system

Abstract

We provide the system. [Solution] A means for acquiring audio data and converting said audio data into text data, A means for analyzing the content of an utterance based on the text data and generating a humorous response, Means for determining a gesture corresponding to the humorous response and controlling and displaying an avatar, A system that includes this.

Description

Technical Field

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

Background Art

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

Prior Art Documents

Patent Documents

[0003]

Patent Document 1

Summary of the Invention

Problems to be Solved by the Invention

[0004] In modern times, dialogue agents are widely used in various scenarios, but many of them are impersonal and lack friendliness towards users. Therefore, especially in the fields of monitoring and communication, it is required that the agent respond to the user in a warm manner. With the current technology, it is difficult to generate responses including humor according to individual sensibilities and situations, and it has not been realized to express gestures matching the humor on an avatar. The present invention aims to solve these problems.

Means for Solving the Problems

[0005] This invention accurately understands user speech by including means for acquiring audio data and converting said audio data into text data. Furthermore, it enables friendly dialogue by including means for analyzing the content of the speech based on the text data and generating humorous responses appropriate to the situation. In addition, it realizes visually enjoyable communication by including means for determining gestures corresponding to the humorous responses and controlling and displaying avatars.

[0006] "Audio data" refers to data that represents audio in a digital format.

[0007] "Text data" refers to data created by converting speech or symbols into characters and then into a format that can be processed by a computer.

[0008] "Speech content" refers to information including the meaning and intent of the words spoken by the user.

[0009] "Analysis" is the process of examining given information or data in detail to understand its structure and meaning.

[0010] A "humorous response" refers to an utterance designed to evoke laughter or enjoyment in a conversation.

[0011] "Gesture" is a means of expressing intentions and emotions through body movements or actions by an avatar.

[0012] An "avatar" is a character or 3D model that acts as a representative or proxy for a user in a digital environment. [Brief explanation of the drawing]

[0013] [Figure 1] This is a conceptual diagram showing an example of the configuration of a data processing system according to the first embodiment. [Figure 2] This is a conceptual diagram showing an example of the essential functions of a data processing device and a smart device according to the first embodiment. [Figure 3] It is a conceptual diagram showing an example of the configuration of a data processing system according to the second embodiment. [Figure 4] It is a conceptual diagram showing an example of the main functions of a data processing device and smart glasses according to the second embodiment. [Figure 5] It is a conceptual diagram showing an example of the configuration of a data processing system according to the third embodiment. [Figure 6] It is a conceptual diagram showing an example of the main functions of a data processing device and a headset-type terminal according to the third embodiment. [Figure 7] It is a conceptual diagram showing an example of the configuration of a data processing system according to the fourth embodiment. [Figure 8] It is a conceptual diagram showing an example of the main functions of a data processing device and a robot according to the fourth embodiment. [Figure 9] It shows an emotion map to which a plurality of emotions are mapped. [Figure 10] It shows an emotion map to which a plurality of emotions are mapped. [Figure 11] It is a sequence diagram showing the processing flow of the data processing system in Example 1. [Figure 12] It is a sequence diagram showing the processing flow of the data processing system in Application Example 1. [Figure 13] It is a sequence diagram showing the processing flow of the data processing system in Example 2 when an emotion engine is combined. [Figure 14] It is a sequence diagram showing the processing flow of the data processing system in Application Example 2 when an emotion engine is combined.

Mode for Carrying Out the Invention

[0014] Hereinafter, an example of an embodiment of a system according to the technology of the present disclosure will be described according to the accompanying drawings.

[0015] First, the language used in the following description will be explained.

[0016] In the following embodiments, the numbered processor (hereinafter simply referred to as "processor") may be a single arithmetic unit or a combination of multiple arithmetic units. Also, the processor may be a single type of arithmetic unit or a combination of multiple types of arithmetic units. Examples of arithmetic units include a CPU (Central Processing Unit), a GPU (Graphics Processing Unit), a GPGPU (General-Purpose computing on Graphics Processing Units), an APU (Accelerated Processing Unit), and the like.

[0017] In the following embodiments, the numbered RAM (Random Access Memory) is a memory in which information is temporarily stored and is used as a work memory by the processor.

[0018] In the following embodiments, the numbered storage is one or more non-volatile storage devices that store various programs and various parameters, etc. Examples of non-volatile storage devices include flash memory (SSD (Solid State Drive)), magnetic disks (e.g., hard disks), or magnetic tapes, etc.

[0019] In the following embodiments, the numbered communication I / F (Interface) is an interface including a communication processor and 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), or Bluetooth (registered trademark), etc.

[0020] In the following embodiments, "A and / or B" is synonymous with "at least one of A and B." That is, "A and / or B" means that it may be A alone, or B alone, or a combination of A and B. Furthermore, in this specification, the same concept as "A and / or B" applies when expressing three or more things linked by "and / or."

[0021] [First Embodiment]

[0022] Figure 1 shows an example of the configuration of the data processing system 10 according to the first embodiment.

[0023] As shown in Figure 1, the data processing system 10 includes a data processing device 12 and a smart device 14. An example of the data processing device 12 is a server.

[0024] The data processing device 12 comprises a computer 22, a database 24, and a communication interface 26. The computer 22 is an example of a "computer" related to the technology of this disclosure. The computer 22 comprises a processor 28, RAM 30, and storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication interface 26 are also connected to the bus 34. The communication interface 26 is connected to a network 54. An example of the network 54 is a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0025] The smart device 14 comprises a computer 36, a reception device 38, an output device 40, a camera 42, and a communication interface 44. The computer 36 comprises a processor 46, RAM 48, and storage 50. The processor 46, RAM 48, and storage 50 are connected to a bus 52. The reception device 38, output device 40, and camera 42 are also connected to the bus 52.

[0026] The reception device 38 is equipped with a touch panel 38A and a microphone 38B, etc., and receives user input. The touch panel 38A receives user input by detecting contact with an object (e.g., a pen or finger). The microphone 38B receives user input by detecting the user's voice. The control unit 46A transmits data indicating the user input received by the touch panel 38A and microphone 38B to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the data indicating the user input.

[0027] The output device 40 includes a display 40A and a speaker 40B, and presents data to the user 20 by outputting the data in a form perceptible to the user 20 (e.g., audio and / or text). The display 40A displays visible information such as text and images according to instructions from the processor 46. The speaker 40B outputs audio according to instructions from the processor 46. The camera 42 is a small digital camera equipped with an optical system such as a lens, aperture, and shutter, and an image sensor such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor.

[0028] Communication interface 44 is connected to network 54. Communication interfaces 44 and 26 are responsible for the exchange of various types of information between processor 46 and processor 28 via network 54.

[0029] Figure 2 shows an example of the main functions of the data processing device 12 and the smart device 14.

[0030] As shown in Figure 2, in the data processing device 12, a specific processing is performed by the processor 28. A specific processing program 56 is stored in the storage 32. The specific processing program 56 is an example of a "program" related to the technology of this disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 according to the specific processing program 56 executed on the RAM 30.

[0031] The storage 32 stores the data generation model 58 and the emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[0032] In the smart device 14, the processor 46 performs the reception output processing. The storage 50 stores the reception output program 60. The reception output program 60 is used in conjunction with a specific processing program 56 by the data processing system 10. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output processing is realized by the processor 46 operating as a control unit 46A according to the reception output program 60 executed on the RAM 48.

[0033] Next, the specific processing performed by the specific processing unit 290 of the data processing device 12 will be described. In the following description, the data processing device 12 will be referred to as the "server" and the smart device 14 as the "terminal".

[0034] To implement this invention, it is necessary to prepare a device for acquiring audio data and related software programs. First, the terminal acquires the user's voice in real time and sends the audio data to a cloud server. Here, the audio data is immediately converted into text data. Speech recognition technology is used for the conversion to text. The server analyzes this text data and attempts to understand the meaning and context of the words spoken by the user.

[0035] Next, the server uses a generative AI model to generate humorous responses based on the analyzed text data. These responses include appropriate jokes and witty remarks to make them user-friendly. Furthermore, to determine the gestures corresponding to these humorous responses, the server selects appropriate actions from a gesture library. These gestures enable visual representations that correspond to the content of the conversation.

[0036] The device then combines the generated humorous response and gestures and presents them to the user. The avatar delivers humorous responses audibly and simultaneously performs visual gestures, providing a friendly and enjoyable communication experience.

[0037] For example, if a user says, "I'm tired today," the server analyzes this and generates an appropriate humorous response such as, "You're out of energy! Shall we recharge and have some delicious cake?" In addition, the avatar performs a gesture indicating energy replenishment, providing the user with visual enjoyment. In this way, the system of the present invention makes it possible to reduce the psychological distance between the user and the system and to increase the user's sense of security.

[0038] The following describes the processing flow.

[0039] Step 1:

[0040] The device captures the user's voice using its microphone. This audio data is sent to a cloud server in real time.

[0041] Step 2:

[0042] The server converts the received audio data into text data using speech recognition technology. Advanced speech recognition algorithms are used here to ensure clear audio analysis and accurate text conversion.

[0043] Step 3:

[0044] The server analyzes the text data to understand the user's intent. This process involves using natural language processing (NLP) techniques to extract context and meaning.

[0045] Step 4:

[0046] The server uses a generative AI model to generate humorous responses based on the analysis results. In this step, the model is adjusted to create appropriate jokes and retorts that are relevant to the context.

[0047] Step 5:

[0048] The server determines a gesture to correspond to the generated humorous response. It selects the most appropriate action from the gesture library and generates control commands to have the 3D avatar perform that action.

[0049] Step 6:

[0050] The device presents the user with humorous responses and gestures received from the server. The avatar delivers the humorous responses aloud and simultaneously visually represents the determined gestures, providing the user with a friendly and enjoyable conversational experience.

[0051] (Example 1)

[0052] Next, we will describe Example 1. In the following description, the data processing device 12 will be referred to as the "server," and the smart device 14 will be referred to as the "terminal."

[0053] In today's information society, there is a growing demand for more natural and engaging dialogue when people communicate via digital devices. However, conventional systems struggle to generate and present humorous responses and accompanying actions in real time to put users at ease, failing to provide users with a highly satisfying dialogue experience. This challenge needs to be solved by combining more advanced natural language processing technologies with generative AI models.

[0054] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 1 is realized by the following means.

[0055] In this invention, the server includes means for acquiring voice information and converting said voice information into text information, means for analyzing the content of the speech and generating a humorous response, and means for determining the action corresponding to the humorous response and controlling and displaying a virtual character. This makes it possible to provide the user with an interesting and friendly communication experience that combines visual and auditory elements.

[0056] "Voice information" refers to voice data produced by users using digital devices.

[0057] "Textual information" refers to data obtained by analyzing audio information and representing its content in text.

[0058] "Speech content" refers to the meaning or intent that the user is trying to convey, based on the text information converted from the audio information.

[0059] A "humorous response" refers to a humorous reply generated in response to user input, providing a user-friendly interaction.

[0060] "Actions" refer to visual gestures and animations that appear in conjunction with humorous responses.

[0061] A "virtual character" refers to a computer-generated agent that operates within a digital environment and interacts with the user visually and audibly.

[0062] "Synthetic speech means" refers to technologies and software that convert text information into speech and output it.

[0063] This invention is a system for realizing natural and user-friendly communication with users. Specifically, it includes a series of methods for acquiring voice information from the user, converting it into text information, generating humorous responses, and presenting them through a virtual character.

[0064] First, the device uses a high-precision microphone to acquire the user's voice information in real time. This voice information is temporarily stored digitally within the device. Then, the data is sent to the server using a secure protocol (e.g., HTTPS).

[0065] The server converts received audio information into text using speech recognition technology (e.g., a speech recognition service). Based on this converted text, it analyzes the spoken content using natural language processing technology. During this process, prompt sentences are input to a generative AI model (e.g., an AI text generation engine) based on the analysis results, generating humorous responses.

[0066] To determine the appropriate action related to the generated response, the server selects an appropriate action from a pre-prepared library of actions. This action is instructed to a virtual character and visually presented to the user. Voice responses are generated using synthesized speech technology and communicated to the user in a distinctive voice that matches the humorous content of the response.

[0067] Finally, the device combines the generated humorous responses and actions and presents them to the user. This entire process allows the user to have a meaningful and enjoyable conversational experience.

[0068] For example, if a user says, "I'm tired today," the server will respond with a humorous "You're out of energy! Want to recharge and have some delicious cake?" This response includes a gesture that involves "replenishing energy," which is visually represented through the avatar. As a result, the user can experience friendly communication through both voice and visual means.

[0069] Example of a prompt:

[0070] "Generate a humorous response to the user's statement: 'I'm tired today.'"

[0071] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0072] Step 1:

[0073] The device uses a high-precision microphone to acquire user voice information in real time. The input is the user's voice. The output is audio data in digital format. During this process, the audio is temporarily stored using an audio capture function.

[0074] Step 2:

[0075] The device transmits the acquired audio data to the server via an internet connection using a secure protocol (e.g., HTTPS). The input is digital audio data. The output is the audio data transferred to the server.

[0076] Step 3:

[0077] The server uses speech recognition technology to convert received audio data into text data. The input is audio data. The output is the converted text data. An external speech recognition engine is used for this process.

[0078] Step 4:

[0079] The server utilizes natural language processing technology to analyze text data and understand the content and context of the utterance. The input is text data. The output is the analyzed utterance content and contextual information. Based on the analysis results, prompt sentences are created for the generative AI model.

[0080] Step 5:

[0081] The server inputs a prompt sentence into an AI model based on the analysis results, and generates a humorous response. The input is the prompt sentence. The output is the generated humorous response. An AI text generation engine is used in this step.

[0082] Step 6:

[0083] The server determines the appropriate action to take in response to a humorous response and selects the correct action from the action library. The input is the humorous response. The output is the selected action data. The gesture library is used to select an action.

[0084] Step 7:

[0085] The device uses speech synthesis technology to generate humorous responses as audio and displays them visually in sync with the movements of a virtual character. The input consists of humorous responses and movement data. The output is the audio and animation presented to the user. Animation software is used to provide the user with a visually entertaining experience.

[0086] (Application Example 1)

[0087] Next, we will explain Application Example 1. In the following explanation, the data processing device 12 will be referred to as the "server," and the smart device 14 will be referred to as the "terminal."

[0088] When autonomous devices are used in a work environment, there is a challenge in alleviating the stress and boredom experienced by operators due to repetitive monotonous tasks, thereby making the workplace more comfortable. Furthermore, another challenge is to provide means to enhance affinity with operators by offering more human-like communication in addition to mechanical actions.

[0089] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 1 is realized by the following means.

[0090] In this invention, the server includes means for acquiring voice information and converting said voice information into text information, means for analyzing the content of the utterance based on the text information and generating an entertaining response, and means for determining an action corresponding to the entertaining response and controlling an autonomous device to display it. This makes it possible to provide the operator with entertaining responses and actions even in a monotonous work environment, lighten the atmosphere of the workplace, and increase affinity with the operator.

[0091] "Audio information" refers to human speech and other acoustic signals obtained by converting sound waves into electrical signals.

[0092] "Textual information" refers to text-formatted data generated using speech recognition technology based on audio information.

[0093] "Speech content" refers to the meaning and context of the text information extracted from the audio information.

[0094] "Entertaining responses" refer to responses that use generative AI to add humor and friendliness to the content of the speech.

[0095] "Action" refers to gestures or actions performed by an autonomous device to visually assist in entertaining responses.

[0096] An "autonomous device" refers to a device that automates the acquisition of voice information, the generation of responses, and the execution of actions.

[0097] "Operator" refers to a person who directly or indirectly supervises and controls the operation of an autonomous device.

[0098] A "server" refers to a computer system that processes voice information, generates responses, and provides information to autonomous devices.

[0099] To implement this invention, a device for acquiring voice information and a related software program are provided. The purpose of this system is to process voice input, generate entertaining responses based on a generative AI model, and have an autonomous device perform the corresponding actions.

[0100] The system first acquires voice information from the user wearing smart glasses or a head-mounted display. This is done using the Google® Speech-to-Text API to convert the voice signal into text. The converted text is sent to the server, where the speech content is analyzed. The server uses the OpenAI® ChatGPT® API to generate an entertaining response based on the text information. This response determines and executes the appropriate action from a gesture library configured to suit the user's environment.

[0101] The autonomous device provides entertaining responses to the operator as voice output and performs corresponding actions to lighten the mood in a potentially monotonous work environment. For example, if the operator says, "Today's work is so heavy!", the system will respond, "That sounds like a busy day! But I'll do my best with you!" and perform a gesture of giving a thumbs-up.

[0102] Examples of prompt messages are as follows:

[0103] Example prompt when the voice input says, "Today's work is so heavy and overwhelming!":

[0104] Speech-recognized text: "Today was a busy day with lots of work!"

[0105] Generate an appropriate humorous response: "That's a busy day! But I'll do my best alongside you!"

[0106] Select a related gesture: the action of making a victory pose.

[0107] This makes it possible to build a system that enhances user engagement through entertaining responses and intuitive gestures.

[0108] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0109] Step 1:

[0110] The user provides voice input through smart glasses. The voice input is captured by a microphone built into the smart glasses. The input data is voice information, which is then converted into text information using the Google Speech-to-Text API. Converting the voice signal into a string enables the following processing:

[0111] Step 2:

[0112] The terminal sends the converted text information to the server. The server analyzes the text information and performs natural language processing to understand the spoken content. The input data is text information, and the output data is the analyzed spoken content. This allows the system to understand the user's intent.

[0113] Step 3:

[0114] The server generates entertaining responses using a generative AI model based on the analyzed speech content. The input is the speech content, and the output is the entertaining response. The server uses OpenAI's ChatGPT API to create friendly responses.

[0115] Step 4:

[0116] The server selects an appropriate gesture from a gesture library to determine the action to take in response to the generated entertaining response. The input is the entertaining response, and the output is the corresponding gesture. This allows for visual completion of the response.

[0117] Step 5:

[0118] The device presents the user with a combination of generated, entertaining responses and corresponding gestures. Input consists of responses and gestures, while output is the presentation of audio and actions to the user. This enables the provision of an enjoyable communication experience.

[0119] Furthermore, an emotion engine that estimates the user's emotions may be incorporated. That is, the identification processing unit 290 may use the emotion identification model 59 to estimate the user's emotions and perform identification processing using the user's emotions.

[0120] To implement this invention, it is necessary to construct an integrated system for recognizing the user's emotions and providing a corresponding response. This system includes acquiring voice data and analyzing the user's emotional state using an emotion engine.

[0121] Specifically, the device captures the user's voice using a microphone and acquires audio data. This audio data is sent to a server, where an emotion engine analyzes the characteristics of the voice to determine the user's emotional state. The emotion engine analyzes voice tone, speaking speed, volume changes, etc., based on a pre-trained model. If the user's face is also being analyzed, video data is also used to determine emotions from facial expressions.

[0122] Once the emotion analysis is complete, the server generates a humorous response tailored to the user's emotional state. For example, if the server detects that the user is tired, it will select a lighthearted joke or encouraging words to help them relax. In addition, it determines an appropriate gesture to match the selected response. The gestures are linked to the user's emotions, as they allow the avatar to visually provide a sense of comfort and amusement to the user.

[0123] The terminal receives response information from the server and presents it to the user. At this time, the avatar adjusts its voice tone to reflect the corresponding emotion and delivers a generated humorous response aloud. Furthermore, the determined gestures are appropriately executed through the avatar. For example, if the user expresses dissatisfaction, the avatar will display a softer expression and gentle movements to provide a personalized response that empathizes with the user.

[0124] Thus, this invention can dramatically improve the quality of communication by detecting the user's emotions and using humor and gestures that correspond to them. With this system, users can enjoy a friendly conversational experience while gaining a deeper sense of security by having their individual emotions taken into consideration.

[0125] The following describes the processing flow.

[0126] Step 1:

[0127] The device captures the user's voice using its microphone. Simultaneously with acquiring this audio data, it also captures the user's facial expressions with its camera as needed, saving them as video data.

[0128] Step 2:

[0129] The device transmits the acquired audio data and, if possible, video data to the server. This transmission is performed in real time, enabling rapid processing.

[0130] Step 3:

[0131] The server processes the received data through an emotion engine, analyzing voice tone, speaking speed, volume, and facial expressions from video data to identify the user's current emotional state. The emotion engine recognizes different emotional categories such as joy, sadness, anger, and surprise.

[0132] Step 4:

[0133] The server analyzes the user's emotional state and uses a generative AI model to generate humorous responses appropriate to the user. These responses are designed to consider the user's emotions and provide a pleasant experience.

[0134] Step 5:

[0135] The server selects a gesture appropriate to the humorous response generated. It chooses a gesture from a library of actions to be performed by the avatar that matches the atmosphere and the user's emotions.

[0136] Step 6:

[0137] The terminal receives responses and gesture information from the server and presents them to the user. The avatar plays a humorous voice response while simultaneously visually representing the selected gesture.

[0138] Step 7:

[0139] When the user makes a new utterance or facial expression, the device captures it again and repeats the aforementioned process, enabling a continuous dialogue. By responding to the user's changing emotions in real time, it provides a friendly and empathetic dialogue.

[0140] (Example 2)

[0141] Next, we will describe Example 2. In the following description, the data processing device 12 will be referred to as the "server" and the smart device 14 as the "terminal".

[0142] Conventional dialogue systems have struggled to accurately analyze the user's emotional state and generate natural, approachable responses accordingly. Furthermore, it has been difficult to conduct dialogues that incorporate visual presentations while considering the user's emotions, limiting the potential for improving the communication experience. Therefore, the present invention aims to provide a more natural and human-like dialogue experience that takes the user's emotions into consideration.

[0143] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means.

[0144] In this invention, the server includes means for acquiring voice data and analyzing the voice data based on the emotional state; means for generating a humorous response and determining a corresponding action based on the emotional state; and means for controlling the humorous response and the corresponding action to present a visual representation. This makes it possible to realize natural and friendly dialogue that responds to the user's emotional state and improve the quality of communication.

[0145] "Voice data" refers to data that digitally records the user's speech.

[0146] "Emotional state" refers to the emotional state expressed by the user, and is analyzed from factors such as voice and facial expressions.

[0147] A "humorous response" is a response generated to provide a familiar and pleasant reaction to the user's emotional state.

[0148] "Action" refers to the behavior of avatars or systems that are visually presented to the user.

[0149] "Visual representation" refers to visual information presented to the user using a display or similar device, and includes text information and avatar gestures.

[0150] To implement this invention, it is necessary to construct an integrated system that acquires the user's voice and facial input and generates a corresponding response. The system is configured as follows:

[0151] First, the user uses the device's microphone to input voice data. The device has a built-in high-quality microphone that captures the voice data. Next, the voice data captured on the device is transmitted to the server via wireless communication technology or an internet connection.

[0152] The server has the capability to receive audio data and analyzes it using a generative AI model. The emotion engine detects changes in voice tone, speaking speed, and volume, and identifies the user's emotional state based on these. In some cases, the system can also capture and send a video of the user's face using the device's camera, allowing it to determine emotions from facial expressions as well. This dual analysis enables more accurate emotion prediction.

[0153] Once the emotion analysis is complete, the server generates a response corresponding to the identified emotional state. This response, based on a pre-trained database and dialogue model, is designed to convey natural humor relevant to the scenario. Simultaneously, gestures presented by the avatar are selected to reflect the user's emotions.

[0154] The selected response and gesture information is transmitted to the terminal via the network. The terminal controls the avatar based on the received information. The avatar uses synthesized speech to provide voice responses to the user and displays visual gestures. This allows the user to receive responses both verbally and visually, resulting in a friendly and engaging conversational experience.

[0155] Specific example:

[0156] For example, if a user says "I'm tired today," the server will recognize this as a state of fatigue. It will then generate a response saying, "You must be tired. It's a good idea to take a break," and the avatar will smile and shrug.

[0157] Example of a prompt:

[0158] The prompt for the generative AI model should be set as follows: "Determine the user's emotions and generate friendly and humorous responses and gestures. For example, consider a response if the user says, 'I'm tired today.'"

[0159] This invention enables users to enjoy seamless and natural conversations and to communicate in a way that takes their emotional needs into consideration.

[0160] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0161] Step 1: Obtaining voice input

[0162] The device uses its microphone to capture the user's voice. It acquires a raw audio signal as input. This audio signal is digitized and stored as audio data. Specifically, the device records the audio in real time and optimizes the sound quality by performing noise filtering.

[0163] Step 2: Sending the audio data

[0164] The terminal sends audio data to the server. A digital audio file is used as input. This audio data is transmitted to the server via a secure internet connection. The terminal uses a data transfer protocol to compress the audio data during transmission.

[0165] Step 3: Analyzing the audio data

[0166] The server receives audio data and performs analysis using a generative AI model. The input is audio data sent from the terminal. The emotion engine analyzes the audio data, examining changes in tone, speech rate, and volume to identify the user's emotional state. The server's operation involves extracting audio features and inputting them into the AI ​​model.

[0167] Step 4: Response Generation

[0168] The server generates humorous responses based on the analyzed emotional state. It uses identified emotional information as input. The output is a text-based response, which is adjusted to create a natural conversation. Specifically, the server refers to past conversation history and a set of predefined dialogues to construct the most appropriate response.

[0169] Step 5: Deciding on a gesture

[0170] The server selects an action that matches the generated response. The generated text response is used as input. This action becomes the movement displayed by the avatar as a visual representation. The server's action involves selecting a gesture pattern from a database that corresponds to the user's emotional state.

[0171] Step 6: Presenting responses and gestures

[0172] The terminal presents the user with the response received from the server and gesture information. The input is a set of data transferred from the server. As output, the avatar interacts with the user using voice and actions. The terminal's specific actions include having the avatar speak lines using synthesized speech and visually reproducing selected gestures.

[0173] (Application Example 2)

[0174] Next, we will explain application example 2. In the following explanation, the data processing device 12 will be referred to as the "server," and the smart device 14 will be referred to as the "terminal."

[0175] In customer service, there is a growing demand for more personalized responses to users. However, conventional systems struggle to respond in accordance with users' emotions and emotional states, failing to provide satisfactory communication. Therefore, a system is needed that provides responses and gestures tailored to users' emotions, thereby improving the customer experience.

[0176] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means.

[0177] In this invention, the server includes means for acquiring voice information and converting said voice information into text data; means for analyzing utterance information based on said text data and generating a humorous response; means for determining an action corresponding to the humorous response and controlling and displaying a visual avatar; and means for generating voice output and actions according to the customer's emotional state. This makes it possible to provide more personalized communication to the user.

[0178] "Audio information" refers to sound data obtained from users' conversations and statements.

[0179] "Text data" refers to information in text format that has been converted from audio information.

[0180] "Speech information" refers to information that includes content and meaning obtained by analyzing text data.

[0181] A "humorous response" is a reply generated based on the user's spoken information and emotional state, designed to make the conversation more pleasant.

[0182] "Actions" refer to gestures and behaviors that avatars or other entities perform, either physically or visually.

[0183] A "visual avatar" is a character or image used to communicate with users in an observable manner.

[0184] "Emotional state" refers to the state of a user's feelings and psychological condition.

[0185] "Audio output" refers to the output used to convey the generated response to the user as sound.

[0186] "Customer experience" refers to the series of experiences and impressions that users have when interacting with a product or service.

[0187] This invention is a system for providing responses that correspond to the user's emotional state. The server uses a microphone connected to the terminal to acquire voice information. The acquired voice information is converted into text data. Next, the server analyzes this text data and extracts speech information. A generative AI model is used for the analysis, taking into account changes in voice tone, speaking speed, and volume.

[0188] The server generates humorous responses based on the extracted speech information. These responses are also used to determine actions that correspond to the user's emotional state, i.e., the avatar's gestures. The visual avatar is controlled according to the user's emotional state and visually represents their actions.

[0189] The device transmits the generated audio output to the user. For example, the avatar might use gentle facial expressions and calming movements to interact with the user in a way that feels empathetic.

[0190] As a concrete example, a smart customer service assistant in a store could read a customer's psychological state when they pick up a new product and provide the most appropriate response and gesture. This would improve the customer experience and allow users to experience a more friendly interaction.

[0191] An example of a prompt to be input to a generative AI model is: "Use the capabilities of the emotion recognition system to devise measures to reduce the user's stress level. Specifically, suggest appropriate responses and gestures as ways to improve the customer experience in a store."

[0192] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0193] Step 1:

[0194] The terminal uses a microphone to acquire user voice information. The input is the user's voice, and the output is digital voice data. This digital voice data is sent to the server.

[0195] Step 2:

[0196] The server converts the audio information into text data. The input is the audio data obtained in step 1, and the output is text data. Speech recognition technology is used to convert it into text data.

[0197] Step 3:

[0198] The server analyzes text data and extracts speech information. The input is the text data obtained in step 2, and the output is information including the intent and emotion of the speech. Here, a generative AI model is used, and the speech information is analyzed using natural language processing techniques.

[0199] Step 4:

[0200] The server analyzes the user's emotional state and generates a humorous response. The input is the speech information obtained in step 3, and the output is an appropriate response text based on the user's state. An emotion analysis engine is used to generate the response, producing a response with optimal humor based on the conversation content.

[0201] Step 5:

[0202] The server determines the actions of the visual avatar based on the generated response. The input is the response text obtained in step 4, and the output is the actions and gestures performed by the avatar. A gesture database based on emotions and responses is used to determine the actions.

[0203] Step 6:

[0204] The terminal uses audio output and gesture information received from the server to provide the user with visual and auditory feedback. The input consists of response text and gesture information obtained in steps 4 and 5, while the output is audio playback and avatar visual actions as a response to the user. Information is presented via the speaker and display.

[0205] The specific processing unit 290 transmits the result of the specific processing to the smart device 14. In the smart device 14, the control unit 46A causes the output device 40 to output the result of the specific processing. The microphone 38B acquires audio indicating user input for the result of the specific processing. The control unit 46A transmits the audio data indicating user input acquired by the microphone 38B to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the audio data.

[0206] Data generation model 58 is a type of so-called generative AI (Artificial Intelligence). One example of data generation model 58 is ChatGPT (Internet Search).<URL: https: / / openai.com / blog / chatgpt> ), Gemini (registered trademark) (Internet search) <url: https: gemini.google.com ?hl="ja">Examples of generative AI include the following. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 is input with prompts containing instructions, and with inference data such as audio data representing speech, text data representing text, and image data representing images. The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference results in data formats such as audio data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[0207] In the above embodiment, an example was given in which specific processing is performed by the data processing device 12, but the technology of this disclosure is not limited thereto, and the specific processing may also be performed by the smart device 14.

[0208] [Second Embodiment]

[0209] Figure 3 shows an example of the configuration of the data processing system 210 according to the second embodiment.

[0210] As shown in Figure 3, the data processing system 210 includes a data processing device 12 and smart glasses 214. An example of the data processing device 12 is a server.

[0211] The data processing device 12 comprises a computer 22, a database 24, and a communication interface 26. The computer 22 is an example of a "computer" related to the technology of this disclosure. The computer 22 comprises a processor 28, RAM 30, and storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication interface 26 are also connected to the bus 34. The communication interface 26 is connected to a network 54. An example of the network 54 is a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0212] The smart glasses 214 include a computer 36, a microphone 238, a speaker 240, a camera 42, and a communication interface 44. The computer 36 includes a processor 46, RAM 48, and storage 50. The processor 46, RAM 48, and storage 50 are connected to a bus 52. The microphone 238, speaker 240, and camera 42 are also connected to the bus 52.

[0213] The microphone 238 receives voice signals from the user 20 and receives instructions from the user 20. The microphone 238 captures the voice signals from the user 20, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to the instructions from the processor 46.

[0214] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an image sensor such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the area around the user 20 (for example, an imaging range defined by a field of view equivalent to the width of a typical healthy person's field of vision).

[0215] Communication interface 44 is connected to network 54. Communication interfaces 44 and 26 are responsible for the exchange of various information between processor 46 and processor 28 via network 54. The exchange of various information between processor 46 and processor 28 using communication interfaces 44 and 26 is performed in a secure manner.

[0216] Figure 4 shows an example of the main functions of the data processing device 12 and the smart glasses 214. As shown in Figure 4, the data processing device 12 performs specific processing using the processor 28. The storage 32 stores the specific processing program 56.

[0217] The specific processing program 56 is an example of a "program" relating to the technology of this disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[0218] The storage 32 stores the data generation model 58 and the emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[0219] In the smart glasses 214, the processor 46 performs the reception output processing. The storage 50 stores the reception output program 60. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output processing is realized by the processor 46 operating as a control unit 46A according to the reception output program 60 executed on the RAM 48.

[0220] Next, the identification processing performed by the identification processing unit 290 of the data processing device 12 will be described. In the following description, the data processing device 12 will be referred to as the "server" and the smart glasses 214 will be referred to as the "terminal".

[0221] To implement this invention, it is necessary to prepare a device for acquiring audio data and related software programs. First, the terminal acquires the user's voice in real time and sends the audio data to a cloud server. Here, the audio data is immediately converted into text data. Speech recognition technology is used for the conversion to text. The server analyzes this text data and attempts to understand the meaning and context of the words spoken by the user.

[0222] Next, the server uses a generative AI model to generate humorous responses based on the analyzed text data. These responses include appropriate jokes and witty remarks to make them user-friendly. Furthermore, to determine the gestures corresponding to these humorous responses, the server selects appropriate actions from a gesture library. These gestures enable visual representations that correspond to the content of the conversation.

[0223] The device then combines the generated humorous response and gestures and presents them to the user. The avatar delivers humorous responses audibly and simultaneously performs visual gestures, providing a friendly and enjoyable communication experience.

[0224] For example, if a user says, "I'm tired today," the server analyzes this and generates an appropriate humorous response such as, "You're out of energy! Shall we recharge and have some delicious cake?" In addition, the avatar performs a gesture indicating energy replenishment, providing the user with visual enjoyment. In this way, the system of the present invention makes it possible to reduce the psychological distance between the user and the system and to increase the user's sense of security.

[0225] The following describes the processing flow.

[0226] Step 1:

[0227] The device captures the user's voice using its microphone. This audio data is sent to a cloud server in real time.

[0228] Step 2:

[0229] The server converts the received audio data into text data using speech recognition technology. Advanced speech recognition algorithms are used here to ensure clear audio analysis and accurate text conversion.

[0230] Step 3:

[0231] The server analyzes the text data to understand the user's intent. This process involves using natural language processing (NLP) techniques to extract context and meaning.

[0232] Step 4:

[0233] The server uses a generative AI model to generate humorous responses based on the analysis results. In this step, the model is adjusted to create appropriate jokes and retorts that are relevant to the context.

[0234] Step 5:

[0235] The server determines a gesture to correspond to the generated humorous response. It selects the most appropriate action from the gesture library and generates control commands to have the 3D avatar perform that action.

[0236] Step 6:

[0237] The device presents the user with humorous responses and gestures received from the server. The avatar delivers the humorous responses aloud and simultaneously visually represents the determined gestures, providing the user with a friendly and enjoyable conversational experience.

[0238] (Example 1)

[0239] Next, we will describe Example 1. In the following description, the data processing device 12 will be referred to as the "server," and the smart glasses 214 will be referred to as the "terminal."

[0240] In today's information society, there is a growing demand for more natural and engaging dialogue when people communicate via digital devices. However, conventional systems struggle to generate and present humorous responses and accompanying actions in real time to put users at ease, failing to provide users with a highly satisfying dialogue experience. This challenge needs to be solved by combining more advanced natural language processing technologies with generative AI models.

[0241] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 1 is realized by the following means.

[0242] In this invention, the server includes means for acquiring voice information and converting said voice information into text information, means for analyzing the content of the speech and generating a humorous response, and means for determining the action corresponding to the humorous response and controlling and displaying a virtual character. This makes it possible to provide the user with an interesting and friendly communication experience that combines visual and auditory elements.

[0243] "Voice information" refers to voice data produced by users using digital devices.

[0244] "Textual information" refers to data obtained by analyzing audio information and representing its content in text.

[0245] "Speech content" refers to the meaning or intent that the user is trying to convey, based on the text information converted from the audio information.

[0246] A "humorous response" refers to a humorous reply generated in response to user input, providing a user-friendly interaction.

[0247] "Actions" refer to visual gestures and animations that appear in conjunction with humorous responses.

[0248] A "virtual character" refers to a computer-generated agent that operates within a digital environment and interacts with the user visually and audibly.

[0249] "Synthetic speech means" refers to technologies and software that convert text information into speech and output it.

[0250] This invention is a system for realizing natural and user-friendly communication with users. Specifically, it includes a series of methods for acquiring voice information from the user, converting it into text information, generating humorous responses, and presenting them through a virtual character.

[0251] First, the device uses a high-precision microphone to acquire the user's voice information in real time. This voice information is temporarily stored digitally within the device. Then, the data is sent to the server using a secure protocol (e.g., HTTPS).

[0252] The server converts received audio information into text using speech recognition technology (e.g., a speech recognition service). Based on this converted text, it analyzes the spoken content using natural language processing technology. During this process, prompt sentences are input to a generative AI model (e.g., an AI text generation engine) based on the analysis results, generating humorous responses.

[0253] To determine the appropriate action related to the generated response, the server selects an appropriate action from a pre-prepared library of actions. This action is instructed to a virtual character and visually presented to the user. Voice responses are generated using synthesized speech technology and communicated to the user in a distinctive voice that matches the humorous content of the response.

[0254] Finally, the device combines the generated humorous responses and actions and presents them to the user. This entire process allows the user to have a meaningful and enjoyable conversational experience.

[0255] For example, if a user says, "I'm tired today," the server will respond with a humorous "You're out of energy! Want to recharge and have some delicious cake?" This response includes a gesture that involves "replenishing energy," which is visually represented through the avatar. As a result, the user can experience friendly communication through both voice and visual means.

[0256] Example of a prompt:

[0257] "Generate a humorous response to the user's statement: 'I'm tired today.'"

[0258] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0259] Step 1:

[0260] The device uses a high-precision microphone to acquire user voice information in real time. The input is the user's voice. The output is audio data in digital format. During this process, the audio is temporarily stored using an audio capture function.

[0261] Step 2:

[0262] The device transmits the acquired audio data to the server via an internet connection using a secure protocol (e.g., HTTPS). The input is digital audio data. The output is the audio data transferred to the server.

[0263] Step 3:

[0264] The server uses speech recognition technology to convert received audio data into text data. The input is audio data. The output is the converted text data. An external speech recognition engine is used for this process.

[0265] Step 4:

[0266] The server utilizes natural language processing technology to analyze text data and understand the content and context of the utterance. The input is text data. The output is the analyzed utterance content and contextual information. Based on the analysis results, prompt sentences are created for the generative AI model.

[0267] Step 5:

[0268] The server inputs a prompt sentence into an AI model based on the analysis results, and generates a humorous response. The input is the prompt sentence. The output is the generated humorous response. An AI text generation engine is used in this step.

[0269] Step 6:

[0270] The server determines the appropriate action to take in response to a humorous response and selects the correct action from the action library. The input is the humorous response. The output is the selected action data. The gesture library is used to select an action.

[0271] Step 7:

[0272] The device uses speech synthesis technology to generate humorous responses as audio and displays them visually in sync with the movements of a virtual character. The input consists of humorous responses and movement data. The output is the audio and animation presented to the user. Animation software is used to provide the user with a visually entertaining experience.

[0273] (Application Example 1)

[0274] Next, we will explain Application Example 1. In the following explanation, the data processing device 12 will be referred to as the "server," and the smart glasses 214 will be referred to as the "terminal."

[0275] When autonomous devices are used in a work environment, there is a challenge in alleviating the stress and boredom experienced by operators due to repetitive monotonous tasks, thereby making the workplace more comfortable. Furthermore, another challenge is to provide means to enhance affinity with operators by offering more human-like communication in addition to mechanical actions.

[0276] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 1 is realized by the following means.

[0277] In this invention, the server includes means for acquiring voice information and converting said voice information into text information, means for analyzing the content of the utterance based on the text information and generating an entertaining response, and means for determining an action corresponding to the entertaining response and controlling an autonomous device to display it. This makes it possible to provide the operator with entertaining responses and actions even in a monotonous work environment, lighten the atmosphere of the workplace, and increase affinity with the operator.

[0278] "Audio information" refers to human speech and other acoustic signals obtained by converting sound waves into electrical signals.

[0279] "Textual information" refers to text-formatted data generated using speech recognition technology based on audio information.

[0280] "Speech content" refers to the meaning and context of the text information extracted from the audio information.

[0281] "Entertaining responses" refer to responses that use generative AI to add humor and friendliness to the content of the speech.

[0282] "Action" refers to gestures or actions performed by an autonomous device to visually assist in entertaining responses.

[0283] An "autonomous device" refers to a device that automates the acquisition of voice information, the generation of responses, and the execution of actions.

[0284] The "operator" refers to a person who directly or indirectly supervises and operates the operation of the autonomous device.

[0285] The "server" refers to a computer system that processes voice information and generates responses, and provides information to the autonomous device.

[0286] To implement the present invention, a device for acquiring voice information and a related software program are prepared. This system aims to process voice input, generate an entertaining response based on a generated AI model, and execute corresponding actions by the autonomous device.

[0287] The system first acquires voice information from an operator wearing smart glasses or a head-mounted display. For this, the Google Speech-to-Text API is used to convert the voice signal into character information. The converted character information is transmitted to the server, and the content of the utterance is analyzed. The server uses the OpenAI's ChatGPT API to generate an entertaining response based on the character information. This response determines an appropriate action from a gesture library set according to the operating environment and executes it.

[0288] The autonomous device presents an entertaining response to the operator as voice output and performs corresponding actions, thereby alleviating the monotonous working environment. As a specific example, when the operator says "There's so much work today, it's really tough!", the system responds with "That's a busy day! But I'll work hard with you too!" and performs the action of taking a guts pose.

[0289] Examples of prompt texts are as follows.

[0290] Example of a prompt text when the voice input is "There's so much work today, it's really tough!":

[0291] Recognized voice text: "There's so much work today, it's really tough!"

[0292] Generate an appropriate humorous response: "That's a busy day! But I'll do my best alongside you!"

[0293] Select a related gesture: the action of making a victory pose.

[0294] This makes it possible to build a system that enhances user engagement through entertaining responses and intuitive gestures.

[0295] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0296] Step 1:

[0297] The user provides voice input through smart glasses. The voice input is captured by a microphone built into the smart glasses. The input data is voice information, which is then converted into text information using the Google Speech-to-Text API. Converting the voice signal into a string enables the following processing:

[0298] Step 2:

[0299] The terminal sends the converted text information to the server. The server analyzes the text information and performs natural language processing to understand the spoken content. The input data is text information, and the output data is the analyzed spoken content. This allows the system to understand the user's intent.

[0300] Step 3:

[0301] The server generates entertaining responses using a generative AI model based on the analyzed speech content. The input is the speech content, and the output is the entertaining response. The server uses OpenAI's ChatGPT API to create friendly responses.

[0302] Step 4:

[0303] The server selects an appropriate gesture from the gesture library to determine an action corresponding to the generated entertaining response. The input is the entertaining response, and the output is the corresponding gesture. This enables the visual complementation of the response content.

[0304] Step 5:

[0305] The terminal combines the generated entertaining response and the corresponding gesture and presents them to the user. The input is the response and the gesture, and the output is the presentation of voice and actions to the user. This makes it possible to provide an enjoyable communication experience.

[0306] Furthermore, an emotion engine for estimating the user's emotion may be combined. That is, the specific processing unit 290 may estimate the user's emotion using the emotion recognition model 59 and perform specific processing using the user's emotion.

[0307] To implement this invention, it is necessary to construct an integrated system for recognizing the user's emotion and making a response accordingly. This system includes acquiring voice data and analyzing the user's emotional state using an emotion engine.

[0308] Specifically, the terminal captures the user's voice with a microphone and acquires voice data. This voice data is transmitted to the server, where the emotion engine analyzes the characteristics of the voice to determine the user's emotional state. The emotion engine analyzes the tone of voice, speech rate, changes in volume, etc. based on a pre-trained model. Also, when analyzing the user's facial video, video data is also used to discriminate emotion from expressions.

[0309] Once the emotion analysis is complete, the server generates a humorous response tailored to the user's emotional state. For example, if the server detects that the user is tired, it will select a lighthearted joke or encouraging words to help them relax. In addition, it determines an appropriate gesture to match the selected response. The gestures are linked to the user's emotions, as they allow the avatar to visually provide a sense of comfort and amusement to the user.

[0310] The terminal receives response information from the server and presents it to the user. At this time, the avatar adjusts its voice tone to reflect the corresponding emotion and delivers a generated humorous response aloud. Furthermore, the determined gestures are appropriately executed through the avatar. For example, if the user expresses dissatisfaction, the avatar will display a softer expression and gentle movements to provide a personalized response that empathizes with the user.

[0311] Thus, this invention can dramatically improve the quality of communication by detecting the user's emotions and using humor and gestures that correspond to them. With this system, users can enjoy a friendly conversational experience while gaining a deeper sense of security by having their individual emotions taken into consideration.

[0312] The following describes the processing flow.

[0313] Step 1:

[0314] The device captures the user's voice using its microphone. Simultaneously with acquiring this audio data, it also captures the user's facial expressions with its camera as needed, saving them as video data.

[0315] Step 2:

[0316] The device transmits the acquired audio data and, if possible, video data to the server. This transmission is performed in real time, enabling rapid processing.

[0317] Step 3:

[0318] The server processes the received data through an emotion engine, analyzing voice tone, speaking speed, volume, and facial expressions from video data to identify the user's current emotional state. The emotion engine recognizes different emotional categories such as joy, sadness, anger, and surprise.

[0319] Step 4:

[0320] The server analyzes the user's emotional state and uses a generative AI model to generate humorous responses appropriate to the user. These responses are designed to consider the user's emotions and provide a pleasant experience.

[0321] Step 5:

[0322] The server selects a gesture appropriate to the humorous response generated. It chooses a gesture from a library of actions to be performed by the avatar that matches the atmosphere and the user's emotions.

[0323] Step 6:

[0324] The terminal receives responses and gesture information from the server and presents them to the user. The avatar plays a humorous voice response while simultaneously visually representing the selected gesture.

[0325] Step 7:

[0326] When the user makes a new utterance or facial expression, the device captures it again and repeats the aforementioned process, enabling a continuous dialogue. By responding to the user's changing emotions in real time, it provides a friendly and empathetic dialogue.

[0327] (Example 2)

[0328] Next, we will describe Example 2. In the following description, the data processing device 12 will be referred to as the "server" and the smart glasses 214 will be referred to as the "terminal".

[0329] Conventional dialogue systems have struggled to accurately analyze the user's emotional state and generate natural, approachable responses accordingly. Furthermore, it has been difficult to conduct dialogues that incorporate visual presentations while considering the user's emotions, limiting the potential for improving the communication experience. Therefore, the present invention aims to provide a more natural and human-like dialogue experience that takes the user's emotions into consideration.

[0330] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means.

[0331] In this invention, the server includes means for acquiring voice data and analyzing the voice data based on the emotional state; means for generating a humorous response and determining a corresponding action based on the emotional state; and means for controlling the humorous response and the corresponding action to present a visual representation. This makes it possible to realize natural and friendly dialogue that responds to the user's emotional state and improve the quality of communication.

[0332] "Voice data" refers to data that digitally records the user's speech.

[0333] "Emotional state" refers to the emotional state expressed by the user, and is analyzed from factors such as voice and facial expressions.

[0334] A "humorous response" is a response generated to provide a familiar and pleasant reaction to the user's emotional state.

[0335] "Action" refers to the behavior of avatars or systems that are visually presented to the user.

[0336] "Visual representation" refers to visual information presented to the user using a display or similar device, and includes text information and avatar gestures.

[0337] To implement this invention, it is necessary to construct an integrated system that acquires the user's voice and facial input and generates a corresponding response. The system is configured as follows:

[0338] First, the user uses the device's microphone to input voice data. The device has a built-in high-quality microphone that captures the voice data. Next, the voice data captured on the device is transmitted to the server via wireless communication technology or an internet connection.

[0339] The server has the capability to receive audio data and analyzes it using a generative AI model. The emotion engine detects changes in voice tone, speaking speed, and volume, and identifies the user's emotional state based on these. In some cases, the system can also capture and send a video of the user's face using the device's camera, allowing it to determine emotions from facial expressions as well. This dual analysis enables more accurate emotion prediction.

[0340] Once the emotion analysis is complete, the server generates a response corresponding to the identified emotional state. This response, based on a pre-trained database and dialogue model, is designed to convey natural humor relevant to the scenario. Simultaneously, gestures presented by the avatar are selected to reflect the user's emotions.

[0341] The selected response and gesture information is transmitted to the terminal via the network. The terminal controls the avatar based on the received information. The avatar uses synthesized speech to provide voice responses to the user and displays visual gestures. This allows the user to receive responses both verbally and visually, resulting in a friendly and engaging conversational experience.

[0342] Specific example:

[0343] For example, if a user says "I'm tired today," the server will recognize this as a state of fatigue. It will then generate a response saying, "You must be tired. It's a good idea to take a break," and the avatar will smile and shrug.

[0344] Example of a prompt:

[0345] The prompt for the generative AI model should be set as follows: "Determine the user's emotions and generate friendly and humorous responses and gestures. For example, consider a response if the user says, 'I'm tired today.'"

[0346] This invention enables users to enjoy seamless and natural conversations and to communicate in a way that takes their emotional needs into consideration.

[0347] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0348] Step 1: Obtaining voice input

[0349] The device uses its microphone to capture the user's voice. It acquires a raw audio signal as input. This audio signal is digitized and stored as audio data. Specifically, the device records the audio in real time and optimizes the sound quality by performing noise filtering.

[0350] Step 2: Sending the audio data

[0351] The terminal sends audio data to the server. A digital audio file is used as input. This audio data is transmitted to the server via a secure internet connection. The terminal uses a data transfer protocol to compress the audio data during transmission.

[0352] Step 3: Analyzing the audio data

[0353] The server receives audio data and performs analysis using a generative AI model. The input is audio data sent from the terminal. The emotion engine analyzes the audio data, examining changes in tone, speech rate, and volume to identify the user's emotional state. The server's operation involves extracting audio features and inputting them into the AI ​​model.

[0354] Step 4: Response Generation

[0355] The server generates humorous responses based on the analyzed emotional state. It uses identified emotional information as input. The output is a text-based response, which is adjusted to create a natural conversation. Specifically, the server refers to past conversation history and a set of predefined dialogues to construct the most appropriate response.

[0356] Step 5: Deciding on a gesture

[0357] The server selects an action that matches the generated response. The generated text response is used as input. This action becomes the movement displayed by the avatar as a visual representation. The server's action involves selecting a gesture pattern from a database that corresponds to the user's emotional state.

[0358] Step 6: Presenting responses and gestures

[0359] The terminal presents the user with the response received from the server and gesture information. The input is a set of data transferred from the server. As output, the avatar interacts with the user using voice and actions. The terminal's specific actions include having the avatar speak lines using synthesized speech and visually reproducing selected gestures.

[0360] (Application Example 2)

[0361] Next, we will explain application example 2. In the following explanation, the data processing device 12 will be referred to as the "server," and the smart glasses 214 will be referred to as the "terminal."

[0362] In customer service, there is a growing demand for more personalized responses to users. However, conventional systems struggle to respond in accordance with users' emotions and emotional states, failing to provide satisfactory communication. Therefore, a system is needed that provides responses and gestures tailored to users' emotions, thereby improving the customer experience.

[0363] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means.

[0364] In this invention, the server includes means for acquiring voice information and converting said voice information into text data; means for analyzing utterance information based on said text data and generating a humorous response; means for determining an action corresponding to the humorous response and controlling and displaying a visual avatar; and means for generating voice output and actions according to the customer's emotional state. This makes it possible to provide more personalized communication to the user.

[0365] "Audio information" refers to sound data obtained from users' conversations and statements.

[0366] "Text data" refers to information in text format that has been converted from audio information.

[0367] "Speech information" refers to information that includes content and meaning obtained by analyzing text data.

[0368] A "humorous response" is a reply generated based on the user's spoken information and emotional state, designed to make the conversation more pleasant.

[0369] "Actions" refer to gestures and behaviors that avatars or other entities perform, either physically or visually.

[0370] A "visual avatar" is a character or image used to communicate with users in an observable manner.

[0371] "Emotional state" refers to the state of a user's feelings and psychological condition.

[0372] "Audio output" refers to the output used to convey the generated response to the user as sound.

[0373] "Customer experience" refers to the series of experiences and impressions that users have when interacting with a product or service.

[0374] This invention is a system for providing responses that correspond to the user's emotional state. The server uses a microphone connected to the terminal to acquire voice information. The acquired voice information is converted into text data. Next, the server analyzes this text data and extracts speech information. A generative AI model is used for the analysis, taking into account changes in voice tone, speaking speed, and volume.

[0375] The server generates humorous responses based on the extracted speech information. These responses are also used to determine actions that correspond to the user's emotional state, i.e., the avatar's gestures. The visual avatar is controlled according to the user's emotional state and visually represents their actions.

[0376] The device transmits the generated audio output to the user. For example, the avatar might use gentle facial expressions and calming movements to interact with the user in a way that feels empathetic.

[0377] As a concrete example, a smart customer service assistant in a store could read a customer's psychological state when they pick up a new product and provide the most appropriate response and gesture. This would improve the customer experience and allow users to experience a more friendly interaction.

[0378] An example of a prompt to be input to a generative AI model is: "Use the capabilities of the emotion recognition system to devise measures to reduce the user's stress level. Specifically, suggest appropriate responses and gestures as ways to improve the customer experience in a store."

[0379] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0380] Step 1:

[0381] The terminal uses a microphone to acquire user voice information. The input is the user's voice, and the output is digital voice data. This digital voice data is sent to the server.

[0382] Step 2:

[0383] The server converts the audio information into text data. The input is the audio data obtained in step 1, and the output is text data. Speech recognition technology is used to convert it into text data.

[0384] Step 3:

[0385] The server analyzes text data and extracts speech information. The input is the text data obtained in step 2, and the output is information including the intent and emotion of the speech. Here, a generative AI model is used, and the speech information is analyzed using natural language processing techniques.

[0386] Step 4:

[0387] The server analyzes the user's emotional state and generates a humorous response. The input is the speech information obtained in step 3, and the output is an appropriate response text based on the user's state. An emotion analysis engine is used to generate the response, producing a response with optimal humor based on the conversation content.

[0388] Step 5:

[0389] The server determines the actions of the visual avatar based on the generated response. The input is the response text obtained in step 4, and the output is the actions and gestures performed by the avatar. A gesture database based on emotions and responses is used to determine the actions.

[0390] Step 6:

[0391] The terminal uses audio output and gesture information received from the server to provide the user with visual and auditory feedback. The input consists of response text and gesture information obtained in steps 4 and 5, while the output is audio playback and avatar visual actions as a response to the user. Information is presented via the speaker and display.

[0392] The specific processing unit 290 transmits the result of the specific processing to the smart glasses 214. In the smart glasses 214, the control unit 46A causes the speaker 240 to output the result of the specific processing. The microphone 238 acquires audio indicating user input for the result of the specific processing. The control unit 46A transmits the audio data indicating user input acquired by the microphone 238 to the data processing unit 12. In the data processing unit 12, the specific processing unit 290 acquires the audio data.

[0393] Data generation model 58 is a type of so-called generative AI (Artificial Intelligence). One example of data generation model 58 is ChatGPT (Internet Search).<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search) <url: https: gemini.google.com ?hl="ja">Examples of generative AI include the following. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 is input with prompts containing instructions, and with inference data such as audio data representing speech, text data representing text, and image data representing images. The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference results in data formats such as audio data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[0394] In the above embodiment, an example was given in which specific processing is performed by the data processing device 12, but the technology of this disclosure is not limited thereto, and the specific processing may also be performed by the smart glasses 214.

[0395] [Third Embodiment]

[0396] Figure 5 shows an example of the configuration of the data processing system 310 according to the third embodiment.

[0397] As shown in Figure 5, the data processing system 310 includes a data processing device 12 and a headset terminal 314. An example of the data processing device 12 is a server.

[0398] The data processing device 12 comprises a computer 22, a database 24, and a communication interface 26. The computer 22 is an example of a "computer" related to the technology of this disclosure. The computer 22 comprises a processor 28, RAM 30, and storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication interface 26 are also connected to the bus 34. The communication interface 26 is connected to a network 54. An example of the network 54 is a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0399] The headset terminal 314 includes a computer 36, a microphone 238, a speaker 240, a camera 42, a communication interface 44, and a display 343. The computer 36 includes a processor 46, RAM 48, and storage 50. The processor 46, RAM 48, and storage 50 are connected to a bus 52. The microphone 238, speaker 240, camera 42, and display 343 are also connected to the bus 52.

[0400] The microphone 238 receives voice signals from the user 20 and receives instructions from the user 20. The microphone 238 captures the voice signals from the user 20, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to the instructions from the processor 46.

[0401] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an image sensor such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the area around the user 20 (for example, an imaging range defined by a field of view equivalent to the width of a typical healthy person's field of vision).

[0402] Communication interface 44 is connected to network 54. Communication interfaces 44 and 26 are responsible for the exchange of various information between processor 46 and processor 28 via network 54. The exchange of various information between processor 46 and processor 28 using communication interfaces 44 and 26 is performed in a secure manner.

[0403] Figure 6 shows an example of the main functions of the data processing device 12 and the headset terminal 314. As shown in Figure 6, the data processing device 12 performs specific processing using the processor 28. The storage 32 stores the specific processing program 56.

[0404] The specific processing program 56 is an example of a "program" relating to the technology of this disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[0405] The storage 32 stores the data generation model 58 and the emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[0406] In the headset terminal 314, the processor 46 performs the reception output processing. The storage 50 stores the reception output program 60. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output processing is realized by the processor 46 operating as a control unit 46A according to the reception output program 60 executed on the RAM 48.

[0407] Next, the specific processing performed by the specific processing unit 290 of the data processing device 12 will be described. In the following description, the data processing device 12 will be referred to as the "server" and the headset terminal 314 will be referred to as the "terminal".

[0408] To implement this invention, it is necessary to prepare a device for acquiring audio data and related software programs. First, the terminal acquires the user's voice in real time and sends the audio data to a cloud server. Here, the audio data is immediately converted into text data. Speech recognition technology is used for the conversion to text. The server analyzes this text data and attempts to understand the meaning and context of the words spoken by the user.

[0409] Next, the server uses a generative AI model to generate humorous responses based on the analyzed text data. These responses include appropriate jokes and witty remarks to make them user-friendly. Furthermore, to determine the gestures corresponding to these humorous responses, the server selects appropriate actions from a gesture library. These gestures enable visual representations that correspond to the content of the conversation.

[0410] The device then combines the generated humorous response and gestures and presents them to the user. The avatar delivers humorous responses audibly and simultaneously performs visual gestures, providing a friendly and enjoyable communication experience.

[0411] For example, if a user says, "I'm tired today," the server analyzes this and generates an appropriate humorous response such as, "You're out of energy! Shall we recharge and have some delicious cake?" In addition, the avatar performs a gesture indicating energy replenishment, providing the user with visual enjoyment. In this way, the system of the present invention makes it possible to reduce the psychological distance between the user and the system and to increase the user's sense of security.

[0412] The following describes the processing flow.

[0413] Step 1:

[0414] The device captures the user's voice using its microphone. This audio data is sent to a cloud server in real time.

[0415] Step 2:

[0416] The server converts the received audio data into text data using speech recognition technology. Advanced speech recognition algorithms are used here to ensure clear audio analysis and accurate text conversion.

[0417] Step 3:

[0418] The server analyzes the text data to understand the user's intent. This process involves using natural language processing (NLP) techniques to extract context and meaning.

[0419] Step 4:

[0420] The server uses a generative AI model to generate humorous responses based on the analysis results. In this step, the model is adjusted to create appropriate jokes and retorts that are relevant to the context.

[0421] Step 5:

[0422] The server determines a gesture to correspond to the generated humorous response. It selects the most appropriate action from the gesture library and generates control commands to have the 3D avatar perform that action.

[0423] Step 6:

[0424] The device presents the user with humorous responses and gestures received from the server. The avatar delivers the humorous responses aloud and simultaneously visually represents the determined gestures, providing the user with a friendly and enjoyable conversational experience.

[0425] (Example 1)

[0426] Next, we will describe Example 1. In the following description, the data processing device 12 will be referred to as the "server," and the headset-type terminal 314 will be referred to as the "terminal."

[0427] In today's information society, there is a growing demand for more natural and engaging dialogue when people communicate via digital devices. However, conventional systems struggle to generate and present humorous responses and accompanying actions in real time to put users at ease, failing to provide users with a highly satisfying dialogue experience. This challenge needs to be solved by combining more advanced natural language processing technologies with generative AI models.

[0428] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 1 is realized by the following means.

[0429] In this invention, the server includes means for acquiring voice information and converting said voice information into text information, means for analyzing the content of the speech and generating a humorous response, and means for determining the action corresponding to the humorous response and controlling and displaying a virtual character. This makes it possible to provide the user with an interesting and friendly communication experience that combines visual and auditory elements.

[0430] "Voice information" refers to voice data produced by users using digital devices.

[0431] "Textual information" refers to data obtained by analyzing audio information and representing its content in text.

[0432] "Speech content" refers to the meaning or intent that the user is trying to convey, based on the text information converted from the audio information.

[0433] A "humorous response" refers to a humorous reply generated in response to user input, providing a user-friendly interaction.

[0434] "Actions" refer to visual gestures and animations that appear in conjunction with humorous responses.

[0435] A "virtual character" refers to a computer-generated agent that operates within a digital environment and interacts with the user visually and audibly.

[0436] "Synthetic speech means" refers to technologies and software that convert text information into speech and output it.

[0437] This invention is a system for realizing natural and user-friendly communication with users. Specifically, it includes a series of methods for acquiring voice information from the user, converting it into text information, generating humorous responses, and presenting them through a virtual character.

[0438] First, the device uses a high-precision microphone to acquire the user's voice information in real time. This voice information is temporarily stored digitally within the device. Then, the data is sent to the server using a secure protocol (e.g., HTTPS).

[0439] The server converts received audio information into text using speech recognition technology (e.g., a speech recognition service). Based on this converted text, it analyzes the spoken content using natural language processing technology. During this process, prompt sentences are input to a generative AI model (e.g., an AI text generation engine) based on the analysis results, generating humorous responses.

[0440] To determine the appropriate action related to the generated response, the server selects an appropriate action from a pre-prepared library of actions. This action is instructed to a virtual character and visually presented to the user. Voice responses are generated using synthesized speech technology and communicated to the user in a distinctive voice that matches the humorous content of the response.

[0441] Finally, the device combines the generated humorous responses and actions and presents them to the user. This entire process allows the user to have a meaningful and enjoyable conversational experience.

[0442] For example, if a user says, "I'm tired today," the server will respond with a humorous "You're out of energy! Want to recharge and have some delicious cake?" This response includes a gesture that involves "replenishing energy," which is visually represented through the avatar. As a result, the user can experience friendly communication through both voice and visual means.

[0443] Example of a prompt:

[0444] "Generate a humorous response to the user's statement: 'I'm tired today.'"

[0445] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0446] Step 1:

[0447] The device uses a high-precision microphone to acquire user voice information in real time. The input is the user's voice. The output is audio data in digital format. During this process, the audio is temporarily stored using an audio capture function.

[0448] Step 2:

[0449] The device transmits the acquired audio data to the server via an internet connection using a secure protocol (e.g., HTTPS). The input is digital audio data. The output is the audio data transferred to the server.

[0450] Step 3:

[0451] The server uses speech recognition technology to convert received audio data into text data. The input is audio data. The output is the converted text data. An external speech recognition engine is used for this process.

[0452] Step 4:

[0453] The server utilizes natural language processing technology to analyze text data and understand the content and context of the utterance. The input is text data. The output is the analyzed utterance content and contextual information. Based on the analysis results, prompt sentences are created for the generative AI model.

[0454] Step 5:

[0455] The server inputs a prompt sentence into an AI model based on the analysis results, and generates a humorous response. The input is the prompt sentence. The output is the generated humorous response. An AI text generation engine is used in this step.

[0456] Step 6:

[0457] The server determines the appropriate action to take in response to a humorous response and selects the correct action from the action library. The input is the humorous response. The output is the selected action data. The gesture library is used to select an action.

[0458] Step 7:

[0459] The device uses speech synthesis technology to generate humorous responses as audio and displays them visually in sync with the movements of a virtual character. The input consists of humorous responses and movement data. The output is the audio and animation presented to the user. Animation software is used to provide the user with a visually entertaining experience.

[0460] (Application Example 1)

[0461] Next, we will explain Application Example 1. In the following explanation, the data processing device 12 will be referred to as the "server," and the headset-type terminal 314 will be referred to as the "terminal."

[0462] When autonomous devices are used in a work environment, there is a challenge in alleviating the stress and boredom experienced by operators due to repetitive monotonous tasks, thereby making the workplace more comfortable. Furthermore, another challenge is to provide means to enhance affinity with operators by offering more human-like communication in addition to mechanical actions.

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

[0464] In this invention, the server includes means for acquiring voice information and converting said voice information into text information, means for analyzing the content of the utterance based on the text information and generating an entertaining response, and means for determining an action corresponding to the entertaining response and controlling an autonomous device to display it. This makes it possible to provide the operator with entertaining responses and actions even in a monotonous work environment, lighten the atmosphere of the workplace, and increase affinity with the operator.

[0465] "Audio information" refers to human speech and other acoustic signals obtained by converting sound waves into electrical signals.

[0466] "Textual information" refers to text-formatted data generated using speech recognition technology based on audio information.

[0467] "Speech content" refers to the meaning and context of the text information extracted from the audio information.

[0468] "Entertaining responses" refer to responses that use generative AI to add humor and friendliness to the content of the speech.

[0469] "Action" refers to gestures or actions performed by an autonomous device to visually assist in entertaining responses.

[0470] An "autonomous device" refers to a device that automates the acquisition of voice information, the generation of responses, and the execution of actions.

[0471] "Operator" refers to a person who directly or indirectly supervises and controls the operation of an autonomous device.

[0472] A "server" refers to a computer system that processes voice information, generates responses, and provides information to autonomous devices.

[0473] To implement this invention, a device for acquiring voice information and a related software program are provided. The purpose of this system is to process voice input, generate entertaining responses based on a generative AI model, and have an autonomous device perform the corresponding actions.

[0474] The system first acquires voice information from the user wearing smart glasses or a head-mounted display. This is done using the Google Speech-to-Text API to convert the voice signal into text. The converted text is sent to a server where the speech content is analyzed. The server uses OpenAI's ChatGPT API to generate an entertaining response based on the text. This response determines and executes the appropriate action from a gesture library configured to suit the user's environment.

[0475] The autonomous device provides entertaining responses to the operator as voice output and performs corresponding actions to lighten the mood in a potentially monotonous work environment. For example, if the operator says, "Today's work is so heavy!", the system will respond, "That sounds like a busy day! But I'll do my best with you!" and perform a gesture of giving a thumbs-up.

[0476] Examples of prompt messages are as follows:

[0477] Example prompt when the voice input says, "Today's work is so heavy and overwhelming!":

[0478] Speech-recognized text: "Today was a busy day with lots of work!"

[0479] Generate an appropriate humorous response: "That's a busy day! But I'll do my best alongside you!"

[0480] Select a related gesture: the action of making a victory pose.

[0481] This makes it possible to build a system that enhances user engagement through entertaining responses and intuitive gestures.

[0482] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0483] Step 1:

[0484] The user provides voice input through smart glasses. The voice input is captured by a microphone built into the smart glasses. The input data is voice information, which is then converted into text information using the Google Speech-to-Text API. Converting the voice signal into a string enables the following processing:

[0485] Step 2:

[0486] The terminal sends the converted text information to the server. The server analyzes the text information and performs natural language processing to understand the spoken content. The input data is text information, and the output data is the analyzed spoken content. This allows the system to understand the user's intent.

[0487] Step 3:

[0488] The server generates entertaining responses using a generative AI model based on the analyzed speech content. The input is the speech content, and the output is the entertaining response. The server uses OpenAI's ChatGPT API to create friendly responses.

[0489] Step 4:

[0490] The server selects an appropriate gesture from a gesture library to determine the action to take in response to the generated entertaining response. The input is the entertaining response, and the output is the corresponding gesture. This allows for visual completion of the response.

[0491] Step 5:

[0492] The device presents the user with a combination of generated, entertaining responses and corresponding gestures. Input consists of responses and gestures, while output is the presentation of audio and actions to the user. This enables the provision of an enjoyable communication experience.

[0493] Furthermore, an emotion engine that estimates the user's emotions may be incorporated. That is, the identification processing unit 290 may use the emotion identification model 59 to estimate the user's emotions and perform identification processing using the user's emotions.

[0494] To implement this invention, it is necessary to construct an integrated system for recognizing the user's emotions and providing a corresponding response. This system includes acquiring voice data and analyzing the user's emotional state using an emotion engine.

[0495] Specifically, the device captures the user's voice using a microphone and acquires audio data. This audio data is sent to a server, where an emotion engine analyzes the characteristics of the voice to determine the user's emotional state. The emotion engine analyzes voice tone, speaking speed, volume changes, etc., based on a pre-trained model. If the user's face is also being analyzed, video data is also used to determine emotions from facial expressions.

[0496] Once the emotion analysis is complete, the server generates a humorous response tailored to the user's emotional state. For example, if the server detects that the user is tired, it will select a lighthearted joke or encouraging words to help them relax. In addition, it determines an appropriate gesture to match the selected response. The gestures are linked to the user's emotions, as they allow the avatar to visually provide a sense of comfort and amusement to the user.

[0497] The terminal receives response information from the server and presents it to the user. At this time, the avatar adjusts its voice tone to reflect the corresponding emotion and delivers a generated humorous response aloud. Furthermore, the determined gestures are appropriately executed through the avatar. For example, if the user expresses dissatisfaction, the avatar will display a softer expression and gentle movements to provide a personalized response that empathizes with the user.

[0498] Thus, this invention can dramatically improve the quality of communication by detecting the user's emotions and using humor and gestures that correspond to them. With this system, users can enjoy a friendly conversational experience while gaining a deeper sense of security by having their individual emotions taken into consideration.

[0499] The following describes the processing flow.

[0500] Step 1:

[0501] The device captures the user's voice using its microphone. Simultaneously with acquiring this audio data, it also captures the user's facial expressions with its camera as needed, saving them as video data.

[0502] Step 2:

[0503] The device transmits the acquired audio data and, if possible, video data to the server. This transmission is performed in real time, enabling rapid processing.

[0504] Step 3:

[0505] The server processes the received data through an emotion engine, analyzing voice tone, speaking speed, volume, and facial expressions from video data to identify the user's current emotional state. The emotion engine recognizes different emotional categories such as joy, sadness, anger, and surprise.

[0506] Step 4:

[0507] The server analyzes the user's emotional state and uses a generative AI model to generate humorous responses appropriate to the user. These responses are designed to consider the user's emotions and provide a pleasant experience.

[0508] Step 5:

[0509] The server selects a gesture appropriate to the humorous response generated. It chooses a gesture from a library of actions to be performed by the avatar that matches the atmosphere and the user's emotions.

[0510] Step 6:

[0511] The terminal receives responses and gesture information from the server and presents them to the user. The avatar plays a humorous voice response while simultaneously visually representing the selected gesture.

[0512] Step 7:

[0513] When the user makes a new utterance or facial expression, the device captures it again and repeats the aforementioned process, enabling a continuous dialogue. By responding to the user's changing emotions in real time, it provides a friendly and empathetic dialogue.

[0514] (Example 2)

[0515] Next, we will describe Example 2. In the following description, the data processing device 12 will be referred to as the "server," and the headset-type terminal 314 will be referred to as the "terminal."

[0516] Conventional dialogue systems have struggled to accurately analyze the user's emotional state and generate natural, approachable responses accordingly. Furthermore, it has been difficult to conduct dialogues that incorporate visual presentations while considering the user's emotions, limiting the potential for improving the communication experience. Therefore, the present invention aims to provide a more natural and human-like dialogue experience that takes the user's emotions into consideration.

[0517] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means.

[0518] In this invention, the server includes means for acquiring voice data and analyzing the voice data based on the emotional state; means for generating a humorous response and determining a corresponding action based on the emotional state; and means for controlling the humorous response and the corresponding action to present a visual representation. This makes it possible to realize natural and friendly dialogue that responds to the user's emotional state and improve the quality of communication.

[0519] "Voice data" refers to data that digitally records the user's speech.

[0520] "Emotional state" refers to the emotional state expressed by the user, and is analyzed from factors such as voice and facial expressions.

[0521] A "humorous response" is a response generated to provide a familiar and pleasant reaction to the user's emotional state.

[0522] "Action" refers to the behavior of avatars or systems that are visually presented to the user.

[0523] "Visual representation" refers to visual information presented to the user using a display or similar device, and includes text information and avatar gestures.

[0524] To implement this invention, it is necessary to construct an integrated system that acquires the user's voice and facial input and generates a corresponding response. The system is configured as follows:

[0525] First, the user uses the device's microphone to input voice data. The device has a built-in high-quality microphone that captures the voice data. Next, the voice data captured on the device is transmitted to the server via wireless communication technology or an internet connection.

[0526] The server has the capability to receive audio data and analyzes it using a generative AI model. The emotion engine detects changes in voice tone, speaking speed, and volume, and identifies the user's emotional state based on these. In some cases, the system can also capture and send a video of the user's face using the device's camera, allowing it to determine emotions from facial expressions as well. This dual analysis enables more accurate emotion prediction.

[0527] Once the emotion analysis is complete, the server generates a response corresponding to the identified emotional state. This response, based on a pre-trained database and dialogue model, is designed to convey natural humor relevant to the scenario. Simultaneously, gestures presented by the avatar are selected to reflect the user's emotions.

[0528] The selected response and gesture information is transmitted to the terminal via the network. The terminal controls the avatar based on the received information. The avatar uses synthesized speech to provide voice responses to the user and displays visual gestures. This allows the user to receive responses both verbally and visually, resulting in a friendly and engaging conversational experience.

[0529] Specific example:

[0530] For example, if a user says "I'm tired today," the server will recognize this as a state of fatigue. It will then generate a response saying, "You must be tired. It's a good idea to take a break," and the avatar will smile and shrug.

[0531] Example of a prompt:

[0532] The prompt for the generative AI model should be set as follows: "Determine the user's emotions and generate friendly and humorous responses and gestures. For example, consider a response if the user says, 'I'm tired today.'"

[0533] This invention enables users to enjoy seamless and natural conversations and to communicate in a way that takes their emotional needs into consideration.

[0534] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0535] Step 1: Obtaining voice input

[0536] The device uses its microphone to capture the user's voice. It acquires a raw audio signal as input. This audio signal is digitized and stored as audio data. Specifically, the device records the audio in real time and optimizes the sound quality by performing noise filtering.

[0537] Step 2: Sending the audio data

[0538] The terminal sends audio data to the server. A digital audio file is used as input. This audio data is transmitted to the server via a secure internet connection. The terminal uses a data transfer protocol to compress the audio data during transmission.

[0539] Step 3: Analyzing the audio data

[0540] The server receives audio data and performs analysis using a generative AI model. The input is audio data sent from the terminal. The emotion engine analyzes the audio data, examining changes in tone, speech rate, and volume to identify the user's emotional state. The server's operation involves extracting audio features and inputting them into the AI ​​model.

[0541] Step 4: Response Generation

[0542] The server generates humorous responses based on the analyzed emotional state. It uses identified emotional information as input. The output is a text-based response, which is adjusted to create a natural conversation. Specifically, the server refers to past conversation history and a set of predefined dialogues to construct the most appropriate response.

[0543] Step 5: Deciding on a gesture

[0544] The server selects an action that matches the generated response. The generated text response is used as input. This action becomes the movement displayed by the avatar as a visual representation. The server's action involves selecting a gesture pattern from a database that corresponds to the user's emotional state.

[0545] Step 6: Presenting responses and gestures

[0546] The terminal presents the user with the response received from the server and gesture information. The input is a set of data transferred from the server. As output, the avatar interacts with the user using voice and actions. The terminal's specific actions include having the avatar speak lines using synthesized speech and visually reproducing selected gestures.

[0547] (Application Example 2)

[0548] Next, we will explain application example 2. In the following explanation, the data processing device 12 will be referred to as the "server," and the headset-type terminal 314 will be referred to as the "terminal."

[0549] In customer service, there is a growing demand for more personalized responses to users. However, conventional systems struggle to respond in accordance with users' emotions and emotional states, failing to provide satisfactory communication. Therefore, a system is needed that provides responses and gestures tailored to users' emotions, thereby improving the customer experience.

[0550] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means.

[0551] In this invention, the server includes means for acquiring voice information and converting said voice information into text data; means for analyzing utterance information based on said text data and generating a humorous response; means for determining an action corresponding to the humorous response and controlling and displaying a visual avatar; and means for generating voice output and actions according to the customer's emotional state. This makes it possible to provide more personalized communication to the user.

[0552] "Audio information" refers to sound data obtained from users' conversations and statements.

[0553] "Text data" refers to information in text format that has been converted from audio information.

[0554] "Speech information" refers to information that includes content and meaning obtained by analyzing text data.

[0555] A "humorous response" is a reply generated based on the user's spoken information and emotional state, designed to make the conversation more pleasant.

[0556] "Actions" refer to gestures and behaviors that avatars or other entities perform, either physically or visually.

[0557] A "visual avatar" is a character or image used to communicate with users in an observable manner.

[0558] "Emotional state" refers to the state of a user's feelings and psychological condition.

[0559] "Audio output" refers to the output used to convey the generated response to the user as sound.

[0560] "Customer experience" refers to the series of experiences and impressions that users have when interacting with a product or service.

[0561] This invention is a system for providing responses that correspond to the user's emotional state. The server uses a microphone connected to the terminal to acquire voice information. The acquired voice information is converted into text data. Next, the server analyzes this text data and extracts speech information. A generative AI model is used for the analysis, taking into account changes in voice tone, speaking speed, and volume.

[0562] The server generates humorous responses based on the extracted speech information. These responses are also used to determine actions that correspond to the user's emotional state, i.e., the avatar's gestures. The visual avatar is controlled according to the user's emotional state and visually represents their actions.

[0563] The device transmits the generated audio output to the user. For example, the avatar might use gentle facial expressions and calming movements to interact with the user in a way that feels empathetic.

[0564] As a concrete example, a smart customer service assistant in a store could read a customer's psychological state when they pick up a new product and provide the most appropriate response and gesture. This would improve the customer experience and allow users to experience a more friendly interaction.

[0565] An example of a prompt to be input to a generative AI model is: "Use the capabilities of the emotion recognition system to devise measures to reduce the user's stress level. Specifically, suggest appropriate responses and gestures as ways to improve the customer experience in a store."

[0566] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0567] Step 1:

[0568] The terminal uses a microphone to acquire user voice information. The input is the user's voice, and the output is digital voice data. This digital voice data is sent to the server.

[0569] Step 2:

[0570] The server converts the audio information into text data. The input is the audio data obtained in step 1, and the output is text data. Speech recognition technology is used to convert it into text data.

[0571] Step 3:

[0572] The server analyzes text data and extracts speech information. The input is the text data obtained in step 2, and the output is information including the intent and emotion of the speech. Here, a generative AI model is used, and the speech information is analyzed using natural language processing techniques.

[0573] Step 4:

[0574] The server analyzes the user's emotional state and generates a humorous response. The input is the speech information obtained in step 3, and the output is an appropriate response text based on the user's state. An emotion analysis engine is used to generate the response, producing a response with optimal humor based on the conversation content.

[0575] Step 5:

[0576] The server determines the actions of the visual avatar based on the generated response. The input is the response text obtained in step 4, and the output is the actions and gestures performed by the avatar. A gesture database based on emotions and responses is used to determine the actions.

[0577] Step 6:

[0578] The terminal uses audio output and gesture information received from the server to provide the user with visual and auditory feedback. The input consists of response text and gesture information obtained in steps 4 and 5, while the output is audio playback and avatar visual actions as a response to the user. Information is presented via the speaker and display.

[0579] The specific processing unit 290 transmits the result of the specific processing to the headset terminal 314. In the headset terminal 314, the control unit 46A causes the speaker 240 and display 343 to output the result of the specific processing. The microphone 238 acquires audio indicating user input for the result of the specific processing. The control unit 46A transmits the audio data indicating user input acquired by the microphone 238 to the data processing unit 12. In the data processing unit 12, the specific processing unit 290 acquires the audio data.

[0580] Data generation model 58 is a type of so-called generative AI (Artificial Intelligence). One example of data generation model 58 is ChatGPT (Internet Search).<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search) <url: https: gemini.google.com ?hl="ja">Examples of generative AI include the following. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 is input with prompts containing instructions, and with inference data such as audio data representing speech, text data representing text, and image data representing images. The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference results in data formats such as audio data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[0581] In the above embodiment, an example was given in which specific processing is performed by the data processing device 12, but the technology of this disclosure is not limited thereto, and specific processing may also be performed by the headset terminal 314.

[0582] [Fourth Embodiment]

[0583] Figure 7 shows an example of the configuration of the data processing system 410 according to the fourth embodiment.

[0584] As shown in Figure 7, the data processing system 410 includes a data processing device 12 and a robot 414. An example of the data processing device 12 is a server.

[0585] The data processing device 12 comprises a computer 22, a database 24, and a communication interface 26. The computer 22 is an example of a "computer" related to the technology of this disclosure. The computer 22 comprises a processor 28, RAM 30, and storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication interface 26 are also connected to the bus 34. The communication interface 26 is connected to a network 54. An example of the network 54 is a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0586] The robot 414 includes a computer 36, a microphone 238, a speaker 240, a camera 42, a communication interface 44, and a controlled object 443. The computer 36 includes a processor 46, RAM 48, and storage 50. The processor 46, RAM 48, and storage 50 are connected to a bus 52. The microphone 238, speaker 240, camera 42, and controlled object 443 are also connected to the bus 52.

[0587] The microphone 238 receives voice signals from the user 20 and receives instructions from the user 20. The microphone 238 captures the voice signals from the user 20, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to the instructions from the processor 46.

[0588] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an image sensor such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the area around the user 20 (for example, an imaging range defined by a field of view equivalent to the width of a typical healthy person's field of vision).

[0589] Communication interface 44 is connected to network 54. Communication interfaces 44 and 26 are responsible for the exchange of various information between processor 46 and processor 28 via network 54. The exchange of various information between processor 46 and processor 28 using communication interfaces 44 and 26 is performed in a secure manner.

[0590] The controlled object 443 includes a display device, LEDs in the eyes, and motors that drive the arms, hands, and feet. The posture and gestures of the robot 414 are controlled by controlling the motors of the arms, hands, and feet. Some of the robot 414's emotions can be expressed by controlling these motors. Furthermore, the robot 414's facial expressions can also be expressed by controlling the illumination state of the LEDs in its eyes.

[0591] Figure 8 shows an example of the main functions of the data processing device 12 and the robot 414. As shown in Figure 8, the data processing device 12 performs specific processing using the processor 28. The storage 32 stores the specific processing program 56.

[0592] The specific processing program 56 is an example of a "program" relating to the technology of this disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[0593] The storage 32 stores the data generation model 58 and the emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[0594] In robot 414, the processor 46 performs the reception output processing. The storage 50 stores the reception output program 60. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output processing is realized by the processor 46 operating as a control unit 46A according to the reception output program 60 executed on the RAM 48.

[0595] Next, the specific processing performed by the specific processing unit 290 of the data processing device 12 will be described. In the following description, the data processing device 12 will be referred to as the "server" and the robot 414 as the "terminal".

[0596] To implement this invention, it is necessary to prepare a device for acquiring audio data and related software programs. First, the terminal acquires the user's voice in real time and sends the audio data to a cloud server. Here, the audio data is immediately converted into text data. Speech recognition technology is used for the conversion to text. The server analyzes this text data and attempts to understand the meaning and context of the words spoken by the user.

[0597] Next, the server uses a generative AI model to generate humorous responses based on the analyzed text data. These responses include appropriate jokes and witty remarks to make them user-friendly. Furthermore, to determine the gestures corresponding to these humorous responses, the server selects appropriate actions from a gesture library. These gestures enable visual representations that correspond to the content of the conversation.

[0598] The device then combines the generated humorous response and gestures and presents them to the user. The avatar delivers humorous responses audibly and simultaneously performs visual gestures, providing a friendly and enjoyable communication experience.

[0599] For example, if a user says, "I'm tired today," the server analyzes this and generates an appropriate humorous response such as, "You're out of energy! Shall we recharge and have some delicious cake?" In addition, the avatar performs a gesture indicating energy replenishment, providing the user with visual enjoyment. In this way, the system of the present invention makes it possible to reduce the psychological distance between the user and the system and to increase the user's sense of security.

[0600] The following describes the processing flow.

[0601] Step 1:

[0602] The device captures the user's voice using its microphone. This audio data is sent to a cloud server in real time.

[0603] Step 2:

[0604] The server converts the received audio data into text data using speech recognition technology. Advanced speech recognition algorithms are used here to ensure clear audio analysis and accurate text conversion.

[0605] Step 3:

[0606] The server analyzes the text data to understand the user's intent. This process involves using natural language processing (NLP) techniques to extract context and meaning.

[0607] Step 4:

[0608] The server uses a generative AI model to generate humorous responses based on the analysis results. In this step, the model is adjusted to create appropriate jokes and retorts that are relevant to the context.

[0609] Step 5:

[0610] The server determines a gesture to correspond to the generated humorous response. It selects the most appropriate action from the gesture library and generates control commands to have the 3D avatar perform that action.

[0611] Step 6:

[0612] The device presents the user with humorous responses and gestures received from the server. The avatar delivers the humorous responses aloud and simultaneously visually represents the determined gestures, providing the user with a friendly and enjoyable conversational experience.

[0613] (Example 1)

[0614] Next, we will describe Example 1. In the following description, the data processing device 12 will be referred to as the "server" and the robot 414 as the "terminal".

[0615] In today's information society, there is a growing demand for more natural and engaging dialogue when people communicate via digital devices. However, conventional systems struggle to generate and present humorous responses and accompanying actions in real time to put users at ease, failing to provide users with a highly satisfying dialogue experience. This challenge needs to be solved by combining more advanced natural language processing technologies with generative AI models.

[0616] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 1 is realized by the following means.

[0617] In this invention, the server includes means for acquiring voice information and converting said voice information into text information, means for analyzing the content of the speech and generating a humorous response, and means for determining the action corresponding to the humorous response and controlling and displaying a virtual character. This makes it possible to provide the user with an interesting and friendly communication experience that combines visual and auditory elements.

[0618] "Voice information" refers to voice data produced by users using digital devices.

[0619] "Textual information" refers to data obtained by analyzing audio information and representing its content in text.

[0620] "Speech content" refers to the meaning or intent that the user is trying to convey, based on the text information converted from the audio information.

[0621] A "humorous response" refers to a humorous reply generated in response to user input, providing a user-friendly interaction.

[0622] "Actions" refer to visual gestures and animations that appear in conjunction with humorous responses.

[0623] A "virtual character" refers to a computer-generated agent that operates within a digital environment and interacts with the user visually and audibly.

[0624] "Synthetic speech means" refers to technologies and software that convert text information into speech and output it.

[0625] This invention is a system for realizing natural and user-friendly communication with users. Specifically, it includes a series of methods for acquiring voice information from the user, converting it into text information, generating humorous responses, and presenting them through a virtual character.

[0626] First, the device uses a high-precision microphone to acquire the user's voice information in real time. This voice information is temporarily stored digitally within the device. Then, the data is sent to the server using a secure protocol (e.g., HTTPS).

[0627] The server converts received audio information into text using speech recognition technology (e.g., a speech recognition service). Based on this converted text, it analyzes the spoken content using natural language processing technology. During this process, prompt sentences are input to a generative AI model (e.g., an AI text generation engine) based on the analysis results, generating humorous responses.

[0628] To determine the appropriate action related to the generated response, the server selects an appropriate action from a pre-prepared library of actions. This action is instructed to a virtual character and visually presented to the user. Voice responses are generated using synthesized speech technology and communicated to the user in a distinctive voice that matches the humorous content of the response.

[0629] Finally, the device combines the generated humorous responses and actions and presents them to the user. This entire process allows the user to have a meaningful and enjoyable conversational experience.

[0630] For example, if a user says, "I'm tired today," the server will respond with a humorous "You're out of energy! Want to recharge and have some delicious cake?" This response includes a gesture that involves "replenishing energy," which is visually represented through the avatar. As a result, the user can experience friendly communication through both voice and visual means.

[0631] Example of a prompt:

[0632] "Generate a humorous response to the user's statement: 'I'm tired today.'"

[0633] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0634] Step 1:

[0635] The device uses a high-precision microphone to acquire user voice information in real time. The input is the user's voice. The output is audio data in digital format. During this process, the audio is temporarily stored using an audio capture function.

[0636] Step 2:

[0637] The device transmits the acquired audio data to the server via an internet connection using a secure protocol (e.g., HTTPS). The input is digital audio data. The output is the audio data transferred to the server.

[0638] Step 3:

[0639] The server uses speech recognition technology to convert received audio data into text data. The input is audio data. The output is the converted text data. An external speech recognition engine is used for this process.

[0640] Step 4:

[0641] The server utilizes natural language processing technology to analyze text data and understand the content and context of the utterance. The input is text data. The output is the analyzed utterance content and contextual information. Based on the analysis results, prompt sentences are created for the generative AI model.

[0642] Step 5:

[0643] The server inputs a prompt sentence into an AI model based on the analysis results, and generates a humorous response. The input is the prompt sentence. The output is the generated humorous response. An AI text generation engine is used in this step.

[0644] Step 6:

[0645] The server determines the appropriate action to take in response to a humorous response and selects the correct action from the action library. The input is the humorous response. The output is the selected action data. The gesture library is used to select an action.

[0646] Step 7:

[0647] The device uses speech synthesis technology to generate humorous responses as audio and displays them visually in sync with the movements of a virtual character. The input consists of humorous responses and movement data. The output is the audio and animation presented to the user. Animation software is used to provide the user with a visually entertaining experience.

[0648] (Application Example 1)

[0649] Next, we will explain Application Example 1. In the following explanation, the data processing device 12 will be referred to as the "server" and the robot 414 as the "terminal".

[0650] When autonomous devices are used in a work environment, there is a challenge in alleviating the stress and boredom experienced by operators due to repetitive monotonous tasks, thereby making the workplace more comfortable. Furthermore, another challenge is to provide means to enhance affinity with operators by offering more human-like communication in addition to mechanical actions.

[0651] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 1 is realized by the following means.

[0652] In this invention, the server includes means for acquiring voice information and converting said voice information into text information, means for analyzing the content of the utterance based on the text information and generating an entertaining response, and means for determining an action corresponding to the entertaining response and controlling an autonomous device to display it. This makes it possible to provide the operator with entertaining responses and actions even in a monotonous work environment, lighten the atmosphere of the workplace, and increase affinity with the operator.

[0653] "Audio information" refers to human speech and other acoustic signals obtained by converting sound waves into electrical signals.

[0654] "Textual information" refers to text-formatted data generated using speech recognition technology based on audio information.

[0655] "Speech content" refers to the meaning and context of the text information extracted from the audio information.

[0656] "Entertaining responses" refer to responses that use generative AI to add humor and friendliness to the content of the speech.

[0657] "Action" refers to gestures or actions performed by an autonomous device to visually assist in entertaining responses.

[0658] An "autonomous device" refers to a device that automates the acquisition of voice information, the generation of responses, and the execution of actions.

[0659] "Operator" refers to a person who directly or indirectly supervises and controls the operation of an autonomous device.

[0660] A "server" refers to a computer system that processes voice information, generates responses, and provides information to autonomous devices.

[0661] To implement this invention, a device for acquiring voice information and a related software program are provided. The purpose of this system is to process voice input, generate entertaining responses based on a generative AI model, and have an autonomous device perform the corresponding actions.

[0662] The system first acquires voice information from the user wearing smart glasses or a head-mounted display. This is done using the Google Speech-to-Text API to convert the voice signal into text. The converted text is sent to a server where the speech content is analyzed. The server uses OpenAI's ChatGPT API to generate an entertaining response based on the text. This response determines and executes the appropriate action from a gesture library configured to suit the user's environment.

[0663] The autonomous device provides entertaining responses to the operator as voice output and performs corresponding actions to lighten the mood in a potentially monotonous work environment. For example, if the operator says, "Today's work is so heavy!", the system will respond, "That sounds like a busy day! But I'll do my best with you!" and perform a gesture of giving a thumbs-up.

[0664] Examples of prompt messages are as follows:

[0665] Example prompt when the voice input says, "Today's work is so heavy and overwhelming!":

[0666] Speech-recognized text: "Today was a busy day with lots of work!"

[0667] Generate an appropriate humorous response: "That's a busy day! But I'll do my best alongside you!"

[0668] Select a related gesture: the action of making a victory pose.

[0669] This makes it possible to build a system that enhances user engagement through entertaining responses and intuitive gestures.

[0670] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0671] Step 1:

[0672] The user provides voice input through smart glasses. The voice input is captured by a microphone built into the smart glasses. The input data is voice information, which is then converted into text information using the Google Speech-to-Text API. Converting the voice signal into a string enables the following processing:

[0673] Step 2:

[0674] The terminal sends the converted text information to the server. The server analyzes the text information and performs natural language processing to understand the spoken content. The input data is text information, and the output data is the analyzed spoken content. This allows the system to understand the user's intent.

[0675] Step 3:

[0676] The server generates entertaining responses using a generative AI model based on the analyzed speech content. The input is the speech content, and the output is the entertaining response. The server uses OpenAI's ChatGPT API to create friendly responses.

[0677] Step 4:

[0678] The server selects an appropriate gesture from a gesture library to determine the action to take in response to the generated entertaining response. The input is the entertaining response, and the output is the corresponding gesture. This allows for visual completion of the response.

[0679] Step 5:

[0680] The device presents the user with a combination of generated, entertaining responses and corresponding gestures. Input consists of responses and gestures, while output is the presentation of audio and actions to the user. This enables the provision of an enjoyable communication experience.

[0681] Furthermore, an emotion engine that estimates the user's emotions may be incorporated. That is, the identification processing unit 290 may use the emotion identification model 59 to estimate the user's emotions and perform identification processing using the user's emotions.

[0682] To implement this invention, it is necessary to construct an integrated system for recognizing the user's emotions and providing a corresponding response. This system includes acquiring voice data and analyzing the user's emotional state using an emotion engine.

[0683] Specifically, the device captures the user's voice using a microphone and acquires audio data. This audio data is sent to a server, where an emotion engine analyzes the characteristics of the voice to determine the user's emotional state. The emotion engine analyzes voice tone, speaking speed, volume changes, etc., based on a pre-trained model. If the user's face is also being analyzed, video data is also used to determine emotions from facial expressions.

[0684] Once the emotion analysis is complete, the server generates a humorous response tailored to the user's emotional state. For example, if the server detects that the user is tired, it will select a lighthearted joke or encouraging words to help them relax. In addition, it determines an appropriate gesture to match the selected response. The gestures are linked to the user's emotions, as they allow the avatar to visually provide a sense of comfort and amusement to the user.

[0685] The terminal receives response information from the server and presents it to the user. At this time, the avatar adjusts its voice tone to reflect the corresponding emotion and delivers a generated humorous response aloud. Furthermore, the determined gestures are appropriately executed through the avatar. For example, if the user expresses dissatisfaction, the avatar will display a softer expression and gentle movements to provide a personalized response that empathizes with the user.

[0686] Thus, this invention can dramatically improve the quality of communication by detecting the user's emotions and using humor and gestures that correspond to them. With this system, users can enjoy a friendly conversational experience while gaining a deeper sense of security by having their individual emotions taken into consideration.

[0687] The following describes the processing flow.

[0688] Step 1:

[0689] The device captures the user's voice using its microphone. Simultaneously with acquiring this audio data, it also captures the user's facial expressions with its camera as needed, saving them as video data.

[0690] Step 2:

[0691] The device transmits the acquired audio data and, if possible, video data to the server. This transmission is performed in real time, enabling rapid processing.

[0692] Step 3:

[0693] The server processes the received data through an emotion engine, analyzing voice tone, speaking speed, volume, and facial expressions from video data to identify the user's current emotional state. The emotion engine recognizes different emotional categories such as joy, sadness, anger, and surprise.

[0694] Step 4:

[0695] The server analyzes the user's emotional state and uses a generative AI model to generate humorous responses appropriate to the user. These responses are designed to consider the user's emotions and provide a pleasant experience.

[0696] Step 5:

[0697] The server selects a gesture appropriate to the humorous response generated. It chooses a gesture from a library of actions to be performed by the avatar that matches the atmosphere and the user's emotions.

[0698] Step 6:

[0699] The terminal receives responses and gesture information from the server and presents them to the user. The avatar plays a humorous voice response while simultaneously visually representing the selected gesture.

[0700] Step 7:

[0701] When the user makes a new utterance or facial expression, the device captures it again and repeats the aforementioned process, enabling a continuous dialogue. By responding to the user's changing emotions in real time, it provides a friendly and empathetic dialogue.

[0702] (Example 2)

[0703] Next, we will describe Example 2. In the following description, the data processing device 12 will be referred to as the "server" and the robot 414 as the "terminal".

[0704] Conventional dialogue systems have struggled to accurately analyze the user's emotional state and generate natural, approachable responses accordingly. Furthermore, it has been difficult to conduct dialogues that incorporate visual presentations while considering the user's emotions, limiting the potential for improving the communication experience. Therefore, the present invention aims to provide a more natural and human-like dialogue experience that takes the user's emotions into consideration.

[0705] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means.

[0706] In this invention, the server includes means for acquiring voice data and analyzing the voice data based on the emotional state; means for generating a humorous response and determining a corresponding action based on the emotional state; and means for controlling the humorous response and the corresponding action to present a visual representation. This makes it possible to realize natural and friendly dialogue that responds to the user's emotional state and improve the quality of communication.

[0707] "Voice data" refers to data that digitally records the user's speech.

[0708] "Emotional state" refers to the emotional state expressed by the user, and is analyzed from factors such as voice and facial expressions.

[0709] A "humorous response" is a response generated to provide a familiar and pleasant reaction to the user's emotional state.

[0710] "Action" refers to the behavior of avatars or systems that are visually presented to the user.

[0711] "Visual representation" refers to visual information presented to the user using a display or similar device, and includes text information and avatar gestures.

[0712] To implement this invention, it is necessary to construct an integrated system that acquires the user's voice and facial input and generates a corresponding response. The system is configured as follows:

[0713] First, the user uses the device's microphone to input voice data. The device has a built-in high-quality microphone that captures the voice data. Next, the voice data captured on the device is transmitted to the server via wireless communication technology or an internet connection.

[0714] The server has the capability to receive audio data and analyzes it using a generative AI model. The emotion engine detects changes in voice tone, speaking speed, and volume, and identifies the user's emotional state based on these. In some cases, the system can also capture and send a video of the user's face using the device's camera, allowing it to determine emotions from facial expressions as well. This dual analysis enables more accurate emotion prediction.

[0715] Once the emotion analysis is complete, the server generates a response corresponding to the identified emotional state. This response, based on a pre-trained database and dialogue model, is designed to convey natural humor relevant to the scenario. Simultaneously, gestures presented by the avatar are selected to reflect the user's emotions.

[0716] The selected response and gesture information is transmitted to the terminal via the network. The terminal controls the avatar based on the received information. The avatar uses synthesized speech to provide voice responses to the user and displays visual gestures. This allows the user to receive responses both verbally and visually, resulting in a friendly and engaging conversational experience.

[0717] Specific example:

[0718] For example, if a user says "I'm tired today," the server will recognize this as a state of fatigue. It will then generate a response saying, "You must be tired. It's a good idea to take a break," and the avatar will smile and shrug.

[0719] Example of a prompt:

[0720] The prompt for the generative AI model should be set as follows: "Determine the user's emotions and generate friendly and humorous responses and gestures. For example, consider a response if the user says, 'I'm tired today.'"

[0721] This invention enables users to enjoy seamless and natural conversations and to communicate in a way that takes their emotional needs into consideration.

[0722] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0723] Step 1: Obtaining voice input

[0724] The device uses its microphone to capture the user's voice. It acquires a raw audio signal as input. This audio signal is digitized and stored as audio data. Specifically, the device records the audio in real time and optimizes the sound quality by performing noise filtering.

[0725] Step 2: Sending the audio data

[0726] The terminal sends audio data to the server. A digital audio file is used as input. This audio data is transmitted to the server via a secure internet connection. The terminal uses a data transfer protocol to compress the audio data during transmission.

[0727] Step 3: Analyzing the audio data

[0728] The server receives audio data and performs analysis using a generative AI model. The input is audio data sent from the terminal. The emotion engine analyzes the audio data, examining changes in tone, speech rate, and volume to identify the user's emotional state. The server's operation involves extracting audio features and inputting them into the AI ​​model.

[0729] Step 4: Response Generation

[0730] The server generates humorous responses based on the analyzed emotional state. It uses identified emotional information as input. The output is a text-based response, which is adjusted to create a natural conversation. Specifically, the server refers to past conversation history and a set of predefined dialogues to construct the most appropriate response.

[0731] Step 5: Deciding on a gesture

[0732] The server selects an action that matches the generated response. The generated text response is used as input. This action becomes the movement displayed by the avatar as a visual representation. The server's action involves selecting a gesture pattern from a database that corresponds to the user's emotional state.

[0733] Step 6: Presenting responses and gestures

[0734] The terminal presents the user with the response received from the server and gesture information. The input is a set of data transferred from the server. As output, the avatar interacts with the user using voice and actions. The terminal's specific actions include having the avatar speak lines using synthesized speech and visually reproducing selected gestures.

[0735] (Application Example 2)

[0736] Next, we will explain application example 2. In the following explanation, the data processing device 12 will be referred to as the "server" and the robot 414 as the "terminal".

[0737] In customer service, there is a growing demand for more personalized responses to users. However, conventional systems struggle to respond in accordance with users' emotions and emotional states, failing to provide satisfactory communication. Therefore, a system is needed that provides responses and gestures tailored to users' emotions, thereby improving the customer experience.

[0738] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means.

[0739] In this invention, the server includes means for acquiring voice information and converting said voice information into text data; means for analyzing utterance information based on said text data and generating a humorous response; means for determining an action corresponding to the humorous response and controlling and displaying a visual avatar; and means for generating voice output and actions according to the customer's emotional state. This makes it possible to provide more personalized communication to the user.

[0740] "Audio information" refers to sound data obtained from users' conversations and statements.

[0741] "Text data" refers to information in text format that has been converted from audio information.

[0742] "Speech information" refers to information that includes content and meaning obtained by analyzing text data.

[0743] A "humorous response" is a reply generated based on the user's spoken information and emotional state, designed to make the conversation more pleasant.

[0744] "Actions" refer to gestures and behaviors that avatars or other entities perform, either physically or visually.

[0745] A "visual avatar" is a character or image used to communicate with users in an observable manner.

[0746] "Emotional state" refers to the state of a user's feelings and psychological condition.

[0747] "Audio output" refers to the output used to convey the generated response to the user as sound.

[0748] "Customer experience" refers to the series of experiences and impressions that users have when interacting with a product or service.

[0749] This invention is a system for providing responses that correspond to the user's emotional state. The server uses a microphone connected to the terminal to acquire voice information. The acquired voice information is converted into text data. Next, the server analyzes this text data and extracts speech information. A generative AI model is used for the analysis, taking into account changes in voice tone, speaking speed, and volume.

[0750] The server generates humorous responses based on the extracted speech information. These responses are also used to determine actions that correspond to the user's emotional state, i.e., the avatar's gestures. The visual avatar is controlled according to the user's emotional state and visually represents their actions.

[0751] The device transmits the generated audio output to the user. For example, the avatar might use gentle facial expressions and calming movements to interact with the user in a way that feels empathetic.

[0752] As a concrete example, a smart customer service assistant in a store could read a customer's psychological state when they pick up a new product and provide the most appropriate response and gesture. This would improve the customer experience and allow users to experience a more friendly interaction.

[0753] An example of a prompt to be input to a generative AI model is: "Use the capabilities of the emotion recognition system to devise measures to reduce the user's stress level. Specifically, suggest appropriate responses and gestures as ways to improve the customer experience in a store."

[0754] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0755] Step 1:

[0756] The terminal uses a microphone to acquire user voice information. The input is the user's voice, and the output is digital voice data. This digital voice data is sent to the server.

[0757] Step 2:

[0758] The server converts the audio information into text data. The input is the audio data obtained in step 1, and the output is text data. Speech recognition technology is used to convert it into text data.

[0759] Step 3:

[0760] The server analyzes text data and extracts speech information. The input is the text data obtained in step 2, and the output is information including the intent and emotion of the speech. Here, a generative AI model is used, and the speech information is analyzed using natural language processing techniques.

[0761] Step 4:

[0762] The server analyzes the user's emotional state and generates a humorous response. The input is the speech information obtained in step 3, and the output is an appropriate response text based on the user's state. An emotion analysis engine is used to generate the response, producing a response with optimal humor based on the conversation content.

[0763] Step 5:

[0764] The server determines the actions of the visual avatar based on the generated response. The input is the response text obtained in step 4, and the output is the actions and gestures performed by the avatar. A gesture database based on emotions and responses is used to determine the actions.

[0765] Step 6:

[0766] The terminal uses audio output and gesture information received from the server to provide the user with visual and auditory feedback. The input consists of response text and gesture information obtained in steps 4 and 5, while the output is audio playback and avatar visual actions as a response to the user. Information is presented via the speaker and display.

[0767] The specific processing unit 290 transmits the result of the specific processing to the robot 414. In the robot 414, the control unit 46A causes the speaker 240 and the controlled object 443 to output the result of the specific processing. The microphone 238 acquires audio indicating user input for the result of the specific processing. The control unit 46A transmits the audio data indicating user input acquired by the microphone 238 to the data processing unit 12. In the data processing unit 12, the specific processing unit 290 acquires the audio data.

[0768] Data generation model 58 is a type of so-called generative AI (Artificial Intelligence). One example of data generation model 58 is ChatGPT (Internet Search).<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search) <url: https: gemini.google.com ?hl="ja">Examples of generative AI include the following. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 is input with prompts containing instructions, and with inference data such as audio data representing speech, text data representing text, and image data representing images. The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference results in data formats such as audio data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[0769] In the above embodiment, an example was given in which specific processing is performed by the data processing device 12, but the technology of this disclosure is not limited thereto, and the specific processing may also be performed by the robot 414.

[0770] Furthermore, the emotion identification model 59, acting as an emotion engine, may determine the user's emotion according to a specific mapping. Specifically, the emotion identification model 59 may determine the user's emotion according to a specific mapping, which is an emotion map (see Figure 9). Similarly, the emotion identification model 59 may also determine the robot's emotion, and the identification processing unit 290 may perform identification processing using the robot's emotion.

[0771] Figure 9 shows an emotion map 400 in which multiple emotions are mapped. In the emotion map 400, emotions are arranged in concentric circles radiating from the center. The closer to the center of the concentric circles, the more primitive the emotions are located. Further out of the concentric circles, emotions representing states and actions arising from mental states are located. Emotion is a concept that includes feelings and mental states. On the left side of the concentric circles, emotions that are generally generated from reactions occurring in the brain are located. On the right side of the concentric circles, emotions that are generally induced by situational judgment are located. Above and below the concentric circles, emotions that are generally generated from reactions occurring in the brain and induced by situational judgment are located. In addition, the emotion of "pleasure" is located on the upper side of the concentric circles, and the emotion of "displeasure" is located on the lower side. Thus, in the emotion map 400, multiple emotions are mapped based on the structure in which emotions arise, and emotions that are likely to occur simultaneously are mapped close together.

[0772] These emotions are distributed at the 3 o'clock position on the Emotion Map 400, and usually fluctuate between feelings of security and anxiety. In the right half of the Emotion Map 400, situational awareness takes precedence over internal feelings, resulting in a calm impression.

[0773] The inside of the Emotion Map 400 represents inner thoughts, while the outside represents actions. Therefore, the further you go from the outside of the Emotion Map 400, the more visible (expressed in actions) your emotions become.

[0774] Here, human emotions are based on various balances, such as posture and blood sugar levels. When these balances deviate from the ideal, it results in discomfort, and when they approach the ideal, it results in pleasure. Similarly, in robots, cars, motorcycles, etc., emotions can be created based on various balances, such as posture and battery level. When these balances deviate from the ideal, it results in discomfort, and when they approach the ideal, it results in pleasure. The emotion map can be generated, for example, based on Dr. Mitsuyoshi's emotion map (Research on a system for analyzing brain physiological signals of speech emotion recognition and emotion, Tokushima University, doctoral dissertation: https: / / ci.nii.ac.jp / naid / 500000375379). The left half of the emotion map contains emotions belonging to a region called "response," where sensation is dominant. The right half of the emotion map contains emotions belonging to a region called "situation," where situational awareness is dominant.

[0775] The emotion map defines two emotions that promote learning. One is the emotion around the middle of the negative "repentance" and "reflection" on the situation side. In other words, it is when the robot experiences negative emotions such as "I never want to feel this way again" or "I don't want to be scolded again." The other is the emotion around the positive "desire" on the reaction side. In other words, it is when the robot has positive feelings such as "I want more" or "I want to know more."

[0776] The emotion identification model 59 inputs user input into a pre-trained neural network, obtains emotion values ​​representing each emotion shown in the emotion map 400, and determines the user's emotion. This neural network is pre-trained based on multiple training data sets, which are combinations of user input and emotion values ​​representing each emotion shown in the emotion map 400. Furthermore, this neural network is trained so that emotions located close together have similar values, as shown in the emotion map 900 in Figure 10. Figure 10 shows an example where multiple emotions such as "reassured," "calm," and "confident" have similar emotion values.

[0777] The above description primarily focuses on the functions of the data processing device 12 in relation to this disclosure. However, the system related to this disclosure is not necessarily implemented on a server. The system related to this disclosure may be implemented as a general information processing system. This disclosure may be implemented, for example, as a software program that runs on a personal computer or as an application that runs on a smartphone. The method related to this disclosure may be provided to users in SaaS (Software as a Service) format.

[0778] In the above embodiment, an example was given in which a specific process is performed by a single computer 22. However, the technology of this disclosure is not limited thereto, and a distributed processing of the specific process may be performed by multiple computers, including computer 22. For example, a data generation model 58 may be provided in an external device of the data processing device 12, and the external device may generate data according to the input data.

[0779] In the above embodiment, an example was given in which the specific processing program 56 is stored in the storage 32, but the technology of this disclosure is not limited thereto. For example, the specific processing program 56 may be stored in a portable, computer-readable, non-temporary storage medium such as a USB (Universal Serial Bus) memory. The specific processing program 56 stored in the non-temporary storage medium is installed in the computer 22 of the data processing device 12. The processor 28 executes specific processing according to the specific processing program 56.

[0780] 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.

[0781] Furthermore, it is not necessary to store the entirety of the specific processing program 56 in a storage device such as a server connected to the data processing device 12 via the network 54, or to store the entirety of the specific processing program 56 in the storage 32; it is acceptable to store only a portion of the specific processing program 56.

[0782] The following types of processors can be used as hardware resources to perform specific processing. Examples of processors include a CPU, a general-purpose processor that functions as a hardware resource to perform specific processing by executing software, i.e., a program. Other examples of processors include dedicated electrical circuits, such as FPGAs (Field-Programmable Gate Arrays), PLDs (Programmable Logic Devices), or ASICs (Application Specific Integrated Circuits), which have circuit configurations specifically designed to perform specific processing. All of these processors have built-in or connected memory, and all of them perform specific processing by using memory.

[0783] The hardware resource that performs a specific process may consist of one of these various processors, or it may consist of a combination of two or more processors of the same or different types (for example, a combination of multiple FPGAs, or a combination of a CPU and an FPGA). Alternatively, the hardware resource that performs a specific process may consist of a single processor.

[0784] Examples of configurations using a single processor include, firstly, a configuration in which one or more CPUs and software are combined to form a single processor, and this processor functions as a hardware resource that performs a specific process. Secondly, there is a configuration using a processor that realizes the functions of the entire system, including multiple hardware resources that perform a specific process, on a single IC chip, as exemplified by SoCs (System-on-a-chip). In this way, a specific process is realized using one or more of the above types of processors as hardware resources.

[0785] Furthermore, the hardware structure of these various processors can more specifically utilize electrical circuits that combine circuit elements such as semiconductor devices. Also, the specific processing described above is merely an example. Therefore, it goes without saying that unnecessary steps can be deleted, new steps added, or the processing order rearranged, as long as it does not deviate from the main purpose.

[0786] The descriptions and illustrations presented above are detailed explanations of the technical aspects of this disclosure and are merely examples of the technical aspects. For example, the above descriptions of the structure, function, operation, and effect are examples of the structure, function, operation, and effect of the technical aspects of this disclosure. Therefore, it goes without saying that you may delete unnecessary parts, add new elements, or replace elements in the descriptions and illustrations presented above, as long as you do not deviate from the essence of the technical aspects of this disclosure. Furthermore, in order to avoid confusion and facilitate understanding of the technical aspects of this disclosure, explanations of common technical knowledge and the like that do not require special explanation to enable the implementation of the technical aspects of this disclosure have been omitted from the descriptions and illustrations presented above.

[0787] All documents, patent applications, and technical standards described herein are incorporated by reference to the same extent as if each individual document, patent application, and technical standard were specifically and individually noted as being incorporated by reference.

[0788] The following is further disclosed regarding the embodiments described above.

[0789] (Claim 1)

[0790] A means for acquiring audio data and converting said audio data into text data,

[0791] A means for analyzing the content of an utterance based on the text data and generating a humorous response,

[0792] Means for determining a gesture corresponding to the humorous response and controlling and displaying an avatar,

[0793] A system that includes this.

[0794] (Claim 2)

[0795] The system according to claim 1, which combines generated humorous responses and gestures and presents them to the user.

[0796] (Claim 3)

[0797] The system according to claim 1, which waits for new input from the user and continues the conversation.

[0798] "Example 1"

[0799] (Claim 1)

[0800] A means for acquiring audio information and converting said audio information into text information,

[0801] A means for analyzing the content of a speech utterance based on the textual information and generating a humorous response,

[0802] Means for determining the action to respond to the comical response and controlling and displaying the virtual character,

[0803] Means of creating visual representations based on humorous responses,

[0804] A synthesized speech means for outputting humorous responses as audio,

[0805] A system that includes this.

[0806] (Claim 2)

[0807] The system according to claim 1, which combines generated humorous responses and actions and presents them to the user.

[0808] (Claim 3)

[0809] The system according to claim 1, which waits for new input from the user and continues communication.

[0810] "Application Example 1"

[0811] (Claim 1)

[0812] A means for acquiring audio information and converting said audio information into text information,

[0813] A means for analyzing spoken content based on the textual information and generating an entertaining response,

[0814] Means for determining an action corresponding to the entertaining response and controlling and displaying it in an autonomous device,

[0815] Means for outputting the above-mentioned responses and operations to a person operating the autonomous device in the work environment,

[0816] A system that includes this.

[0817] (Claim 2)

[0818] The system according to claim 1, which combines generated entertaining responses and actions and presents them to the user, thereby creating a more pleasant trading environment for the operator.

[0819] (Claim 3)

[0820] The system according to claim 1, which waits for new input from the operator and continues the dialogue.

[0821] "Example 2 of combining an emotion engine"

[0822] (Claim 1)

[0823] A means for acquiring audio data and analyzing said audio data based on emotional state,

[0824] A means for generating a humorous response based on the emotional state and determining a corresponding action,

[0825] A means for controlling the humorous response and corresponding actions to present a visual representation,

[0826] A system that includes this.

[0827] (Claim 2)

[0828] The system according to claim 1, which combines generated humorous responses and actions and presents them to the user, thereby facilitating an emotionally responsive, ergonomically controlled interaction.

[0829] (Claim 3)

[0830] The system according to claim 1, which continuously waits for input from the user and maintains a continuous dialogue.

[0831] "Application example 2 of combining emotional engines"

[0832] (Claim 1)

[0833] A means for acquiring audio information and converting said audio information into text data,

[0834] A means for analyzing speech information based on the text data and generating a humorous response,

[0835] Means for determining the action to respond to the humorous response and controlling and displaying a visual avatar,

[0836] A means for generating voice output and actions corresponding to the customer's emotional state,

[0837] ...

[0838] A system that includes this.

[0839] (Claim 2)

[0840] The system according to claim 1, which combines generated humorous responses and actions and presents them to the user.

[0841] (Claim 3)

[0842] The system according to claim 1, which waits for new input from the user and continues the dialogue. [Explanation of Symbols]

[0843] 10, 210, 310, 410 Data Processing Systems 12 Data Processing Devices 14 Smart Devices 214 Smart Glasses 314 Headset-type terminal 414 Robots< / url:> < / url:> < / url:> < / url:>

Claims

1. A means for acquiring audio data and converting said audio data into text data, A means for analyzing the content of an utterance based on the text data and generating a humorous response, Means for determining a gesture corresponding to the humorous response and controlling and displaying an avatar, A system that includes this.

2. The system according to claim 1, which combines generated humorous responses and gestures and presents them to the user.

3. The system according to claim 1, which waits for new input from the user and continues the conversation.

Images