.

[1647] First, the user inputs the virtual persona's configuration information, including occupation, personality, characteristics, etc., using a terminal application or web interface. This configuration information is then sent to the server in an appropriate format.

[1648] The server receives the setting information sent by the user and generates a virtual personality using a generative AI model (e.g., GPT-4). The generated virtual personality data is stored on the server.

[1649] Next, the user asks the virtual persona a question by voice through the device. The user's voice input is converted into text in real time by a speech recognition engine (e.g., Google Speech-to-Text) within the device, and this text data is sent to the server.

[1650] The server uses an emotion engine (e.g., IBM Watson Tone Analyzer) to recognize emotions from the user's voice input in addition to the transmitted text data. The emotion engine analyzes the tone, rate, and other parameters of the user's voice to generate emotion data.

[1651] Based on the submitted question text and emotion data, the server uses a generative AI model to generate an answer from the virtual personality. For example, it utilizes a natural language processing algorithm. The generated answer is passed to a speech synthesis engine (e.g., Amazon Polly) and generated as audio data. This audio data is sent to the device and played back to the user.

[1652] The server also stores the interview content as a text record in the form of minutes, including emotional data, and audio data, so users can review the interview content later.

[1653] Specific examples

[1654] 1. Example of user preference input

[1655] An example of the setting information entered by the user is as follows:

[1656] Occupation: Psychologist

[1657] Personality: Friendly

[1658] Traits: Emotionally sensitive

[1659] 2. Virtual personality generation

[1660] Based on the above configuration information, the server uses a generative AI model (e.g., GPT-4) to generate a virtual personality. For example, a personality with characteristics such as "psychologist," "friendly," and "sensitive to emotions" is generated.

[1661] 3. Example user questions

[1662] The user verbally asks, "Tell me how you deal with stress."

[1663] 4. Emotion Recognition Example

[1664] The server analyzes the user's voice input and uses an emotion engine (e.g., IBM Watson Tone Analyzer) to recognize the user's emotion, which indicates slight anxiety.

[1665] 5. Example of answer generation and speech output

[1666] The server generates an answer based on the question and the perceived anxiety level. For example, "When you feel stressed, it's important to first take a deep breath and calm yourself down." The generated answer is synthesized into voice and sent to the device.

[1667] 6. Examples of interview recording

[1668] The server saves the entire interview as a text file containing transcripts, including emotional data. The audio data is also saved in MP3 format.

[1669] Prompt Sentence Examples

[1670] The following is an example of a prompt sentence:

[1671] Role: Virtual Psychologist

[1672] Occupation: Psychologist

[1673] Personality: Friendly

[1674] Traits: Emotionally sensitive

[1675] User Question: What do you do when you feel stressed?

[1676] Recognized emotion: Anxiety

[1677] By implementing the invention in accordance with the above aspects, users can efficiently and effectively interview virtual personalities and obtain appropriate responses and answers that take emotions into account, thereby gaining new insights and deeper understanding based on emotions.

[1678] The flow of the identification process in the second embodiment will be described with reference to FIG.

[1679] Step 1: User Settings Input

[1680] The user uses a terminal application or a web interface to input configuration information for the virtual personality, including occupation, personality, and characteristics. For example, the user might input information such as "Occupation: Psychologist, Personality: Friendly, Characteristics: Sensitive to Emotions."

[1681] Input: The user enters the configuration information.

[1682] Output: The device converts the input configuration information into the appropriate format, checks for errors, and sends the converted configuration information to the server.

[1683] Step 2: Virtual personality generation

[1684] The server receives the setting information sent by the user.

[1685] Based on the received information, the server invokes a generative AI model (e.g., GPT-4) to generate a virtual personality that reflects the user's specified occupation, personality, and characteristics.

[1686] Input: The server receives user configuration information.

[1687] Data processing: The server calls the generative AI model and generates a virtual personality based on the setting information.

[1688] Output: The server stores the generated virtual personality data in its own database.

[1689] Step 3: Start the interview

[1690] The user uses the device to ask the virtual personality a question by voice. The user types the question into the device's microphone. For example, the user might ask, "Tell me how to deal with stress."

[1691] The device uses a speech recognition engine such as Google Speech-to-Text to convert the user's speech into text.

[1692] Input: User's voice input.

[1693] Data processing: The device uses a speech recognition engine to convert the user's speech into text.

[1694] Output: The converted text data is sent to the server.

[1695] Step 4: Emotion Recognition

[1696] The server receives the transmitted text data and, if necessary, also analyzes the user's voice data.

[1697] The server uses emotion engines such as IBM Watson Tone Analyzer to recognize the user's emotions from text and audio data, including tone of voice, speaking rate and word choice.

[1698] Input: Text and audio data.

[1699] Data processing: The server uses the emotion engine to generate emotion data.

[1700] Output: Add the recognized emotion data to the prompt sentence.

[1701] Step 5: Answer generation and speech output

[1702] The server generates an appropriate answer using a generative AI model (e.g., GPT-4) based on the user's question text and emotion data. For example, if the server recognizes anxiety in response to the question, "Please tell me how to deal with stress," it will generate an answer such as, "When you feel stressed, it's important to take a deep breath and calm yourself down first."

[1703] The server passes the generated answer to a speech synthesis engine such as Amazon Polly to generate voice data.

[1704] Input: Question text and sentiment data.

[1705] Data processing: The server uses the generative AI model to generate an appropriate answer, which is then converted into voice data using a speech synthesis engine.

[1706] Output: The generated audio data is sent to the device.

[1707] The terminal plays the received audio data so that it reaches the user.

[1708] Step 6: Record the interview

[1709] The server stores all the conversations in the interview as transcripts in text format, including emotional data.

[1710] The server also stores the audio data for later reference, for example in mp3 format.

[1711] Users can log in later to check the minutes and audio data.

[1712] Input: Interview audio and text data.

[1713] Data processing: The server stores the minutes and audio data in a database.

[1714] Output: Saved transcripts and audio data.

[1715] (Application example 2)

[1716] 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."

[1717] In modern society, users have more opportunities to access a variety of content, but finding content that is optimized for their emotional state and interests remains a difficult challenge. Furthermore, there is a lack of easy ways for users to obtain recommended content tailored to their emotions and circumstances. To address this issue, there is a need for a method to provide optimal content based on the user's input information and emotional state.

[1718] The specific processing by the specific processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means. In this invention, the server includes means for generating a virtual personality based on setting information entered by the user, means for recognizing the user's voice input and converting it into text, means for the generated virtual personality to recommend content, means for analyzing the user's emotions using an emotion engine, and means for audibly outputting emotion-based content recommendations based on this data. This makes it possible to recommend personalized content that is optimized for the user's emotional state and interests.

[1719] "User preference input" is the process by which a user inputs information required for a virtual personality or recommendation system.

[1720] A "virtual personality" is a virtual agent with specific characteristics, occupations, and personalities that is generated based on the user's settings.

[1721] "Speech recognition" is a technology that converts a user's voice input into text data.

[1722] An "emotion engine" is an algorithm or software that analyzes voice and text data to recognize the user's emotions.

[1723] A "natural language processing algorithm" is a technology that analyzes the meaning of text data and is used to generate content and answers.

[1724] "Content recommendation" is the process of suggesting the most suitable content, such as movies, music, or books, based on a user's interests and emotional state.

[1725] "Emotion analysis" is a technology that uses a user's voice and text data to identify their emotional state at that time.

[1726] "Speech synthesis" is a technology that generates synthetic speech based on text data.

[1727] "Minutes" are the contents of interviews or conversations recorded as text data.

[1728] "Audio data preservation" is the process of storing recorded audio in digital form.

[1729] By "operating on a smartphone" it is meant that the present invention is executable on a smartphone device.

[1730] A specific embodiment of the present invention will now be described in detail. The present invention provides a system that generates a virtual personality based on setting information input by a user and recommends content that is optimized for the user's emotions through interaction with the virtual personality.

[1731] First, a user launches the application through their device and enters their personal settings, including their interests, favorite actors and music genres, and other characteristics. This information is then sent to the server and used to generate a unique virtual personality for the user.

[1732] The server uses a generative AI model based on the received settings to generate a virtual personality that matches the user's interests and characteristics. This virtual personality acts as an agent that recommends content through dialogue with the user.

[1733] Next, the user speaks a question to the virtual agent, such as, "What movies are good to watch today?" The device uses a speech recognition engine (e.g., Google Speech-to-Text) to convert the user's voice into text in real time and send it to the server.

[1734] The server analyzes the received text data and uses an emotion engine (e.g., IBM Watson Tone Analyzer) to recognize the user's emotion. For example, if it recognizes that the user is tired, it will use this information to suggest the most appropriate content.

[1735] The generated answer is adjusted based on emotion recognition and is generated in the form of, for example, "You seem tired today. How about a relaxing comedy movie?" This answer is passed to a speech synthesis engine (e.g., Amazon Polly) and generated as synthetic speech. The generated speech data is sent to the device and played back to the user.

[1736] The server also stores the interview as a text transcript, including the questions asked, emotional data, and the virtual agent's responses, as well as audio data, so the user can review the interview later.

[1737] As a concrete example, consider a scenario where a user asks a question by voice, "What are the latest action movies starring Will Smith?" In this case, the system works to recommend the most suitable movie, taking into account the user's emotional state.

[1738] Example prompt sentence:

[1739] User: Want to watch a relaxing movie today?

[1740] Virtual Agent: You seem tired today. How about a relaxing comedy movie?

[1741] This enables personalized content recommendations that are optimized for the user's emotional state and interests.

[1742] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[1743] Step 1:

[1744] The user launches the application through their device and enters their personal settings, including their interests, favorite actors and music genres, and other characteristics. This data is sent to the server in an appropriate format, in JSON format, and is saved as the user's profile information on the server side.

[1745] Step 2:

[1746] The server uses a generative AI model based on the received configuration information to generate a virtual personality. A generative AI model (e.g., GPT-3) is used to create a virtual agent tailored to the user's interests and characteristics. This virtual personality data is stored on the server and used in subsequent interactions and recommendation processes. Specifically, the generative AI model generates text data and stores it as a virtual personality profile.

[1747] Step 3:

[1748] The user asks a question to the virtual agent by voice. The device uses a speech recognition engine (e.g., Google Speech-to-Text) to convert the user's voice into text in real time and send it to the server. The input voice data is digitized at a sample rate and converted into text by the speech recognition engine. The converted text is sent to the server in JSON format.

[1749] Step 4:

[1750] The server analyzes the received text data and recognizes the user's emotions using an emotion engine (e.g., IBM Watson Tone Analyzer). Specifically, the emotion engine extracts emotion parameters (e.g., happiness, sadness, anger, etc.) from the text data and saves them as emotion analysis results. This emotion data is saved in JSON format as metadata such as the intensity and type of emotion.

[1751] Step 5:

[1752] The server uses the user's question text and emotional data to generate the best answer from the generated virtual personality. It uses a natural language processing algorithm to generate an answer optimized for the user's emotional state. For example, if the user is tired, it will recommend a relaxing movie. A generative AI model is used in this answer generation process.

[1753] Step 6:

[1754] The generated answer is passed to a speech synthesis engine (e.g., Amazon Polly) to generate synthetic speech. This generated speech data is sent to the device and played back to the user. The speech synthesis engine converts the text data into speech waveforms and sends the speech data to the device.

[1755] Step 7:

[1756] The server saves the entire interview as a text file containing the questions asked, emotional data, and the virtual agent's responses. The audio data is also saved digitally so that it can be played back later if necessary. The server then saves this data in a suitable format on the file system, making it accessible to the user.

[1757] 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.

[1758] 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.

[1759] In the above embodiment, an example was given in which the specific processing is performed by the data processing device 12, but the technology of the present disclosure is not limited to this, and the specific processing may be performed by the robot 414.

[1760] 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.

[1761] FIG. 9 is a diagram illustrating an emotion map 400 on which multiple emotions are mapped. In the emotion map 400, emotions are arranged in concentric circles radiating from the center. Emotions closer to the center of the concentric circles are more primitive. Emotions representing states and actions arising from a state of mind are arranged on the outer edges of the concentric circles. The concept of emotion includes both affect and mental states. Emotions generally generated from reactions occurring in the brain are arranged on the left side of the concentric circles. Emotions generally induced by situational judgment are arranged on the right side of the concentric circles. Emotions generally generated from reactions occurring in the brain and induced by situational judgment are arranged on the upper and lower sides of the concentric circles. Furthermore, the emotion of "pleasure" is arranged on the upper side of the concentric circles, and the emotion of "discomfort" is arranged on the lower side. In this way, in the emotion map 400, multiple emotions are mapped based on the structure by which emotions are generated, and emotions that tend to occur simultaneously are mapped close to each other.

[1762] 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.

[1763] 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).

[1764] 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.

[1765] 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."

[1766] 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.

[1767] 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).

[1768] 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.

[1769] 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.

[1770] 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.

[1771] 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.

[1772] 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.

[1773] 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.

[1774] 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.

[1775] 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.

[1776] 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.

[1777] 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.

[1778] The following is further disclosed regarding the above embodiment.

[1779] (Claim 1)

[1780] A means for generating a virtual personality based on setting information input by a user;

[1781] a means of recognizing and converting a user's voice input into text; and

[1782] a means for the generated virtual personality to generate answers to the user's questions;

[1783] means for synthesizing and playing back the generated answer;

[1784] A means to save the interview contents as minutes,

[1785] The system includes a means for storing audio data of the interview.

[1786] (Claim 2)

[1787] 10. The system of claim 1, further comprising: means for providing an interface for a user to input configuration information.

[1788] (Claim 3)

[1789] 10. The system of claim 1, further comprising means for the generated virtual personality to use a natural language processing algorithm in generating answers to the user's questions.

[1790] "Example 1"

[1791] (Claim 1)

[1792] A means for generating a virtual personality based on setting information input by a user;

[1793] a means of recognizing and converting a user's voice input into text; and

[1794] A means for generating a virtual personality using a generative AI model;

[1795] a means for the generated virtual personality to generate answers to the user's questions;

[1796] means for synthesizing and playing back the generated answer;

[1797] A means to save the interview contents as minutes,

[1798] The system includes a means for storing audio data of the interview.

[1799] (Claim 2)

[1800] 10. The system of claim 1, further comprising: means for providing an interface for a user to input configuration information.

[1801] (Claim 3)

[1802] 10. The system of claim 1, further comprising means for the generated virtual personality to use a natural language processing algorithm in generating answers to the user's questions.

[1803] "Application Example 1"

[1804] (Claim 1)

[1805] A means for generating a virtual personality based on setting information input by a user;

[1806] a means of recognizing and converting a user's voice input into text; and

[1807] a means for the generated virtual personality to generate answers to the user's questions;

[1808] means for synthesizing and playing back the generated answer;

[1809] A means to save the interview contents as minutes,

[1810] a means for storing the audio data of the interview;

[1811] A means for generating a shopping assistant based on user settings and providing voice support for product selection;

[1812] means for generating product recommendation information based on the inquiry content;

[1813] A means for outputting the generated recommendation information by voice

[1814] A system including:

[1815] (Claim 2)

[1816] 10. The system of claim 1, further comprising: means for providing an interface for a user to input configuration information.

[1817] (Claim 3)

[1818] 10. The system of claim 1, further comprising means for the generated virtual personality to use a natural language processing algorithm in generating answers to the user's questions.

[1819] "Example 2: Combining Emotion Engines"

[1820] (Claim 1)

[1821] A means for generating a virtual personality based on setting information input by a user;

[1822] a means of recognizing and converting a user's voice input into text; and

[1823] a means for the generated virtual personality to generate answers to the user's questions;

[1824] means for synthesizing and playing back the generated answer;

[1825] A means to save the interview contents as minutes,

[1826] a means for storing the audio data of the interview;

[1827] a means for recognizing emotions from a user's voice input;

[1828] a means for the virtual personality to generate an answer based on the recognized emotion data;

[1829] A system including:

[1830] (Claim 2)

[1831] 10. The system of claim 1, further comprising: means for providing an interface for a user to input configuration information.

[1832] (Claim 3)

[1833] 10. The system of claim 1, further comprising means for the generated virtual personality to use a natural language processing algorithm in generating answers to the user's questions.

[1834] "Application example 2 when combining emotion engines"

[1835] (Claim 1)

[1836] A means for generating a virtual personality based on setting information input by a user;

[1837] a means of recognizing and converting a user's voice input into text; and

[1838] a means for the generated virtual personality to generate answers to the user's questions;

[1839] means for synthesizing and playing back the generated answer;

[1840] A means to save the interview contents as minutes,

[1841] a means for storing the audio data of the interview;

[1842] A means for the generated virtual personality to recommend content;

[1843] a means for analyzing user sentiment using an emotion engine;

[1844] a means for generating answers based on user sentiment;

[1845] means for audibly outputting emotion-based content recommendations;

[1846] A system including means operating on a smartphone.

[1847] (Claim 2)

[1848] 10. The system of claim 1, further comprising: means for providing an interface for a user to input configuration information.

[1849] (Claim 3)

[1850] 10. The system of claim 1, further comprising means for the generated virtual personality to use a natural language processing algorithm in generating answers to the user's questions. [Explanation of symbols]

[1851] 10, 210, 310, 410 Data Processing Systems 12 Data Processing Device 14 Smart Devices 214 Smart Glasses 314 Headset-type terminal 414 Robot< / url:> < / url:> < / url:> < / url:>

Claims

1. A means for generating a virtual personality based on setting information input by a user; a means of recognizing and converting a user's voice input into text; and a means for the generated virtual personality to generate answers to the user's questions; means for synthesizing and playing back the generated answer; A means to save the interview contents as minutes, The system includes a means for storing audio data of the interview.

2. 10. The system of claim 1, further comprising means for providing an interface for a user to input configuration information.

3. 10. The system of claim 1, further comprising means for causing the generated virtual personality to use a natural language processing algorithm in generating answers to the user's questions.

Images