System

Abstract

A system is provided.SOLUTION: A system comprising: means for allowing a user to input a destination and a purpose of a call; means for encoding the input data and transmitting the encoded data to a server; means for receiving and decoding the transmitted data; means for generating natural conversation content based on the decoded data; means for executing a call using the generated conversation content; means for acquiring a result of the call; and means for feeding back the acquired result to the user.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] Currently, for many people, making a phone call poses a significant psychological hurdle, particularly in certain situations such as making restaurant reservations or speaking in a foreign language. Furthermore, for people with hearing impairments, making a phone call is a difficult task. Effective solutions to these problems are needed. [Means for solving the problem]

[0005] The present invention provides a means for a user to input the destination and purpose of a call, encode it, and send it to a server. The server decodes the received data and generates natural-sounding conversation content using a generative AI model. The generated conversation content is used to execute a call using AI voice synthesis, and the call results are obtained. Finally, the above-mentioned problem is solved by providing a system that includes a means for feeding back the obtained results to the user and displaying them in a visually intuitive manner.

[0006] "User" refers to an individual or organization that uses the system and inputs the destination and purpose of a call.

[0007] "Call destination" refers to the physical or virtual location of the person to whom a user places a call.

[0008] The "business" refers to the specific content or purpose that the user wants to accomplish over the phone.

[0009] A "means" refers to a method, device, or technique used to achieve a particular purpose.

[0010] "Encoding" refers to the process of converting data into a form that can be transmitted.

[0011] A "server" refers to a computer system that receives and processes data sent by users and provides new data or services based on that data.

[0012] "Decoding" refers to the process of returning received data to a form that can be parsed.

[0013] A "generative AI model" refers to an algorithm or software that generates natural-sounding conversational content based on user-specified content.

[0014] The "means for making a call" refers to the method or technology for actually making a call using the generated conversation content.

[0015] "AI speech synthesis" refers to artificial intelligence technology that automatically generates speech, and is a technology that generates human-like speech from text data.

[0016] "Results of the call" refers to the information or results obtained through the call.

[0017] "Feedback" refers to the process or method of returning call results to the user.

[0018] "Visually intuitive form" refers to a graphical user interface or display method that is easy for users to understand. [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 telephone answering system in which a user specifies a specific destination and purpose, and the system automatically answers the call. The program of this system works in conjunction with a server and a terminal, and generates natural conversation using a generative AI model based on user input data, and then conducts the call. Below, we will describe in detail the embodiments of the present invention.

[0041] 1. User Input

[0042] Terminal: The user uses a terminal such as a mobile phone or PC to input the destination of the call (e.g., the name of the restaurant) and the purpose of the call (e.g., the date and time of the reservation and the number of people). The input screen is designed to be intuitive and easy to use.

[0043] 2. Data Transmission

[0044] Terminal: Data entered by the user is encoded and securely sent to the server. By default, communication is encrypted to protect privacy.

[0045] 3. Data Receipt and Confirmation

[0046] Server: The server receives the data sent from the device, decodes it, and converts it into an analyzable format. It then checks the integrity and completeness of the data.

[0047] 4. Conversation Generation

[0048] Server: The server uses a generative AI model to generate natural-sounding dialogue based on user input, appropriate for the specific scenario.

[0049] 5. Make a call

[0050] Server: The server uses speech synthesis technology to convert the generated conversational text into natural-sounding speech. It then automatically calls the specified recipient. During the call, the AI ​​system responds appropriately based on the recipient's response.

[0051] 6. Get call results

[0052] Server: When the call is completed, the server obtains the call content and results (e.g., reservation confirmation information, confirmation items, etc.), which are then stored and managed in a database.

[0053] 7. Feedback Generation and Submission

[0054] Server: The server organizes the call results and creates feedback data for the user. This data is then encoded again and sent to the device.

[0055] 8. Results display

[0056] Terminal: The terminal decodes the received feedback data and displays it in a format that is intuitive to the user. For example, it displays specific information such as, "Your reservation has been confirmed. The date and time is June 15th at 7 PM for two people."

[0057] This eliminates the need for users to make phone calls themselves, reducing the psychological burden. It also enables people with hearing impairments to make phone calls without having to go through a proxy.

[0058] Specific examples

[0059] Reservation example

[0060] Suppose a user uses a terminal to request a reservation for "Restaurant X, June 15th, 7pm, for 2 people."

[0061] 1. User Input: The user enters information at the terminal.

[0062] 2. Data transmission: The device encodes the data and sends it to the server.

[0063] 3. Data reception and verification: The server receives the data, decodes it, and parses it.

[0064] 4. Conversation generation: The generative AI model generates the conversation sentence, "I would like to make a reservation for two people at 7 p.m. on June 15th."

[0065] 5. Call execution: The server makes the call and reads out the conversation generated by speech synthesis.

[0066] 6. Obtain call result: The server receives the answer from the restaurant and records the content.

[0067] 7. Feedback generation and transmission: Organize the call results and send them to the device.

[0068] 8. Display result: The device displays the feedback it received to the user. For example, it displays "Your reservation has been confirmed. We are waiting for two people at 7 PM on June 15th."

[0069] As described above, the system provided by the present invention automatically carries out the call content specified by the user and provides feedback on the results to the user. This lowers the psychological barrier to making a call and is particularly useful for people with hearing impairments or who have difficulty speaking in a foreign language.

[0070] The processing flow will be explained below.

[0071] Step 1:

[0072] User: Enter the destination and purpose of the call into the device's input screen. For example, enter information such as the restaurant name "Restaurant X," the reservation date and time "June 15th, 7 PM," and the number of people "2."

[0073] Step 2:

[0074] Terminal: Encodes the data entered by the user and converts it into a format that can be transmitted. For security reasons, it may encrypt the data.

[0075] Step 3:

[0076] Terminal: Sends the encoded data to the server using a secure protocol such as HTTPS.

[0077] Step 4:

[0078] Server: Receives data sent from the device and temporarily stores the received data in local storage.

[0079] Step 5:

[0080] Server: Decodes the received data and restores it to its original form. Through the decoding process, information entered by the user, such as the destination, purpose, date and time, and number of people, is obtained.

[0081] Step 6:

[0082] Server: Checks the integrity of the decoded data. Checks that all necessary information is present and that the format is correct. If there is a deficiency, generates an error message and prepares to send it to the terminal.

[0083] Step 7:

[0084] Server: If the data is correct, the generative AI model is invoked to generate natural-sounding conversational content based on the input data. For example, it generates a conversational sentence like, "Hello, is this Restaurant X? I'd like to make a reservation for two people at 7 p.m. on June 15th."

[0085] Step 8:

[0086] Server: Converts the generated conversation content from text to speech. It uses speech synthesis technology to generate natural-sounding speech.

[0087] Step 9:

[0088] Server: Automatically calls the specified phone number. Uses AI voice synthesis to make the call using the generated voice.

[0089] Step 10:

[0090] Server: Analyzes responses from the other party in real time during the call and responds appropriately. If necessary, generates new conversation content and converts it back into voice to continue the call.

[0091] Step 11:

[0092] Server: When the call ends, record the call result and information obtained from the other party. For example, obtain information such as "The reservation has been confirmed. Two people will be waiting for you at 7 PM on June 15th."

[0093] Step 12:

[0094] Server: Organizes the call results and generates data to provide feedback to the user. The feedback data includes the call results and confirmations.

[0095] Step 13:

[0096] Server: The generated feedback data is encoded and prepared for transmission to the device. Security measures such as encryption are again applied.

[0097] Step 14:

[0098] Terminal: Receives feedback data sent from the server. Decodes the received data and converts it into an analyzable format.

[0099] Step 15:

[0100] Terminal: Visually display feedback data to the user. For example, "Your reservation has been confirmed. Please go to Restaurant X on June 15th at 7pm for two people."

[0101] As described above, this system performs a series of processes based on the data entered by the user, handles the call on behalf of the user, and provides feedback on the results to the user.

[0102] Example 1

[0103] 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."

[0104] There is a need to eliminate the psychological burden of making phone calls and the difficulties faced by hearing-impaired users. In particular, for certain tasks such as making reservations or inquiries, a system is needed that allows users to achieve their goals through natural conversation without having to make a direct phone call.

[0105] 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.

[0106] In this invention, the server includes means for a user to input a destination and purpose of a call, means for encoding the input data and transmitting it to the server, means for receiving and decoding the transmitted data, means for generating natural conversation content using a generative AI model based on the decoded data, means for executing a call using the generated conversation content with speech synthesis technology, means for acquiring and storing the results of the call in a database, and means for encoding the acquired results and feeding them back to the user. This reduces the psychological burden on the user without the need to make a call directly, and makes it easy for even hearing-impaired users to make calls.

[0107] "User" refers to any individual or legal entity that uses the System.

[0108] "Terminal" refers to a device used by a user, such as a mobile phone, computer, or tablet.

[0109] "Call" refers to a telephone communication based on a destination and purpose.

[0110] "Destination" refers to the location or organization that the user specifies to place the call.

[0111] "Purpose" refers to the content or purpose that the user wants to achieve through the call.

[0112] "Encoding" refers to the process of encrypting or converting the format of data to be sent.

[0113] "Decoding" refers to the process of returning received encrypted data or format-converted data to its original format.

[0114] "Server" refers to a computer system that receives, processes, stores, and transmits data.

[0115] A "generative AI model" refers to an algorithm or model that uses artificial intelligence technology to generate natural-sounding conversational sentences.

[0116] "Speech synthesis technology" refers to the technology that converts text data into natural speech.

[0117] "Database" refers to a data storage system for storing obtained call results and other information.

[0118] "Feedback" refers to the process of communicating call results and other information to the user.

[0119] This invention is a telephone answering system in which a user specifies a specific destination and purpose, and the system automatically answers the call. This system works in cooperation with a server and terminals, and generates natural conversations using a generative AI model based on user input data, and then executes the call.

[0120] First, the user uses a device such as a mobile phone or PC to input the destination (e.g., restaurant) and the purpose of the call (e.g., reservation date and time and number of people). The input screen is designed to be intuitive and easy to use, with features such as drop-down menus and calendar selection functions.

[0121] The data entered by the user is then encoded on the terminal and sent securely to the server, for example using the HTTPS protocol for secure communication.

[0122] The server receives the data sent from the device, decodes it, and converts it into an analyzable format. After decoding, the integrity and completeness of the received data are checked, and invalid or incomplete data is filtered out.

[0123] Based on the decoded data, the server uses a generative AI model to generate natural-sounding conversations. This generative AI model has been pre-trained with a large amount of conversation data, allowing it to generate natural conversations for a variety of scenarios. For example, if a user requests a reservation for "Restaurant X, June 15th at 7 PM for two people," the generated conversation will be "I'd like to make a reservation for two people at 7 PM on June 15th."

[0124] The generated conversational text is converted into natural-sounding speech on the server using speech synthesis technology. This converted speech is then used to automatically place a call to the specified recipient. During the call, the AI ​​system analyzes the other party's response in real time and provides an appropriate reply. For example, in response to the inquiry "Is a reservation possible?", the system will ask the appropriate next question or confirm the answer depending on whether the other party answers "yes" or "no."

[0125] Once the call is completed, the server retrieves the call details and results, which include, for example, reservation confirmation information and confirmation items, and stores them in a database.

[0126] The acquired call results are organized, and data for providing feedback to the user is generated in the server. This feedback data is then encoded again and sent to the terminal.

[0127] The device decodes the received feedback data and displays it in a format that the user can intuitively understand, such as "Your reservation has been confirmed. The date and time is June 15th at 7 PM for two people."

[0128] As a concrete example, consider a scenario where a user requests a reservation for "Restaurant X, June 15th, 7pm, for two people" on a device. When the user enters information on the input screen and clicks the send button, the data is encoded and sent to the server. The server receives, decodes, and analyzes the data. The generative AI model then generates appropriate conversational text and makes a call using speech synthesis technology. The results of the call are obtained, sent to the device as feedback data, and displayed to the user.

[0129] Example prompt sentence:

[0130] "I'd like to make a reservation for two at Restaurant X on June 15th at 7pm."

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

[0132] Step 1:

[0133] The user uses a device such as a mobile phone or PC to input the destination and purpose of the call. Specifically, the user enters information such as the restaurant name, reservation date and time, and number of people on the device's input screen. For example, the user might enter, "I'd like to make a reservation for two people at Restaurant X on June 15th at 7 PM."

[0134] Input: Destination (e.g. restaurant name), purpose (e.g. reservation date and time and number of people)

[0135] Output: Data entered by the user

[0136] Step 2:

[0137] The terminal encodes the data entered by the user and sends it to the server. Specifically, the terminal encrypts the entered data and sends it to the server using a secure communication protocol (e.g., HTTPS). When the send button is clicked, the data is encoded in real time and sent to the server.

[0138] Input: Data entered by the user

[0139] Output: Encoded data

[0140] Step 3:

[0141] The server receives and decodes the data sent from the device. Since the received data is encrypted, the server decrypts it and converts it into an analyzable format. Here, the server checks the integrity and completeness of the data and filters out any invalid or incomplete data.

[0142] Input: Encoded data

[0143] Output: Decoded data

[0144] Step 4:

[0145] The server uses the decoded data to run a generative AI model and generate natural-sounding conversational sentences. The generative AI model has been trained with a large amount of conversational data in advance, allowing it to smoothly generate natural conversations that meet the user's requests. For example, the generated conversational sentence would be, "I'd like to make a reservation for two people at 7 p.m. on June 15th."

[0146] Input: Decoded data

[0147] Output: Generated dialogue

[0148] Step 5:

[0149] The server uses speech synthesis technology to convert the generated conversational text into natural-sounding speech and automatically calls the specified recipient. During the call, the AI ​​system analyzes the other party's response in real time and generates an appropriate response. For example, in response to the question "Is a reservation possible?", the next question or confirmation will be asked depending on the other party's answer of "yes" or "no."

[0150] Input: Generated conversation

[0151] Output: Synthesized speech

[0152] Step 6:

[0153] Once the call is completed, the server retrieves the call details and results, which include, for example, reservation confirmation information and confirmation items, and stores them in a database.

[0154] Input: Call result (audio data)

[0155] Output: Analyzed call results (text data)

[0156] Step 7:

[0157] The server generates data for providing feedback to the user based on the acquired call result, and the generated feedback data is encoded and transmitted to the terminal.

[0158] Input: Parsed call results

[0159] Output: Encoded feedback data

[0160] Step 8:

[0161] The device decodes the received feedback data and displays it in a format that is intuitive to the user. For example, it displays specific information such as, "Your reservation has been confirmed. It is for 7 PM on June 15th, for two people."

[0162] Input: Encoded feedback data

[0163] Output: Decoded feedback data (for display)

[0164] The above is the specific processing flow of this system.

[0165] (Application example 1)

[0166] 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."

[0167] In today's world, many people feel a psychological burden when making phone calls themselves, and this barrier is even greater for those with hearing impairments or who have difficulty speaking a foreign language. Furthermore, there are problems with not being able to easily respond to sudden reservations or confirmations. A system that can solve these problems is needed.

[0168] 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.

[0169] In this invention, the server includes a means for a user to input the destination and purpose of the call, a means for receiving, decoding, and analyzing the transmitted data, a means for generating natural conversation content using a generative AI model, a means for executing an automated call, a means for obtaining the call result and providing feedback to the user, and a means for displaying the feedback. This allows the user to easily and quickly make call reservations or inquiries using a smartphone and intuitively understand the results.

[0170] The "user input means" is a means for the user to input the destination and purpose of the call.

[0171] The "data transmission means" is a means for encoding input data and transmitting it to the server.

[0172] "Data receiving means" refers to means for receiving and decoding transmitted data.

[0173] The "conversation generation means" is a means for generating natural conversation content based on the decoded data.

[0174] The "call execution means" is a means for executing a call using the generated conversation content.

[0175] The "result acquisition means" is a means for acquiring the result of a call.

[0176] The "feedback means" is a means for providing feedback of the obtained results to the user.

[0177] The "display means" is a means for displaying feedback to the user.

[0178] A "smartphone" is a portable information terminal that allows users to enter data and check results.

[0179] A "generative AI model" is an artificial intelligence model that generates natural conversation content based on input data.

[0180] A "physical store application" is a smartphone application that automatically handles physical store reservations and inquiries.

[0181] "Speech synthesis" is a technology that converts conversation content generated using AI technology into natural-sounding speech.

[0182] This invention is a system that uses a smartphone application for brick-and-mortar stores to make reservations and inquiries without the user having to make a phone call. In an embodiment of the invention, a server, a terminal (smartphone), a generative AI model, a voice synthesis technology, and a call API work together.

[0183] Hardware and software used

[0184] Smartphone: A device on which users can input information and check the results. A dedicated application is installed on the smartphone.

[0185] Server: A device that receives and analyzes data, runs generative AI models, manages calls, and provides feedback on results. The server software uses Node.js, Express, Python, GPT-4 API, and Flask.

[0186] Generative AI model: An artificial intelligence model for generating natural conversation content. Specifically, we use GPT-4.

[0187] Call API: An API for making automated calls. Uses the Twilio API.

[0188] Database: A database for storing call logs and results. MongoDB is used.

[0189] System Operation Overview

[0190] 1. User Input

[0191] The smartphone application allows users to input the destination of the call (e.g., the name of the restaurant) and the purpose of the call (e.g., the date and time of the reservation and the number of people). The application is designed to be intuitive and easy to use.

[0192] 2. Data Transmission

[0193] The smartphone encodes the entered data and sends it securely to the server, where the communication is encrypted to protect privacy.

[0194] 3. Data Receipt and Confirmation

[0195] The server receives the data sent by the smartphone, decodes it, and converts it into an analyzable format, after which it checks the data for consistency and integrity.

[0196] 4. Conversation Generation

[0197] The server uses a generative AI model (GPT-4) to generate natural-sounding conversational sentences based on user-specified content. Prompt sentences are used in this process.

[0198] Example prompt sentence:

[0199] "Cafe Z, please generate a conversation to confirm whether a reservation for two people can be made on August 10th at 2pm."

[0200] 5. Make a call

[0201] The server uses speech synthesis technology to convert the generated conversation into natural-sounding speech, then automatically calls the specified recipient using the Twilio API and executes the call.

[0202] 6. Get call results

[0203] Once the call is complete, the Twilio API sends the call details and results to the server, which analyzes the information and stores it in a database.

[0204] 7. Feedback Generation and Submission

[0205] The server organizes the call results and generates data to provide feedback to the user. This data is then re-encoded and sent to the smartphone.

[0206] 8. Results display

[0207] The smartphone decodes the received feedback data and displays it in a format that is easy for the user to understand. For example, it may display specific information such as, "Your reservation has been confirmed. We are waiting for two people at 2:00 PM on August 10th."

[0208] As a concrete example, when a user enters "Cafe Z, August 10th, 2pm, 2 people" into their smartphone, the server generates a conversation saying "Is a reservation for 2 people possible on August 10th at 2pm?", and the Twilio API automatically calls the cafe to confirm the reservation. The result is displayed on the smartphone as "Reservation confirmed." This series of steps reduces the psychological burden on the user, and allows even users who are not good at making phone calls or who are hearing impaired to easily make reservations.

[0209] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0210] Step 1:

[0211] The user launches the smartphone application and enters the call destination (e.g., the name of the restaurant) and the purpose of the call (e.g., the date and time of the reservation and the number of people). The entered data is encoded in JSON format. Input: Restaurant name, reservation date and time, and number of people. Output: Encoded JSON data.

[0212] Step 2:

[0213] The device sends the encoded data to the server via HTTPS. Communication is encrypted to protect privacy. Input: Encoded JSON data. Output: Encrypted data packet.

[0214] Step 3:

[0215] The server receives the data sent from the terminal, decrypts it, and converts it into an analyzable format. During this process, it checks the integrity and completeness of the data. Input: Encrypted data packet. Output: Data in an analyzable format.

[0216] Step 4:

[0217] The server sends prompts to the generative AI model (GPT-4) based on the decoded data to generate natural-sounding conversational sentences. During this process, the user's input is given to the model as a prompt. Input: Parsed data and prompt. Output: Generated conversational sentences.

[0218] Step 5:

[0219] The generated conversational text is converted into natural-sounding speech on the server using speech synthesis technology (e.g., Amazon Polly, Google Text-to-Speech, etc.). Input: Generated conversational text. Output: Synthesized speech data.

[0220] Step 6:

[0221] The server automatically calls the specified recipient using the Twilio API and executes the conversation using synthesized voice. During the call, it analyzes the recipient's responses in real time and generates appropriate responses. Input: Recipient's phone number and voice data. Output: Call execution and real-time response data.

[0222] Step 7:

[0223] When the call is completed, the Twilio API sends the call details and results (e.g., reservation confirmation information) to the server. The server analyzes the details and stores them in a database (e.g., MongoDB). Input: Call result data. Output: Analyzed reservation confirmation information and its storage.

[0224] Step 8:

[0225] The server organizes the acquired call results and generates data to provide feedback to the user. This data is then encoded again and sent to the device. Input: Call result data. Output: Encoded data for feedback.

[0226] Step 9:

[0227] The smartphone device decodes the received feedback data and displays it in a format that the user can intuitively understand. For example, specific information such as "The reservation has been confirmed. The date and time is August 10th at 2pm for two people" is displayed. Input: Encoded data for feedback. Output: Specific reservation information displayed to the user.

[0228] 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.

[0229] The present invention relates to a telephone answering system in which a user specifies a specific destination and purpose, and the system automatically handles the call, while also incorporating an emotion engine that recognizes the user's emotions. The system's program works in conjunction with a server and terminals, and generates natural conversations using a generative AI model based on the user's input data and emotions, and then carries out the call. The following describes in detail an embodiment of the present invention.

[0230] 1. User Input

[0231] Terminal: The user uses a terminal such as a mobile phone or PC to input the destination of the call (e.g., the name of the restaurant) and the purpose of the reservation (e.g., the date and time of the reservation and the number of people). The input screen is designed to be intuitive and easy to use, and a function that recognizes the user's emotions has been added.

[0232] 2. User Emotion Recognition

[0233] Terminal: While the user is typing, the terminal's built-in emotion engine recognizes emotions from the user's tone of voice, facial expressions, text content, etc. This emotion data is also used to generate the call content.

[0234] 3. Data Transmission

[0235] Terminal: The data and emotion data entered by the user are encoded and securely transmitted to the server. Encrypted communication is used to protect privacy.

[0236] 4. Data Receipt and Confirmation

[0237] Server: The server receives the data sent by the device, decodes it, and converts it into an analyzable format. It then checks the integrity and completeness of the data.

[0238] 5. Conversation Generation

[0239] Server: The server uses a generative AI model and emotion engine to generate natural-sounding conversations based on the user's specified content and emotions. For example, if the server recognizes that the user is feeling nervous, the generated conversations will have a relaxing tone.

[0240] 6. Make a call

[0241] Server: Converts the generated conversation content from text to speech. It uses speech synthesis technology to generate natural-sounding speech. It then automatically calls the specified recipient. During the call, the AI ​​system responds appropriately based on the recipient's responses, and uses an emotion engine to generate responses that reflect the user's emotions if necessary.

[0242] 7. Get call results

[0243] Server: When the call is completed, the server obtains the call content and results (e.g., reservation confirmation information, confirmation items, etc.), which are then stored and managed in a database.

[0244] 8. Feedback Generation and Submission

[0245] Server: The server organizes the call results and creates feedback data for the user. This data is then encoded again and sent to the device.

[0246] 9. Results display

[0247] Terminal: The terminal decodes the received feedback data and displays it in a format that is intuitive to the user. For example, it displays specific information such as, "Your reservation has been confirmed. The date and time is June 15th at 7 PM for two people."

[0248] Specific examples

[0249] Reservation example

[0250] Suppose a user uses a terminal to request a reservation for "Restaurant X, June 15th, 7pm, for 2 people."

[0251] 1. User Input: While the user is inputting information into the device, the emotion engine recognizes tense emotions.

[0252] 2. Data transmission: The device encodes the data and emotion data and sends them to the server.

[0253] 3. Data reception and verification: The server receives the data and emotion data, decodes it, and analyzes it.

[0254] 4. Conversation generation: The generative AI model and emotion engine generate the following conversational sentence in a neutral tone: "I'd like to make a reservation for two people at 7pm on June 15th."

[0255] 5. Call execution: The server makes a call and reads out the conversation generated by speech synthesis. It also generates a response to the other party's response that reflects the user's emotions.

[0256] 6. Obtain call result: The server receives the answer from the restaurant and records the content.

[0257] 7. Feedback generation and transmission: Organize the call results and send them to the device.

[0258] 8. Display result: The device displays the feedback it received to the user. For example, it displays "Your reservation has been confirmed. We are waiting for two people at 7 PM on June 15th."

[0259] As described above, the system provided by the present invention automatically handles the call content specified by the user and uses an emotion engine to respond in a way that reflects the user's emotions, providing a more natural and comfortable call experience. This lowers the psychological barrier to making a call and is particularly useful for people with hearing impairments and those in stressful situations.

[0260] The processing flow will be explained below.

[0261] Step 1:

[0262] User: Enter the destination and purpose of the call into the input screen of the device. For example, enter information such as "Restaurant X, June 15th, 7 PM, 2 people."

[0263] Step 2:

[0264] Terminal: While accepting user input, the emotion engine analyzes the user's voice tone, facial expressions, and input content to detect the user's emotional state.

[0265] Step 3:

[0266] Terminal: The input data and detected emotion data are encoded and sent to the server using encrypted communication.

[0267] Step 4:

[0268] Server: Receives the encoded data sent from the device. The received data is first stored in secure local storage.

[0269] Step 5:

[0270] Server: Decodes the received data and extracts the user's destination, purpose, and emotion data. It checks the data for consistency and generates an error message if there are any errors.

[0271] Step 6:

[0272] Server: Calls up a generative AI model based on the decoded data and generates natural conversational sentences that incorporate the user's emotional data. For example, if the user is nervous, it adds phrases to help them relax.

[0273] Step 7:

[0274] Server: Based on the generated conversational text, a natural voice is generated using speech synthesis technology, with a tone that reflects the user's emotions.

[0275] Step 8:

[0276] Server: Automatically calls the specified destination phone number. When the call starts, the generated voice is spoken to the other party.

[0277] Step 9:

[0278] Server: Analyzes responses from the other party in real time during the call and generates appropriate responses. Here too, the emotion engine generates responses that reflect the user's emotions based on the other party's responses.

[0279] Step 10:

[0280] Server: Once the call is over, record the outcome of the call, for example, whether the reservation was confirmed or not, and if there are any further questions.

[0281] Step 11:

[0282] Server: Organizes the call results and generates feedback data to the user. This feedback data is also encoded.

[0283] Step 12:

[0284] Server: Sends the generated feedback data to the terminal using encrypted communication.

[0285] Step 13:

[0286] Terminal: Receives feedback data sent from the server. Decodes the received data and converts it into an analyzable format.

[0287] Step 14:

[0288] Terminal: Visually display feedback information to the user, for example, "Your reservation has been confirmed. Please go to Restaurant X on June 15th at 7pm for two people."

[0289] As described above, the system of the present invention recognizes the user's emotions and generates natural conversation content and voice that reflects those emotions, making call answering more comfortable. This allows users in particularly stressful situations or with hearing impairments to make phone calls with peace of mind.

[0290] Example 2

[0291] 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."

[0292] Conventional telephone answering systems often cause users to feel nervous or anxious when making a call, making it difficult for them to make a smooth call, especially for those with hearing impairments or in situations where they feel psychological pressure. Furthermore, the lack of naturalness in the call content can cause discomfort to the other party, which can sometimes prevent users from achieving their intended purpose. The present invention aims to solve these problems and provide a more natural and emotionally sensitive call experience.

[0293] The identification process by the identification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means. In this invention, the server includes means for a user to input a destination and purpose of a call, means for encoding the input data and the user's emotional data and transmitting them to the server, means for receiving and decoding the transmitted data, means for generating natural conversation content using a generative AI model based on the decoded data and emotional data, means for converting the generated conversation content into voice using AI speech synthesis and executing the call, means for generating an appropriate response based on the other party's response during the call, means for acquiring the result of the call, and means for feeding back the acquired result to the user. This makes it possible to realize a natural and smooth call while taking the user's emotions into consideration, and to reliably achieve the purpose of the call.

[0294] A "user" is a person who utilizes the system to input the destination and purpose of a call.

[0295] A "call destination" is the person or location to which a user wishes to place a call.

[0296] The "matters" are the contents or purpose that the user wants to convey through the call.

[0297] A "terminal" is a device used by a user to input the destination and purpose of a call, and includes a mobile phone, a personal computer, and the like.

[0298] "Emotion data" is data that represents the user's psychological state, obtained from the user's tone of voice, facial expression, and input text content.

[0299] "Encoding" is the process of converting data to be transmitted into a specific format.

[0300] A "server" is a device that receives and processes data sent from a terminal.

[0301] "Decoding" is the process of converting received data back into its original format.

[0302] A "generative AI model" is an algorithm or program that uses artificial intelligence technology to generate natural-sounding conversation content based on input data.

[0303] "AI voice synthesis" is a technology that converts text data into voice data.

[0304] A "call" is an act of actually having a conversation based on the destination and purpose input by the user.

[0305] A "response" is a reply or response received from the other party during a call.

[0306] "Feedback" is information that reports the results of a call to the user.

[0307] This invention is a telephone answering system in which a user specifies a specific destination and purpose, and the system automatically answers the call. The system also incorporates an emotion engine that recognizes the user's emotions, and the server and terminals work together. Detailed embodiments for implementing this system are described below.

[0308] 1. User Input

[0309] Device: The user uses a device such as a mobile phone or PC to input the destination (e.g., restaurant name) and purpose (e.g., reservation date and time and number of people). The input interface is designed to be intuitive for users, with features such as check boxes and drop-down menus. In addition, the microphone and camera are activated when inputting information, and the device is equipped with a function that recognizes the user's tone of voice and facial expressions in real time.

[0310] 2. Emotion recognition

[0311] Terminal: While the user is entering information, the emotion engine analyzes voice tone, facial expression recognition, and the input text content to detect the user's emotional state. For example, it determines whether the user is nervous based on the intonation of their voice or facial expression. This function generates the user's emotional data.

[0312] 3. Data Transmission

[0313] Terminal: The data and emotion data entered by the user are encoded and securely transmitted to the server using encrypted communication technology such as HTTPS, preventing data leakage and degradation.

[0314] 4. Data Receipt and Confirmation

[0315] Server: Receives the data sent from the device, decodes it, and converts it into an analyzable format. The server checks the consistency and integrity of the data to ensure it has not been tampered with. It also calculates checksums and verifies the data format.

[0316] 5. Conversation Generation

[0317] Server: Using a generative AI model, the server generates natural-sounding conversational sentences based on the content and emotional data specified by the user. For example, if the server detects that the user is nervous, it generates a conversational sentence with a relaxed tone, such as "Please make a reservation for two people at 7 p.m. on June 15th." The generative AI model uses the prompt to generate the conversational sentence.

[0318] 6. Make a call

[0319] Server: Converts the generated conversation content from text to speech. It uses speech synthesis technology (e.g., Google Text-to-Speech) to generate natural-sounding speech and automatically calls the specified recipient. During the call, the conversational AI generates appropriate responses in real time based on the recipient's responses, and uses an emotion engine to respond in a way that reflects the user's emotions.

[0320] 7. Get call results

[0321] Server: When the call is completed, the call content and results (e.g., reservation confirmation information, confirmation items, etc.) are obtained and saved in a database. This information can be referenced later, improving user convenience.

[0322] 8. Feedback Generation and Submission

[0323] Server: Organizes the call results and generates data to provide feedback to the user. This is then encoded again and securely sent to the device using HTTPS.

[0324] 9. Results display

[0325] Terminal: Decodes the received feedback data and displays it in a format that is easy for the user to understand. For example, it displays specific information such as "The reservation has been confirmed. It will be made on June 15th at 7pm for two people." It is also possible to notify the user of the results using a voice readout function.

[0326] Specific examples

[0327] A specific example will be given in which a user uses a terminal to request a reservation for "Restaurant X, June 15th, 7pm, for 2 people."

[0328] 1. User input: The user enters "Restaurant X, June 15th, 7pm, 2 people" into the terminal, and the emotion engine recognizes the tension.

[0329] 2. Data transmission: The device encodes the data and emotion data and sends them to the server.

[0330] 3. Data reception and verification: The server receives the data, decodes it, and verifies its integrity.

[0331] 4. Conversation generation: The generative AI model generates the following conversation in a neutral tone: "I'd like to make a reservation for two people at 7 p.m. on June 15th."

[0332] 5. Call execution: The server makes the call and reads out the conversation generated by speech synthesis technology. Depending on the other party's response, an appropriate response reflecting the other party's emotions is given.

[0333] 6. Obtain call result: The server receives a confirmation of the reservation from the restaurant and records the details.

[0334] 7. Feedback generation and transmission: Organize the call results and send them to the device.

[0335] 8. Displaying the result: The terminal displays the result to the user: "Reservation confirmed. Two guests will be waiting at 7 PM on June 15th."

[0336] In this way, the system of the present invention provides a natural calling experience that takes into account the user's emotions, enabling the purpose of the call to be achieved efficiently.

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

[0338] Step 1: User Input

[0339] Device: The user enters the call destination (e.g., restaurant name) and purpose (e.g., reservation date and time and number of people) on a device such as a mobile phone or PC. The input interface is equipped with check boxes and drop-down menus, and is designed to allow users to operate it intuitively. Input data includes the destination "Restaurant X," the date and time "June 15th, 7:00 PM," and the number of people "2." In addition, the microphone and camera are activated to collect the user's voice tone and facial expressions.

[0340] Input: Destination, purpose (reservation date and time, number of people)

[0341] Output: Input data, emotion data

[0342] Step 2: Emotion Recognition

[0343] Terminal: The emotion engine generates emotion data by analyzing the user's voice tone, facial expression recognition, and input text content. For example, it determines whether the user is nervous based on the intonation of their voice and facial expression. This provides emotion data that indicates the user's psychological state.

[0344] Input: Voice tone, facial expression data, input text

[0345] Output: Emotion data

[0346] Step 3: Send data

[0347] Terminal: Input data and emotion data are encoded and sent securely to the server using encryption technology (e.g., HTTPS). Data is transferred in a manner that prevents degradation and leakage.

[0348] Input: Input data, emotion data

[0349] Output: Encrypted data

[0350] Step 4: Data Receipt and Verification

[0351] Server: Receives encrypted data sent from the device. Decodes the received data and converts it into an analyzable format. Then, calculates checksums and verifies the data format to ensure data integrity and completeness.

[0352] Input: Encrypted data

[0353] Output: Decoded data

[0354] Step 5: Conversation generation

[0355] Server: Using a generative AI model, the server generates natural-sounding conversational sentences based on the decoded input data and emotional data. For example, if the user is recognized as nervous, the server generates a conversational sentence in a relaxed tone, such as "I'd like to make a reservation for two people at 7 p.m. on June 15th." The server uses a prompt sentence.

[0356] Input: Decoded data, emotion data

[0357] Output: Conversation

[0358] Step 6: Make the call

[0359] Server: Converts the generated conversational text from text to speech. It uses speech synthesis technology (e.g., Google Text-to-Speech) to generate natural-sounding speech and automatically calls the specified recipient. During the call, the conversational AI generates appropriate responses in real time based on the recipient's responses, and the emotion engine responds by reflecting the user's emotions.

[0360] Input: Conversation

[0361] Output: Audio data, call answering

[0362] Step 7: Get call results

[0363] Server: Once the call is completed, the server obtains the call details and results (e.g., reservation confirmation information, confirmation items, etc.). The obtained data is stored in a database.

[0364] Input:Call Answer

[0365] Output: Call result data

[0366] Step 8: Generate and send feedback

[0367] Server: Organizes the acquired call results and generates data to provide feedback to the user. This feedback data is then re-encoded and sent to the device using encryption technology.

[0368] Input: Call result data

[0369] Output: Feedback data

[0370] Step 9: View the results

[0371] Terminal: Decodes the received feedback data and displays the results in a format that is easy for the user to understand. For example, specific information such as "Reservation confirmed. June 15th at 7pm for two people" is displayed on the terminal screen. Voice notification is also possible.

[0372] Input: Feedback data

[0373] Output: Display result

[0374] (Application example 2)

[0375] 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."

[0376] In autonomous vehicles, users are expected to be able to comfortably use various services (restaurant reservations, hotel reservations, medical appointments, etc.) from inside the vehicle, but there is a lack of a system that automatically generates and executes natural responses based on input information that reflect the user's emotions.In addition, since calls that ignore the user's emotions can be unnatural and stressful, it is necessary to provide natural conversations that take the user's emotions into consideration.

[0377] 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 a user to input the destination and purpose of the call, means for recognizing emotions from the user's tone of voice, facial expression, text content, etc., means for encoding the input data and emotional data and transmitting them to the server, means for receiving and decoding the transmitted data and emotional data, means for using a generative AI model to generate natural conversation content based on the decoded data, means for adjusting the tone of the conversation based on the user's emotional data, means for conducting a call using the generated conversation content, means for acquiring the results of the call, and means for feeding back the acquired results to the user. This enables comfortable service use in an autonomous vehicle and realizes natural conversation responses that correspond to the user's emotions.

[0378] "Means for users to input the destination and purpose of the call" refers to the means by which users use a terminal such as a mobile phone or computer to input the destination (e.g., restaurant, hotel, medical institution, etc.) and the purpose (e.g., reservation date and time, number of people, etc.).

[0379] The "means for recognizing emotions" refers to a means for automatically recognizing emotions from the user's tone of voice, facial expressions, text content, etc., using an emotion engine or sensor installed in the device.

[0380] The "means for encoding data and emotion data and transmitting them to the server" refers to a means for encoding (encrypting) the destination and purpose data entered by the user and the emotion data obtained from the emotion recognition means and transmitting them securely to the server.

[0381] The "means for receiving and decoding" refers to the means by which the server receives the data and emotion data sent from the terminal and decodes (decodes) it into an analyzable format.

[0382] "Means for using a generative AI model" refers to means by which the server generates natural conversation content using a generative AI model based on data and emotional data sent by the user.

[0383] The "means for adjusting the tone of the conversation" is a means for adjusting the tone of the conversation (e.g., relaxed tone, gentle tone, etc.) based on the user's emotional data in the generated conversation content.

[0384] The "means for executing a call using the conversation content" is a means for converting the generated conversation content from text to voice and automatically making a call to a designated recipient.

[0385] The "means for obtaining the results of a call" refers to the means by which the server obtains the contents of the call and its results (e.g., reservation confirmation information, confirmation items, etc.) when the call is completed.

[0386] The "means for providing feedback to the user" is a means for encoding data to feed back the acquired call result to the user, transmitting the data to the terminal, and displaying the data in a form that the user can intuitively understand.

[0387] This invention describes a specific embodiment of a voice assistant application installed in an autonomous vehicle. This application allows the user to specify the destination and purpose of a reservation from inside the vehicle, and the system automatically handles the call. Furthermore, it can recognize the user's emotions and generate natural conversations using a generative AI model.

[0388] First, the user uses the voice assistant app in the autonomous vehicle to specify the destination (e.g., restaurant, hotel, medical institution, etc.) and purpose (e.g., reservation date and time, number of people, etc.). This input is converted into text using voice recognition technology. For voice recognition, Google Speech Recognition API, for example, is used.

[0389] Next, the emotion engine installed on the device recognizes emotions from the voice tone, facial expressions, text content, etc. while the user is typing. For emotion recognition, for example, the Python library "Emotion Recognition" is used.

[0390] The input data and emotion data are encoded (encrypted) and securely transmitted to the server. This communication is via the Internet and uses encryption protocols (e.g., TLS / SSL).

[0391] The server receives the data and emotion data sent from the device and decodes it. After decoding, the server uses a generative AI model (such as GPT-3) to generate natural-sounding conversation content based on the content and emotion specified by the user. The tone of the conversation is also adjusted based on the emotion data. For example, if the user is nervous, a relaxing tone of voice will be generated.

[0392] The generated conversation is converted into natural-sounding speech using speech synthesis technology (such as the Google Text-to-Speech API). The call is then automatically placed to the specified recipient. During the call, the AI ​​system responds appropriately based on the recipient's response, and uses an emotion engine to generate responses that reflect the user's emotions, if necessary.

[0393] Once the call is completed, the server obtains the results of the call (e.g., reservation confirmation information, confirmation items, etc.), stores them in a database, and manages them. This information is then encoded and sent back to the device.

[0394] Finally, the device decodes the received feedback data and displays it in a format that is intuitive to the user, such as "Your reservation has been confirmed. The date and time is June 15th at 7 PM for two people."

[0395] Examples of specific prompts include:

[0396] User: "I'd like to make a reservation for two at Restaurant X on June 15th at 7pm."

[0397] Input to AI model: "Reservation call - user is nervous. Please speak in a relaxed tone."

[0398] Generated dialogue: "Hello, Restaurant X. I'd like to make a reservation for two people on June 15th at 7pm." "Yes, I understand. We look forward to seeing you."

[0399] In this way, the system of the present invention enables comfortable use of services inside an autonomous vehicle and is capable of providing natural conversational responses that correspond to the user's emotions.

[0400] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[0401] Step 1:

[0402] The user inputs the destination and purpose of the call. Using the voice assistant app in the autonomous vehicle, the user specifies the destination (e.g., restaurant, hotel, medical institution, etc.) and purpose (e.g., reservation date and time, number of people, etc.). This input is converted into text using voice recognition technology (e.g., Google Speech Recognition API). The input data is obtained in the form of text: "destination" and "purpose."

[0403] Step 2:

[0404] The device recognizes emotions from the user's voice tone, facial expressions, text content, etc. The emotion engine (e.g., Emotion Recognition library) installed on the device analyzes the voice tone while the user is typing and recognizes the user's emotions in real time. Emotion data is obtained in the form of "emotional state."

[0405] Step 3:

[0406] The device encodes the input data and emotion data and sends them to the server. The encoding (encryption) process uses, for example, the TLS / SSL protocol. The encoded data is securely sent to the server. The input data and emotion data are sent as a single encrypted packet.

[0407] Step 4:

[0408] The server receives and decodes the transmitted data and emotional data. The server receives the encrypted data transmitted from the device and decodes it into an analyzable format. This allows the "destination," "message," and "emotional state" data to arrive at the server.

[0409] Step 5:

[0410] The server uses a generative AI model (e.g., GPT-3) based on the decoded data to generate natural-sounding conversation content. The server inputs the "destination," "purpose," and "emotional state" data into the generative AI model to generate appropriate conversation content. The tone of the conversation is adjusted based on the user's emotional state. The output is obtained as "conversation content."

[0411] Step 6:

[0412] The server converts the generated conversation content into natural-sounding speech using speech synthesis technology (e.g., Google Text-to-Speech API). The server then converts the text-format "conversation content" into voice data and prepares to make a call to the specified recipient. The output is obtained as voice data.

[0413] Step 7:

[0414] The server automatically calls the specified recipient. During the call, the AI ​​system responds appropriately based on the recipient's response and uses an emotion engine to generate a response that reflects the user's emotions. Emotion recognition continues as the conversation progresses, and any necessary corrections are made. Data is exchanged in real time.

[0415] Step 8:

[0416] Once the call is complete, the server obtains the call results (e.g., reservation confirmation information, confirmation items, etc.). After the call ends, the server collects various confirmation data and stores it in a database that manages it. The output is obtained as "call result data."

[0417] Step 9:

[0418] The server organizes the call results it has obtained and creates data to provide feedback to the user. It re-encodes (encrypts) the call result data and sends it to the device. The encoded feedback data is then securely sent to the device.

[0419] Step 10:

[0420] The device decodes the received feedback data and displays it in a format that is intuitively understandable to the user. The decoded feedback content is displayed to the user as specific information, such as "The reservation has been confirmed. The date and time is June 15th at 7 PM for two people."

[0421] 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.

[0422] 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.

[0423] 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.

[0424] [Second embodiment]

[0425] FIG. 3 shows an example of the configuration of a data processing system 210 according to the second embodiment.

[0426] 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.

[0427] 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).

[0428] 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.

[0429] 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.

[0430] 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).

[0431] 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.

[0432] 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.

[0433] 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.

[0434] 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.

[0435] 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.

[0436] 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."

[0437] The present invention relates to a telephone answering system in which a user specifies a specific destination and purpose, and the system automatically answers the call. The program of this system works in conjunction with a server and a terminal, and generates natural conversation using a generative AI model based on user input data, and then conducts the call. Below, we will describe in detail the embodiments of the present invention.

[0438] 1. User Input

[0439] Terminal: The user uses a terminal such as a mobile phone or PC to input the destination of the call (e.g., the name of the restaurant) and the purpose of the call (e.g., the date and time of the reservation and the number of people). The input screen is designed to be intuitive and easy to use.

[0440] 2. Data Transmission

[0441] Terminal: Data entered by the user is encoded and securely sent to the server. By default, communication is encrypted to protect privacy.

[0442] 3. Data Receipt and Confirmation

[0443] Server: The server receives the data sent from the device, decodes it, and converts it into an analyzable format. It then checks the integrity and completeness of the data.

[0444] 4. Conversation Generation

[0445] Server: The server uses a generative AI model to generate natural-sounding dialogue based on user input, appropriate for the specific scenario.

[0446] 5. Make a call

[0447] Server: The server uses speech synthesis technology to convert the generated conversational text into natural-sounding speech. It then automatically calls the specified recipient. During the call, the AI ​​system responds appropriately based on the recipient's response.

[0448] 6. Get call results

[0449] Server: When the call is completed, the server obtains the call content and results (e.g., reservation confirmation information, confirmation items, etc.), which are then stored and managed in a database.

[0450] 7. Feedback Generation and Submission

[0451] Server: The server organizes the call results and creates feedback data for the user. This data is then encoded again and sent to the device.

[0452] 8. Results display

[0453] Terminal: The terminal decodes the received feedback data and displays it in a format that is intuitive to the user. For example, it displays specific information such as, "Your reservation has been confirmed. The date and time is June 15th at 7 PM for two people."

[0454] This eliminates the need for users to make phone calls themselves, reducing the psychological burden. It also enables people with hearing impairments to make phone calls without having to go through a proxy.

[0455] Specific examples

[0456] Reservation example

[0457] Suppose a user uses a terminal to request a reservation for "Restaurant X, June 15th, 7pm, for 2 people."

[0458] 1. User Input: The user enters information at the terminal.

[0459] 2. Data transmission: The device encodes the data and sends it to the server.

[0460] 3. Data reception and verification: The server receives the data, decodes it, and parses it.

[0461] 4. Conversation generation: The generative AI model generates the conversation sentence, "I would like to make a reservation for two people at 7 p.m. on June 15th."

[0462] 5. Call execution: The server makes the call and reads out the conversation generated by speech synthesis.

[0463] 6. Obtain call result: The server receives the answer from the restaurant and records the content.

[0464] 7. Feedback generation and transmission: Organize the call results and send them to the device.

[0465] 8. Display result: The device displays the feedback it received to the user. For example, it displays "Your reservation has been confirmed. We are waiting for two people at 7 PM on June 15th."

[0466] As described above, the system provided by the present invention automatically carries out the call content specified by the user and provides feedback on the results to the user. This lowers the psychological barrier to making a call and is particularly useful for people with hearing impairments or who have difficulty speaking in a foreign language.

[0467] The processing flow will be explained below.

[0468] Step 1:

[0469] User: Enter the destination and purpose of the call into the device's input screen. For example, enter information such as the restaurant name "Restaurant X," the reservation date and time "June 15th, 7 PM," and the number of people "2."

[0470] Step 2:

[0471] Terminal: Encodes the data entered by the user and converts it into a format that can be transmitted. For security reasons, it may encrypt the data.

[0472] Step 3:

[0473] Terminal: Sends the encoded data to the server using a secure protocol such as HTTPS.

[0474] Step 4:

[0475] Server: Receives data sent from the device and temporarily stores the received data in local storage.

[0476] Step 5:

[0477] Server: Decodes the received data and restores it to its original form. Through the decoding process, information entered by the user, such as the destination, purpose, date and time, and number of people, is obtained.

[0478] Step 6:

[0479] Server: Checks the integrity of the decoded data. Checks that all necessary information is present and that the format is correct. If there is a deficiency, generates an error message and prepares to send it to the terminal.

[0480] Step 7:

[0481] Server: If the data is correct, the generative AI model is invoked to generate natural-sounding conversational content based on the input data. For example, it generates a conversational sentence like, "Hello, is this Restaurant X? I'd like to make a reservation for two people at 7 p.m. on June 15th."

[0482] Step 8:

[0483] Server: Converts the generated conversation content from text to speech. It uses speech synthesis technology to generate natural-sounding speech.

[0484] Step 9:

[0485] Server: Automatically calls the specified phone number. Uses AI voice synthesis to make the call using the generated voice.

[0486] Step 10:

[0487] Server: Analyzes responses from the other party in real time during the call and responds appropriately. If necessary, generates new conversation content and converts it back into voice to continue the call.

[0488] Step 11:

[0489] Server: When the call ends, record the call result and information obtained from the other party. For example, obtain information such as "The reservation has been confirmed. Two people will be waiting for you at 7 PM on June 15th."

[0490] Step 12:

[0491] Server: Organizes the call results and generates data to provide feedback to the user. The feedback data includes the call results and confirmations.

[0492] Step 13:

[0493] Server: The generated feedback data is encoded and prepared for transmission to the device. Security measures such as encryption are again applied.

[0494] Step 14:

[0495] Terminal: Receives feedback data sent from the server. Decodes the received data and converts it into an analyzable format.

[0496] Step 15:

[0497] Terminal: Visually display feedback data to the user. For example, "Your reservation has been confirmed. Please go to Restaurant X on June 15th at 7pm for two people."

[0498] As described above, this system performs a series of processes based on the data entered by the user, handles the call on behalf of the user, and provides feedback on the results to the user.

[0499] Example 1

[0500] 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."

[0501] There is a need to eliminate the psychological burden of making phone calls and the difficulties faced by hearing-impaired users. In particular, for certain tasks such as making reservations or inquiries, a system is needed that allows users to achieve their goals through natural conversation without having to make a direct phone call.

[0502] 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.

[0503] In this invention, the server includes means for a user to input a destination and purpose of a call, means for encoding the input data and transmitting it to the server, means for receiving and decoding the transmitted data, means for generating natural conversation content using a generative AI model based on the decoded data, means for executing a call using the generated conversation content with speech synthesis technology, means for acquiring and storing the results of the call in a database, and means for encoding the acquired results and feeding them back to the user. This reduces the psychological burden on the user without the need to make a call directly, and makes it easy for even hearing-impaired users to make calls.

[0504] "User" refers to any individual or legal entity that uses the System.

[0505] "Terminal" refers to a device used by a user, such as a mobile phone, computer, or tablet.

[0506] "Call" refers to a telephone communication based on a destination and purpose.

[0507] "Destination" refers to the location or organization that the user specifies to place the call.

[0508] "Purpose" refers to the content or purpose that the user wants to achieve through the call.

[0509] "Encoding" refers to the process of encrypting or converting the format of data to be sent.

[0510] "Decoding" refers to the process of returning received encrypted data or format-converted data to its original format.

[0511] "Server" refers to a computer system that receives, processes, stores, and transmits data.

[0512] A "generative AI model" refers to an algorithm or model that uses artificial intelligence technology to generate natural-sounding conversational sentences.

[0513] "Speech synthesis technology" refers to the technology that converts text data into natural speech.

[0514] "Database" refers to a data storage system for storing obtained call results and other information.

[0515] "Feedback" refers to the process of communicating call results and other information to the user.

[0516] This invention is a telephone answering system in which a user specifies a specific destination and purpose, and the system automatically answers the call. This system works in cooperation with a server and terminals, and generates natural conversations using a generative AI model based on user input data, and then executes the call.

[0517] First, the user uses a device such as a mobile phone or PC to input the destination (e.g., restaurant) and the purpose of the call (e.g., reservation date and time and number of people). The input screen is designed to be intuitive and easy to use, with features such as drop-down menus and calendar selection functions.

[0518] The data entered by the user is then encoded on the terminal and sent securely to the server, for example using the HTTPS protocol for secure communication.

[0519] The server receives the data sent from the device, decodes it, and converts it into an analyzable format. After decoding, the integrity and completeness of the received data are checked, and invalid or incomplete data is filtered out.

[0520] Based on the decoded data, the server uses a generative AI model to generate natural-sounding conversations. This generative AI model has been pre-trained with a large amount of conversation data, allowing it to generate natural conversations for a variety of scenarios. For example, if a user requests a reservation for "Restaurant X, June 15th at 7 PM for two people," the generated conversation will be "I'd like to make a reservation for two people at 7 PM on June 15th."

[0521] The generated conversational text is converted into natural-sounding speech on the server using speech synthesis technology. This converted speech is then used to automatically place a call to the specified recipient. During the call, the AI ​​system analyzes the other party's response in real time and provides an appropriate reply. For example, in response to the inquiry "Is a reservation possible?", the system will ask the appropriate next question or confirm the answer depending on whether the other party answers "yes" or "no."

[0522] Once the call is completed, the server retrieves the call details and results, which include, for example, reservation confirmation information and confirmation items, and stores them in a database.

[0523] The acquired call results are organized, and data for providing feedback to the user is generated in the server. This feedback data is then encoded again and sent to the terminal.

[0524] The device decodes the received feedback data and displays it in a format that the user can intuitively understand, such as "Your reservation has been confirmed. The date and time is June 15th at 7 PM for two people."

[0525] As a concrete example, consider a scenario where a user requests a reservation for "Restaurant X, June 15th, 7pm, for two people" on a device. When the user enters information on the input screen and clicks the send button, the data is encoded and sent to the server. The server receives, decodes, and analyzes the data. The generative AI model then generates appropriate conversational text and makes a call using speech synthesis technology. The results of the call are obtained, sent to the device as feedback data, and displayed to the user.

[0526] Example prompt sentence:

[0527] "I'd like to make a reservation for two at Restaurant X on June 15th at 7pm."

[0528] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0529] Step 1:

[0530] The user uses a device such as a mobile phone or PC to input the destination and purpose of the call. Specifically, the user enters information such as the restaurant name, reservation date and time, and number of people on the device's input screen. For example, the user might enter, "I'd like to make a reservation for two people at Restaurant X on June 15th at 7 PM."

[0531] Input: Destination (e.g. restaurant name), purpose (e.g. reservation date and time and number of people)

[0532] Output: Data entered by the user

[0533] Step 2:

[0534] The terminal encodes the data entered by the user and sends it to the server. Specifically, the terminal encrypts the entered data and sends it to the server using a secure communication protocol (e.g., HTTPS). When the send button is clicked, the data is encoded in real time and sent to the server.

[0535] Input: Data entered by the user

[0536] Output: Encoded data

[0537] Step 3:

[0538] The server receives and decodes the data sent from the device. Since the received data is encrypted, the server decrypts it and converts it into an analyzable format. Here, the server checks the integrity and completeness of the data and filters out any invalid or incomplete data.

[0539] Input: Encoded data

[0540] Output: Decoded data

[0541] Step 4:

[0542] The server uses the decoded data to run a generative AI model and generate natural-sounding conversational sentences. The generative AI model has been trained with a large amount of conversational data in advance, allowing it to smoothly generate natural conversations that meet the user's requests. For example, the generated conversational sentence would be, "I'd like to make a reservation for two people at 7 p.m. on June 15th."

[0543] Input: Decoded data

[0544] Output: Generated dialogue

[0545] Step 5:

[0546] The server uses speech synthesis technology to convert the generated conversational text into natural-sounding speech and automatically calls the specified recipient. During the call, the AI ​​system analyzes the other party's response in real time and generates an appropriate response. For example, in response to the question "Is a reservation possible?", the next question or confirmation will be asked depending on the other party's answer of "yes" or "no."

[0547] Input: Generated conversation

[0548] Output: Synthesized speech

[0549] Step 6:

[0550] Once the call is completed, the server retrieves the call details and results, which include, for example, reservation confirmation information and confirmation items, and stores them in a database.

[0551] Input: Call result (audio data)

[0552] Output: Analyzed call results (text data)

[0553] Step 7:

[0554] The server generates data for providing feedback to the user based on the acquired call result, and the generated feedback data is encoded and transmitted to the terminal.

[0555] Input: Parsed call results

[0556] Output: Encoded feedback data

[0557] Step 8:

[0558] The device decodes the received feedback data and displays it in a format that is intuitive to the user. For example, it displays specific information such as, "Your reservation has been confirmed. It is for 7 PM on June 15th, for two people."

[0559] Input: Encoded feedback data

[0560] Output: Decoded feedback data (for display)

[0561] The above is the specific processing flow of this system.

[0562] (Application example 1)

[0563] 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."

[0564] In today's world, many people feel a psychological burden when making phone calls themselves, and this barrier is even greater for those with hearing impairments or who have difficulty speaking a foreign language. Furthermore, there are problems with not being able to easily respond to sudden reservations or confirmations. A system that can solve these problems is needed.

[0565] 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.

[0566] In this invention, the server includes a means for a user to input the destination and purpose of the call, a means for receiving, decoding, and analyzing the transmitted data, a means for generating natural conversation content using a generative AI model, a means for executing an automated call, a means for obtaining the call result and providing feedback to the user, and a means for displaying the feedback. This allows the user to easily and quickly make call reservations or inquiries using a smartphone and intuitively understand the results.

[0567] The "user input means" is a means for the user to input the destination and purpose of the call.

[0568] The "data transmission means" is a means for encoding input data and transmitting it to the server.

[0569] "Data receiving means" refers to means for receiving and decoding transmitted data.

[0570] The "conversation generation means" is a means for generating natural conversation content based on the decoded data.

[0571] The "call execution means" is a means for executing a call using the generated conversation content.

[0572] The "result acquisition means" is a means for acquiring the result of a call.

[0573] The "feedback means" is a means for providing feedback of the obtained results to the user.

[0574] The "display means" is a means for displaying feedback to the user.

[0575] A "smartphone" is a portable information terminal that allows users to enter data and check results.

[0576] A "generative AI model" is an artificial intelligence model that generates natural conversation content based on input data.

[0577] A "physical store application" is a smartphone application that automatically handles physical store reservations and inquiries.

[0578] "Speech synthesis" is a technology that converts conversation content generated using AI technology into natural-sounding speech.

[0579] This invention is a system that uses a smartphone application for brick-and-mortar stores to make reservations and inquiries without the user having to make a phone call. In an embodiment of the invention, a server, a terminal (smartphone), a generative AI model, a voice synthesis technology, and a call API work together.

[0580] Hardware and software used

[0581] Smartphone: A device on which users can input information and check the results. A dedicated application is installed on the smartphone.

[0582] Server: A device that receives and analyzes data, runs generative AI models, manages calls, and provides feedback on results. The server software uses Node.js, Express, Python, GPT-4 API, and Flask.

[0583] Generative AI model: An artificial intelligence model for generating natural conversation content. Specifically, we use GPT-4.

[0584] Call API: An API for making automated calls. Uses the Twilio API.

[0585] Database: A database for storing call logs and results. MongoDB is used.

[0586] System Operation Overview

[0587] 1. User Input

[0588] The smartphone application allows users to input the destination of the call (e.g., the name of the restaurant) and the purpose of the call (e.g., the date and time of the reservation and the number of people). The application is designed to be intuitive and easy to use.

[0589] 2. Data Transmission

[0590] The smartphone encodes the entered data and sends it securely to the server, where the communication is encrypted to protect privacy.

[0591] 3. Data Receipt and Confirmation

[0592] The server receives the data sent by the smartphone, decodes it, and converts it into an analyzable format, after which it checks the data for consistency and integrity.

[0593] 4. Conversation Generation

[0594] The server uses a generative AI model (GPT-4) to generate natural-sounding conversational sentences based on user-specified content. Prompt sentences are used in this process.

[0595] Example prompt sentence:

[0596] "Cafe Z, please generate a conversation to confirm whether a reservation for two people can be made on August 10th at 2pm."

[0597] 5. Make a call

[0598] The server uses speech synthesis technology to convert the generated conversation into natural-sounding speech, then automatically calls the specified recipient using the Twilio API and executes the call.

[0599] 6. Get call results

[0600] Once the call is complete, the Twilio API sends the call details and results to the server, which analyzes the information and stores it in a database.

[0601] 7. Feedback Generation and Submission

[0602] The server organizes the call results and generates data to provide feedback to the user. This data is then re-encoded and sent to the smartphone.

[0603] 8. Results display

[0604] The smartphone decodes the received feedback data and displays it in a format that is easy for the user to understand. For example, it may display specific information such as, "Your reservation has been confirmed. We are waiting for two people at 2:00 PM on August 10th."

[0605] As a concrete example, when a user enters "Cafe Z, August 10th, 2pm, 2 people" into their smartphone, the server generates a conversation saying "Is a reservation for 2 people possible on August 10th at 2pm?", and the Twilio API automatically calls the cafe to confirm the reservation. The result is displayed on the smartphone as "Reservation confirmed." This series of steps reduces the psychological burden on the user, and allows even users who are not good at making phone calls or who are hearing impaired to easily make reservations.

[0606] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0607] Step 1:

[0608] The user launches the smartphone application and enters the call destination (e.g., the name of the restaurant) and the purpose of the call (e.g., the date and time of the reservation and the number of people). The entered data is encoded in JSON format. Input: Restaurant name, reservation date and time, and number of people. Output: Encoded JSON data.

[0609] Step 2:

[0610] The device sends the encoded data to the server via HTTPS. Communication is encrypted to protect privacy. Input: Encoded JSON data. Output: Encrypted data packet.

[0611] Step 3:

[0612] The server receives the data sent from the terminal, decrypts it, and converts it into an analyzable format. During this process, it checks the integrity and completeness of the data. Input: Encrypted data packet. Output: Data in an analyzable format.

[0613] Step 4:

[0614] The server sends prompts to the generative AI model (GPT-4) based on the decoded data to generate natural-sounding conversational sentences. During this process, the user's input is given to the model as a prompt. Input: Parsed data and prompt. Output: Generated conversational sentences.

[0615] Step 5:

[0616] The generated conversational text is converted into natural-sounding speech on the server using speech synthesis technology (e.g., Amazon Polly, Google Text-to-Speech, etc.). Input: Generated conversational text. Output: Synthesized speech data.

[0617] Step 6:

[0618] The server automatically calls the specified recipient using the Twilio API and executes the conversation using synthesized voice. During the call, it analyzes the recipient's responses in real time and generates appropriate responses. Input: Recipient's phone number and voice data. Output: Call execution and real-time response data.

[0619] Step 7:

[0620] When the call is completed, the Twilio API sends the call details and results (e.g., reservation confirmation information) to the server. The server analyzes the details and stores them in a database (e.g., MongoDB). Input: Call result data. Output: Analyzed reservation confirmation information and its storage.

[0621] Step 8:

[0622] The server organizes the acquired call results and generates data to provide feedback to the user. This data is then encoded again and sent to the device. Input: Call result data. Output: Encoded data for feedback.

[0623] Step 9:

[0624] The smartphone device decodes the received feedback data and displays it in a format that the user can intuitively understand. For example, specific information such as "The reservation has been confirmed. The date and time is August 10th at 2pm for two people" is displayed. Input: Encoded data for feedback. Output: Specific reservation information displayed to the user.

[0625] 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.

[0626] The present invention relates to a telephone answering system in which a user specifies a specific destination and purpose, and the system automatically handles the call, while also incorporating an emotion engine that recognizes the user's emotions. The system's program works in conjunction with a server and terminals, and generates natural conversations using a generative AI model based on the user's input data and emotions, and then carries out the call. The following describes in detail an embodiment of the present invention.

[0627] 1. User Input

[0628] Terminal: The user uses a terminal such as a mobile phone or PC to input the destination of the call (e.g., the name of the restaurant) and the purpose of the reservation (e.g., the date and time of the reservation and the number of people). The input screen is designed to be intuitive and easy to use, and a function that recognizes the user's emotions has been added.

[0629] 2. User Emotion Recognition

[0630] Terminal: While the user is typing, the terminal's built-in emotion engine recognizes emotions from the user's tone of voice, facial expressions, text content, etc. This emotion data is also used to generate the call content.

[0631] 3. Data Transmission

[0632] Terminal: The data and emotion data entered by the user are encoded and securely transmitted to the server. Encrypted communication is used to protect privacy.

[0633] 4. Data Receipt and Confirmation

[0634] Server: The server receives the data sent by the device, decodes it, and converts it into an analyzable format. It then checks the integrity and completeness of the data.

[0635] 5. Conversation Generation

[0636] Server: The server uses a generative AI model and emotion engine to generate natural-sounding conversations based on the user's specified content and emotions. For example, if the server recognizes that the user is feeling nervous, the generated conversations will have a relaxing tone.

[0637] 6. Make a call

[0638] Server: Converts the generated conversation content from text to speech. It uses speech synthesis technology to generate natural-sounding speech. It then automatically calls the specified recipient. During the call, the AI ​​system responds appropriately based on the recipient's responses, and uses an emotion engine to generate responses that reflect the user's emotions if necessary.

[0639] 7. Get call results

[0640] Server: When the call is completed, the server obtains the call content and results (e.g., reservation confirmation information, confirmation items, etc.), which are then stored and managed in a database.

[0641] 8. Feedback Generation and Submission

[0642] Server: The server organizes the call results and creates feedback data for the user. This data is then encoded again and sent to the device.

[0643] 9. Results display

[0644] Terminal: The terminal decodes the received feedback data and displays it in a format that is intuitive to the user. For example, it displays specific information such as, "Your reservation has been confirmed. The date and time is June 15th at 7 PM for two people."

[0645] Specific examples

[0646] Reservation example

[0647] Suppose a user uses a terminal to request a reservation for "Restaurant X, June 15th, 7pm, for 2 people."

[0648] 1. User Input: While the user is inputting information into the device, the emotion engine recognizes tense emotions.

[0649] 2. Data transmission: The device encodes the data and emotion data and sends them to the server.

[0650] 3. Data reception and verification: The server receives the data and emotion data, decodes it, and analyzes it.

[0651] 4. Conversation generation: The generative AI model and emotion engine generate the following conversational sentence in a neutral tone: "I'd like to make a reservation for two people at 7pm on June 15th."

[0652] 5. Call execution: The server makes a call and reads out the conversation generated by speech synthesis. It also generates a response to the other party's response that reflects the user's emotions.

[0653] 6. Obtain call result: The server receives the answer from the restaurant and records the content.

[0654] 7. Feedback generation and transmission: Organize the call results and send them to the device.

[0655] 8. Display result: The device displays the feedback it received to the user. For example, it displays "Your reservation has been confirmed. We are waiting for two people at 7 PM on June 15th."

[0656] As described above, the system provided by the present invention automatically handles the call content specified by the user and uses an emotion engine to respond in a way that reflects the user's emotions, providing a more natural and comfortable call experience. This lowers the psychological barrier to making a call and is particularly useful for people with hearing impairments and those in stressful situations.

[0657] The processing flow will be explained below.

[0658] Step 1:

[0659] User: Enter the destination and purpose of the call into the input screen of the device. For example, enter information such as "Restaurant X, June 15th, 7 PM, 2 people."

[0660] Step 2:

[0661] Terminal: While accepting user input, the emotion engine analyzes the user's voice tone, facial expressions, and input content to detect the user's emotional state.

[0662] Step 3:

[0663] Terminal: The input data and detected emotion data are encoded and sent to the server using encrypted communication.

[0664] Step 4:

[0665] Server: Receives the encoded data sent from the device. The received data is first stored in secure local storage.

[0666] Step 5:

[0667] Server: Decodes the received data and extracts the user's destination, purpose, and emotion data. It checks the data for consistency and generates an error message if there are any errors.

[0668] Step 6:

[0669] Server: Calls up a generative AI model based on the decoded data and generates natural conversational sentences that incorporate the user's emotional data. For example, if the user is nervous, it adds phrases to help them relax.

[0670] Step 7:

[0671] Server: Based on the generated conversational text, a natural voice is generated using speech synthesis technology, with a tone that reflects the user's emotions.

[0672] Step 8:

[0673] Server: Automatically calls the specified destination phone number. When the call starts, the generated voice is spoken to the other party.

[0674] Step 9:

[0675] Server: Analyzes responses from the other party in real time during the call and generates appropriate responses. Here too, the emotion engine generates responses that reflect the user's emotions based on the other party's responses.

[0676] Step 10:

[0677] Server: Once the call is over, record the outcome of the call, for example, whether the reservation was confirmed or not, and if there are any further questions.

[0678] Step 11:

[0679] Server: Organizes the call results and generates feedback data to the user. This feedback data is also encoded.

[0680] Step 12:

[0681] Server: Sends the generated feedback data to the terminal using encrypted communication.

[0682] Step 13:

[0683] Terminal: Receives feedback data sent from the server. Decodes the received data and converts it into an analyzable format.

[0684] Step 14:

[0685] Terminal: Visually display feedback information to the user, for example, "Your reservation has been confirmed. Please go to Restaurant X on June 15th at 7pm for two people."

[0686] As described above, the system of the present invention recognizes the user's emotions and generates natural conversation content and voice that reflects those emotions, making call answering more comfortable. This allows users in particularly stressful situations or with hearing impairments to make phone calls with peace of mind.

[0687] Example 2

[0688] 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."

[0689] Conventional telephone answering systems often cause users to feel nervous or anxious when making a call, making it difficult for them to make a smooth call, especially for those with hearing impairments or in situations where they feel psychological pressure. Furthermore, the lack of naturalness in the call content can cause discomfort to the other party, which can sometimes prevent users from achieving their intended purpose. The present invention aims to solve these problems and provide a more natural and emotionally sensitive call experience.

[0690] The identification process by the identification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means. In this invention, the server includes means for a user to input a destination and purpose of a call, means for encoding the input data and the user's emotional data and transmitting them to the server, means for receiving and decoding the transmitted data, means for generating natural conversation content using a generative AI model based on the decoded data and emotional data, means for converting the generated conversation content into voice using AI speech synthesis and executing the call, means for generating an appropriate response based on the other party's response during the call, means for acquiring the result of the call, and means for feeding back the acquired result to the user. This makes it possible to realize a natural and smooth call while taking the user's emotions into consideration, and to reliably achieve the purpose of the call.

[0691] A "user" is a person who utilizes the system to input the destination and purpose of a call.

[0692] A "call destination" is the person or location to which a user wishes to place a call.

[0693] The "matters" are the contents or purpose that the user wants to convey through the call.

[0694] A "terminal" is a device used by a user to input the destination and purpose of a call, and includes a mobile phone, a personal computer, and the like.

[0695] "Emotion data" is data that represents the user's psychological state, obtained from the user's tone of voice, facial expression, and input text content.

[0696] "Encoding" is the process of converting data to be transmitted into a specific format.

[0697] A "server" is a device that receives and processes data sent from a terminal.

[0698] "Decoding" is the process of converting received data back into its original format.

[0699] A "generative AI model" is an algorithm or program that uses artificial intelligence technology to generate natural-sounding conversation content based on input data.

[0700] "AI voice synthesis" is a technology that converts text data into voice data.

[0701] A "call" is an act of actually having a conversation based on the destination and purpose input by the user.

[0702] A "response" is a reply or response received from the other party during a call.

[0703] "Feedback" is information that reports the results of a call to the user.

[0704] This invention is a telephone answering system in which a user specifies a specific destination and purpose, and the system automatically answers the call. The system also incorporates an emotion engine that recognizes the user's emotions, and the server and terminals work together. Detailed embodiments for implementing this system are described below.

[0705] 1. User Input

[0706] Device: The user uses a device such as a mobile phone or PC to input the destination (e.g., restaurant name) and purpose (e.g., reservation date and time and number of people). The input interface is designed to be intuitive for users, with features such as check boxes and drop-down menus. In addition, the microphone and camera are activated when inputting information, and the device is equipped with a function that recognizes the user's tone of voice and facial expressions in real time.

[0707] 2. Emotion recognition

[0708] Terminal: While the user is entering information, the emotion engine analyzes voice tone, facial expression recognition, and the input text content to detect the user's emotional state. For example, it determines whether the user is nervous based on the intonation of their voice or facial expression. This function generates the user's emotional data.

[0709] 3. Data Transmission

[0710] Terminal: The data and emotion data entered by the user are encoded and securely transmitted to the server using encrypted communication technology such as HTTPS, preventing data leakage and degradation.

[0711] 4. Data Receipt and Confirmation

[0712] Server: Receives the data sent from the device, decodes it, and converts it into an analyzable format. The server checks the consistency and integrity of the data to ensure it has not been tampered with. It also calculates checksums and verifies the data format.

[0713] 5. Conversation Generation

[0714] Server: Using a generative AI model, the server generates natural-sounding conversational sentences based on the content and emotional data specified by the user. For example, if the server detects that the user is nervous, it generates a conversational sentence with a relaxed tone, such as "Please make a reservation for two people at 7 p.m. on June 15th." The generative AI model uses the prompt to generate the conversational sentence.

[0715] 6. Make a call

[0716] Server: Converts the generated conversation content from text to speech. It uses speech synthesis technology (e.g., Google Text-to-Speech) to generate natural-sounding speech and automatically calls the specified recipient. During the call, the conversational AI generates appropriate responses in real time based on the recipient's responses, and uses an emotion engine to respond in a way that reflects the user's emotions.

[0717] 7. Get call results

[0718] Server: When the call is completed, the call content and results (e.g., reservation confirmation information, confirmation items, etc.) are obtained and saved in a database. This information can be referenced later, improving user convenience.

[0719] 8. Feedback Generation and Submission

[0720] Server: Organizes the call results and generates data to provide feedback to the user. This is then encoded again and securely sent to the device using HTTPS.

[0721] 9. Results display

[0722] Terminal: Decodes the received feedback data and displays it in a format that is easy for the user to understand. For example, it displays specific information such as "The reservation has been confirmed. It will be made on June 15th at 7pm for two people." It is also possible to notify the user of the results using a voice readout function.

[0723] Specific examples

[0724] A specific example will be given in which a user uses a terminal to request a reservation for "Restaurant X, June 15th, 7pm, for 2 people."

[0725] 1. User input: The user enters "Restaurant X, June 15th, 7pm, 2 people" into the terminal, and the emotion engine recognizes the tension.

[0726] 2. Data transmission: The device encodes the data and emotion data and sends them to the server.

[0727] 3. Data reception and verification: The server receives the data, decodes it, and verifies its integrity.

[0728] 4. Conversation generation: The generative AI model generates the following conversation in a neutral tone: "I'd like to make a reservation for two people at 7 p.m. on June 15th."

[0729] 5. Call execution: The server makes the call and reads out the conversation generated by speech synthesis technology. Depending on the other party's response, an appropriate response reflecting the other party's emotions is given.

[0730] 6. Obtain call result: The server receives a confirmation of the reservation from the restaurant and records the details.

[0731] 7. Feedback generation and transmission: Organize the call results and send them to the device.

[0732] 8. Displaying the result: The terminal displays the result to the user: "Reservation confirmed. Two guests will be waiting at 7 PM on June 15th."

[0733] In this way, the system of the present invention provides a natural calling experience that takes into account the user's emotions, enabling the purpose of the call to be achieved efficiently.

[0734] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0735] Step 1: User Input

[0736] Device: The user enters the call destination (e.g., restaurant name) and purpose (e.g., reservation date and time and number of people) on a device such as a mobile phone or PC. The input interface is equipped with check boxes and drop-down menus, and is designed to allow users to operate it intuitively. Input data includes the destination "Restaurant X," the date and time "June 15th, 7:00 PM," and the number of people "2." In addition, the microphone and camera are activated to collect the user's voice tone and facial expressions.

[0737] Input: Destination, purpose (reservation date and time, number of people)

[0738] Output: Input data, emotion data

[0739] Step 2: Emotion Recognition

[0740] Terminal: The emotion engine generates emotion data by analyzing the user's voice tone, facial expression recognition, and input text content. For example, it determines whether the user is nervous based on the intonation of their voice and facial expression. This provides emotion data that indicates the user's psychological state.

[0741] Input: Voice tone, facial expression data, input text

[0742] Output: Emotion data

[0743] Step 3: Send data

[0744] Terminal: Input data and emotion data are encoded and sent securely to the server using encryption technology (e.g., HTTPS). Data is transferred in a manner that prevents degradation and leakage.

[0745] Input: Input data, emotion data

[0746] Output: Encrypted data

[0747] Step 4: Data Receipt and Verification

[0748] Server: Receives encrypted data sent from the device. Decodes the received data and converts it into an analyzable format. Then, calculates checksums and verifies the data format to ensure data integrity and completeness.

[0749] Input: Encrypted data

[0750] Output: Decoded data

[0751] Step 5: Conversation generation

[0752] Server: Using a generative AI model, the server generates natural-sounding conversational sentences based on the decoded input data and emotional data. For example, if the user is recognized as nervous, the server generates a conversational sentence in a relaxed tone, such as "I'd like to make a reservation for two people at 7 p.m. on June 15th." The server uses a prompt sentence.

[0753] Input: Decoded data, emotion data

[0754] Output: Conversation

[0755] Step 6: Make the call

[0756] Server: Converts the generated conversational text from text to speech. It uses speech synthesis technology (e.g., Google Text-to-Speech) to generate natural-sounding speech and automatically calls the specified recipient. During the call, the conversational AI generates appropriate responses in real time based on the recipient's responses, and the emotion engine responds by reflecting the user's emotions.

[0757] Input: Conversation

[0758] Output: Audio data, call answering

[0759] Step 7: Get call results

[0760] Server: Once the call is completed, the server obtains the call details and results (e.g., reservation confirmation information, confirmation items, etc.). The obtained data is stored in a database.

[0761] Input:Call Answer

[0762] Output: Call result data

[0763] Step 8: Generate and send feedback

[0764] Server: Organizes the acquired call results and generates data to provide feedback to the user. This feedback data is then re-encoded and sent to the device using encryption technology.

[0765] Input: Call result data

[0766] Output: Feedback data

[0767] Step 9: View the results

[0768] Terminal: Decodes the received feedback data and displays the results in a format that is easy for the user to understand. For example, specific information such as "Reservation confirmed. June 15th at 7pm for two people" is displayed on the terminal screen. Voice notification is also possible.

[0769] Input: Feedback data

[0770] Output: Display result

[0771] (Application example 2)

[0772] 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."

[0773] In autonomous vehicles, users are expected to be able to comfortably use various services (restaurant reservations, hotel reservations, medical appointments, etc.) from inside the vehicle, but there is a lack of a system that automatically generates and executes natural responses based on input information that reflect the user's emotions.In addition, since calls that ignore the user's emotions can be unnatural and stressful, it is necessary to provide natural conversations that take the user's emotions into consideration.

[0774] 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 a user to input the destination and purpose of the call, means for recognizing emotions from the user's tone of voice, facial expression, text content, etc., means for encoding the input data and emotional data and transmitting them to the server, means for receiving and decoding the transmitted data and emotional data, means for using a generative AI model to generate natural conversation content based on the decoded data, means for adjusting the tone of the conversation based on the user's emotional data, means for conducting a call using the generated conversation content, means for acquiring the results of the call, and means for feeding back the acquired results to the user. This enables comfortable service use in an autonomous vehicle and realizes natural conversation responses that correspond to the user's emotions.

[0775] "Means for users to input the destination and purpose of the call" refers to the means by which users use a terminal such as a mobile phone or computer to input the destination (e.g., restaurant, hotel, medical institution, etc.) and the purpose (e.g., reservation date and time, number of people, etc.).

[0776] The "means for recognizing emotions" refers to a means for automatically recognizing emotions from the user's tone of voice, facial expressions, text content, etc., using an emotion engine or sensor installed in the device.

[0777] The "means for encoding data and emotion data and transmitting them to the server" refers to a means for encoding (encrypting) the destination and purpose data entered by the user and the emotion data obtained from the emotion recognition means and transmitting them securely to the server.

[0778] The "means for receiving and decoding" refers to the means by which the server receives the data and emotion data sent from the terminal and decodes (decodes) it into an analyzable format.

[0779] "Means for using a generative AI model" refers to means by which the server generates natural conversation content using a generative AI model based on data and emotional data sent by the user.

[0780] The "means for adjusting the tone of the conversation" is a means for adjusting the tone of the conversation (e.g., relaxed tone, gentle tone, etc.) based on the user's emotional data in the generated conversation content.

[0781] The "means for executing a call using the conversation content" is a means for converting the generated conversation content from text to voice and automatically making a call to a designated recipient.

[0782] The "means for obtaining the results of a call" refers to the means by which the server obtains the contents of the call and its results (e.g., reservation confirmation information, confirmation items, etc.) when the call is completed.

[0783] The "means for providing feedback to the user" is a means for encoding data to feed back the acquired call result to the user, transmitting the data to the terminal, and displaying the data in a form that the user can intuitively understand.

[0784] This invention describes a specific embodiment of a voice assistant application installed in an autonomous vehicle. This application allows the user to specify the destination and purpose of a reservation from inside the vehicle, and the system automatically handles the call. Furthermore, it can recognize the user's emotions and generate natural conversations using a generative AI model.

[0785] First, the user uses the voice assistant app in the autonomous vehicle to specify the destination (e.g., restaurant, hotel, medical institution, etc.) and purpose (e.g., reservation date and time, number of people, etc.). This input is converted into text using voice recognition technology. For voice recognition, Google Speech Recognition API, for example, is used.

[0786] Next, the emotion engine installed on the device recognizes emotions from the voice tone, facial expressions, text content, etc. while the user is typing. For emotion recognition, for example, the Python library "Emotion Recognition" is used.

[0787] The input data and emotion data are encoded (encrypted) and securely transmitted to the server. This communication is via the Internet and uses encryption protocols (e.g., TLS / SSL).

[0788] The server receives the data and emotion data sent from the device and decodes it. After decoding, the server uses a generative AI model (such as GPT-3) to generate natural-sounding conversation content based on the content and emotion specified by the user. The tone of the conversation is also adjusted based on the emotion data. For example, if the user is nervous, a relaxing tone of voice will be generated.

[0789] The generated conversation is converted into natural-sounding speech using speech synthesis technology (such as the Google Text-to-Speech API). The call is then automatically placed to the specified recipient. During the call, the AI ​​system responds appropriately based on the recipient's response, and uses an emotion engine to generate responses that reflect the user's emotions, if necessary.

[0790] Once the call is completed, the server obtains the results of the call (e.g., reservation confirmation information, confirmation items, etc.), stores them in a database, and manages them. This information is then encoded and sent back to the device.

[0791] Finally, the device decodes the received feedback data and displays it in a format that is intuitive to the user, such as "Your reservation has been confirmed. The date and time is June 15th at 7 PM for two people."

[0792] Examples of specific prompts include:

[0793] User: "I'd like to make a reservation for two at Restaurant X on June 15th at 7pm."

[0794] Input to AI model: "Reservation call - user is nervous. Please speak in a relaxed tone."

[0795] Generated dialogue: "Hello, Restaurant X. I'd like to make a reservation for two people on June 15th at 7pm." "Yes, I understand. We look forward to seeing you."

[0796] In this way, the system of the present invention enables comfortable use of services inside an autonomous vehicle and is capable of providing natural conversational responses that correspond to the user's emotions.

[0797] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[0798] Step 1:

[0799] The user inputs the destination and purpose of the call. Using the voice assistant app in the autonomous vehicle, the user specifies the destination (e.g., restaurant, hotel, medical institution, etc.) and purpose (e.g., reservation date and time, number of people, etc.). This input is converted into text using voice recognition technology (e.g., Google Speech Recognition API). The input data is obtained in the form of text: "destination" and "purpose."

[0800] Step 2:

[0801] The device recognizes emotions from the user's voice tone, facial expressions, text content, etc. The emotion engine (e.g., Emotion Recognition library) installed on the device analyzes the voice tone while the user is typing and recognizes the user's emotions in real time. Emotion data is obtained in the form of "emotional state."

[0802] Step 3:

[0803] The device encodes the input data and emotion data and sends them to the server. The encoding (encryption) process uses, for example, the TLS / SSL protocol. The encoded data is securely sent to the server. The input data and emotion data are sent as a single encrypted packet.

[0804] Step 4:

[0805] The server receives and decodes the transmitted data and emotional data. The server receives the encrypted data transmitted from the device and decodes it into an analyzable format. This allows the "destination," "message," and "emotional state" data to arrive at the server.

[0806] Step 5:

[0807] The server uses a generative AI model (e.g., GPT-3) based on the decoded data to generate natural-sounding conversation content. The server inputs the "destination," "purpose," and "emotional state" data into the generative AI model to generate appropriate conversation content. The tone of the conversation is adjusted based on the user's emotional state. The output is obtained as "conversation content."

[0808] Step 6:

[0809] The server converts the generated conversation content into natural-sounding speech using speech synthesis technology (e.g., Google Text-to-Speech API). The server then converts the text-format "conversation content" into voice data and prepares to make a call to the specified recipient. The output is obtained as voice data.

[0810] Step 7:

[0811] The server automatically calls the specified recipient. During the call, the AI ​​system responds appropriately based on the recipient's response and uses an emotion engine to generate a response that reflects the user's emotions. Emotion recognition continues as the conversation progresses, and any necessary corrections are made. Data is exchanged in real time.

[0812] Step 8:

[0813] Once the call is complete, the server obtains the call results (e.g., reservation confirmation information, confirmation items, etc.). After the call ends, the server collects various confirmation data and stores it in a database that manages it. The output is obtained as "call result data."

[0814] Step 9:

[0815] The server organizes the call results it has obtained and creates data to provide feedback to the user. It re-encodes (encrypts) the call result data and sends it to the device. The encoded feedback data is then securely sent to the device.

[0816] Step 10:

[0817] The device decodes the received feedback data and displays it in a format that is intuitively understandable to the user. The decoded feedback content is displayed to the user as specific information, such as "The reservation has been confirmed. The date and time is June 15th at 7 PM for two people."

[0818] 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.

[0819] 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.

[0820] 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.

[0821] [Third embodiment]

[0822] FIG. 5 shows an example of the configuration of a data processing system 310 according to the third embodiment.

[0823] 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.

[0824] 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).

[0825] 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.

[0826] 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.

[0827] 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).

[0828] 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.

[0829] 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.

[0830] 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.

[0831] 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.

[0832] 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.

[0833] 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."

[0834] The present invention relates to a telephone answering system in which a user specifies a specific destination and purpose, and the system automatically answers the call. The program of this system works in conjunction with a server and a terminal, and generates natural conversation using a generative AI model based on user input data, and then conducts the call. Below, we will describe in detail the embodiments of the present invention.

[0835] 1. User Input

[0836] Terminal: The user uses a terminal such as a mobile phone or PC to input the destination of the call (e.g., the name of the restaurant) and the purpose of the call (e.g., the date and time of the reservation and the number of people). The input screen is designed to be intuitive and easy to use.

[0837] 2. Data Transmission

[0838] Terminal: Data entered by the user is encoded and securely sent to the server. By default, communication is encrypted to protect privacy.

[0839] 3. Data Receipt and Confirmation

[0840] Server: The server receives the data sent from the device, decodes it, and converts it into an analyzable format. It then checks the integrity and completeness of the data.

[0841] 4. Conversation Generation

[0842] Server: The server uses a generative AI model to generate natural-sounding dialogue based on user input, appropriate for the specific scenario.

[0843] 5. Make a call

[0844] Server: The server uses speech synthesis technology to convert the generated conversational text into natural-sounding speech. It then automatically calls the specified recipient. During the call, the AI ​​system responds appropriately based on the recipient's response.

[0845] 6. Get call results

[0846] Server: When the call is completed, the server obtains the call content and results (e.g., reservation confirmation information, confirmation items, etc.), which are then stored and managed in a database.

[0847] 7. Feedback Generation and Submission

[0848] Server: The server organizes the call results and creates feedback data for the user. This data is then encoded again and sent to the device.

[0849] 8. Results display

[0850] Terminal: The terminal decodes the received feedback data and displays it in a format that is intuitive to the user. For example, it displays specific information such as, "Your reservation has been confirmed. The date and time is June 15th at 7 PM for two people."

[0851] This eliminates the need for users to make phone calls themselves, reducing the psychological burden. It also enables people with hearing impairments to make phone calls without having to go through a proxy.

[0852] Specific examples

[0853] Reservation example

[0854] Suppose a user uses a terminal to request a reservation for "Restaurant X, June 15th, 7pm, for 2 people."

[0855] 1. User Input: The user enters information at the terminal.

[0856] 2. Data transmission: The device encodes the data and sends it to the server.

[0857] 3. Data reception and verification: The server receives the data, decodes it, and parses it.

[0858] 4. Conversation generation: The generative AI model generates the conversation sentence, "I would like to make a reservation for two people at 7 p.m. on June 15th."

[0859] 5. Call execution: The server makes the call and reads out the conversation generated by speech synthesis.

[0860] 6. Obtain call result: The server receives the answer from the restaurant and records the content.

[0861] 7. Feedback generation and transmission: Organize the call results and send them to the device.

[0862] 8. Display result: The device displays the feedback it received to the user. For example, it displays "Your reservation has been confirmed. We are waiting for two people at 7 PM on June 15th."

[0863] As described above, the system provided by the present invention automatically carries out the call content specified by the user and provides feedback on the results to the user. This lowers the psychological barrier to making a call and is particularly useful for people with hearing impairments or who have difficulty speaking in a foreign language.

[0864] The processing flow will be explained below.

[0865] Step 1:

[0866] User: Enter the destination and purpose of the call into the device's input screen. For example, enter information such as the restaurant name "Restaurant X," the reservation date and time "June 15th, 7 PM," and the number of people "2."

[0867] Step 2:

[0868] Terminal: Encodes the data entered by the user and converts it into a format that can be transmitted. For security reasons, it may encrypt the data.

[0869] Step 3:

[0870] Terminal: Sends the encoded data to the server using a secure protocol such as HTTPS.

[0871] Step 4:

[0872] Server: Receives data sent from the device and temporarily stores the received data in local storage.

[0873] Step 5:

[0874] Server: Decodes the received data and restores it to its original form. Through the decoding process, information entered by the user, such as the destination, purpose, date and time, and number of people, is obtained.

[0875] Step 6:

[0876] Server: Checks the integrity of the decoded data. Checks that all necessary information is present and that the format is correct. If there is a deficiency, generates an error message and prepares to send it to the terminal.

[0877] Step 7:

[0878] Server: If the data is correct, the generative AI model is invoked to generate natural-sounding conversational content based on the input data. For example, it generates a conversational sentence like, "Hello, is this Restaurant X? I'd like to make a reservation for two people at 7 p.m. on June 15th."

[0879] Step 8:

[0880] Server: Converts the generated conversation content from text to speech. It uses speech synthesis technology to generate natural-sounding speech.

[0881] Step 9:

[0882] Server: Automatically calls the specified phone number. Uses AI voice synthesis to make the call using the generated voice.

[0883] Step 10:

[0884] Server: Analyzes responses from the other party in real time during the call and responds appropriately. If necessary, generates new conversation content and converts it back into voice to continue the call.

[0885] Step 11:

[0886] Server: When the call ends, record the call result and information obtained from the other party. For example, obtain information such as "The reservation has been confirmed. Two people will be waiting for you at 7 PM on June 15th."

[0887] Step 12:

[0888] Server: Organizes the call results and generates data to provide feedback to the user. The feedback data includes the call results and confirmations.

[0889] Step 13:

[0890] Server: The generated feedback data is encoded and prepared for transmission to the device. Security measures such as encryption are again applied.

[0891] Step 14:

[0892] Terminal: Receives feedback data sent from the server. Decodes the received data and converts it into an analyzable format.

[0893] Step 15:

[0894] Terminal: Visually display feedback data to the user. For example, "Your reservation has been confirmed. Please go to Restaurant X on June 15th at 7pm for two people."

[0895] As described above, this system performs a series of processes based on the data entered by the user, handles the call on behalf of the user, and provides feedback on the results to the user.

[0896] Example 1

[0897] 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."

[0898] There is a need to eliminate the psychological burden of making phone calls and the difficulties faced by hearing-impaired users. In particular, for certain tasks such as making reservations or inquiries, a system is needed that allows users to achieve their goals through natural conversation without having to make a direct phone call.

[0899] 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.

[0900] In this invention, the server includes means for a user to input a destination and purpose of a call, means for encoding the input data and transmitting it to the server, means for receiving and decoding the transmitted data, means for generating natural conversation content using a generative AI model based on the decoded data, means for executing a call using the generated conversation content with speech synthesis technology, means for acquiring and storing the results of the call in a database, and means for encoding the acquired results and feeding them back to the user. This reduces the psychological burden on the user without the need to make a call directly, and makes it easy for even hearing-impaired users to make calls.

[0901] "User" refers to any individual or legal entity that uses the System.

[0902] "Terminal" refers to a device used by a user, such as a mobile phone, computer, or tablet.

[0903] "Call" refers to a telephone communication based on a destination and purpose.

[0904] "Destination" refers to the location or organization that the user specifies to place the call.

[0905] "Purpose" refers to the content or purpose that the user wants to achieve through the call.

[0906] "Encoding" refers to the process of encrypting or converting the format of data to be sent.

[0907] "Decoding" refers to the process of returning received encrypted data or format-converted data to its original format.

[0908] "Server" refers to a computer system that receives, processes, stores, and transmits data.

[0909] A "generative AI model" refers to an algorithm or model that uses artificial intelligence technology to generate natural-sounding conversational sentences.

[0910] "Speech synthesis technology" refers to the technology that converts text data into natural speech.

[0911] "Database" refers to a data storage system for storing obtained call results and other information.

[0912] "Feedback" refers to the process of communicating call results and other information to the user.

[0913] This invention is a telephone answering system in which a user specifies a specific destination and purpose, and the system automatically answers the call. This system works in cooperation with a server and terminals, and generates natural conversations using a generative AI model based on user input data, and then executes the call.

[0914] First, the user uses a device such as a mobile phone or PC to input the destination (e.g., restaurant) and the purpose of the call (e.g., reservation date and time and number of people). The input screen is designed to be intuitive and easy to use, with features such as drop-down menus and calendar selection functions.

[0915] The data entered by the user is then encoded on the terminal and sent securely to the server, for example using the HTTPS protocol for secure communication.

[0916] The server receives the data sent from the device, decodes it, and converts it into an analyzable format. After decoding, the integrity and completeness of the received data are checked, and invalid or incomplete data is filtered out.

[0917] Based on the decoded data, the server uses a generative AI model to generate natural-sounding conversations. This generative AI model has been pre-trained with a large amount of conversation data, allowing it to generate natural conversations for a variety of scenarios. For example, if a user requests a reservation for "Restaurant X, June 15th at 7 PM for two people," the generated conversation will be "I'd like to make a reservation for two people at 7 PM on June 15th."

[0918] The generated conversational text is converted into natural-sounding speech on the server using speech synthesis technology. This converted speech is then used to automatically place a call to the specified recipient. During the call, the AI ​​system analyzes the other party's response in real time and provides an appropriate reply. For example, in response to the inquiry "Is a reservation possible?", the system will ask the appropriate next question or confirm the answer depending on whether the other party answers "yes" or "no."

[0919] Once the call is completed, the server retrieves the call details and results, which include, for example, reservation confirmation information and confirmation items, and stores them in a database.

[0920] The acquired call results are organized, and data for providing feedback to the user is generated in the server. This feedback data is then encoded again and sent to the terminal.

[0921] The device decodes the received feedback data and displays it in a format that the user can intuitively understand, such as "Your reservation has been confirmed. The date and time is June 15th at 7 PM for two people."

[0922] As a concrete example, consider a scenario where a user requests a reservation for "Restaurant X, June 15th, 7pm, for two people" on a device. When the user enters information on the input screen and clicks the send button, the data is encoded and sent to the server. The server receives, decodes, and analyzes the data. The generative AI model then generates appropriate conversational text and makes a call using speech synthesis technology. The results of the call are obtained, sent to the device as feedback data, and displayed to the user.

[0923] Example prompt sentence:

[0924] "I'd like to make a reservation for two at Restaurant X on June 15th at 7pm."

[0925] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0926] Step 1:

[0927] The user uses a device such as a mobile phone or PC to input the destination and purpose of the call. Specifically, the user enters information such as the restaurant name, reservation date and time, and number of people on the device's input screen. For example, the user might enter, "I'd like to make a reservation for two people at Restaurant X on June 15th at 7 PM."

[0928] Input: Destination (e.g. restaurant name), purpose (e.g. reservation date and time and number of people)

[0929] Output: Data entered by the user

[0930] Step 2:

[0931] The terminal encodes the data entered by the user and sends it to the server. Specifically, the terminal encrypts the entered data and sends it to the server using a secure communication protocol (e.g., HTTPS). When the send button is clicked, the data is encoded in real time and sent to the server.

[0932] Input: Data entered by the user

[0933] Output: Encoded data

[0934] Step 3:

[0935] The server receives and decodes the data sent from the device. Since the received data is encrypted, the server decrypts it and converts it into an analyzable format. Here, the server checks the integrity and completeness of the data and filters out any invalid or incomplete data.

[0936] Input: Encoded data

[0937] Output: Decoded data

[0938] Step 4:

[0939] The server uses the decoded data to run a generative AI model and generate natural-sounding conversational sentences. The generative AI model has been trained with a large amount of conversational data in advance, allowing it to smoothly generate natural conversations that meet the user's requests. For example, the generated conversational sentence would be, "I'd like to make a reservation for two people at 7 p.m. on June 15th."

[0940] Input: Decoded data

[0941] Output: Generated dialogue

[0942] Step 5:

[0943] The server uses speech synthesis technology to convert the generated conversational text into natural-sounding speech and automatically calls the specified recipient. During the call, the AI ​​system analyzes the other party's response in real time and generates an appropriate response. For example, in response to the question "Is a reservation possible?", the next question or confirmation will be asked depending on the other party's answer of "yes" or "no."

[0944] Input: Generated conversation

[0945] Output: Synthesized speech

[0946] Step 6:

[0947] Once the call is completed, the server retrieves the call details and results, which include, for example, reservation confirmation information and confirmation items, and stores them in a database.

[0948] Input: Call result (audio data)

[0949] Output: Analyzed call results (text data)

[0950] Step 7:

[0951] The server generates data for providing feedback to the user based on the acquired call result, and the generated feedback data is encoded and transmitted to the terminal.

[0952] Input: Parsed call results

[0953] Output: Encoded feedback data

[0954] Step 8:

[0955] The device decodes the received feedback data and displays it in a format that is intuitive to the user. For example, it displays specific information such as, "Your reservation has been confirmed. It is for 7 PM on June 15th, for two people."

[0956] Input: Encoded feedback data

[0957] Output: Decoded feedback data (for display)

[0958] The above is the specific processing flow of this system.

[0959] (Application example 1)

[0960] 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."

[0961] In today's world, many people feel a psychological burden when making phone calls themselves, and this barrier is even greater for those with hearing impairments or who have difficulty speaking a foreign language. Furthermore, there are problems with not being able to easily respond to sudden reservations or confirmations. A system that can solve these problems is needed.

[0962] 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.

[0963] In this invention, the server includes a means for a user to input the destination and purpose of the call, a means for receiving, decoding, and analyzing the transmitted data, a means for generating natural conversation content using a generative AI model, a means for executing an automated call, a means for obtaining the call result and providing feedback to the user, and a means for displaying the feedback. This allows the user to easily and quickly make call reservations or inquiries using a smartphone and intuitively understand the results.

[0964] The "user input means" is a means for the user to input the destination and purpose of the call.

[0965] The "data transmission means" is a means for encoding input data and transmitting it to the server.

[0966] "Data receiving means" refers to means for receiving and decoding transmitted data.

[0967] The "conversation generation means" is a means for generating natural conversation content based on the decoded data.

[0968] The "call execution means" is a means for executing a call using the generated conversation content.

[0969] The "result acquisition means" is a means for acquiring the result of a call.

[0970] The "feedback means" is a means for providing feedback of the obtained results to the user.

[0971] The "display means" is a means for displaying feedback to the user.

[0972] A "smartphone" is a portable information terminal that allows users to enter data and check results.

[0973] A "generative AI model" is an artificial intelligence model that generates natural conversation content based on input data.

[0974] A "physical store application" is a smartphone application that automatically handles physical store reservations and inquiries.

[0975] "Speech synthesis" is a technology that converts conversation content generated using AI technology into natural-sounding speech.

[0976] This invention is a system that uses a smartphone application for brick-and-mortar stores to make reservations and inquiries without the user having to make a phone call. In an embodiment of the invention, a server, a terminal (smartphone), a generative AI model, a voice synthesis technology, and a call API work together.

[0977] Hardware and software used

[0978] Smartphone: A device on which users can input information and check the results. A dedicated application is installed on the smartphone.

[0979] Server: A device that receives and analyzes data, runs generative AI models, manages calls, and provides feedback on results. The server software uses Node.js, Express, Python, GPT-4 API, and Flask.

[0980] Generative AI model: An artificial intelligence model for generating natural conversation content. Specifically, we use GPT-4.

[0981] Call API: An API for making automated calls. Uses the Twilio API.

[0982] Database: A database for storing call logs and results. MongoDB is used.

[0983] System Operation Overview

[0984] 1. User Input

[0985] The smartphone application allows users to input the destination of the call (e.g., the name of the restaurant) and the purpose of the call (e.g., the date and time of the reservation and the number of people). The application is designed to be intuitive and easy to use.

[0986] 2. Data Transmission

[0987] The smartphone encodes the entered data and sends it securely to the server, where the communication is encrypted to protect privacy.

[0988] 3. Data Receipt and Confirmation

[0989] The server receives the data sent by the smartphone, decodes it, and converts it into an analyzable format, after which it checks the data for consistency and integrity.

[0990] 4. Conversation Generation

[0991] The server uses a generative AI model (GPT-4) to generate natural-sounding conversational sentences based on user-specified content. Prompt sentences are used in this process.

[0992] Example prompt sentence:

[0993] "Cafe Z, please generate a conversation to confirm whether a reservation for two people can be made on August 10th at 2pm."

[0994] 5. Make a call

[0995] The server uses speech synthesis technology to convert the generated conversation into natural-sounding speech, then automatically calls the specified recipient using the Twilio API and executes the call.

[0996] 6. Get call results

[0997] Once the call is complete, the Twilio API sends the call details and results to the server, which analyzes the information and stores it in a database.

[0998] 7. Feedback Generation and Submission

[0999] The server organizes the call results and generates data to provide feedback to the user. This data is then re-encoded and sent to the smartphone.

[1000] 8. Results display

[1001] The smartphone decodes the received feedback data and displays it in a format that is easy for the user to understand. For example, it may display specific information such as, "Your reservation has been confirmed. We are waiting for two people at 2:00 PM on August 10th."

[1002] As a concrete example, when a user enters "Cafe Z, August 10th, 2pm, 2 people" into their smartphone, the server generates a conversation saying "Is a reservation for 2 people possible on August 10th at 2pm?", and the Twilio API automatically calls the cafe to confirm the reservation. The result is displayed on the smartphone as "Reservation confirmed." This series of steps reduces the psychological burden on the user, and allows even users who are not good at making phone calls or who are hearing impaired to easily make reservations.

[1003] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[1004] Step 1:

[1005] The user launches the smartphone application and enters the call destination (e.g., the name of the restaurant) and the purpose of the call (e.g., the date and time of the reservation and the number of people). The entered data is encoded in JSON format. Input: Restaurant name, reservation date and time, and number of people. Output: Encoded JSON data.

[1006] Step 2:

[1007] The device sends the encoded data to the server via HTTPS. Communication is encrypted to protect privacy. Input: Encoded JSON data. Output: Encrypted data packet.

[1008] Step 3:

[1009] The server receives the data sent from the terminal, decrypts it, and converts it into an analyzable format. During this process, it checks the integrity and completeness of the data. Input: Encrypted data packet. Output: Data in an analyzable format.

[1010] Step 4:

[1011] The server sends prompts to the generative AI model (GPT-4) based on the decoded data to generate natural-sounding conversational sentences. During this process, the user's input is given to the model as a prompt. Input: Parsed data and prompt. Output: Generated conversational sentences.

[1012] Step 5:

[1013] The generated conversational text is converted into natural-sounding speech on the server using speech synthesis technology (e.g., Amazon Polly, Google Text-to-Speech, etc.). Input: Generated conversational text. Output: Synthesized speech data.

[1014] Step 6:

[1015] The server automatically calls the specified recipient using the Twilio API and executes the conversation using synthesized voice. During the call, it analyzes the recipient's responses in real time and generates appropriate responses. Input: Recipient's phone number and voice data. Output: Call execution and real-time response data.

[1016] Step 7:

[1017] When the call is completed, the Twilio API sends the call details and results (e.g., reservation confirmation information) to the server. The server analyzes the details and stores them in a database (e.g., MongoDB). Input: Call result data. Output: Analyzed reservation confirmation information and its storage.

[1018] Step 8:

[1019] The server organizes the acquired call results and generates data to provide feedback to the user. This data is then encoded again and sent to the device. Input: Call result data. Output: Encoded data for feedback.

[1020] Step 9:

[1021] The smartphone device decodes the received feedback data and displays it in a format that the user can intuitively understand. For example, specific information such as "The reservation has been confirmed. The date and time is August 10th at 2pm for two people" is displayed. Input: Encoded data for feedback. Output: Specific reservation information displayed to the user.

[1022] 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.

[1023] The present invention relates to a telephone answering system in which a user specifies a specific destination and purpose, and the system automatically handles the call, while also incorporating an emotion engine that recognizes the user's emotions. The system's program works in conjunction with a server and terminals, and generates natural conversations using a generative AI model based on the user's input data and emotions, and then carries out the call. The following describes in detail an embodiment of the present invention.

[1024] 1. User Input

[1025] Terminal: The user uses a terminal such as a mobile phone or PC to input the destination of the call (e.g., the name of the restaurant) and the purpose of the reservation (e.g., the date and time of the reservation and the number of people). The input screen is designed to be intuitive and easy to use, and a function that recognizes the user's emotions has been added.

[1026] 2. User Emotion Recognition

[1027] Terminal: While the user is typing, the terminal's built-in emotion engine recognizes emotions from the user's tone of voice, facial expressions, text content, etc. This emotion data is also used to generate the call content.

[1028] 3. Data Transmission

[1029] Terminal: The data and emotion data entered by the user are encoded and securely transmitted to the server. Encrypted communication is used to protect privacy.

[1030] 4. Data Receipt and Confirmation

[1031] Server: The server receives the data sent by the device, decodes it, and converts it into an analyzable format. It then checks the integrity and completeness of the data.

[1032] 5. Conversation Generation

[1033] Server: The server uses a generative AI model and emotion engine to generate natural-sounding conversations based on the user's specified content and emotions. For example, if the server recognizes that the user is feeling nervous, the generated conversations will have a relaxing tone.

[1034] 6. Make a call

[1035] Server: Converts the generated conversation content from text to speech. It uses speech synthesis technology to generate natural-sounding speech. It then automatically calls the specified recipient. During the call, the AI ​​system responds appropriately based on the recipient's responses, and uses an emotion engine to generate responses that reflect the user's emotions if necessary.

[1036] 7. Get call results

[1037] Server: When the call is completed, the server obtains the call content and results (e.g., reservation confirmation information, confirmation items, etc.), which are then stored and managed in a database.

[1038] 8. Feedback Generation and Submission

[1039] Server: The server organizes the call results and creates feedback data for the user. This data is then encoded again and sent to the device.

[1040] 9. Results display

[1041] Terminal: The terminal decodes the received feedback data and displays it in a format that is intuitive to the user. For example, it displays specific information such as, "Your reservation has been confirmed. The date and time is June 15th at 7 PM for two people."

[1042] Specific examples

[1043] Reservation example

[1044] Suppose a user uses a terminal to request a reservation for "Restaurant X, June 15th, 7pm, for 2 people."

[1045] 1. User Input: While the user is inputting information into the device, the emotion engine recognizes tense emotions.

[1046] 2. Data transmission: The device encodes the data and emotion data and sends them to the server.

[1047] 3. Data reception and verification: The server receives the data and emotion data, decodes it, and analyzes it.

[1048] 4. Conversation generation: The generative AI model and emotion engine generate the following conversational sentence in a neutral tone: "I'd like to make a reservation for two people at 7pm on June 15th."

[1049] 5. Call execution: The server makes a call and reads out the conversation generated by speech synthesis. It also generates a response to the other party's response that reflects the user's emotions.

[1050] 6. Obtain call result: The server receives the answer from the restaurant and records the content.

[1051] 7. Feedback generation and transmission: Organize the call results and send them to the device.

[1052] 8. Display result: The device displays the feedback it received to the user. For example, it displays "Your reservation has been confirmed. We are waiting for two people at 7 PM on June 15th."

[1053] As described above, the system provided by the present invention automatically handles the call content specified by the user and uses an emotion engine to respond in a way that reflects the user's emotions, providing a more natural and comfortable call experience. This lowers the psychological barrier to making a call and is particularly useful for people with hearing impairments and those in stressful situations.

[1054] The processing flow will be explained below.

[1055] Step 1:

[1056] User: Enter the destination and purpose of the call into the input screen of the device. For example, enter information such as "Restaurant X, June 15th, 7 PM, 2 people."

[1057] Step 2:

[1058] Terminal: While accepting user input, the emotion engine analyzes the user's voice tone, facial expressions, and input content to detect the user's emotional state.

[1059] Step 3:

[1060] Terminal: The input data and detected emotion data are encoded and sent to the server using encrypted communication.

[1061] Step 4:

[1062] Server: Receives the encoded data sent from the device. The received data is first stored in secure local storage.

[1063] Step 5:

[1064] Server: Decodes the received data and extracts the user's destination, purpose, and emotion data. It checks the data for consistency and generates an error message if there are any errors.

[1065] Step 6:

[1066] Server: Calls up a generative AI model based on the decoded data and generates natural conversational sentences that incorporate the user's emotional data. For example, if the user is nervous, it adds phrases to help them relax.

[1067] Step 7:

[1068] Server: Based on the generated conversational text, a natural voice is generated using speech synthesis technology, with a tone that reflects the user's emotions.

[1069] Step 8:

[1070] Server: Automatically calls the specified destination phone number. When the call starts, the generated voice is spoken to the other party.

[1071] Step 9:

[1072] Server: Analyzes responses from the other party in real time during the call and generates appropriate responses. Here too, the emotion engine generates responses that reflect the user's emotions based on the other party's responses.

[1073] Step 10:

[1074] Server: Once the call is over, record the outcome of the call, for example, whether the reservation was confirmed or not, and if there are any further questions.

[1075] Step 11:

[1076] Server: Organizes the call results and generates feedback data to the user. This feedback data is also encoded.

[1077] Step 12:

[1078] Server: Sends the generated feedback data to the terminal using encrypted communication.

[1079] Step 13:

[1080] Terminal: Receives feedback data sent from the server. Decodes the received data and converts it into an analyzable format.

[1081] Step 14:

[1082] Terminal: Visually display feedback information to the user, for example, "Your reservation has been confirmed. Please go to Restaurant X on June 15th at 7pm for two people."

[1083] As described above, the system of the present invention recognizes the user's emotions and generates natural conversation content and voice that reflects those emotions, making call answering more comfortable. This allows users in particularly stressful situations or with hearing impairments to make phone calls with peace of mind.

[1084] Example 2

[1085] 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."

[1086] Conventional telephone answering systems often cause users to feel nervous or anxious when making a call, making it difficult for them to make a smooth call, especially for those with hearing impairments or in situations where they feel psychological pressure. Furthermore, the lack of naturalness in the call content can cause discomfort to the other party, which can sometimes prevent users from achieving their intended purpose. The present invention aims to solve these problems and provide a more natural and emotionally sensitive call experience.

[1087] The identification process by the identification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means. In this invention, the server includes means for a user to input a destination and purpose of a call, means for encoding the input data and the user's emotional data and transmitting them to the server, means for receiving and decoding the transmitted data, means for generating natural conversation content using a generative AI model based on the decoded data and emotional data, means for converting the generated conversation content into voice using AI speech synthesis and executing the call, means for generating an appropriate response based on the other party's response during the call, means for acquiring the result of the call, and means for feeding back the acquired result to the user. This makes it possible to realize a natural and smooth call while taking the user's emotions into consideration, and to reliably achieve the purpose of the call.

[1088] A "user" is a person who utilizes the system to input the destination and purpose of a call.

[1089] A "call destination" is the person or location to which a user wishes to place a call.

[1090] The "matters" are the contents or purpose that the user wants to convey through the call.

[1091] A "terminal" is a device used by a user to input the destination and purpose of a call, and includes a mobile phone, a personal computer, and the like.

[1092] "Emotion data" is data that represents the user's psychological state, obtained from the user's tone of voice, facial expression, and input text content.

[1093] "Encoding" is the process of converting data to be transmitted into a specific format.

[1094] A "server" is a device that receives and processes data sent from a terminal.

[1095] "Decoding" is the process of converting received data back into its original format.

[1096] A "generative AI model" is an algorithm or program that uses artificial intelligence technology to generate natural-sounding conversation content based on input data.

[1097] "AI voice synthesis" is a technology that converts text data into voice data.

[1098] A "call" is an act of actually having a conversation based on the destination and purpose input by the user.

[1099] A "response" is a reply or response received from the other party during a call.

[1100] "Feedback" is information that reports the results of a call to the user.

[1101] This invention is a telephone answering system in which a user specifies a specific destination and purpose, and the system automatically answers the call. The system also incorporates an emotion engine that recognizes the user's emotions, and the server and terminals work together. Detailed embodiments for implementing this system are described below.

[1102] 1. User Input

[1103] Device: The user uses a device such as a mobile phone or PC to input the destination (e.g., restaurant name) and purpose (e.g., reservation date and time and number of people). The input interface is designed to be intuitive for users, with features such as check boxes and drop-down menus. In addition, the microphone and camera are activated when inputting information, and the device is equipped with a function that recognizes the user's tone of voice and facial expressions in real time.

[1104] 2. Emotion recognition

[1105] Terminal: While the user is entering information, the emotion engine analyzes voice tone, facial expression recognition, and the input text content to detect the user's emotional state. For example, it determines whether the user is nervous based on the intonation of their voice or facial expression. This function generates the user's emotional data.

[1106] 3. Data Transmission

[1107] Terminal: The data and emotion data entered by the user are encoded and securely transmitted to the server using encrypted communication technology such as HTTPS, preventing data leakage and degradation.

[1108] 4. Data Receipt and Confirmation

[1109] Server: Receives the data sent from the device, decodes it, and converts it into an analyzable format. The server checks the consistency and integrity of the data to ensure it has not been tampered with. It also calculates checksums and verifies the data format.

[1110] 5. Conversation Generation

[1111] Server: Using a generative AI model, the server generates natural-sounding conversational sentences based on the content and emotional data specified by the user. For example, if the server detects that the user is nervous, it generates a conversational sentence with a relaxed tone, such as "Please make a reservation for two people at 7 p.m. on June 15th." The generative AI model uses the prompt to generate the conversational sentence.

[1112] 6. Make a call

[1113] Server: Converts the generated conversation content from text to speech. It uses speech synthesis technology (e.g., Google Text-to-Speech) to generate natural-sounding speech and automatically calls the specified recipient. During the call, the conversational AI generates appropriate responses in real time based on the recipient's responses, and uses an emotion engine to respond in a way that reflects the user's emotions.

[1114] 7. Get call results

[1115] Server: When the call is completed, the call content and results (e.g., reservation confirmation information, confirmation items, etc.) are obtained and saved in a database. This information can be referenced later, improving user convenience.

[1116] 8. Feedback Generation and Submission

[1117] Server: Organizes the call results and generates data to provide feedback to the user. This is then encoded again and securely sent to the device using HTTPS.

[1118] 9. Results display

[1119] Terminal: Decodes the received feedback data and displays it in a format that is easy for the user to understand. For example, it displays specific information such as "The reservation has been confirmed. It will be made on June 15th at 7pm for two people." It is also possible to notify the user of the results using a voice readout function.

[1120] Specific examples

[1121] A specific example will be given in which a user uses a terminal to request a reservation for "Restaurant X, June 15th, 7pm, for 2 people."

[1122] 1. User input: The user enters "Restaurant X, June 15th, 7pm, 2 people" into the terminal, and the emotion engine recognizes the tension.

[1123] 2. Data transmission: The device encodes the data and emotion data and sends them to the server.

[1124] 3. Data reception and verification: The server receives the data, decodes it, and verifies its integrity.

[1125] 4. Conversation generation: The generative AI model generates the following conversation in a neutral tone: "I'd like to make a reservation for two people at 7 p.m. on June 15th."

[1126] 5. Call execution: The server makes the call and reads out the conversation generated by speech synthesis technology. Depending on the other party's response, an appropriate response reflecting the other party's emotions is given.

[1127] 6. Obtain call result: The server receives a confirmation of the reservation from the restaurant and records the details.

[1128] 7. Feedback generation and transmission: Organize the call results and send them to the device.

[1129] 8. Displaying the result: The terminal displays the result to the user: "Reservation confirmed. Two guests will be waiting at 7 PM on June 15th."

[1130] In this way, the system of the present invention provides a natural calling experience that takes into account the user's emotions, enabling the purpose of the call to be achieved efficiently.

[1131] The flow of the identification process in the second embodiment will be described with reference to FIG.

[1132] Step 1: User Input

[1133] Device: The user enters the call destination (e.g., restaurant name) and purpose (e.g., reservation date and time and number of people) on a device such as a mobile phone or PC. The input interface is equipped with check boxes and drop-down menus, and is designed to allow users to operate it intuitively. Input data includes the destination "Restaurant X," the date and time "June 15th, 7:00 PM," and the number of people "2." In addition, the microphone and camera are activated to collect the user's voice tone and facial expressions.

[1134] Input: Destination, purpose (reservation date and time, number of people)

[1135] Output: Input data, emotion data

[1136] Step 2: Emotion Recognition

[1137] Terminal: The emotion engine generates emotion data by analyzing the user's voice tone, facial expression recognition, and input text content. For example, it determines whether the user is nervous based on the intonation of their voice and facial expression. This provides emotion data that indicates the user's psychological state.

[1138] Input: Voice tone, facial expression data, input text

[1139] Output: Emotion data

[1140] Step 3: Send data

[1141] Terminal: Input data and emotion data are encoded and sent securely to the server using encryption technology (e.g., HTTPS). Data is transferred in a manner that prevents degradation and leakage.

[1142] Input: Input data, emotion data

[1143] Output: Encrypted data

[1144] Step 4: Data Receipt and Verification

[1145] Server: Receives encrypted data sent from the device. Decodes the received data and converts it into an analyzable format. Then, calculates checksums and verifies the data format to ensure data integrity and completeness.

[1146] Input: Encrypted data

[1147] Output: Decoded data

[1148] Step 5: Conversation generation

[1149] Server: Using a generative AI model, the server generates natural-sounding conversational sentences based on the decoded input data and emotional data. For example, if the user is recognized as nervous, the server generates a conversational sentence in a relaxed tone, such as "I'd like to make a reservation for two people at 7 p.m. on June 15th." The server uses a prompt sentence.

[1150] Input: Decoded data, emotion data

[1151] Output: Conversation

[1152] Step 6: Make the call

[1153] Server: Converts the generated conversational text from text to speech. It uses speech synthesis technology (e.g., Google Text-to-Speech) to generate natural-sounding speech and automatically calls the specified recipient. During the call, the conversational AI generates appropriate responses in real time based on the recipient's responses, and the emotion engine responds by reflecting the user's emotions.

[1154] Input: Conversation

[1155] Output: Audio data, call answering

[1156] Step 7: Get call results

[1157] Server: Once the call is completed, the server obtains the call details and results (e.g., reservation confirmation information, confirmation items, etc.). The obtained data is stored in a database.

[1158] Input:Call Answer

[1159] Output: Call result data

[1160] Step 8: Generate and send feedback

[1161] Server: Organizes the acquired call results and generates data to provide feedback to the user. This feedback data is then re-encoded and sent to the device using encryption technology.

[1162] Input: Call result data

[1163] Output: Feedback data

[1164] Step 9: View the results

[1165] Terminal: Decodes the received feedback data and displays the results in a format that is easy for the user to understand. For example, specific information such as "Reservation confirmed. June 15th at 7pm for two people" is displayed on the terminal screen. Voice notification is also possible.

[1166] Input: Feedback data

[1167] Output: Display result

[1168] (Application example 2)

[1169] 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."

[1170] In autonomous vehicles, users are expected to be able to comfortably use various services (restaurant reservations, hotel reservations, medical appointments, etc.) from inside the vehicle, but there is a lack of a system that automatically generates and executes natural responses based on input information that reflect the user's emotions.In addition, since calls that ignore the user's emotions can be unnatural and stressful, it is necessary to provide natural conversations that take the user's emotions into consideration.

[1171] 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 a user to input the destination and purpose of the call, means for recognizing emotions from the user's tone of voice, facial expression, text content, etc., means for encoding the input data and emotional data and transmitting them to the server, means for receiving and decoding the transmitted data and emotional data, means for using a generative AI model to generate natural conversation content based on the decoded data, means for adjusting the tone of the conversation based on the user's emotional data, means for conducting a call using the generated conversation content, means for acquiring the results of the call, and means for feeding back the acquired results to the user. This enables comfortable service use in an autonomous vehicle and realizes natural conversation responses that correspond to the user's emotions.

[1172] "Means for users to input the destination and purpose of the call" refers to the means by which users use a terminal such as a mobile phone or computer to input the destination (e.g., restaurant, hotel, medical institution, etc.) and the purpose (e.g., reservation date and time, number of people, etc.).

[1173] The "means for recognizing emotions" refers to a means for automatically recognizing emotions from the user's tone of voice, facial expressions, text content, etc., using an emotion engine or sensor installed in the device.

[1174] The "means for encoding data and emotion data and transmitting them to the server" refers to a means for encoding (encrypting) the destination and purpose data entered by the user and the emotion data obtained from the emotion recognition means and transmitting them securely to the server.

[1175] The "means for receiving and decoding" refers to the means by which the server receives the data and emotion data sent from the terminal and decodes (decodes) it into an analyzable format.

[1176] "Means for using a generative AI model" refers to means by which the server generates natural conversation content using a generative AI model based on data and emotional data sent by the user.

[1177] The "means for adjusting the tone of the conversation" is a means for adjusting the tone of the conversation (e.g., relaxed tone, gentle tone, etc.) based on the user's emotional data in the generated conversation content.

[1178] The "means for executing a call using the conversation content" is a means for converting the generated conversation content from text to voice and automatically making a call to a designated recipient.

[1179] The "means for obtaining the results of a call" refers to the means by which the server obtains the contents of the call and its results (e.g., reservation confirmation information, confirmation items, etc.) when the call is completed.

[1180] The "means for providing feedback to the user" is a means for encoding data to feed back the acquired call result to the user, transmitting the data to the terminal, and displaying the data in a form that the user can intuitively understand.

[1181] This invention describes a specific embodiment of a voice assistant application installed in an autonomous vehicle. This application allows the user to specify the destination and purpose of a reservation from inside the vehicle, and the system automatically handles the call. Furthermore, it can recognize the user's emotions and generate natural conversations using a generative AI model.

[1182] First, the user uses the voice assistant app in the autonomous vehicle to specify the destination (e.g., restaurant, hotel, medical institution, etc.) and purpose (e.g., reservation date and time, number of people, etc.). This input is converted into text using voice recognition technology. For voice recognition, Google Speech Recognition API, for example, is used.

[1183] Next, the emotion engine installed on the device recognizes emotions from the voice tone, facial expressions, text content, etc. while the user is typing. For emotion recognition, for example, the Python library "Emotion Recognition" is used.

[1184] The input data and emotion data are encoded (encrypted) and securely transmitted to the server. This communication is via the Internet and uses encryption protocols (e.g., TLS / SSL).

[1185] The server receives the data and emotion data sent from the device and decodes it. After decoding, the server uses a generative AI model (such as GPT-3) to generate natural-sounding conversation content based on the content and emotion specified by the user. The tone of the conversation is also adjusted based on the emotion data. For example, if the user is nervous, a relaxing tone of voice will be generated.

[1186] The generated conversation is converted into natural-sounding speech using speech synthesis technology (such as the Google Text-to-Speech API). The call is then automatically placed to the specified recipient. During the call, the AI ​​system responds appropriately based on the recipient's response, and uses an emotion engine to generate responses that reflect the user's emotions, if necessary.

[1187] Once the call is completed, the server obtains the results of the call (e.g., reservation confirmation information, confirmation items, etc.), stores them in a database, and manages them. This information is then encoded and sent back to the device.

[1188] Finally, the device decodes the received feedback data and displays it in a format that is intuitive to the user, such as "Your reservation has been confirmed. The date and time is June 15th at 7 PM for two people."

[1189] Examples of specific prompts include:

[1190] User: "I'd like to make a reservation for two at Restaurant X on June 15th at 7pm."

[1191] Input to AI model: "Reservation call - user is nervous. Please speak in a relaxed tone."

[1192] Generated dialogue: "Hello, Restaurant X. I'd like to make a reservation for two people on June 15th at 7pm." "Yes, I understand. We look forward to seeing you."

[1193] In this way, the system of the present invention enables comfortable use of services inside an autonomous vehicle and is capable of providing natural conversational responses that correspond to the user's emotions.

[1194] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[1195] Step 1:

[1196] The user inputs the destination and purpose of the call. Using the voice assistant app in the autonomous vehicle, the user specifies the destination (e.g., restaurant, hotel, medical institution, etc.) and purpose (e.g., reservation date and time, number of people, etc.). This input is converted into text using voice recognition technology (e.g., Google Speech Recognition API). The input data is obtained in the form of text: "destination" and "purpose."

[1197] Step 2:

[1198] The device recognizes emotions from the user's voice tone, facial expressions, text content, etc. The emotion engine (e.g., Emotion Recognition library) installed on the device analyzes the voice tone while the user is typing and recognizes the user's emotions in real time. Emotion data is obtained in the form of "emotional state."

[1199] Step 3:

[1200] The device encodes the input data and emotion data and sends them to the server. The encoding (encryption) process uses, for example, the TLS / SSL protocol. The encoded data is securely sent to the server. The input data and emotion data are sent as a single encrypted packet.

[1201] Step 4:

[1202] The server receives and decodes the transmitted data and emotional data. The server receives the encrypted data transmitted from the device and decodes it into an analyzable format. This allows the "destination," "message," and "emotional state" data to arrive at the server.

[1203] Step 5:

[1204] The server uses a generative AI model (e.g., GPT-3) based on the decoded data to generate natural-sounding conversation content. The server inputs the "destination," "purpose," and "emotional state" data into the generative AI model to generate appropriate conversation content. The tone of the conversation is adjusted based on the user's emotional state. The output is obtained as "conversation content."

[1205] Step 6:

[1206] The server converts the generated conversation content into natural-sounding speech using speech synthesis technology (e.g., Google Text-to-Speech API). The server then converts the text-format "conversation content" into voice data and prepares to make a call to the specified recipient. The output is obtained as voice data.

[1207] Step 7:

[1208] The server automatically calls the specified recipient. During the call, the AI ​​system responds appropriately based on the recipient's response and uses an emotion engine to generate a response that reflects the user's emotions. Emotion recognition continues as the conversation progresses, and any necessary corrections are made. Data is exchanged in real time.

[1209] Step 8:

[1210] Once the call is complete, the server obtains the call results (e.g., reservation confirmation information, confirmation items, etc.). After the call ends, the server collects various confirmation data and stores it in a database that manages it. The output is obtained as "call result data."

[1211] Step 9:

[1212] The server organizes the call results it has obtained and creates data to provide feedback to the user. It re-encodes (encrypts) the call result data and sends it to the device. The encoded feedback data is then securely sent to the device.

[1213] Step 10:

[1214] The device decodes the received feedback data and displays it in a format that is intuitively understandable to the user. The decoded feedback content is displayed to the user as specific information, such as "The reservation has been confirmed. The date and time is June 15th at 7 PM for two people."

[1215] 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.

[1216] 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.

[1217] 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.

[1218] [Fourth embodiment]

[1219] FIG. 7 shows an example of the configuration of a data processing system 410 according to the fourth embodiment.

[1220] 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.

[1221] 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).

[1222] 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.

[1223] 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.

[1224] 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).

[1225] 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.

[1226] 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.

[1227] 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.

[1228] 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.

[1229] 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.

[1230] 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.

[1231] 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."

[1232] The present invention relates to a telephone answering system in which a user specifies a specific destination and purpose, and the system automatically answers the call. The program of this system works in conjunction with a server and a terminal, and generates natural conversation using a generative AI model based on user input data, and then conducts the call. Below, we will describe in detail the embodiments of the present invention.

[1233] 1. User Input

[1234] Terminal: The user uses a terminal such as a mobile phone or PC to input the destination of the call (e.g., the name of the restaurant) and the purpose of the call (e.g., the date and time of the reservation and the number of people). The input screen is designed to be intuitive and easy to use.

[1235] 2. Data Transmission

[1236] Terminal: Data entered by the user is encoded and securely sent to the server. By default, communication is encrypted to protect privacy.

[1237] 3. Data Receipt and Confirmation

[1238] Server: The server receives the data sent from the device, decodes it, and converts it into an analyzable format. It then checks the integrity and completeness of the data.

[1239] 4. Conversation Generation

[1240] Server: The server uses a generative AI model to generate natural-sounding dialogue based on user input, appropriate for the specific scenario.

[1241] 5. Make a call

[1242] Server: The server uses speech synthesis technology to convert the generated conversational text into natural-sounding speech. It then automatically calls the specified recipient. During the call, the AI ​​system responds appropriately based on the recipient's response.

[1243] 6. Get call results

[1244] Server: When the call is completed, the server obtains the call content and results (e.g., reservation confirmation information, confirmation items, etc.), which are then stored and managed in a database.

[1245] 7. Feedback Generation and Submission

[1246] Server: The server organizes the call results and creates feedback data for the user. This data is then encoded again and sent to the device.

[1247] 8. Results display

[1248] Terminal: The terminal decodes the received feedback data and displays it in a format that is intuitive to the user. For example, it displays specific information such as, "Your reservation has been confirmed. The date and time is June 15th at 7 PM for two people."

[1249] This eliminates the need for users to make phone calls themselves, reducing the psychological burden. It also enables people with hearing impairments to make phone calls without having to go through a proxy.

[1250] Specific examples

[1251] Reservation example

[1252] Suppose a user uses a terminal to request a reservation for "Restaurant X, June 15th, 7pm, for 2 people."

[1253] 1. User Input: The user enters information at the terminal.

[1254] 2. Data transmission: The device encodes the data and sends it to the server.

[1255] 3. Data reception and verification: The server receives the data, decodes it, and parses it.

[1256] 4. Conversation generation: The generative AI model generates the conversation sentence, "I would like to make a reservation for two people at 7 p.m. on June 15th."

[1257] 5. Call execution: The server makes the call and reads out the conversation generated by speech synthesis.

[1258] 6. Obtain call result: The server receives the answer from the restaurant and records the content.

[1259] 7. Feedback generation and transmission: Organize the call results and send them to the device.

[1260] 8. Display result: The device displays the feedback it received to the user. For example, it displays "Your reservation has been confirmed. We are waiting for two people at 7 PM on June 15th."

[1261] As described above, the system provided by the present invention automatically carries out the call content specified by the user and provides feedback on the results to the user. This lowers the psychological barrier to making a call and is particularly useful for people with hearing impairments or who have difficulty speaking in a foreign language.

[1262] The processing flow will be explained below.

[1263] Step 1:

[1264] User: Enter the destination and purpose of the call into the device's input screen. For example, enter information such as the restaurant name "Restaurant X," the reservation date and time "June 15th, 7 PM," and the number of people "2."

[1265] Step 2:

[1266] Terminal: Encodes the data entered by the user and converts it into a format that can be transmitted. For security reasons, it may encrypt the data.

[1267] Step 3:

[1268] Terminal: Sends the encoded data to the server using a secure protocol such as HTTPS.

[1269] Step 4:

[1270] Server: Receives data sent from the device and temporarily stores the received data in local storage.

[1271] Step 5:

[1272] Server: Decodes the received data and restores it to its original form. Through the decoding process, information entered by the user, such as the destination, purpose, date and time, and number of people, is obtained.

[1273] Step 6:

[1274] Server: Checks the integrity of the decoded data. Checks that all necessary information is present and that the format is correct. If there is a deficiency, generates an error message and prepares to send it to the terminal.

[1275] Step 7:

[1276] Server: If the data is correct, the generative AI model is invoked to generate natural-sounding conversational content based on the input data. For example, it generates a conversational sentence like, "Hello, is this Restaurant X? I'd like to make a reservation for two people at 7 p.m. on June 15th."

[1277] Step 8:

[1278] Server: Converts the generated conversation content from text to speech. It uses speech synthesis technology to generate natural-sounding speech.

[1279] Step 9:

[1280] Server: Automatically calls the specified phone number. Uses AI voice synthesis to make the call using the generated voice.

[1281] Step 10:

[1282] Server: Analyzes responses from the other party in real time during the call and responds appropriately. If necessary, generates new conversation content and converts it back into voice to continue the call.

[1283] Step 11:

[1284] Server: When the call ends, record the call result and information obtained from the other party. For example, obtain information such as "The reservation has been confirmed. Two people will be waiting for you at 7 PM on June 15th."

[1285] Step 12:

[1286] Server: Organizes the call results and generates data to provide feedback to the user. The feedback data includes the call results and confirmations.

[1287] Step 13:

[1288] Server: The generated feedback data is encoded and prepared for transmission to the device. Security measures such as encryption are again applied.

[1289] Step 14:

[1290] Terminal: Receives feedback data sent from the server. Decodes the received data and converts it into an analyzable format.

[1291] Step 15:

[1292] Terminal: Visually display feedback data to the user. For example, "Your reservation has been confirmed. Please go to Restaurant X on June 15th at 7pm for two people."

[1293] As described above, this system performs a series of processes based on the data entered by the user, handles the call on behalf of the user, and provides feedback on the results to the user.

[1294] Example 1

[1295] 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."

[1296] There is a need to eliminate the psychological burden of making phone calls and the difficulties faced by hearing-impaired users. In particular, for certain tasks such as making reservations or inquiries, a system is needed that allows users to achieve their goals through natural conversation without having to make a direct phone call.

[1297] 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.

[1298] In this invention, the server includes means for a user to input a destination and purpose of a call, means for encoding the input data and transmitting it to the server, means for receiving and decoding the transmitted data, means for generating natural conversation content using a generative AI model based on the decoded data, means for executing a call using the generated conversation content with speech synthesis technology, means for acquiring and storing the results of the call in a database, and means for encoding the acquired results and feeding them back to the user. This reduces the psychological burden on the user without the need to make a call directly, and makes it easy for even hearing-impaired users to make calls.

[1299] "User" refers to any individual or legal entity that uses the System.

[1300] "Terminal" refers to a device used by a user, such as a mobile phone, computer, or tablet.

[1301] "Call" refers to a telephone communication based on a destination and purpose.

[1302] "Destination" refers to the location or organization that the user specifies to place the call.

[1303] "Purpose" refers to the content or purpose that the user wants to achieve through the call.

[1304] "Encoding" refers to the process of encrypting or converting the format of data to be sent.

[1305] "Decoding" refers to the process of returning received encrypted data or format-converted data to its original format.

[1306] "Server" refers to a computer system that receives, processes, stores, and transmits data.

[1307] A "generative AI model" refers to an algorithm or model that uses artificial intelligence technology to generate natural-sounding conversational sentences.

[1308] "Speech synthesis technology" refers to the technology that converts text data into natural speech.

[1309] "Database" refers to a data storage system for storing obtained call results and other information.

[1310] "Feedback" refers to the process of communicating call results and other information to the user.

[1311] This invention is a telephone answering system in which a user specifies a specific destination and purpose, and the system automatically answers the call. This system works in cooperation with a server and terminals, and generates natural conversations using a generative AI model based on user input data, and then executes the call.

[1312] First, the user uses a device such as a mobile phone or PC to input the destination (e.g., restaurant) and the purpose of the call (e.g., reservation date and time and number of people). The input screen is designed to be intuitive and easy to use, with features such as drop-down menus and calendar selection functions.

[1313] The data entered by the user is then encoded on the terminal and sent securely to the server, for example using the HTTPS protocol for secure communication.

[1314] The server receives the data sent from the device, decodes it, and converts it into an analyzable format. After decoding, the integrity and completeness of the received data are checked, and invalid or incomplete data is filtered out.

[1315] Based on the decoded data, the server uses a generative AI model to generate natural-sounding conversations. This generative AI model has been pre-trained with a large amount of conversation data, allowing it to generate natural conversations for a variety of scenarios. For example, if a user requests a reservation for "Restaurant X, June 15th at 7 PM for two people," the generated conversation will be "I'd like to make a reservation for two people at 7 PM on June 15th."

[1316] The generated conversational text is converted into natural-sounding speech on the server using speech synthesis technology. This converted speech is then used to automatically place a call to the specified recipient. During the call, the AI ​​system analyzes the other party's response in real time and provides an appropriate reply. For example, in response to the inquiry "Is a reservation possible?", the system will ask the appropriate next question or confirm the answer depending on whether the other party answers "yes" or "no."

[1317] Once the call is completed, the server retrieves the call details and results, which include, for example, reservation confirmation information and confirmation items, and stores them in a database.

[1318] The acquired call results are organized, and data for providing feedback to the user is generated in the server. This feedback data is then encoded again and sent to the terminal.

[1319] The device decodes the received feedback data and displays it in a format that the user can intuitively understand, such as "Your reservation has been confirmed. The date and time is June 15th at 7 PM for two people."

[1320] As a concrete example, consider a scenario where a user requests a reservation for "Restaurant X, June 15th, 7pm, for two people" on a device. When the user enters information on the input screen and clicks the send button, the data is encoded and sent to the server. The server receives, decodes, and analyzes the data. The generative AI model then generates appropriate conversational text and makes a call using speech synthesis technology. The results of the call are obtained, sent to the device as feedback data, and displayed to the user.

[1321] Example prompt sentence:

[1322] "I'd like to make a reservation for two at Restaurant X on June 15th at 7pm."

[1323] The flow of the identification process in the first embodiment will be described with reference to FIG.

[1324] Step 1:

[1325] The user uses a device such as a mobile phone or PC to input the destination and purpose of the call. Specifically, the user enters information such as the restaurant name, reservation date and time, and number of people on the device's input screen. For example, the user might enter, "I'd like to make a reservation for two people at Restaurant X on June 15th at 7 PM."

[1326] Input: Destination (e.g. restaurant name), purpose (e.g. reservation date and time and number of people)

[1327] Output: Data entered by the user

[1328] Step 2:

[1329] The terminal encodes the data entered by the user and sends it to the server. Specifically, the terminal encrypts the entered data and sends it to the server using a secure communication protocol (e.g., HTTPS). When the send button is clicked, the data is encoded in real time and sent to the server.

[1330] Input: Data entered by the user

[1331] Output: Encoded data

[1332] Step 3:

[1333] The server receives and decodes the data sent from the device. Since the received data is encrypted, the server decrypts it and converts it into an analyzable format. Here, the server checks the integrity and completeness of the data and filters out any invalid or incomplete data.

[1334] Input: Encoded data

[1335] Output: Decoded data

[1336] Step 4:

[1337] The server uses the decoded data to run a generative AI model and generate natural-sounding conversational sentences. The generative AI model has been trained with a large amount of conversational data in advance, allowing it to smoothly generate natural conversations that meet the user's requests. For example, the generated conversational sentence would be, "I'd like to make a reservation for two people at 7 p.m. on June 15th."

[1338] Input: Decoded data

[1339] Output: Generated dialogue

[1340] Step 5:

[1341] The server uses speech synthesis technology to convert the generated conversational text into natural-sounding speech and automatically calls the specified recipient. During the call, the AI ​​system analyzes the other party's response in real time and generates an appropriate response. For example, in response to the question "Is a reservation possible?", the next question or confirmation will be asked depending on the other party's answer of "yes" or "no."

[1342] Input: Generated conversation

[1343] Output: Synthesized speech

[1344] Step 6:

[1345] Once the call is completed, the server retrieves the call details and results, which include, for example, reservation confirmation information and confirmation items, and stores them in a database.

[1346] Input: Call result (audio data)

[1347] Output: Analyzed call results (text data)

[1348] Step 7:

[1349] The server generates data for providing feedback to the user based on the acquired call result, and the generated feedback data is encoded and transmitted to the terminal.

[1350] Input: Parsed call results

[1351] Output: Encoded feedback data

[1352] Step 8:

[1353] The device decodes the received feedback data and displays it in a format that is intuitive to the user. For example, it displays specific information such as, "Your reservation has been confirmed. It is for 7 PM on June 15th, for two people."

[1354] Input: Encoded feedback data

[1355] Output: Decoded feedback data (for display)

[1356] The above is the specific processing flow of this system.

[1357] (Application example 1)

[1358] 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."

[1359] In today's world, many people feel a psychological burden when making phone calls themselves, and this barrier is even greater for those with hearing impairments or who have difficulty speaking a foreign language. Furthermore, there are problems with not being able to easily respond to sudden reservations or confirmations. A system that can solve these problems is needed.

[1360] 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.

[1361] In this invention, the server includes a means for a user to input the destination and purpose of the call, a means for receiving, decoding, and analyzing the transmitted data, a means for generating natural conversation content using a generative AI model, a means for executing an automated call, a means for obtaining the call result and providing feedback to the user, and a means for displaying the feedback. This allows the user to easily and quickly make call reservations or inquiries using a smartphone and intuitively understand the results.

[1362] The "user input means" is a means for the user to input the destination and purpose of the call.

[1363] The "data transmission means" is a means for encoding input data and transmitting it to the server.

[1364] "Data receiving means" refers to means for receiving and decoding transmitted data.

[1365] The "conversation generation means" is a means for generating natural conversation content based on the decoded data.

[1366] The "call execution means" is a means for executing a call using the generated conversation content.

[1367] The "result acquisition means" is a means for acquiring the result of a call.

[1368] The "feedback means" is a means for providing feedback of the obtained results to the user.

[1369] The "display means" is a means for displaying feedback to the user.

[1370] A "smartphone" is a portable information terminal that allows users to enter data and check results.

[1371] A "generative AI model" is an artificial intelligence model that generates natural conversation content based on input data.

[1372] A "physical store application" is a smartphone application that automatically handles physical store reservations and inquiries.

[1373] "Speech synthesis" is a technology that converts conversation content generated using AI technology into natural-sounding speech.

[1374] This invention is a system that uses a smartphone application for brick-and-mortar stores to make reservations and inquiries without the user having to make a phone call. In an embodiment of the invention, a server, a terminal (smartphone), a generative AI model, a voice synthesis technology, and a call API work together.

[1375] Hardware and software used

[1376] Smartphone: A device on which users can input information and check the results. A dedicated application is installed on the smartphone.

[1377] Server: A device that receives and analyzes data, runs generative AI models, manages calls, and provides feedback on results. The server software uses Node.js, Express, Python, GPT-4 API, and Flask.

[1378] Generative AI model: An artificial intelligence model for generating natural conversation content. Specifically, we use GPT-4.

[1379] Call API: An API for making automated calls. Uses the Twilio API.

[1380] Database: A database for storing call logs and results. MongoDB is used.

[1381] System Operation Overview

[1382] 1. User Input

[1383] The smartphone application allows users to input the destination of the call (e.g., the name of the restaurant) and the purpose of the call (e.g., the date and time of the reservation and the number of people). The application is designed to be intuitive and easy to use.

[1384] 2. Data Transmission

[1385] The smartphone encodes the entered data and sends it securely to the server, where the communication is encrypted to protect privacy.

[1386] 3. Data Receipt and Confirmation

[1387] The server receives the data sent by the smartphone, decodes it, and converts it into an analyzable format, after which it checks the data for consistency and integrity.

[1388] 4. Conversation Generation

[1389] The server uses a generative AI model (GPT-4) to generate natural-sounding conversational sentences based on user-specified content. Prompt sentences are used in this process.

[1390] Example prompt sentence:

[1391] "Cafe Z, please generate a conversation to confirm whether a reservation for two people can be made on August 10th at 2pm."

[1392] 5. Make a call

[1393] The server uses speech synthesis technology to convert the generated conversation into natural-sounding speech, then automatically calls the specified recipient using the Twilio API and executes the call.

[1394] 6. Get call results

[1395] Once the call is complete, the Twilio API sends the call details and results to the server, which analyzes the information and stores it in a database.

[1396] 7. Feedback Generation and Submission

[1397] The server organizes the call results and generates data to provide feedback to the user. This data is then re-encoded and sent to the smartphone.

[1398] 8. Results display

[1399] The smartphone decodes the received feedback data and displays it in a format that is easy for the user to understand. For example, it may display specific information such as, "Your reservation has been confirmed. We are waiting for two people at 2:00 PM on August 10th."

[1400] As a concrete example, when a user enters "Cafe Z, August 10th, 2pm, 2 people" into their smartphone, the server generates a conversation saying "Is a reservation for 2 people possible on August 10th at 2pm?", and the Twilio API automatically calls the cafe to confirm the reservation. The result is displayed on the smartphone as "Reservation confirmed." This series of steps reduces the psychological burden on the user, and allows even users who are not good at making phone calls or who are hearing impaired to easily make reservations.

[1401] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[1402] Step 1:

[1403] The user launches the smartphone application and enters the call destination (e.g., the name of the restaurant) and the purpose of the call (e.g., the date and time of the reservation and the number of people). The entered data is encoded in JSON format. Input: Restaurant name, reservation date and time, and number of people. Output: Encoded JSON data.

[1404] Step 2:

[1405] The device sends the encoded data to the server via HTTPS. Communication is encrypted to protect privacy. Input: Encoded JSON data. Output: Encrypted data packet.

[1406] Step 3:

[1407] The server receives the data sent from the terminal, decrypts it, and converts it into an analyzable format. During this process, it checks the integrity and completeness of the data. Input: Encrypted data packet. Output: Data in an analyzable format.

[1408] Step 4:

[1409] The server sends prompts to the generative AI model (GPT-4) based on the decoded data to generate natural-sounding conversational sentences. During this process, the user's input is given to the model as a prompt. Input: Parsed data and prompt. Output: Generated conversational sentences.

[1410] Step 5:

[1411] The generated conversational text is converted into natural-sounding speech on the server using speech synthesis technology (e.g., Amazon Polly, Google Text-to-Speech, etc.). Input: Generated conversational text. Output: Synthesized speech data.

[1412] Step 6:

[1413] The server automatically calls the specified recipient using the Twilio API and executes the conversation using synthesized voice. During the call, it analyzes the recipient's responses in real time and generates appropriate responses. Input: Recipient's phone number and voice data. Output: Call execution and real-time response data.

[1414] Step 7:

[1415] When the call is completed, the Twilio API sends the call details and results (e.g., reservation confirmation information) to the server. The server analyzes the details and stores them in a database (e.g., MongoDB). Input: Call result data. Output: Analyzed reservation confirmation information and its storage.

[1416] Step 8:

[1417] The server organizes the acquired call results and generates data to provide feedback to the user. This data is then encoded again and sent to the device. Input: Call result data. Output: Encoded data for feedback.

[1418] Step 9:

[1419] The smartphone device decodes the received feedback data and displays it in a format that the user can intuitively understand. For example, specific information such as "The reservation has been confirmed. The date and time is August 10th at 2pm for two people" is displayed. Input: Encoded data for feedback. Output: Specific reservation information displayed to the user.

[1420] 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.

[1421] The present invention relates to a telephone answering system in which a user specifies a specific destination and purpose, and the system automatically handles the call, while also incorporating an emotion engine that recognizes the user's emotions. The system's program works in conjunction with a server and terminals, and generates natural conversations using a generative AI model based on the user's input data and emotions, and then carries out the call. The following describes in detail an embodiment of the present invention.

[1422] 1. User Input

[1423] Terminal: The user uses a terminal such as a mobile phone or PC to input the destination of the call (e.g., the name of the restaurant) and the purpose of the reservation (e.g., the date and time of the reservation and the number of people). The input screen is designed to be intuitive and easy to use, and a function that recognizes the user's emotions has been added.

[1424] 2. User Emotion Recognition

[1425] Terminal: While the user is typing, the terminal's built-in emotion engine recognizes emotions from the user's tone of voice, facial expressions, text content, etc. This emotion data is also used to generate the call content.

[1426] 3. Data Transmission

[1427] Terminal: The data and emotion data entered by the user are encoded and securely transmitted to the server. Encrypted communication is used to protect privacy.

[1428] 4. Data Receipt and Confirmation

[1429] Server: The server receives the data sent by the device, decodes it, and converts it into an analyzable format. It then checks the integrity and completeness of the data.

[1430] 5. Conversation Generation

[1431] Server: The server uses a generative AI model and emotion engine to generate natural-sounding conversations based on the user's specified content and emotions. For example, if the server recognizes that the user is feeling nervous, the generated conversations will have a relaxing tone.

[1432] 6. Make a call

[1433] Server: Converts the generated conversation content from text to speech. It uses speech synthesis technology to generate natural-sounding speech. It then automatically calls the specified recipient. During the call, the AI ​​system responds appropriately based on the recipient's responses, and uses an emotion engine to generate responses that reflect the user's emotions if necessary.

[1434] 7. Get call results

[1435] Server: When the call is completed, the server obtains the call content and results (e.g., reservation confirmation information, confirmation items, etc.), which are then stored and managed in a database.

[1436] 8. Feedback Generation and Submission

[1437] Server: The server organizes the call results and creates feedback data for the user. This data is then encoded again and sent to the device.

[1438] 9. Results display

[1439] Terminal: The terminal decodes the received feedback data and displays it in a format that is intuitive to the user. For example, it displays specific information such as, "Your reservation has been confirmed. The date and time is June 15th at 7 PM for two people."

[1440] Specific examples

[1441] Reservation example

[1442] Suppose a user uses a terminal to request a reservation for "Restaurant X, June 15th, 7pm, for 2 people."

[1443] 1. User Input: While the user is inputting information into the device, the emotion engine recognizes tense emotions.

[1444] 2. Data transmission: The device encodes the data and emotion data and sends them to the server.

[1445] 3. Data reception and verification: The server receives the data and emotion data, decodes it, and analyzes it.

[1446] 4. Conversation generation: The generative AI model and emotion engine generate the following conversational sentence in a neutral tone: "I'd like to make a reservation for two people at 7pm on June 15th."

[1447] 5. Call execution: The server makes a call and reads out the conversation generated by speech synthesis. It also generates a response to the other party's response that reflects the user's emotions.

[1448] 6. Obtain call result: The server receives the answer from the restaurant and records the content.

[1449] 7. Feedback generation and transmission: Organize the call results and send them to the device.

[1450] 8. Display result: The device displays the feedback it received to the user. For example, it displays "Your reservation has been confirmed. We are waiting for two people at 7 PM on June 15th."

[1451] As described above, the system provided by the present invention automatically handles the call content specified by the user and uses an emotion engine to respond in a way that reflects the user's emotions, providing a more natural and comfortable call experience. This lowers the psychological barrier to making a call and is particularly useful for people with hearing impairments and those in stressful situations.

[1452] The processing flow will be explained below.

[1453] Step 1:

[1454] User: Enter the destination and purpose of the call into the input screen of the device. For example, enter information such as "Restaurant X, June 15th, 7 PM, 2 people."

[1455] Step 2:

[1456] Terminal: While accepting user input, the emotion engine analyzes the user's voice tone, facial expressions, and input content to detect the user's emotional state.

[1457] Step 3:

[1458] Terminal: The input data and detected emotion data are encoded and sent to the server using encrypted communication.

[1459] Step 4:

[1460] Server: Receives the encoded data sent from the device. The received data is first stored in secure local storage.

[1461] Step 5:

[1462] Server: Decodes the received data and extracts the user's destination, purpose, and emotion data. It checks the data for consistency and generates an error message if there are any errors.

[1463] Step 6:

[1464] Server: Calls up a generative AI model based on the decoded data and generates natural conversational sentences that incorporate the user's emotional data. For example, if the user is nervous, it adds phrases to help them relax.

[1465] Step 7:

[1466] Server: Based on the generated conversational text, a natural voice is generated using speech synthesis technology, with a tone that reflects the user's emotions.

[1467] Step 8:

[1468] Server: Automatically calls the specified destination phone number. When the call starts, the generated voice is spoken to the other party.

[1469] Step 9:

[1470] Server: Analyzes responses from the other party in real time during the call and generates appropriate responses. Here too, the emotion engine generates responses that reflect the user's emotions based on the other party's responses.

[1471] Step 10:

[1472] Server: Once the call is over, record the outcome of the call, for example, whether the reservation was confirmed or not, and if there are any further questions.

[1473] Step 11:

[1474] Server: Organizes the call results and generates feedback data to the user. This feedback data is also encoded.

[1475] Step 12:

[1476] Server: Sends the generated feedback data to the terminal using encrypted communication.

[1477] Step 13:

[1478] Terminal: Receives feedback data sent from the server. Decodes the received data and converts it into an analyzable format.

[1479] Step 14:

[1480] Terminal: Visually display feedback information to the user, for example, "Your reservation has been confirmed. Please go to Restaurant X on June 15th at 7pm for two people."

[1481] As described above, the system of the present invention recognizes the user's emotions and generates natural conversation content and voice that reflects those emotions, making call answering more comfortable. This allows users in particularly stressful situations or with hearing impairments to make phone calls with peace of mind.

[1482] Example 2

[1483] 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."

[1484] Conventional telephone answering systems often cause users to feel nervous or anxious when making a call, making it difficult for them to make a smooth call, especially for those with hearing impairments or in situations where they feel psychological pressure. Furthermore, the lack of naturalness in the call content can cause discomfort to the other party, which can sometimes prevent users from achieving their intended purpose. The present invention aims to solve these problems and provide a more natural and emotionally sensitive call experience.

[1485] The identification process by the identification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means. In this invention, the server includes means for a user to input a destination and purpose of a call, means for encoding the input data and the user's emotional data and transmitting them to the server, means for receiving and decoding the transmitted data, means for generating natural conversation content using a generative AI model based on the decoded data and emotional data, means for converting the generated conversation content into voice using AI speech synthesis and executing the call, means for generating an appropriate response based on the other party's response during the call, means for acquiring the result of the call, and means for feeding back the acquired result to the user. This makes it possible to realize a natural and smooth call while taking the user's emotions into consideration, and to reliably achieve the purpose of the call.

[1486] A "user" is a person who utilizes the system to input the destination and purpose of a call.

[1487] A "call destination" is the person or location to which a user wishes to place a call.

[1488] The "matters" are the contents or purpose that the user wants to convey through the call.

[1489] A "terminal" is a device used by a user to input the destination and purpose of a call, and includes a mobile phone, a personal computer, and the like.

[1490] "Emotion data" is data that represents the user's psychological state, obtained from the user's tone of voice, facial expression, and input text content.

[1491] "Encoding" is the process of converting data to be transmitted into a specific format.

[1492] A "server" is a device that receives and processes data sent from a terminal.

[1493] "Decoding" is the process of converting received data back into its original format.

[1494] A "generative AI model" is an algorithm or program that uses artificial intelligence technology to generate natural-sounding conversation content based on input data.

[1495] "AI voice synthesis" is a technology that converts text data into voice data.

[1496] A "call" is an act of actually having a conversation based on the destination and purpose input by the user.

[1497] A "response" is a reply or response received from the other party during a call.

[1498] "Feedback" is information that reports the results of a call to the user.

[1499] This invention is a telephone answering system in which a user specifies a specific destination and purpose, and the system automatically answers the call. The system also incorporates an emotion engine that recognizes the user's emotions, and the server and terminals work together. Detailed embodiments for implementing this system are described below.

[1500] 1. User Input

[1501] Device: The user uses a device such as a mobile phone or PC to input the destination (e.g., restaurant name) and purpose (e.g., reservation date and time and number of people). The input interface is designed to be intuitive for users, with features such as check boxes and drop-down menus. In addition, the microphone and camera are activated when inputting information, and the device is equipped with a function that recognizes the user's tone of voice and facial expressions in real time.

[1502] 2. Emotion recognition

[1503] Terminal: While the user is entering information, the emotion engine analyzes voice tone, facial expression recognition, and the input text content to detect the user's emotional state. For example, it determines whether the user is nervous based on the intonation of their voice or facial expression. This function generates the user's emotional data.

[1504] 3. Data Transmission

[1505] Terminal: The data and emotion data entered by the user are encoded and securely transmitted to the server using encrypted communication technology such as HTTPS, preventing data leakage and degradation.

[1506] 4. Data Receipt and Confirmation

[1507] Server: Receives the data sent from the device, decodes it, and converts it into an analyzable format. The server checks the consistency and integrity of the data to ensure it has not been tampered with. It also calculates checksums and verifies the data format.

[1508] 5. Conversation Generation

[1509] Server: Using a generative AI model, the server generates natural-sounding conversational sentences based on the content and emotional data specified by the user. For example, if the server detects that the user is nervous, it generates a conversational sentence with a relaxed tone, such as "Please make a reservation for two people at 7 p.m. on June 15th." The generative AI model uses the prompt to generate the conversational sentence.

[1510] 6. Make a call

[1511] Server: Converts the generated conversation content from text to speech. It uses speech synthesis technology (e.g., Google Text-to-Speech) to generate natural-sounding speech and automatically calls the specified recipient. During the call, the conversational AI generates appropriate responses in real time based on the recipient's responses, and uses an emotion engine to respond in a way that reflects the user's emotions.

[1512] 7. Get call results

[1513] Server: When the call is completed, the call content and results (e.g., reservation confirmation information, confirmation items, etc.) are obtained and saved in a database. This information can be referenced later, improving user convenience.

[1514] 8. Feedback Generation and Submission

[1515] Server: Organizes the call results and generates data to provide feedback to the user. This is then encoded again and securely sent to the device using HTTPS.

[1516] 9. Results display

[1517] Terminal: Decodes the received feedback data and displays it in a format that is easy for the user to understand. For example, it displays specific information such as "The reservation has been confirmed. It will be made on June 15th at 7pm for two people." It is also possible to notify the user of the results using a voice readout function.

[1518] Specific examples

[1519] A specific example will be given in which a user uses a terminal to request a reservation for "Restaurant X, June 15th, 7pm, for 2 people."

[1520] 1. User input: The user enters "Restaurant X, June 15th, 7pm, 2 people" into the terminal, and the emotion engine recognizes the tension.

[1521] 2. Data transmission: The device encodes the data and emotion data and sends them to the server.

[1522] 3. Data reception and verification: The server receives the data, decodes it, and verifies its integrity.

[1523] 4. Conversation generation: The generative AI model generates the following conversation in a neutral tone: "I'd like to make a reservation for two people at 7 p.m. on June 15th."

[1524] 5. Call execution: The server makes the call and reads out the conversation generated by speech synthesis technology. Depending on the other party's response, an appropriate response reflecting the other party's emotions is given.

[1525] 6. Obtain call result: The server receives a confirmation of the reservation from the restaurant and records the details.

[1526] 7. Feedback generation and transmission: Organize the call results and send them to the device.

[1527] 8. Displaying the result: The terminal displays the result to the user: "Reservation confirmed. Two guests will be waiting at 7 PM on June 15th."

[1528] In this way, the system of the present invention provides a natural calling experience that takes into account the user's emotions, enabling the purpose of the call to be achieved efficiently.

[1529] The flow of the identification process in the second embodiment will be described with reference to FIG.

[1530] Step 1: User Input

[1531] Device: The user enters the call destination (e.g., restaurant name) and purpose (e.g., reservation date and time and number of people) on a device such as a mobile phone or PC. The input interface is equipped with check boxes and drop-down menus, and is designed to allow users to operate it intuitively. Input data includes the destination "Restaurant X," the date and time "June 15th, 7:00 PM," and the number of people "2." In addition, the microphone and camera are activated to collect the user's voice tone and facial expressions.

[1532] Input: Destination, purpose (reservation date and time, number of people)

[1533] Output: Input data, emotion data

[1534] Step 2: Emotion Recognition

[1535] Terminal: The emotion engine generates emotion data by analyzing the user's voice tone, facial expression recognition, and input text content. For example, it determines whether the user is nervous based on the intonation of their voice and facial expression. This provides emotion data that indicates the user's psychological state.

[1536] Input: Voice tone, facial expression data, input text

[1537] Output: Emotion data

[1538] Step 3: Send data

[1539] Terminal: Input data and emotion data are encoded and sent securely to the server using encryption technology (e.g., HTTPS). Data is transferred in a manner that prevents degradation and leakage.

[1540] Input: Input data, emotion data

[1541] Output: Encrypted data

[1542] Step 4: Data Receipt and Verification

[1543] Server: Receives encrypted data sent from the device. Decodes the received data and converts it into an analyzable format. Then, calculates checksums and verifies the data format to ensure data integrity and completeness.

[1544] Input: Encrypted data

[1545] Output: Decoded data

[1546] Step 5: Conversation generation

[1547] Server: Using a generative AI model, the server generates natural-sounding conversational sentences based on the decoded input data and emotional data. For example, if the user is recognized as nervous, the server generates a conversational sentence in a relaxed tone, such as "I'd like to make a reservation for two people at 7 p.m. on June 15th." The server uses a prompt sentence.

[1548] Input: Decoded data, emotion data

[1549] Output: Conversation

[1550] Step 6: Make the call

[1551] Server: Converts the generated conversational text from text to speech. It uses speech synthesis technology (e.g., Google Text-to-Speech) to generate natural-sounding speech and automatically calls the specified recipient. During the call, the conversational AI generates appropriate responses in real time based on the recipient's responses, and the emotion engine responds by reflecting the user's emotions.

[1552] Input: Conversation

[1553] Output: Audio data, call answering

[1554] Step 7: Get call results

[1555] Server: Once the call is completed, the server obtains the call details and results (e.g., reservation confirmation information, confirmation items, etc.). The obtained data is stored in a database.

[1556] Input:Call Answer

[1557] Output: Call result data

[1558] Step 8: Generate and send feedback

[1559] Server: Organizes the acquired call results and generates data to provide feedback to the user. This feedback data is then re-encoded and sent to the device using encryption technology.

[1560] Input: Call result data

[1561] Output: Feedback data

[1562] Step 9: View the results

[1563] Terminal: Decodes the received feedback data and displays the results in a format that is easy for the user to understand. For example, specific information such as "Reservation confirmed. June 15th at 7pm for two people" is displayed on the terminal screen. Voice notification is also possible.

[1564] Input: Feedback data

[1565] Output: Display result

[1566] (Application example 2)

[1567] 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."

[1568] In autonomous vehicles, users are expected to be able to comfortably use various services (restaurant reservations, hotel reservations, medical appointments, etc.) from inside the vehicle, but there is a lack of a system that automatically generates and executes natural responses based on input information that reflect the user's emotions.In addition, since calls that ignore the user's emotions can be unnatural and stressful, it is necessary to provide natural conversations that take the user's emotions into consideration.

[1569] 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 a user to input the destination and purpose of the call, means for recognizing emotions from the user's tone of voice, facial expression, text content, etc., means for encoding the input data and emotional data and transmitting them to the server, means for receiving and decoding the transmitted data and emotional data, means for using a generative AI model to generate natural conversation content based on the decoded data, means for adjusting the tone of the conversation based on the user's emotional data, means for conducting a call using the generated conversation content, means for acquiring the results of the call, and means for feeding back the acquired results to the user. This enables comfortable service use in an autonomous vehicle and realizes natural conversation responses that correspond to the user's emotions.

[1570] "Means for users to input the destination and purpose of the call" refers to the means by which users use a terminal such as a mobile phone or computer to input the destination (e.g., restaurant, hotel, medical institution, etc.) and the purpose (e.g., reservation date and time, number of people, etc.).

[1571] The "means for recognizing emotions" refers to a means for automatically recognizing emotions from the user's tone of voice, facial expressions, text content, etc., using an emotion engine or sensor installed in the device.

[1572] The "means for encoding data and emotion data and transmitting them to the server" refers to a means for encoding (encrypting) the destination and purpose data entered by the user and the emotion data obtained from the emotion recognition means and transmitting them securely to the server.

[1573] The "means for receiving and decoding" refers to the means by which the server receives the data and emotion data sent from the terminal and decodes (decodes) it into an analyzable format.

[1574] "Means for using a generative AI model" refers to means by which the server generates natural conversation content using a generative AI model based on data and emotional data sent by the user.

[1575] The "means for adjusting the tone of the conversation" is a means for adjusting the tone of the conversation (e.g., relaxed tone, gentle tone, etc.) based on the user's emotional data in the generated conversation content.

[1576] The "means for executing a call using the conversation content" is a means for converting the generated conversation content from text to voice and automatically making a call to a designated recipient.

[1577] The "means for obtaining the results of a call" refers to the means by which the server obtains the contents of the call and its results (e.g., reservation confirmation information, confirmation items, etc.) when the call is completed.

[1578] The "means for providing feedback to the user" is a means for encoding data to feed back the acquired call result to the user, transmitting the data to the terminal, and displaying the data in a form that the user can intuitively understand.

[1579] This invention describes a specific embodiment of a voice assistant application installed in an autonomous vehicle. This application allows the user to specify the destination and purpose of a reservation from inside the vehicle, and the system automatically handles the call. Furthermore, it can recognize the user's emotions and generate natural conversations using a generative AI model.

[1580] First, the user uses the voice assistant app in the autonomous vehicle to specify the destination (e.g., restaurant, hotel, medical institution, etc.) and purpose (e.g., reservation date and time, number of people, etc.). This input is converted into text using voice recognition technology. For voice recognition, Google Speech Recognition API, for example, is used.

[1581] Next, the emotion engine installed on the device recognizes emotions from the voice tone, facial expressions, text content, etc. while the user is typing. For emotion recognition, for example, the Python library "Emotion Recognition" is used.

[1582] The input data and emotion data are encoded (encrypted) and securely transmitted to the server. This communication is via the Internet and uses encryption protocols (e.g., TLS / SSL).

[1583] The server receives the data and emotion data sent from the device and decodes it. After decoding, the server uses a generative AI model (such as GPT-3) to generate natural-sounding conversation content based on the content and emotion specified by the user. The tone of the conversation is also adjusted based on the emotion data. For example, if the user is nervous, a relaxing tone of voice will be generated.

[1584] The generated conversation is converted into natural-sounding speech using speech synthesis technology (such as the Google Text-to-Speech API). The call is then automatically placed to the specified recipient. During the call, the AI ​​system responds appropriately based on the recipient's response, and uses an emotion engine to generate responses that reflect the user's emotions, if necessary.

[1585] Once the call is completed, the server obtains the results of the call (e.g., reservation confirmation information, confirmation items, etc.), stores them in a database, and manages them. This information is then encoded and sent back to the device.

[1586] Finally, the device decodes the received feedback data and displays it in a format that is intuitive to the user, such as "Your reservation has been confirmed. The date and time is June 15th at 7 PM for two people."

[1587] Examples of specific prompts include:

[1588] User: "I'd like to make a reservation for two at Restaurant X on June 15th at 7pm."

[1589] Input to AI model: "Reservation call - user is nervous. Please speak in a relaxed tone."

[1590] Generated dialogue: "Hello, Restaurant X. I'd like to make a reservation for two people on June 15th at 7pm." "Yes, I understand. We look forward to seeing you."

[1591] In this way, the system of the present invention enables comfortable use of services inside an autonomous vehicle and is capable of providing natural conversational responses that correspond to the user's emotions.

[1592] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[1593] Step 1:

[1594] The user inputs the destination and purpose of the call. Using the voice assistant app in the autonomous vehicle, the user specifies the destination (e.g., restaurant, hotel, medical institution, etc.) and purpose (e.g., reservation date and time, number of people, etc.). This input is converted into text using voice recognition technology (e.g., Google Speech Recognition API). The input data is obtained in the form of text: "destination" and "purpose."

[1595] Step 2:

[1596] The device recognizes emotions from the user's voice tone, facial expressions, text content, etc. The emotion engine (e.g., Emotion Recognition library) installed on the device analyzes the voice tone while the user is typing and recognizes the user's emotions in real time. Emotion data is obtained in the form of "emotional state."

[1597] Step 3:

[1598] The device encodes the input data and emotion data and sends them to the server. The encoding (encryption) process uses, for example, the TLS / SSL protocol. The encoded data is securely sent to the server. The input data and emotion data are sent as a single encrypted packet.

[1599] Step 4:

[1600] The server receives and decodes the transmitted data and emotional data. The server receives the encrypted data transmitted from the device and decodes it into an analyzable format. This allows the "destination," "message," and "emotional state" data to arrive at the server.

[1601] Step 5:

[1602] The server uses a generative AI model (e.g., GPT-3) based on the decoded data to generate natural-sounding conversation content. The server inputs the "destination," "purpose," and "emotional state" data into the generative AI model to generate appropriate conversation content. The tone of the conversation is adjusted based on the user's emotional state. The output is obtained as "conversation content."

[1603] Step 6:

[1604] The server converts the generated conversation content into natural-sounding speech using speech synthesis technology (e.g., Google Text-to-Speech API). The server then converts the text-format "conversation content" into voice data and prepares to make a call to the specified recipient. The output is obtained as voice data.

[1605] Step 7:

[1606] The server automatically calls the specified recipient. During the call, the AI ​​system responds appropriately based on the recipient's response and uses an emotion engine to generate a response that reflects the user's emotions. Emotion recognition continues as the conversation progresses, and any necessary corrections are made. Data is exchanged in real time.

[1607] Step 8:

[1608] Once the call is complete, the server obtains the call results (e.g., reservation confirmation information, confirmation items, etc.). After the call ends, the server collects various confirmation data and stores it in a database that manages it. The output is obtained as "call result data."

[1609] Step 9:

[1610] The server organizes the call results it has obtained and creates data to provide feedback to the user. It re-encodes (encrypts) the call result data and sends it to the device. The encoded feedback data is then securely sent to the device.

[1611] Step 10:

[1612] The device decodes the received feedback data and displays it in a format that is intuitively understandable to the user. The decoded feedback content is displayed to the user as specific information, such as "The reservation has been confirmed. The date and time is June 15th at 7 PM for two people."

[1613] 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.

[1614] 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.

[1615] 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.

[1616] 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.

[1617] 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.

[1618] 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.

[1619] 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).

[1620] 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.

[1621] 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."

[1622] 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.

[1623] 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).

[1624] 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.

[1625] 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.

[1626] 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.

[1627] 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.

[1628] 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.

[1629] 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.

[1630] 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.

[1631] 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.

[1632] 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.

[1633] 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.

[1634] The following is further disclosed regarding the above embodiment.

[1635] (Claim 1)

[1636] means for a user to input a call destination and purpose;

[1637] means for encoding the input data and transmitting the encoded data to a server;

[1638] means for receiving and decoding the transmitted data;

[1639] means for generating natural conversation content based on the decoded data;

[1640] means for executing a call using the generated conversation content;

[1641] means for obtaining a result of the call;

[1642] The system further comprises means for providing feedback to a user about the obtained results.

[1643] (Claim 2)

[1644] The system according to claim 1, wherein the means for executing the call uses AI voice synthesis to conduct the conversation in a natural voice.

[1645] (Claim 3)

[1646] The system according to claim 1, further comprising means for intuitively displaying the feedback results to the user.

[1647] "Example 1"

[1648] (Claim 1)

[1649] means for a user to input a call destination and purpose;

[1650] means for encoding the input data and transmitting the encoded data to a server;

[1651] means for receiving and decoding the transmitted data;

[1652] means for generating natural conversation content using a generative AI model based on the decoded data;

[1653] a means for executing a call using the generated conversation content with a voice synthesis technology;

[1654] means for obtaining and storing the results of the call in a database;

[1655] The system further comprises means for encoding the obtained results and feeding them back to a user.

[1656] (Claim 2)

[1657] The system according to claim 1, wherein the means for executing the call uses AI voice synthesis to conduct the conversation in a natural voice.

[1658] (Claim 3)

[1659] The system according to claim 1, further comprising means for intuitively displaying the feedback results to the user.

[1660] "Application Example 1"

[1661] (Claim 1)

[1662] means for a user to input a call destination and purpose;

[1663] means for encoding the input data and transmitting the encoded data to a server;

[1664] means for receiving and decoding the transmitted data;

[1665] means for generating natural conversation content based on the decoded data;

[1666] means for executing a call using the generated conversation content;

[1667] means for obtaining a result of the call;

[1668] a means for feeding back the obtained results to a user;

[1669] In a system including the means for displaying the feedback,

[1670] This system includes a brick-and-mortar store application that is installed on a smartphone. When the user inputs a specific location and purpose, the data is sent to a server, which then uses a generative AI model to generate natural conversation content, automatically makes a call using that conversation content, obtains the call results, and displays them as feedback to the user.

[1671] (Claim 2)

[1672] The system according to claim 1, wherein the means for executing the call uses AI voice synthesis to conduct the conversation in a natural voice.

[1673] (Claim 3)

[1674] 10. The system of claim 1, further comprising means for intuitively displaying the feedback results to the user.

[1675] "Example 2: Combining Emotion Engines"

[1676] (Claim 1)

[1677] means for a user to input a call destination and purpose;

[1678] means for encoding the input data and the user's emotion data and transmitting them to a server;

[1679] means for receiving and decoding the transmitted data;

[1680] means for generating natural conversation content using a generative AI model based on the decoded data and emotion data;

[1681] A means for converting the generated conversation content into voice using AI voice synthesis and executing a call;

[1682] means for generating an appropriate response based on the response of the other party during the call;

[1683] means for obtaining a result of the call;

[1684] The system further comprises means for providing feedback to a user about the obtained results.

[1685] (Claim 2)

[1686] 2. The system of claim 1, wherein the means for executing the call and the means for generating an appropriate response based on the response of the other party during the call use an emotion engine that reflects the user's emotion.

[1687] (Claim 3)

[1688] The system according to claim 1, further comprising means for intuitively displaying the results of the feedback to the user on a screen of the terminal.

[1689] "Application example 2 when combining emotion engines"

[1690] (Claim 1)

[1691] means for a user to input a call destination and purpose;

[1692] A means for recognizing emotions from a user's tone of voice, facial expression, text content, etc.;

[1693] means for encoding the input data and emotion data and transmitting them to a server;

[1694] means for receiving and decoding the transmitted data and emotion data;

[1695] means for using a generative AI model to generate natural-sounding conversational content based on the decoded data;

[1696] means for adjusting the tone of the conversation based on the user's emotional data;

[1697] means for executing a call using the generated conversation content;

[1698] means for obtaining a result of the call;

[1699] The system further comprises means for providing feedback to a user about the obtained results.

[1700] (Claim 2)

[1701] The system according to claim 1, wherein the means for executing the call uses AI voice synthesis to conduct the conversation in a natural voice.

[1702] (Claim 3)

[1703] 10. The system of claim 1, further comprising means for intuitively displaying the feedback results to the user. [Explanation of symbols]

[1704] 10, 210, 310, 410 Data Processing Systems 12 Data Processing Device 14 Smart Devices 214 Smart Glasses 314 Headset-type terminal 414 Robot< / url:> < / url:> < / url:> < / url:>

Claims

1. means for a user to input a call destination and purpose; means for encoding the input data and transmitting the encoded data to a server; means for receiving and decoding the transmitted data; means for generating natural conversation content based on the decoded data; means for executing a call using the generated conversation content; means for obtaining a result of the call; The system further comprises means for providing feedback to a user about the obtained results.

2. The system according to claim 1, wherein the means for executing the call uses AI voice synthesis to conduct the conversation in a natural voice.

3. The system of claim 1 , further comprising means for intuitively displaying the feedback results to the user.

Images