system

Abstract

We provide the system. [Solution] An emotion recognition means that receives video and audio data acquired from the user's device and estimates the other party's emotions based on said data, An environmental recognition means that identifies environmental information based on the current location and surrounding information acquired from the user's device, A content generation method that uses a large-scale language model to generate optimal conversation topics and behavioral advice based on estimated emotions and identified environmental information, An advice display means that visually outputs the generated information to the user's display device, A system that includes this.

Description

Technical Field

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

Background Art

[0002] Patent Document 1 discloses a persona chatbot control method performed by at least one processor, including steps of receiving a user utterance, adding the user utterance to a prompt including an instruction sentence related to an explanation of a chatbot character, encoding the prompt, and inputting the encoded prompt into a language model to generate a chatbot utterance as a 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] People often have difficulty finding appropriate topics or considering appropriate responses according to the feelings of the other party in communication scenarios such as dating and business. In particular, it is very difficult to judge in real time what the other party is thinking and how they are reacting, which may cause the communication not to proceed smoothly. There is a need for a system that solves this problem and supports effective and meaningful conversations.

Means for Solving the Problems

[0005] This invention provides a means for performing emotion recognition based on video and audio data acquired from a user's device. Furthermore, it includes means for recognizing the environment based on the user's current location and surrounding information acquired from the user's device, and integrating this information to generate conversation topics and behavioral advice using a large-scale language model. It also provides the generated information to the user and navigates their speech and actions to realize smooth communication. Through feedback processing, the system's learning accuracy is also improved, and it includes functions such as timing instructions to maintain a natural flow of conversation. This enables people to communicate better in situations such as dating and sales.

[0006] "User device" refers to AR glasses and other wearable devices, which are hardware devices used by users to acquire information and receive visual feedback.

[0007] "Video data" refers to visual information acquired using a camera, and in particular, dynamic image information that includes the facial expressions of the person being filmed and the surrounding environment.

[0008] "Audio data" refers to acoustic information acquired using a microphone, including the other party's speech, tone of voice, and surrounding sound environment.

[0009] "Emotion recognition means" refers to algorithms or technologies that analyze received video and audio data to estimate emotional states such as joy and surprise.

[0010] "Environmental information" refers to information about the user's physical location and surrounding landmarks and places, and is acquired through visual or digital means.

[0011] "Environmental recognition means" refers to technologies used to analyze and recognize the user's current location and specific features in the surrounding area in the real world.

[0012] A "large-scale language model" is an AI model that uses natural language processing techniques to learn from large amounts of text data, enabling context-aware text generation and conversational comprehension.

[0013] "Content generation means" refers to the processes and functions used to generate optimal conversation topics and action advice based on the input information.

[0014] "Advice display means" refers to a function that displays generated conversation topics and action instructions on the user's visual device to draw the user's attention.

[0015] "Feedback processing means" refers to a function that collects evaluations and feedback from users and uses them to improve the system and enhance the accuracy of the learning model.

[0016] "Timing instructions" refer to guidance that indicates the appropriate timing for users to receive generated information in order to maintain a natural flow of conversation. [Brief explanation of the drawing]

[0017] [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] This is a conceptual diagram showing an example of the configuration of a data processing system according to the second embodiment. [Figure 4] This 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] This is a conceptual diagram showing an example of the configuration of a data processing system according to the third embodiment. [Figure 6] This 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.

Modes for Carrying Out the Invention

[0018] Hereinafter, an example of an embodiment of a system according to the technology of the present disclosure will be described with reference to the accompanying drawings.

[0019] First, the language used in the following description will be explained.

[0020] In the following embodiments, the signed processor (hereinafter simply referred to as "processor") may be a single arithmetic unit or a combination of multiple arithmetic units. Furthermore, the processor may be a single type of arithmetic unit or a combination of multiple types of arithmetic units. Examples of arithmetic units include CPU (Central Processing Unit), GPU (Graphics Processing Unit), GPGPU (General-Purpose computing on Graphics Processing Units), and APU (Accelerated Processing Unit).

[0021] In the following embodiments, signed RAM (Random Access Memory) is a memory that temporarily stores information and is used as work memory by the processor.

[0022] In the following embodiments, the signed storage is one or more non-volatile storage devices that store various programs and various parameters. Examples of non-volatile storage devices include flash memory (SSD (Solid State Drive)), magnetic disks (e.g., hard disks), or magnetic tapes.

[0023] In the following embodiments, the signed communication interface (I / F) is an interface that includes a communication processor and an antenna, etc. The communication interface manages communication between multiple computers. Examples of communication standards applicable to the communication interface include wireless communication standards such as 5G (5th Generation Mobile Communication System), Wi-Fi (registered trademark), or Bluetooth (registered trademark).

[0024] 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."

[0025] [First Embodiment]

[0026] Figure 1 shows an example of the configuration of the data processing system 10 according to the first embodiment.

[0027] 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.

[0028] 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).

[0029] 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.

[0030] 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.

[0031] 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.

[0032] 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.

[0033] Figure 2 shows an example of the main functions of the data processing device 12 and the smart device 14.

[0034] 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.

[0035] 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.

[0036] 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.

[0037] 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".

[0038] The system of the present invention provides support in communication scenarios using a terminal worn by the user. This system provides effective information through multiple components, including emotion recognition means, environment recognition means, content generation means, and advice display means. Each component is described in detail below.

[0039] First, the terminal is a wearable device, such as AR glasses, worn by the user, and is equipped with a camera and microphone. This terminal is responsible for capturing the other person's facial expressions and voice in real time and sending this data to a server. This allows for the rapid and continuous detection of the other person's speech and changes in facial expressions.

[0040] Next, the server performs digital processing using emotion recognition means based on the video and audio data transmitted from the terminal. Specifically, it extracts facial features from the facial image and estimates multiple emotion labels such as joy, surprise, and boredom. Simultaneously, it also analyzes the audio to grasp the nuances of emotion from the tone and volume of the voice.

[0041] Simultaneously, the device uses environmental recognition to acquire information about the user's current location and major landmarks in the surrounding area. For example, if the user is on a date, it identifies nearby restaurants and tourist attractions; if the user is in business, it identifies information about buildings and conference rooms, and sends this information to the server. This information is used as supplementary information for the conversation.

[0042] By integrating this emotional data and environmental information, the server utilizes a large-scale language model to generate content. Based on the other party's current emotions and location, it generates appropriate conversation topics and behavioral advice suitable for the situation, and sends it to the user's device.

[0043] Ultimately, the device uses an advice display mechanism to visually show the generated advice and topics to the user. For example, during a conversation, advice such as "It would be good to talk about recent news" might be displayed, allowing the user to continue the conversation smoothly.

[0044] As a concrete example, consider a scenario where a user is on a date at a cafe and their date shows a bored expression. The device instantly captures this expression, and the server recognizes it as "boredom." The server analyzes this and automatically generates and sends advice, such as "bring up the topic of a popular new restaurant that recently opened nearby." The user can then use this information to revitalize the conversation with their date.

[0045] This invention enables users to receive specific conversational support based on emotion recognition and environmental information, thereby facilitating effective communication.

[0046] The following describes the processing flow.

[0047] Step 1:

[0048] The device captures the other person's face with the AR glasses' camera and collects audio data with the microphone. The collected video and audio data is compressed in real time and sent to the server.

[0049] Step 2:

[0050] The server performs facial recognition from the received video data. Specifically, it detects facial landmarks (eyes, mouth, eyebrows, etc.) and analyzes the overall facial expression based on these. In addition, it extracts audio features from the audio data and evaluates the tone and speed of the voice.

[0051] Step 3:

[0052] The server estimates emotions based on facial expressions and voice characteristics. Using a deep learning model, it identifies emotion labels such as joy, surprise, and boredom. This information, along with historical data, is stored as a user-specific emotion pattern.

[0053] Step 4:

[0054] The device analyzes its current location information and surrounding video using a VPS to identify landmarks and buildings. It then extracts environmental information and sends it to the server.

[0055] Step 5:

[0056] The server integrates received environmental information and sentiment data, and uses a large-scale language model to generate appropriate conversation topics and advice. Past conversation logs are also referenced in this process.

[0057] Step 6:

[0058] The generated conversation topics and advice are sent to the terminal in short text format. The terminal then displays them appropriately in the user's field of view.

[0059] Step 7:

[0060] The user takes the advice into consideration, continues the conversation, and observes the other person's reactions. If necessary, they return to step 1 and repeat the process.

[0061] Step 8:

[0062] After the conversation ends, the user provides feedback to the system. The server receives this feedback and uses it as training data to improve the accuracy of sentiment estimation and advice generation.

[0063] (Example 1)

[0064] 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."

[0065] In modern social settings, individuals face the challenge of generating appropriate conversations that are responsive to the other person's emotions and the surrounding environment. Finding the right timing to naturally advance conversation within diverse social interactions is also a challenge. This can sometimes lead to interactions not proceeding smoothly.

[0066] 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.

[0067] In this invention, the server includes information processing means for receiving video and audio data acquired from the user's device and estimating the other party's emotions based on said data; information recognition means for identifying environmental information based on location data and surrounding information acquired from the user's device; and information generation means for generating optimal topics and behavioral advice using a large-scale language model based on the estimated emotions and identified environmental information. This enables the user to engage in natural conversations that are appropriate to the other party's emotions and environment, and to facilitate smooth communication.

[0068] "User's device" refers to a terminal device that a user wears or operates to input video and audio data.

[0069] "Video and audio data" refers to digital data of visual and audio information acquired through the user's device.

[0070] "Information processing means" refers to means of analyzing received video and audio data and performing calculations and analyses to estimate the emotions of the other party.

[0071] "Location data and surrounding information" refers to geographical and physical information related to the user's current location, which is acquired through the device.

[0072] "Information recognition means" refers to means for analyzing location data and surrounding information to extract specific environmental information.

[0073] "Environmental information" refers to data about the user's current location and surroundings, which functions as background and supplementary information for conversations.

[0074] A "large-scale language model" is a model that learns from a large amount of language data and generates diverse conversation topics and texts.

[0075] An "information generation method" is a means of generating optimal topics and behavioral advice based on estimated emotions and identified environmental information.

[0076] "Information display means" refers to a display device or method for visually presenting generated topics or advice to a user.

[0077] The embodiment of this invention primarily uses a system in which a terminal and a server work together. The user wears a wearable device, such as AR glasses equipped with a camera and microphone, which functions as the terminal. This terminal captures the facial expressions and voices of people within the user's field of view in real time and transmits them to the server via a communication network.

[0078] The server processes information based on the received video and audio data. Specifically, it uses image recognition software to analyze the facial features of the other person and estimate various emotions from their expressions. Furthermore, it uses speech recognition technology to analyze the tone and volume of the voice and grasp the nuances of emotion. The terminal also acquires location data and surrounding information using GPS and nearby Wi-Fi signals, and provides this information to the server as well.

[0079] The server uses a large-scale language model to generate optimal conversation topics and behavioral advice based on estimated sentiment data and environmental information. This process involves feeding prompt sentences into the generative AI model. An example of a prompt sentence might be: "Generate advice to liven up the conversation based on the user's current situation. For example, if the user is on a date at a cafe and their date seems bored, suggest some topics to bring up."

[0080] Ultimately, the device visually displays topics and advice received from the server in an easy-to-understand format for the user. This allows users to engage in natural conversations and make informed choices based on the situation. For example, if a user is on a date at a cafe, the system can provide appropriate small talk topics and information about nearby places that might be relevant, based on the other person's facial expressions. In this way, the system provides a mechanism to enhance the user's interaction experience.

[0081] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0082] Step 1:

[0083] The device uses the camera and microphone of the AR glasses being worn to capture the other person's facial expressions and voice in real time. It receives video and audio signals captured through the camera and microphone as input. These signals are processed as data, converted into image and audio data, and output.

[0084] Step 2:

[0085] The terminal transmits the acquired image and audio data to the server via the network. Data compression and encryption may be performed during transmission. The input is the image and audio data generated in step 1, and the output is the transmission of data to the server.

[0086] Step 3:

[0087] The server analyzes the image data received from the terminal. Using image processing algorithms, it extracts facial features and estimates emotion labels (such as joy, surprise, or boredom). The input is image data sent from the terminal, and the output is a set of emotion labels.

[0088] Step 4:

[0089] Simultaneously, the server analyzes the audio data, using speech recognition technology to analyze the tone and volume of the voice and grasp the nuances of emotion. The input is the audio data transmitted from the terminal, and the output is an emotion index based on the voice.

[0090] Step 5:

[0091] The device acquires location data and surrounding information from GPS and Wi-Fi information, and transmits this data to the server. The input is data obtained from location sensors, and the output is the transmission of location data and surrounding information to the server.

[0092] Step 6:

[0093] The server integrates received sentiment data and environmental information, and uses a generative AI model to generate optimal conversation topics and behavioral advice. This process uses the prompt, "Generate advice to liven up the conversation based on the user's current situation." The input is sentiment labels and environmental information, and the output is the generated conversation topics and advice.

[0094] Step 7:

[0095] Ultimately, the terminal visually displays the advice sent from the server, allowing the user to review it. The input is the advice data from the server, and the output is the display of information on the user interface. This step helps the user to move the conversation forward at the appropriate time.

[0096] (Application Example 1)

[0097] 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."

[0098] In the work performed by workers, there is a need for a means to quickly and accurately provide appropriate work advice tailored to the individual worker's emotions and surrounding circumstances. However, conventional methods have made it difficult to estimate emotions in real time or identify environmental conditions, making it difficult to improve work efficiency and worker satisfaction. Therefore, the present invention aims to provide a device that accurately grasps the worker's emotions and surrounding circumstances and provides optimal work advice based on that.

[0099] 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.

[0100] In this invention, the server includes emotion estimation means that receives image and audio information acquired from the user's terminal and estimates the emotions of others based on this information; situation recognition means that identifies the surrounding situation based on the current location and surrounding conditions acquired from the user's terminal; and information generation means that generates optimal work advice or action instructions using a language generation model based on the estimated emotions and identified surrounding conditions. This makes it possible to provide optimal advice in real time according to the worker's emotions and surrounding conditions.

[0101] "Emotion estimation means" is a technology that estimates the emotions of others, taking various possibilities into consideration, based on image and audio information acquired from the user's device.

[0102] "Situation recognition means" refers to a technology that uses the user's current location and surrounding situation information sent from their terminal to identify the surrounding situation in real time.

[0103] "Information generation means" refers to a technology that uses language generation models to create optimal work advice and behavioral instructions based on estimated emotions and identified surrounding circumstances.

[0104] An "advice display means" is a device or technology that visually presents generated work advice or action instructions to the worker in an easily understandable manner.

[0105] "Reaction processing means" refers to a technology that analyzes the reaction received from the worker and uses that analysis to improve the accuracy of the information generation means.

[0106] A "language generation model" is an artificial intelligence model that generates diverse texts and information based on large amounts of data.

[0107] A system for implementing this invention requires a user-worn terminal and a server connected to it. The terminal is equipped with a camera and microphone to acquire image and audio information of the user's surroundings. This enables real-time emotion estimation and situational awareness. The acquired data is immediately transmitted to the server.

[0108] The server analyzes transmitted image and audio information using emotion estimation means to estimate the worker's emotions with high accuracy. This process incorporates emotion analysis algorithms that utilize image recognition and natural language processing technologies. In addition, situation recognition means are used to identify the user's current location and surrounding environment, and to obtain information appropriate to the surrounding situation.

[0109] Next, the information generation system uses a language generation model to generate optimal work advice and action instructions based on estimated emotions and identified surrounding circumstances. This provides a beneficial and efficient work environment for the worker. The generated advice is presented in real time to the worker through the advice display system on the terminal.

[0110] For example, if the system determines that a factory worker is not concentrating on their work, it will generate and visually display advice such as "Take a short break" or "Try changing the order of your tasks." An example of a prompt message might be: "Generate the best advice for a worker who is tired. Current environmental data is a temperature of 25 degrees Celsius, humidity of 60%, and noise level of 80 decibels."

[0111] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0112] Step 1:

[0113] The device collects image and audio information from the user's surroundings in real time. Using the camera and microphone, it generates image and audio files from the acquired data. These are then sent to the server as a data stream.

[0114] Step 2:

[0115] The server processes image and audio files sent from the terminal using emotion estimation methods. It extracts facial features from image files using image processing algorithms and analyzes voice tone from audio files using speech recognition technology. Based on these analysis results, it quantifies and outputs the user's emotional state.

[0116] Step 3:

[0117] The server uses situational awareness to identify the user's current location and surrounding environment. It obtains location data using location services and collects environmental information about the user's surroundings. Based on this data, it analyzes the surrounding environment and outputs information about the user's work environment.

[0118] Step 4:

[0119] The server uses information generation means to utilize the emotional state obtained in step 2 and the surrounding situation information obtained in step 3 as input data. A generative AI model is then used to generate optimal work advice and action instructions based on this input data. In this generation process, the generative AI model forms various advice patterns based on prompt sentences and outputs them in text format.

[0120] Step 5:

[0121] The terminal visually displays the generated advice received from the server. It presents the advice clearly to the user via a display device, providing interaction that encourages them to act according to the advice. This display is designed to enhance user efficiency while maintaining a natural workflow.

[0122] 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.

[0123] This invention is a system that effectively supports communication using a device worn by the user, and is particularly characterized by its incorporation of an emotion engine. This system comprises emotion recognition means, environment recognition means, content generation means, and advice display means, and further integrates the emotion engine to analyze and utilize the emotions of both the user and the other party.

[0124] The device is implemented as AR glasses or other wearable devices and is equipped with a camera and microphone. The device first captures the other person's facial expressions and voice in real time, converts this data, and sends it to a server. This allows the system to constantly acquire information about the other person's emotions.

[0125] The server has emotion recognition capabilities to analyze received video and audio data, and uses deep learning technology to estimate emotions. It analyzes the state of joy, anger, sadness, and other emotions from facial expressions and voice, and in parallel builds a user emotion model based on this using an emotion engine. This emotion model learns the user's unique emotion patterns and is used in subsequent conversations.

[0126] Simultaneously, the terminal uses VPS technology to acquire surrounding geographical information and characteristics of the surrounding environment, and sends this information to the server as environmental data. This allows the entire system to understand the user's current location and its characteristics.

[0127] Based on this emotional and environmental information, the server uses a large-scale language model to generate conversation topics and behavioral advice. In this process, it can refer to the user's emotional model via the emotion engine to provide more personalized content. For example, if the user is feeling stressed, it will suggest topics that help them relax.

[0128] The device visually displays the final generated information and prompts the user for action. This facilitates a smoother conversation flow and helps build better communication.

[0129] For example, if a user is feeling nervous during a business meeting, the emotion engine will detect this and display advice on the device such as "advice on relaxing deep breathing" or "talking about a shared hobby with meeting participants." The user can then use this advice to ease the atmosphere. This invention allows users to not only receive information but also receive personalized support, thereby improving the quality of their communication.

[0130] The following describes the processing flow.

[0131] Step 1:

[0132] The device uses AR glasses worn by the user to capture surrounding video and audio in real time. It records the other person's facial expressions through the camera and collects audio with the microphone. The acquired data is immediately transmitted to the server.

[0133] Step 2:

[0134] The server performs facial recognition on the received video data and analyzes facial landmarks using emotion recognition technology. This allows it to detect subtle changes in the other person's facial expressions and generate emotion labels such as joy, anger, sadness, and happiness.

[0135] Step 3:

[0136] Similarly, the server analyzes the audio data and extracts speech features. It evaluates the tone, pitch, and speaking speed of the voice and uses this information to further reinforce the emotional state.

[0137] Step 4:

[0138] The terminal uses VPS technology to determine the user's current location and surrounding environment. The acquired geographical information is transmitted to an environmental recognition system to understand the surrounding landmarks and characteristics of the location.

[0139] Step 5:

[0140] The server integrates collected emotional and environmental information and uses an emotion engine to diagnose the user's emotional state. It then compares this with the user's past emotional history to build a individually tailored emotional model.

[0141] Step 6:

[0142] The server leverages a large-scale language model to generate personalized conversation topics and behavioral advice based on the user's emotion model. For example, if a user is feeling anxious, it might suggest small talk to help them calm down.

[0143] Step 7:

[0144] The generated advice is sent to the device and efficiently displayed within the user's field of view. This visual presentation allows users to quickly understand the information and immediately utilize it in subsequent interactions.

[0145] Step 8:

[0146] Based on the advice provided, users advance the conversation and improve the quality of communication. After the conversation ends, users provide feedback to the system, contributing to its further optimization.

[0147] (Example 2)

[0148] 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".

[0149] In modern communication, it is essential to appropriately understand the emotions of the person you are talking to and the surrounding environment, and to conduct the conversation accordingly. However, achieving this requires advanced emotion analysis and environmental awareness, making it difficult for users to engage in high-quality communication simply by receiving what the other person says. There is a need to improve this situation and provide personalized support that responds to the other person's emotions and environment in real time.

[0150] 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.

[0151] In this invention, the server includes emotion analysis means for receiving video and audio data acquired from the user's information processing device and estimating the emotions of others; environmental analysis means for identifying environmental data based on geographical data and surrounding conditions; content generation means for generating appropriate conversation topics and action instructions based on emotions and environmental data; and emotion engine means for integrating emotion engines to analyze emotions. This makes it possible to analyze the emotions of the user and the person they are talking to in real time and provide personalized support accordingly.

[0152] The term "user" refers to an individual or group that operates a device or technology.

[0153] "Information processing equipment" is a general term for electronic devices used to collect, transmit, and analyze data.

[0154] "Video data" refers to visual information acquired by visual sensors such as cameras.

[0155] "Audio data" refers to sound information acquired by acoustic sensors such as microphones.

[0156] "Emotional analysis means" refers to a technology or device for estimating another person's emotional state based on acquired data.

[0157] "Geographic data" refers to information about the user's location and the surrounding geographical characteristics.

[0158] "Surrounding circumstances" is a concept that includes information about the environment and conditions of the user's location.

[0159] "Environmental analysis means" refers to technologies or devices for identifying environmental data based on acquired geographical data and surrounding condition information.

[0160] "Content generation means" refers to a technology or device for generating appropriate conversation topics and action instructions using analyzed emotion data and environmental data.

[0161] An "emotion engine" is a technology or device used to analyze the emotions of users and others, and to build an emotion model based on that analysis.

[0162] This invention is a system that supports communication by acquiring and analyzing emotional and environmental data in real time via a device worn by the user. Specifically, it uses AR glasses or other wearable devices to acquire video and audio data through a camera and microphone. The device transmits this data to a server, which analyzes it to recognize emotions and the surrounding environment.

[0163] The server uses deep learning-based sentiment analysis to estimate the emotions of others from acquired data. Furthermore, environmental analysis identifies environmental data based on geographical data and surrounding conditions. Based on this information, the server uses a large-scale data model to generate optimal conversation topics and behavioral advice via content generation.

[0164] The generated information is visually displayed on the user's device, allowing the user to communicate more effectively. The emotion engine can learn from the user's past emotional data and build an emotion model that can be used in future interactions.

[0165] For example, if a user is feeling nervous during a business meeting, the device might offer information such as "advice on relaxing deep breathing" or "suggestions for conversations about shared hobbies with other participants." This system combines advanced sentiment analysis and environmental awareness to provide users with personalized communication support.

[0166] As an example of a prompt, using the question, "What conversation topics are effective when the user is feeling nervous?", the generative AI model generates appropriate advice. In this way, users can achieve smoother and higher-quality communication.

[0167] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0168] Step 1:

[0169] The device uses its camera and microphone to capture video and audio data of the person it is talking to in real time. The input consists of the other person's facial expressions and voice, which are converted into digital data. This digital data is temporarily stored on the device for later analysis.

[0170] Step 2:

[0171] The terminal transmits the collected video and audio data to the server via wireless communication. The input is the digital data acquired in step 1, and the output is the data received on the server for analysis. The terminal maintains real-time performance by performing high-speed and stable data transmission.

[0172] Step 3:

[0173] The server analyzes the received video and audio data using emotion analysis tools. The input is the data received in step 2, and the output is information about the identified emotional state of another person. The server uses a deep learning model to identify each emotion (joy, anger, sadness, pleasure) and sends the analysis results to the emotion engine.

[0174] Step 4:

[0175] Simultaneously, the device utilizes VPS technology to acquire geographical data and environmental characteristics of the user's surroundings. The input is sensor information from the device, and the output is environmental data for the identified user. This data reflects the user's location and the surrounding sound and light conditions.

[0176] Step 5:

[0177] The terminal sends the acquired geographical data and environmental characteristics to the server. The input is the environmental data from step 4, and the output is the data received for processing on the server. The server analyzes this data to understand the details of the environment.

[0178] Step 6:

[0179] The server integrates sentiment data and environmental data and uses content generation tools to generate conversation topics and behavioral advice. The input is the output results from steps 3 and 5, and the output is optimized content to be provided to the user. The server uses a generative AI model to refine and personalize the generated advice with a sentiment engine.

[0180] Step 7:

[0181] The device displays the final generated content to the user in a visual format. The input is the content generated in step 6, and the output is information that can be visually interpreted by the user. For example, the display can show advice or conversation topics that the user can use in actual communication.

[0182] (Application Example 2)

[0183] Next, we will explain application example 2. In the following explanation, the data processing device 12 will be referred to as a "server" and the smart device 14 as a "terminal".

[0184] In today's commercial spaces, increasing customer satisfaction requires more than just providing products and services; it demands personalized service that addresses individual needs and emotions. However, traditional customer service has struggled to accurately grasp customers' emotions and respond appropriately on an immediate basis. Therefore, there is a need for a system that can flexibly respond to different emotional states and environments of customers and effectively support customer service.

[0185] 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.

[0186] In this invention, the server includes emotion recognition means that receive video and audio information acquired from the user's device and estimate the emotions of others based on that information; environment recognition means that identify environmental information based on the user's current location and surrounding information acquired from the user's device; and content generation means that use a language model to generate optimal dialogue topics and behavioral advice based on the estimated emotions and identified environmental information. This enables flexible and precise customer service that is in line with the customer's emotions.

[0187] "User's device" refers to a terminal device used for acquiring and displaying data, and includes smart glasses and other wearable devices.

[0188] "Visual information" refers to visual data acquired through a camera, and is primarily used to analyze the facial expressions of others.

[0189] "Audio information" refers to sound data acquired through a microphone, which is used to analyze other people's voices for emotion estimation.

[0190] "Emotion recognition means" refers to a technical function that estimates the emotions of others based on video and audio information, and is mainly realized through deep learning technology.

[0191] "Environmental information" refers to data about the user's current location and surrounding environment, and is used to provide feedback in a specific context.

[0192] "Environmental recognition means" refers to a function that identifies the user's current location and surrounding conditions based on information from the user's device.

[0193] A "language model" refers to an algorithm that uses natural language processing technology to generate optimal dialogue based on emotional and environmental information.

[0194] A "dialogue topic" is a topic suggested in the generated language content to enable users to have natural conversations with others.

[0195] "Behavioral advice" refers to suggestions regarding actions that users should follow to achieve better communication.

[0196] The system that realizes this invention is operated primarily through smart glasses worn by the user. The device has a built-in camera and microphone, which allow it to acquire video and audio information in real time. The device has the function to transmit this data to a server. The server uses emotion recognition means to analyze and estimate the emotions of others from the received video information using deep learning technology. Specifically, it estimates emotions from facial expressions and voice using APIs such as Microsoft's Face API and Google's Speech-to-Text.

[0197] Next, the server uses environmental recognition means to identify environmental information based on the user's current location and surrounding conditions obtained from their smart glasses. For example, by using VPS technology, it can grasp detailed location information and understand the physical characteristics of the surroundings.

[0198] Furthermore, the server uses a language model to generate optimal dialogue topics and behavioral advice based on received emotional and environmental information. In this process, it employs generative AI models such as OpenAI® GPT-3® to create personalized content that reflects the user's individual emotional patterns.

[0199] The generated content is displayed visually on the device's display, providing users with advice on specific customer service methods and conversation flow. For example, if a store detects that a customer has a stern expression, the smart glasses might display "Ask if they have any questions about the products." This allows users to respond flexibly according to the situation.

[0200] An example of a prompt message is: "Provide advice to display when the customer's expression is stern. The options should be friendly and stress-reducing."

[0201] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0202] Step 1:

[0203] The device acquires real-time video and audio information of the customer through its camera and microphone. This information, including the customer's facial expressions and voice, is sent to the server as input data for estimating their emotions.

[0204] Step 2:

[0205] The server analyzes the received video and audio information using emotion recognition technology. Specifically, it analyzes facial expression data using Microsoft's Face API and estimates emotions from audio data using Google's Speech-to-Text. This identifies the customer's emotional state and outputs it as emotion parameters.

[0206] Step 3:

[0207] The server uses environmental recognition capabilities to identify environmental information based on the current location and surrounding conditions received from the terminal. Utilizing VPS technology, it understands the physical characteristics of the space where the user is located and outputs data related to those characteristics.

[0208] Step 4:

[0209] The server inputs estimated emotion parameters and identified environmental information into a language model. At this time, it uses a generative AI model such as OpenAI GPT-3 to generate optimal dialogue topics and behavioral advice. It determines what to provide to the user in the form of prompt statements and outputs personalized content.

[0210] Step 5:

[0211] The generated dialogue topics and behavioral advice are visually displayed on the terminal's display device. Users can review the presented information and utilize it in actual customer interactions. This creates opportunities to improve the quality of service and increase customer satisfaction.

[0212] 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.

[0213] Data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of data generation model 58 is ChatGPT (registered trademark) (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.

[0214] 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.

[0215] [Second Embodiment]

[0216] Figure 3 shows an example of the configuration of the data processing system 210 according to the second embodiment.

[0217] 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.

[0218] 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).

[0219] 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.

[0220] 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.

[0221] 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).

[0222] 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.

[0223] 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.

[0224] 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.

[0225] 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.

[0226] 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.

[0227] 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".

[0228] The system of the present invention provides support in communication scenarios using a terminal worn by the user. This system provides effective information through multiple components, including emotion recognition means, environment recognition means, content generation means, and advice display means. Each component is described in detail below.

[0229] First, the terminal is a wearable device, such as AR glasses, worn by the user, and is equipped with a camera and microphone. This terminal is responsible for capturing the other person's facial expressions and voice in real time and sending this data to a server. This allows for the rapid and continuous detection of the other person's speech and changes in facial expressions.

[0230] Next, the server performs digital processing using emotion recognition means based on the video and audio data transmitted from the terminal. Specifically, it extracts facial features from the facial image and estimates multiple emotion labels such as joy, surprise, and boredom. Simultaneously, it also analyzes the audio to grasp the nuances of emotion from the tone and volume of the voice.

[0231] Simultaneously, the device uses environmental recognition to acquire information about the user's current location and major landmarks in the surrounding area. For example, if the user is on a date, it identifies nearby restaurants and tourist attractions; if the user is in business, it identifies information about buildings and conference rooms, and sends this information to the server. This information is used as supplementary information for the conversation.

[0232] By integrating this emotional data and environmental information, the server utilizes a large-scale language model to generate content. Based on the other party's current emotions and location, it generates appropriate conversation topics and behavioral advice suitable for the situation, and sends it to the user's device.

[0233] Finally, the device uses an advice display mechanism to visually show the generated advice and topics to the user. For example, during a conversation, advice such as "It would be good to talk about recent news" might be displayed, allowing the user to continue the conversation smoothly.

[0234] As a concrete example, consider a scenario where a user is on a date at a cafe and their date shows signs of boredom. The device instantly captures this expression, and the server recognizes it as "boredom." The server analyzes this and automatically generates and sends advice, such as "bring up the topic of a popular new restaurant that recently opened nearby." The user can then use this information to revitalize the conversation with their date.

[0235] This invention enables users to receive specific conversational support based on emotion recognition and environmental information, thereby facilitating effective communication.

[0236] The following describes the processing flow.

[0237] Step 1:

[0238] The device captures the other person's face with the AR glasses' camera and collects audio data with the microphone. The collected video and audio data is compressed in real time and sent to the server.

[0239] Step 2:

[0240] The server performs facial recognition from the received video data. Specifically, it detects facial landmarks (eyes, mouth, eyebrows, etc.) and analyzes the overall facial expression based on these. In addition, it extracts audio features from the audio data and evaluates the tone and speed of the voice.

[0241] Step 3:

[0242] The server estimates emotions based on facial expressions and voice characteristics. Using a deep learning model, it identifies emotion labels such as joy, surprise, and boredom. This information, along with historical data, is stored as a user-specific emotion pattern.

[0243] Step 4:

[0244] The device analyzes its current location information and surrounding video using a VPS to identify landmarks and buildings. It then extracts environmental information and sends it to the server.

[0245] Step 5:

[0246] The server integrates received environmental information and sentiment data, and uses a large-scale language model to generate appropriate conversation topics and advice. Past conversation logs are also referenced in this process.

[0247] Step 6:

[0248] The generated conversation topics and advice are sent to the terminal in short text format. The terminal then displays them appropriately in the user's field of view.

[0249] Step 7:

[0250] The user takes the advice into consideration, continues the conversation, and observes the other person's reactions. If necessary, they return to step 1 and repeat the process.

[0251] Step 8:

[0252] After the conversation ends, the user provides feedback to the system. The server receives this feedback and uses it as training data to improve the accuracy of sentiment estimation and advice generation.

[0253] (Example 1)

[0254] 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."

[0255] In modern social settings, individuals face the challenge of generating appropriate conversations that are responsive to the other person's emotions and the surrounding environment. Finding the right timing to naturally advance conversation within diverse social interactions is also a challenge. This can sometimes lead to interactions not proceeding smoothly.

[0256] 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.

[0257] In this invention, the server includes information processing means for receiving video and audio data acquired from the user's device and estimating the other party's emotions based on that data; information recognition means for identifying environmental information based on location data and surrounding information acquired from the user's device; and information generation means for generating optimal topics and behavioral advice using a large-scale language model based on the estimated emotions and identified environmental information. This enables the user to engage in natural conversations that are appropriate to the other party's emotions and environment, and to facilitate smooth communication.

[0258] "User's device" refers to a terminal device that a user wears or operates to input video and audio data.

[0259] "Video and audio data" refers to digital data of visual and audio information acquired through the user's device.

[0260] "Information processing means" refers to means of analyzing received video and audio data and performing calculations and analyses to estimate the emotions of the other party.

[0261] "Location data and surrounding information" refers to geographical and physical information related to the user's current location, which is acquired through the device.

[0262] "Information recognition means" refers to means for analyzing location data and surrounding information to extract specific environmental information.

[0263] "Environmental information" refers to data about the user's current location and surroundings, which functions as background and supplementary information for conversations.

[0264] A "large-scale language model" is a model that learns from a large amount of language data and generates diverse conversation topics and texts.

[0265] An "information generation method" is a means of generating optimal topics and behavioral advice based on estimated emotions and identified environmental information.

[0266] "Information display means" refers to a display device or method for visually presenting generated topics or advice to a user.

[0267] The embodiment of this invention primarily uses a system in which a terminal and a server work together. The user wears a wearable device, such as AR glasses equipped with a camera and microphone, which functions as the terminal. This terminal captures the facial expressions and voices of people within the user's field of view in real time and transmits them to the server via a communication network.

[0268] The server processes information based on the received video and audio data. Specifically, it uses image recognition software to analyze the facial features of the other person and estimate various emotions from their expressions. Furthermore, it uses speech recognition technology to analyze the tone and volume of the voice and grasp the nuances of emotion. The terminal also acquires location data and surrounding information using GPS and nearby Wi-Fi signals, and provides this information to the server as well.

[0269] The server uses a large-scale language model to generate optimal conversation topics and behavioral advice based on estimated sentiment data and environmental information. This process involves feeding prompt sentences into the generative AI model. An example of a prompt sentence might be: "Generate advice to liven up the conversation based on the user's current situation. For example, if the user is on a date at a cafe and their date seems bored, suggest some topics to bring up."

[0270] Ultimately, the device visually displays topics and advice received from the server in an easy-to-understand format for the user. This allows users to engage in natural conversations and make informed choices based on the situation. For example, if a user is on a date at a cafe, the system can provide appropriate small talk topics and information about nearby places that might be relevant, based on the other person's facial expressions. In this way, the system provides a mechanism to enhance the user's interaction experience.

[0271] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0272] Step 1:

[0273] The device uses the camera and microphone of the AR glasses being worn to capture the other person's facial expressions and voice in real time. It receives video and audio signals captured through the camera and microphone as input. These signals are processed as data, converted into image and audio data, and output.

[0274] Step 2:

[0275] The terminal transmits the acquired image and audio data to the server via the network. Data compression and encryption may be performed during transmission. The input is the image and audio data generated in step 1, and the output is the transmission of data to the server.

[0276] Step 3:

[0277] The server analyzes the image data received from the terminal. Here, by using an image processing algorithm, facial features are extracted and emotion labels (such as joy, surprise, boredom, etc.) are estimated. The input is the image data transmitted from the terminal, and the output is a set of emotion labels.

[0278] Step 4:

[0279] At the same time, the server analyzes the voice data, uses voice recognition technology to analyze the tone and intensity of the voice, and grasps the nuances of emotions. The input is the voice data transmitted from the terminal, and the output is an emotion index based on the voice.

[0280] Step 5:

[0281] The terminal obtains location data and surrounding information obtained from GPS and Wi-Fi information, and transmits this to the server. The input is the data obtained from the location information sensor, and the output is the transmission of location data and surrounding information to the server.

[0282] Step 6:

[0283] The server integrates the received emotion data and environmental information, and uses a generated AI model to generate optimal conversation topics and advice on actions. In this process, a prompt sentence such as "Please generate advice to enliven the conversation based on the user's current situation" is used. The input is the emotion label and environmental information, and the output is the generated conversation topics and advice.

[0284] Step 7:

[0285] Finally, the terminal visually displays the advice transmitted from the server so that the user can confirm the advice. The input is the advice data from the server, and the output is the display of information on the user interface. Through this step, the user can receive assistance in advancing the conversation at an appropriate timing.

[0286] (Application Example 1)

[0287] Next, Application Example 1 will be described. In the following description, the data processing device 12 is referred to as a "server", and the smart glasses 214 are referred to as a "terminal".

[0288] In the work performed by the operator, there is a need for a means to quickly and accurately provide appropriate work advice according to the emotions of individual operators and the surrounding situation. However, with conventional methods, it is difficult to estimate emotions in real time and identify the environmental situation, making it difficult to improve work efficiency and operator satisfaction. Therefore, an object of the present invention is to provide a device that accurately grasps the emotions of the operator and the surrounding situation and provides optimal work advice based thereon.

[0289] The specific processing by the specific processing unit 290 of the data processing device 12 in Application Example 1 is realized by the following means.

[0290] In this invention, the server includes an emotion estimation means for receiving image information and voice information acquired from the user's terminal and estimating the emotions of others based on this information, a situation recognition means for identifying the surrounding situation based on the current position and surrounding situation obtained from the user's terminal, and an information generation means for generating optimal work advice or action instructions using a language generation model based on the estimated emotions and the identified surrounding situation. Thereby, it becomes possible to provide optimal advice according to the emotions of the operator and the surrounding situation in real time.

[0291] The "emotion estimation means" is a technology for estimating the emotions of others in consideration of various possibilities based on the image information and voice information acquired from the user's terminal.

[0292] The "situation recognition means" is a technology for identifying the surrounding situation in real time by using the current position and surrounding situation information sent from the user's terminal.

[0293] "Information generation means" refers to a technology that uses language generation models to create optimal work advice and behavioral instructions based on estimated emotions and identified surrounding circumstances.

[0294] An "advice display means" is a device or technology that visually presents generated work advice or action instructions to the worker in an easily understandable manner.

[0295] "Reaction processing means" refers to a technology that analyzes the reaction received from the worker and uses that analysis to improve the accuracy of the information generation means.

[0296] A "language generation model" is an artificial intelligence model that generates diverse texts and information based on large amounts of data.

[0297] A system for implementing this invention requires a user-worn terminal and a server connected to it. The terminal is equipped with a camera and microphone to acquire image and audio information of the user's surroundings. This enables real-time emotion estimation and situational awareness. The acquired data is immediately transmitted to the server.

[0298] The server analyzes transmitted image and audio information using emotion estimation means to estimate the worker's emotions with high accuracy. This process incorporates emotion analysis algorithms that utilize image recognition and natural language processing technologies. In addition, situation recognition means are used to identify the user's current location and surrounding environment, and to obtain information appropriate to the surrounding situation.

[0299] Next, the information generation system uses a language generation model to generate optimal work advice and action instructions based on estimated emotions and identified surrounding circumstances. This provides a beneficial and efficient work environment for the worker. The generated advice is presented in real time to the worker through the advice display system on the terminal.

[0300] As a specific example, when it is determined that a factory worker is not concentrating on the work, the system generates and visually displays advice such as "Take a short break" or "Let's change the order of work". Examples of the prompt text at that time are in the form of "Please generate the optimal advice when the worker is tired. The current environmental data is a temperature of 25 degrees, a humidity of 60%, and a noise level of 80 decibels."

[0301] The flow of the specific process in Application Example 1 will be described using FIG. 12.

[0302] Step 1:

[0303] The terminal collects the image information and voice information around the user in real time. Using a camera and a microphone, the acquired data is generated as an image file and a voice file. These are transmitted to the server as a data stream.

[0304] Step 2:

[0305] The server processes the image file and voice file transmitted from the terminal using the emotion estimation means. Using an image processing algorithm, the features of the expression are extracted from the image file, and using voice recognition technology, the tone of the voice is analyzed from the voice file. Based on this analysis result, the emotional state of the user is quantified and output.

[0306] Step 3:

[0307] The server identifies the current position information of the user and the surrounding situation using the situation recognition means. Using a location information service, location data is acquired, and environmental information about the user's surroundings is collected. Based on this data, the surrounding situation is analyzed, and information about the user's working environment is output.

[0308] Step 4:

[0309] The server uses information generation means to utilize the emotional state obtained in step 2 and the surrounding situation information obtained in step 3 as input data. A generative AI model is then used to generate optimal work advice and action instructions based on this input data. In this generation process, the generative AI model forms various advice patterns based on prompt sentences and outputs them in text format.

[0310] Step 5:

[0311] The terminal visually displays the generated advice received from the server. It presents the advice clearly to the user via a display device, providing interaction that encourages them to act according to the advice. This display is designed to enhance user efficiency while maintaining a natural workflow.

[0312] 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.

[0313] This invention is a system that effectively supports communication using a device worn by the user, and is particularly characterized by its incorporation of an emotion engine. This system comprises emotion recognition means, environment recognition means, content generation means, and advice display means, and further integrates the emotion engine to analyze and utilize the emotions of both the user and the other party.

[0314] The device is implemented as AR glasses or other wearable devices and is equipped with a camera and microphone. The device first captures the other person's facial expressions and voice in real time, converts this data, and sends it to a server. This allows the system to constantly acquire information about the other person's emotions.

[0315] The server has emotion recognition capabilities to analyze received video and audio data, and uses deep learning technology to estimate emotions. It analyzes the state of joy, anger, sadness, and other emotions from facial expressions and voice, and in parallel builds a user emotion model based on this using an emotion engine. This emotion model learns the user's unique emotion patterns and is used in subsequent conversations.

[0316] Simultaneously, the terminal uses VPS technology to acquire surrounding geographical information and characteristics of the surrounding environment, and sends this information to the server as environmental data. This allows the entire system to understand the user's current location and its characteristics.

[0317] Based on this emotional and environmental information, the server uses a large-scale language model to generate conversation topics and behavioral advice. In this process, it can refer to the user's emotional model via the emotion engine to provide more personalized content. For example, if the user is feeling stressed, it will suggest topics that help them relax.

[0318] The device visually displays the final generated information and prompts the user for action. This facilitates a smoother conversation flow and helps build better communication.

[0319] For example, if a user is feeling nervous during a business meeting, the emotion engine will detect this and display advice on the device such as "advice on relaxing deep breathing" or "talking about a shared hobby with meeting participants." The user can then use this advice to ease the atmosphere. This invention allows users to not only receive information but also receive personalized support, thereby improving the quality of their communication.

[0320] The following describes the processing flow.

[0321] Step 1:

[0322] The device uses AR glasses worn by the user to capture surrounding video and audio in real time. It records the other person's facial expressions through the camera and collects audio with the microphone. The acquired data is immediately transmitted to the server.

[0323] Step 2:

[0324] The server performs facial recognition on the received video data and analyzes facial landmarks using emotion recognition technology. This allows it to detect subtle changes in the other person's facial expressions and generate emotion labels such as joy, anger, sadness, and happiness.

[0325] Step 3:

[0326] Similarly, the server analyzes the audio data and extracts speech features. It evaluates the tone, pitch, and speaking speed of the voice and uses this information to further reinforce the emotional state.

[0327] Step 4:

[0328] The terminal uses VPS technology to determine the user's current location and surrounding environment. The acquired geographical information is transmitted to an environmental recognition system to understand the surrounding landmarks and characteristics of the location.

[0329] Step 5:

[0330] The server integrates collected emotional and environmental information and uses an emotion engine to diagnose the user's emotional state. It then compares this with the user's past emotional history to build a individually tailored emotional model.

[0331] Step 6:

[0332] The server leverages a large-scale language model to generate personalized conversation topics and behavioral advice based on the user's emotion model. For example, if a user is feeling anxious, it might suggest small talk to help them calm down.

[0333] Step 7:

[0334] The generated advice is sent to the device and efficiently displayed within the user's field of view. This visual presentation allows users to quickly understand the information and immediately utilize it in subsequent interactions.

[0335] Step 8:

[0336] Based on the advice provided, users advance the conversation and improve the quality of communication. After the conversation ends, users provide feedback to the system, contributing to its further optimization.

[0337] (Example 2)

[0338] 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".

[0339] In modern communication, it is essential to appropriately understand the emotions of the person you are talking to and the surrounding environment, and to conduct the conversation accordingly. However, achieving this requires advanced emotion analysis and environmental awareness, making it difficult for users to engage in high-quality communication simply by receiving what the other person says. There is a need to improve this situation and provide personalized support that responds to the other person's emotions and environment in real time.

[0340] 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.

[0341] In this invention, the server includes emotion analysis means for receiving video and audio data acquired from the user's information processing device and estimating the emotions of others; environmental analysis means for identifying environmental data based on geographical data and surrounding conditions; content generation means for generating appropriate conversation topics and action instructions based on emotions and environmental data; and emotion engine means for integrating emotion engines to analyze emotions. This makes it possible to analyze the emotions of the user and the person they are talking to in real time and provide personalized support accordingly.

[0342] The term "user" refers to an individual or group that operates a device or technology.

[0343] "Information processing equipment" is a general term for electronic devices used to collect, transmit, and analyze data.

[0344] "Video data" refers to visual information acquired by visual sensors such as cameras.

[0345] "Audio data" refers to sound information acquired by acoustic sensors such as microphones.

[0346] "Emotional analysis means" refers to a technology or device for estimating another person's emotional state based on acquired data.

[0347] "Geographic data" refers to information about the user's location and the surrounding geographical characteristics.

[0348] "Surrounding circumstances" is a concept that includes information about the environment and conditions of the user's location.

[0349] "Environmental analysis means" refers to technologies or devices for identifying environmental data based on acquired geographical data and surrounding condition information.

[0350] "Content generation means" refers to a technology or device for generating appropriate conversation topics and action instructions using analyzed emotion data and environmental data.

[0351] An "emotion engine" is a technology or device used to analyze the emotions of users and others, and to build an emotion model based on that analysis.

[0352] This invention is a system that supports communication by acquiring and analyzing emotional and environmental data in real time via a device worn by the user. Specifically, it uses AR glasses or other wearable devices to acquire video and audio data through a camera and microphone. The device transmits this data to a server, which analyzes it to recognize emotions and the surrounding environment.

[0353] The server uses deep learning-based sentiment analysis to estimate the emotions of others from acquired data. Furthermore, environmental analysis identifies environmental data based on geographical data and surrounding conditions. Based on this information, the server uses a large-scale data model to generate optimal conversation topics and behavioral advice via content generation.

[0354] The generated information is visually displayed on the user's device, allowing the user to communicate more effectively. The emotion engine can learn from the user's past emotional data and build an emotion model that can be used in future interactions.

[0355] For example, if a user is feeling nervous during a business meeting, the device might offer information such as "advice on relaxing deep breathing" or "suggestions for conversations about shared hobbies with other participants." This system combines advanced sentiment analysis and environmental awareness to provide users with personalized communication support.

[0356] As an example of a prompt, using the question, "What conversation topics are effective when the user is feeling nervous?", the generative AI model generates appropriate advice. In this way, users can achieve smoother and higher-quality communication.

[0357] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0358] Step 1:

[0359] The device uses its camera and microphone to capture video and audio data of the person it is talking to in real time. The input consists of the other person's facial expressions and voice, which are converted into digital data. This digital data is temporarily stored on the device for later analysis.

[0360] Step 2:

[0361] The terminal transmits the collected video and audio data to the server via wireless communication. The input is the digital data acquired in step 1, and the output is the data received on the server for analysis. The terminal maintains real-time performance by performing high-speed and stable data transmission.

[0362] Step 3:

[0363] The server analyzes the received video and audio data using emotion analysis tools. The input is the data received in step 2, and the output is information about the identified emotional state of another person. The server uses a deep learning model to identify each emotion (joy, anger, sadness, pleasure) and sends the analysis results to the emotion engine.

[0364] Step 4:

[0365] Simultaneously, the device utilizes VPS technology to acquire geographical data and environmental characteristics of the user's surroundings. The input is sensor information from the device, and the output is environmental data for the identified user. This data reflects the user's location and the surrounding sound and light conditions.

[0366] Step 5:

[0367] The terminal sends the acquired geographical data and environmental characteristics to the server. The input is the environmental data from step 4, and the output is the data received for processing on the server. The server analyzes this data to understand the details of the environment.

[0368] Step 6:

[0369] The server integrates sentiment data and environmental data and uses content generation tools to generate conversation topics and behavioral advice. The input is the output results from steps 3 and 5, and the output is optimized content to be provided to the user. The server uses a generative AI model to refine and personalize the generated advice with a sentiment engine.

[0370] Step 7:

[0371] The device displays the final generated content to the user in a visual format. The input is the content generated in step 6, and the output is information that can be visually interpreted by the user. For example, the display can show advice or conversation topics that the user can use in actual communication.

[0372] (Application Example 2)

[0373] 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."

[0374] In today's commercial spaces, increasing customer satisfaction requires more than just providing products and services; it demands personalized service that addresses individual needs and emotions. However, traditional customer service has struggled to accurately grasp customers' emotions and respond appropriately on an immediate basis. Therefore, there is a need for a system that can flexibly respond to different emotional states and environments of customers and effectively support customer service.

[0375] 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.

[0376] In this invention, the server includes emotion recognition means that receive video and audio information acquired from the user's device and estimate the emotions of others based on that information; environment recognition means that identify environmental information based on the user's current location and surrounding information acquired from the user's device; and content generation means that use a language model to generate optimal dialogue topics and behavioral advice based on the estimated emotions and identified environmental information. This enables flexible and precise customer service that is in line with the customer's emotions.

[0377] "User's device" refers to a terminal device used for acquiring and displaying data, and includes smart glasses and other wearable devices.

[0378] "Visual information" refers to visual data acquired through a camera, and is primarily used to analyze the facial expressions of others.

[0379] "Audio information" refers to sound data acquired through a microphone, which is used to analyze other people's voices for emotion estimation.

[0380] "Emotion recognition means" refers to a technical function that estimates the emotions of others based on video and audio information, and is mainly realized through deep learning technology.

[0381] "Environmental information" refers to data about the user's current location and surrounding environment, and is used to provide feedback in a specific context.

[0382] "Environmental recognition means" refers to a function that identifies the user's current location and surrounding conditions based on information from the user's device.

[0383] A "language model" refers to an algorithm that uses natural language processing technology to generate optimal dialogue based on emotional and environmental information.

[0384] A "dialogue topic" is a topic suggested in the generated language content to enable users to have natural conversations with others.

[0385] "Behavioral advice" refers to suggestions regarding actions that users should follow to achieve better communication.

[0386] The system that realizes this invention is operated primarily through smart glasses worn by the user. The device has a built-in camera and microphone, which allow it to acquire video and audio information in real time. The device has the function to transmit this data to a server. The server uses emotion recognition means to analyze and estimate the emotions of others from the received video information using deep learning technology. Specifically, it estimates emotions from facial expressions and voice using APIs such as Microsoft's Face API and Google's Speech-to-Text.

[0387] Next, the server uses environmental recognition means to identify environmental information based on the user's current location and surrounding conditions obtained from their smart glasses. For example, by using VPS technology, it can grasp detailed location information and understand the physical characteristics of the surroundings.

[0388] Furthermore, the server uses a language model to generate optimal dialogue topics and behavioral advice based on received emotional and environmental information. In this process, a generative AI model such as OpenAI GPT-3 is used to create personalized content that reflects the user's individual emotional patterns.

[0389] The generated content is displayed visually on the device's display, providing users with advice on specific customer service methods and conversation flow. For example, if a store detects that a customer has a stern expression, the smart glasses might display "Ask if they have any questions about the products." This allows users to respond flexibly according to the situation.

[0390] An example of a prompt message is: "Provide advice to display when the customer's expression is stern. The options should be friendly and stress-reducing."

[0391] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0392] Step 1:

[0393] The device acquires real-time video and audio information of the customer through its camera and microphone. This information, including the customer's facial expressions and voice, is sent to the server as input data for estimating their emotions.

[0394] Step 2:

[0395] The server analyzes the received video and audio information using emotion recognition technology. Specifically, it analyzes facial expression data using Microsoft's Face API and estimates emotions from audio data using Google's Speech-to-Text. This identifies the customer's emotional state and outputs it as emotion parameters.

[0396] Step 3:

[0397] The server uses environmental recognition capabilities to identify environmental information based on the current location and surrounding conditions received from the terminal. Utilizing VPS technology, it understands the physical characteristics of the space where the user is located and outputs data related to those characteristics.

[0398] Step 4:

[0399] The server inputs estimated emotion parameters and identified environmental information into a language model. At this time, it uses a generative AI model such as OpenAI GPT-3 to generate optimal dialogue topics and behavioral advice. It determines what to provide to the user in the form of prompt statements and outputs personalized content.

[0400] Step 5:

[0401] The generated dialogue topics and behavioral advice are visually displayed on the terminal's display device. Users can review the presented information and utilize it in actual customer interactions. This creates opportunities to improve the quality of service and increase customer satisfaction.

[0402] 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.

[0403] 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.

[0404] 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.

[0405] [Third Embodiment]

[0406] Figure 5 shows an example of the configuration of the data processing system 310 according to the third embodiment.

[0407] 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.

[0408] 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).

[0409] 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.

[0410] 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.

[0411] 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).

[0412] 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.

[0413] 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.

[0414] 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.

[0415] 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.

[0416] 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.

[0417] 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".

[0418] The system of the present invention provides support in communication scenarios using a terminal worn by the user. This system provides effective information through multiple components, including emotion recognition means, environment recognition means, content generation means, and advice display means. Each component is described in detail below.

[0419] First, the terminal is a wearable device, such as AR glasses, worn by the user, and is equipped with a camera and microphone. This terminal is responsible for capturing the other person's facial expressions and voice in real time and sending this data to a server. This allows for the rapid and continuous detection of the other person's speech and changes in facial expressions.

[0420] Next, the server performs digital processing using emotion recognition means based on the video and audio data transmitted from the terminal. Specifically, it extracts facial features from the facial image and estimates multiple emotion labels such as joy, surprise, and boredom. Simultaneously, it also analyzes the audio to grasp the nuances of emotion from the tone and volume of the voice.

[0421] Simultaneously, the device uses environmental recognition to acquire information about the user's current location and major landmarks in the surrounding area. For example, if the user is on a date, it identifies nearby restaurants and tourist attractions; if the user is in business, it identifies information about buildings and conference rooms, and sends this information to the server. This information is used as supplementary information for the conversation.

[0422] By integrating this emotional data and environmental information, the server utilizes a large-scale language model to generate content. Based on the other party's current emotions and location, it generates appropriate conversation topics and behavioral advice suitable for the situation, and sends it to the user's device.

[0423] Finally, the device uses an advice display mechanism to visually show the generated advice and topics to the user. For example, during a conversation, advice such as "It would be good to talk about recent news" might be displayed, allowing the user to continue the conversation smoothly.

[0424] As a concrete example, consider a scenario where a user is on a date at a cafe and their date shows signs of boredom. The device instantly captures this expression, and the server recognizes it as "boredom." The server analyzes this and automatically generates and sends advice, such as "bring up the topic of a popular new restaurant that recently opened nearby." The user can then use this information to revitalize the conversation with their date.

[0425] This invention enables users to receive specific conversational support based on emotion recognition and environmental information, thereby facilitating effective communication.

[0426] The following describes the processing flow.

[0427] Step 1:

[0428] The device captures the other person's face with the AR glasses' camera and collects audio data with the microphone. The collected video and audio data is compressed in real time and sent to the server.

[0429] Step 2:

[0430] The server performs facial recognition from the received video data. Specifically, it detects facial landmarks (eyes, mouth, eyebrows, etc.) and analyzes the overall facial expression based on these. In addition, it extracts audio features from the audio data and evaluates the tone and speed of the voice.

[0431] Step 3:

[0432] The server estimates emotions based on facial expressions and voice characteristics. Using a deep learning model, it identifies emotion labels such as joy, surprise, and boredom. This information, along with historical data, is stored as a user-specific emotion pattern.

[0433] Step 4:

[0434] The device analyzes its current location information and surrounding video using a VPS to identify landmarks and buildings. It then extracts environmental information and sends it to the server.

[0435] Step 5:

[0436] The server integrates received environmental information and sentiment data, and uses a large-scale language model to generate appropriate conversation topics and advice. Past conversation logs are also referenced in this process.

[0437] Step 6:

[0438] The generated conversation topics and advice are sent to the terminal in short text format. The terminal then displays them appropriately in the user's field of view.

[0439] Step 7:

[0440] The user takes the advice into consideration, continues the conversation, and observes the other person's reactions. If necessary, they return to step 1 and repeat the process.

[0441] Step 8:

[0442] After the conversation ends, the user provides feedback to the system. The server receives this feedback and uses it as training data to improve the accuracy of sentiment estimation and advice generation.

[0443] (Example 1)

[0444] 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."

[0445] In modern social settings, individuals face the challenge of generating appropriate conversations that are responsive to the other person's emotions and the surrounding environment. Finding the right timing to naturally advance conversation within diverse social interactions is also a challenge. This can sometimes lead to interactions not proceeding smoothly.

[0446] 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.

[0447] In this invention, the server includes information processing means for receiving video and audio data acquired from the user's device and estimating the other party's emotions based on that data; information recognition means for identifying environmental information based on location data and surrounding information acquired from the user's device; and information generation means for generating optimal topics and behavioral advice using a large-scale language model based on the estimated emotions and identified environmental information. This enables the user to engage in natural conversations that are appropriate to the other party's emotions and environment, and to facilitate smooth communication.

[0448] "User's device" refers to a terminal device that a user wears or operates to input video and audio data.

[0449] "Video and audio data" refers to digital data of visual and audio information acquired through the user's device.

[0450] "Information processing means" refers to means of analyzing received video and audio data and performing calculations and analyses to estimate the emotions of the other party.

[0451] "Location data and surrounding information" refers to geographical and physical information related to the user's current location, which is acquired through the device.

[0452] "Information recognition means" refers to means for analyzing location data and surrounding information to extract specific environmental information.

[0453] "Environmental information" refers to data about the user's current location and surroundings, which functions as background and supplementary information for conversations.

[0454] A "large-scale language model" is a model that learns from a large amount of language data and generates diverse conversation topics and texts.

[0455] An "information generation method" is a means of generating optimal topics and behavioral advice based on estimated emotions and identified environmental information.

[0456] "Information display means" refers to a display device or method for visually presenting generated topics or advice to a user.

[0457] The embodiment of this invention primarily uses a system in which a terminal and a server work together. The user wears a wearable device, such as AR glasses equipped with a camera and microphone, which functions as the terminal. This terminal captures the facial expressions and voices of people within the user's field of view in real time and transmits them to the server via a communication network.

[0458] The server processes information based on the received video and audio data. Specifically, it uses image recognition software to analyze the facial features of the other person and estimate various emotions from their expressions. Furthermore, it uses speech recognition technology to analyze the tone and volume of the voice and grasp the nuances of emotion. The terminal also acquires location data and surrounding information using GPS and nearby Wi-Fi signals, and provides this information to the server as well.

[0459] The server uses a large-scale language model to generate optimal conversation topics and behavioral advice based on estimated sentiment data and environmental information. This process involves feeding prompt sentences into the generative AI model. An example of a prompt sentence might be: "Generate advice to liven up the conversation based on the user's current situation. For example, if the user is on a date at a cafe and their date seems bored, suggest some topics to bring up."

[0460] Ultimately, the device visually displays topics and advice received from the server in an easy-to-understand format for the user. This allows users to engage in natural conversations and make informed choices based on the situation. For example, if a user is on a date at a cafe, the system can provide appropriate small talk topics and information about nearby places that might be relevant, based on the other person's facial expressions. In this way, the system provides a mechanism to enhance the user's interaction experience.

[0461] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0462] Step 1:

[0463] The device uses the camera and microphone of the AR glasses being worn to capture the other person's facial expressions and voice in real time. It receives video and audio signals captured through the camera and microphone as input. These signals are processed as data, converted into image and audio data, and output.

[0464] Step 2:

[0465] The terminal transmits the acquired image and audio data to the server via the network. Data compression and encryption may be performed during transmission. The input is the image and audio data generated in step 1, and the output is the transmission of data to the server.

[0466] Step 3:

[0467] The server analyzes the image data received from the terminal. Using image processing algorithms, it extracts facial features and estimates emotion labels (such as joy, surprise, or boredom). The input is image data sent from the terminal, and the output is a set of emotion labels.

[0468] Step 4:

[0469] Simultaneously, the server analyzes the audio data, using speech recognition technology to analyze the tone and volume of the voice and grasp the nuances of emotion. The input is the audio data transmitted from the terminal, and the output is an emotion index based on the voice.

[0470] Step 5:

[0471] The device acquires location data and surrounding information from GPS and Wi-Fi information, and transmits this data to the server. The input is data obtained from location sensors, and the output is the transmission of location data and surrounding information to the server.

[0472] Step 6:

[0473] The server integrates received sentiment data and environmental information, and uses a generative AI model to generate optimal conversation topics and behavioral advice. This process uses the prompt, "Generate advice to liven up the conversation based on the user's current situation." The input is sentiment labels and environmental information, and the output is the generated conversation topics and advice.

[0474] Step 7:

[0475] Ultimately, the terminal visually displays the advice sent from the server, allowing the user to review it. The input is the advice data from the server, and the output is the display of information on the user interface. This step helps the user to move the conversation forward at the appropriate time.

[0476] (Application Example 1)

[0477] 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."

[0478] In the work performed by workers, there is a need for a means to quickly and accurately provide appropriate work advice tailored to the individual worker's emotions and surrounding circumstances. However, conventional methods have made it difficult to estimate emotions in real time or identify environmental conditions, making it difficult to improve work efficiency and worker satisfaction. Therefore, the present invention aims to provide a device that accurately grasps the worker's emotions and surrounding circumstances and provides optimal work advice based on that.

[0479] 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.

[0480] In this invention, the server includes emotion estimation means that receives image and audio information acquired from the user's terminal and estimates the emotions of others based on this information; situation recognition means that identifies the surrounding situation based on the current location and surrounding conditions acquired from the user's terminal; and information generation means that generates optimal work advice or action instructions using a language generation model based on the estimated emotions and identified surrounding conditions. This makes it possible to provide optimal advice in real time according to the worker's emotions and surrounding conditions.

[0481] "Emotion estimation means" is a technology that estimates the emotions of others, taking into account various possibilities, based on image and audio information acquired from the user's device.

[0482] "Situation recognition means" refers to a technology that uses the user's current location and surrounding situation information sent from their terminal to identify the surrounding situation in real time.

[0483] "Information generation means" refers to a technology that uses language generation models to create optimal work advice and behavioral instructions based on estimated emotions and identified surrounding circumstances.

[0484] An "advice display means" is a device or technology that visually presents generated work advice or action instructions to the worker in an easily understandable manner.

[0485] "Reaction processing means" refers to a technology that analyzes the reactions received from workers and uses that analysis to improve the accuracy of information generation means.

[0486] A "language generation model" is an artificial intelligence model that generates diverse texts and information based on large amounts of data.

[0487] A system for implementing this invention requires a user-worn terminal and a server connected to it. The terminal is equipped with a camera and microphone to acquire image and audio information of the user's surroundings. This enables real-time emotion estimation and situational awareness. The acquired data is immediately transmitted to the server.

[0488] The server analyzes transmitted image and audio information using emotion estimation means to estimate the worker's emotions with high accuracy. This process incorporates emotion analysis algorithms that utilize image recognition and natural language processing technologies. In addition, situation recognition means are used to identify the user's current location and surrounding environment, and to obtain information appropriate to the surrounding situation.

[0489] Next, the information generation system uses a language generation model to generate optimal work advice and action instructions based on estimated emotions and identified surrounding circumstances. This provides a beneficial and efficient work environment for the worker. The generated advice is presented in real time to the worker through the advice display system on the terminal.

[0490] For example, if the system determines that a factory worker is not concentrating on their work, it will generate and visually display advice such as "Take a short break" or "Try changing the order of your tasks." An example of a prompt message might be: "Generate the best advice for a worker who is tired. Current environmental data is a temperature of 25 degrees Celsius, humidity of 60%, and noise level of 80 decibels."

[0491] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0492] Step 1:

[0493] The device collects image and audio information from the user's surroundings in real time. Using the camera and microphone, it generates image and audio files from the acquired data. These are then sent to the server as a data stream.

[0494] Step 2:

[0495] The server processes image and audio files sent from the terminal using emotion estimation methods. It extracts facial features from image files using image processing algorithms and analyzes voice tone from audio files using speech recognition technology. Based on these analysis results, it quantifies and outputs the user's emotional state.

[0496] Step 3:

[0497] The server uses situational awareness to identify the user's current location and surrounding environment. It obtains location data using location services and collects environmental information about the user's surroundings. Based on this data, it analyzes the surrounding environment and outputs information about the user's work environment.

[0498] Step 4:

[0499] The server uses information generation means to utilize the emotional state obtained in step 2 and the surrounding situation information obtained in step 3 as input data. A generative AI model is then used to generate optimal work advice and action instructions based on this input data. In this generation process, the generative AI model forms various advice patterns based on prompt sentences and outputs them in text format.

[0500] Step 5:

[0501] The terminal visually displays the generated advice received from the server. It presents the advice clearly to the user via a display device, providing interaction that encourages them to act according to the advice. This display is designed to enhance user efficiency while maintaining a natural workflow.

[0502] 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.

[0503] This invention is a system that effectively supports communication using a device worn by the user, and is particularly characterized by its incorporation of an emotion engine. This system comprises emotion recognition means, environment recognition means, content generation means, and advice display means, and further integrates the emotion engine to analyze and utilize the emotions of both the user and the other party.

[0504] The device is implemented as AR glasses or other wearable devices and is equipped with a camera and microphone. The device first captures the other person's facial expressions and voice in real time, converts this data, and sends it to a server. This allows the system to constantly acquire information about the other person's emotions.

[0505] The server has emotion recognition capabilities to analyze received video and audio data, and uses deep learning technology to estimate emotions. It analyzes the state of joy, anger, sadness, and other emotions from facial expressions and voice, and in parallel builds a user emotion model based on this using an emotion engine. This emotion model learns the user's unique emotion patterns and is used in subsequent conversations.

[0506] Simultaneously, the terminal uses VPS technology to acquire surrounding geographical information and characteristics of the surrounding environment, and sends this information to the server as environmental data. This allows the entire system to understand the user's current location and its characteristics.

[0507] Based on this emotional and environmental information, the server uses a large-scale language model to generate conversation topics and behavioral advice. In this process, it can refer to the user's emotional model via the emotion engine to provide more personalized content. For example, if the user is feeling stressed, it will suggest topics that help them relax.

[0508] The device visually displays the final generated information and prompts the user for action. This facilitates a smoother conversation flow and helps build better communication.

[0509] For example, if a user is feeling nervous during a business meeting, the emotion engine will detect this and display advice on the device such as "advice on relaxing deep breathing" or "talking about a shared hobby with meeting participants." The user can then use this advice to ease the atmosphere. This invention allows users to not only receive information but also receive personalized support, thereby improving the quality of their communication.

[0510] The following describes the processing flow.

[0511] Step 1:

[0512] The device uses AR glasses worn by the user to capture surrounding video and audio in real time. It records the other person's facial expressions through the camera and collects audio with the microphone. The acquired data is immediately transmitted to the server.

[0513] Step 2:

[0514] The server performs facial recognition on the received video data and analyzes facial landmarks using emotion recognition technology. This allows it to detect subtle changes in the other person's facial expressions and generate emotion labels such as joy, anger, sadness, and happiness.

[0515] Step 3:

[0516] Similarly, the server analyzes the audio data and extracts speech features. It evaluates the tone, pitch, and speaking speed of the voice and uses this information to further reinforce the emotional state.

[0517] Step 4:

[0518] The terminal uses VPS technology to determine the user's current location and surrounding environment. The acquired geographical information is transmitted to an environmental recognition system to understand the surrounding landmarks and characteristics of the location.

[0519] Step 5:

[0520] The server integrates collected emotional and environmental information and uses an emotion engine to diagnose the user's emotional state. It then compares this with the user's past emotional history to build a individually tailored emotional model.

[0521] Step 6:

[0522] The server leverages a large-scale language model to generate personalized conversation topics and behavioral advice based on the user's emotion model. For example, if the user is feeling anxious, it will suggest small talk to help them calm down.

[0523] Step 7:

[0524] The generated advice is sent to the device and efficiently displayed within the user's field of view. This visual presentation allows users to quickly understand the information and immediately utilize it in subsequent interactions.

[0525] Step 8:

[0526] Based on the advice provided, users advance the conversation and improve the quality of communication. After the conversation ends, users provide feedback to the system, contributing to its further optimization.

[0527] (Example 2)

[0528] 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."

[0529] In modern communication, it is essential to appropriately understand the emotions of the person you are talking to and the surrounding environment, and to conduct the conversation accordingly. However, achieving this requires advanced emotion analysis and environmental awareness, making it difficult for users to engage in high-quality communication simply by receiving what the other person says. There is a need to improve this situation and provide personalized support that responds to the other person's emotions and environment in real time.

[0530] 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.

[0531] In this invention, the server includes emotion analysis means for receiving video and audio data acquired from the user's information processing device and estimating the emotions of others; environmental analysis means for identifying environmental data based on geographical data and surrounding conditions; content generation means for generating appropriate conversation topics and action instructions based on emotions and environmental data; and emotion engine means for integrating emotion engines to analyze emotions. This makes it possible to analyze the emotions of the user and the person they are talking to in real time and provide personalized support accordingly.

[0532] The term "user" refers to an individual or group that operates a device or technology.

[0533] "Information processing equipment" is a general term for electronic devices used to collect, transmit, and analyze data.

[0534] "Video data" refers to visual information acquired by visual sensors such as cameras.

[0535] "Audio data" refers to sound information acquired by acoustic sensors such as microphones.

[0536] "Emotional analysis means" refers to a technology or device for estimating another person's emotional state based on acquired data.

[0537] "Geographic data" refers to information about the user's location and the surrounding geographical characteristics.

[0538] "Surrounding circumstances" is a concept that includes information about the environment and conditions of the user's location.

[0539] "Environmental analysis means" refers to technologies or devices for identifying environmental data based on acquired geographical data and surrounding condition information.

[0540] "Content generation means" refers to a technology or device for generating appropriate conversation topics and action instructions using analyzed emotion data and environmental data.

[0541] An "emotion engine" is a technology or device used to analyze the emotions of users and others, and to build an emotion model based on that analysis.

[0542] This invention is a system that supports communication by acquiring and analyzing emotional and environmental data in real time via a device worn by the user. Specifically, it uses AR glasses or other wearable devices to acquire video and audio data through a camera and microphone. The device transmits this data to a server, which analyzes it to recognize emotions and the surrounding environment.

[0543] The server uses deep learning-based sentiment analysis to estimate the emotions of others from acquired data. Furthermore, environmental analysis identifies environmental data based on geographical data and surrounding conditions. Based on this information, the server uses a large-scale data model to generate optimal conversation topics and behavioral advice via content generation.

[0544] The generated information is visually displayed on the user's device, allowing the user to communicate more effectively. The emotion engine can learn from the user's past emotional data and build an emotion model that can be used in future interactions.

[0545] For example, if a user is feeling nervous during a business meeting, the device might offer information such as "advice on relaxing deep breathing" or "suggestions for conversations about shared hobbies with other participants." This system combines advanced sentiment analysis and environmental awareness to provide users with personalized communication support.

[0546] As an example of a prompt, using the question, "What conversation topics are effective when the user is feeling nervous?", the generative AI model generates appropriate advice. In this way, users can achieve smoother and higher-quality communication.

[0547] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0548] Step 1:

[0549] The device uses its camera and microphone to capture video and audio data of the person it is talking to in real time. The input consists of the other person's facial expressions and voice, which are converted into digital data. This digital data is temporarily stored on the device for later analysis.

[0550] Step 2:

[0551] The terminal transmits the collected video and audio data to the server via wireless communication. The input is the digital data acquired in step 1, and the output is the data received on the server for analysis. The terminal maintains real-time capabilities by performing high-speed and stable data transmission.

[0552] Step 3:

[0553] The server analyzes the received video and audio data using emotion analysis tools. The input is the data received in step 2, and the output is information about the identified emotional state of another person. The server uses a deep learning model to identify each emotion (joy, anger, sadness, pleasure) and sends the analysis results to the emotion engine.

[0554] Step 4:

[0555] Simultaneously, the device utilizes VPS technology to acquire geographical data and environmental characteristics of the user's surroundings. The input is sensor information from the device, and the output is environmental data for the identified user. This data reflects the user's location and the surrounding sound and light conditions.

[0556] Step 5:

[0557] The terminal sends the acquired geographical data and environmental characteristics to the server. The input is the environmental data from step 4, and the output is the data received for processing on the server. The server analyzes this data to understand the details of the environment.

[0558] Step 6:

[0559] The server integrates sentiment data and environmental data and uses content generation tools to generate conversation topics and behavioral advice. The input is the output results from steps 3 and 5, and the output is optimized content to be provided to the user. The server uses a generative AI model to refine and personalize the generated advice with a sentiment engine.

[0560] Step 7:

[0561] The device displays the final generated content to the user in a visual format. The input is the content generated in step 6, and the output is information that can be visually interpreted by the user. For example, the display can show advice or conversation topics that the user can use in actual communication.

[0562] (Application Example 2)

[0563] 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."

[0564] In today's commercial spaces, increasing customer satisfaction requires more than just providing products and services; it demands personalized service that addresses individual needs and emotions. However, traditional customer service has struggled to accurately grasp customers' emotions and respond appropriately on an immediate basis. Therefore, there is a need for a system that can flexibly respond to different emotional states and environments of customers and effectively support customer service.

[0565] 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.

[0566] In this invention, the server includes emotion recognition means that receive video and audio information acquired from the user's device and estimate the emotions of others based on that information; environment recognition means that identify environmental information based on the user's current location and surrounding information acquired from the user's device; and content generation means that use a language model to generate optimal dialogue topics and behavioral advice based on the estimated emotions and identified environmental information. This enables flexible and precise customer service that is in line with the customer's emotions.

[0567] "User's device" refers to a terminal device used for acquiring and displaying data, and includes smart glasses and other wearable devices.

[0568] "Visual information" refers to visual data acquired through a camera, and is primarily used to analyze the facial expressions of others.

[0569] "Audio information" refers to sound data acquired through a microphone, which is used to analyze other people's voices for emotion estimation.

[0570] "Emotion recognition means" refers to a technical function that estimates the emotions of others based on video and audio information, and is mainly realized through deep learning technology.

[0571] "Environmental information" refers to data about the user's current location and surrounding environment, and is used to provide feedback in a specific context.

[0572] "Environmental recognition means" refers to a function that identifies the user's current location and surrounding conditions based on information from the user's device.

[0573] A "language model" refers to an algorithm that uses natural language processing technology to generate optimal dialogue based on emotional and environmental information.

[0574] A "dialogue topic" is a topic suggested in the generated language content to enable users to have natural conversations with others.

[0575] "Behavioral advice" refers to suggestions regarding actions that users should follow to achieve better communication.

[0576] The system that realizes this invention is operated primarily through smart glasses worn by the user. The device has a built-in camera and microphone, which allow it to acquire video and audio information in real time. The device has the function to transmit this data to a server. The server uses emotion recognition means to analyze and estimate the emotions of others from the received video information using deep learning technology. Specifically, it estimates emotions from facial expressions and voice using APIs such as Microsoft's Face API and Google's Speech-to-Text.

[0577] Next, the server uses environmental recognition means to identify environmental information based on the user's current location and surrounding conditions obtained from their smart glasses. For example, by using VPS technology, it can grasp detailed location information and understand the physical characteristics of the surroundings.

[0578] Furthermore, the server uses a language model to generate optimal dialogue topics and behavioral advice based on received emotional and environmental information. In this process, a generative AI model such as OpenAI GPT-3 is used to create personalized content that reflects the user's individual emotional patterns.

[0579] The generated content is displayed visually on the device's display, providing users with advice on specific customer service methods and conversation flow. For example, if a store detects that a customer has a stern expression, the smart glasses might display "Ask if they have any questions about the products." This allows users to respond flexibly to the situation.

[0580] An example of a prompt message is: "Provide advice to display when the customer's expression is stern. The options should be friendly and stress-reducing."

[0581] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0582] Step 1:

[0583] The device acquires real-time video and audio information of the customer through its camera and microphone. This information, including the customer's facial expressions and voice, is sent to the server as input data for estimating their emotions.

[0584] Step 2:

[0585] The server analyzes the received video and audio information using emotion recognition technology. Specifically, it analyzes facial expression data using Microsoft's Face API and estimates emotions from audio data using Google's Speech-to-Text. This identifies the customer's emotional state and outputs it as emotion parameters.

[0586] Step 3:

[0587] The server uses environmental recognition capabilities to identify environmental information based on the current location information and surrounding conditions received from the terminal. Utilizing VPS technology, it understands the physical characteristics of the space where the user is located and outputs data related to those characteristics.

[0588] Step 4:

[0589] The server inputs estimated emotion parameters and identified environmental information into a language model. At this time, it uses a generative AI model such as OpenAI GPT-3 to generate optimal dialogue topics and behavioral advice. It determines what to provide to the user in the form of prompt statements and outputs personalized content.

[0590] Step 5:

[0591] The generated dialogue topics and behavioral advice are visually displayed on the terminal's display device. Users can review the presented information and utilize it in actual customer interactions. This creates opportunities to improve the quality of service and increase customer satisfaction.

[0592] 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.

[0593] 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.

[0594] 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.

[0595] [Fourth Embodiment]

[0596] Figure 7 shows an example of the configuration of the data processing system 410 according to the fourth embodiment.

[0597] 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.

[0598] 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).

[0599] 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.

[0600] 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.

[0601] 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).

[0602] 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.

[0603] 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.

[0604] 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.

[0605] 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.

[0606] 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.

[0607] 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.

[0608] 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".

[0609] The system of the present invention provides support in communication scenarios using a terminal worn by the user. This system provides effective information through multiple components, including emotion recognition means, environment recognition means, content generation means, and advice display means. Each component is described in detail below.

[0610] First, the terminal is a wearable device, such as AR glasses, worn by the user, and is equipped with a camera and microphone. This terminal is responsible for capturing the other person's facial expressions and voice in real time and sending this data to a server. This allows for the rapid and continuous detection of the other person's speech and changes in facial expressions.

[0611] Next, the server performs digital processing using emotion recognition means based on the video and audio data transmitted from the terminal. Specifically, it extracts facial features from the facial image and estimates multiple emotion labels such as joy, surprise, and boredom. Simultaneously, it also analyzes the audio to grasp the nuances of emotion from the tone and volume of the voice.

[0612] Simultaneously, the device uses environmental recognition to acquire information about the user's current location and major landmarks in the surrounding area. For example, if the user is on a date, it identifies nearby restaurants and tourist attractions; if the user is in business, it identifies information about buildings and conference rooms, and sends this information to the server. This information is used as supplementary information for the conversation.

[0613] By integrating this emotional data and environmental information, the server utilizes a large-scale language model to generate content. Based on the other party's current emotions and location, it generates appropriate conversation topics and behavioral advice suitable for the situation, and sends it to the user's device.

[0614] Finally, the device uses an advice display mechanism to visually show the generated advice and topics to the user. For example, during a conversation, advice such as "It would be good to talk about recent news" might be displayed, allowing the user to continue the conversation smoothly.

[0615] As a concrete example, consider a scenario where a user is on a date at a cafe and their date shows signs of boredom. The device instantly captures this expression, and the server recognizes it as "boredom." The server analyzes this and automatically generates and sends advice, such as "bring up the topic of a popular new restaurant that recently opened nearby." The user can then use this information to revitalize the conversation with their date.

[0616] This invention enables users to receive specific conversational support based on emotion recognition and environmental information, thereby facilitating effective communication.

[0617] The following describes the processing flow.

[0618] Step 1:

[0619] The device captures the other person's face with the AR glasses' camera and collects audio data with the microphone. The collected video and audio data is compressed in real time and sent to the server.

[0620] Step 2:

[0621] The server performs facial recognition from the received video data. Specifically, it detects facial landmarks (eyes, mouth, eyebrows, etc.) and analyzes the overall facial expression based on these. In addition, it extracts audio features from the audio data and evaluates the tone and speed of the voice.

[0622] Step 3:

[0623] The server estimates emotions based on facial expressions and voice characteristics. Using a deep learning model, it identifies emotion labels such as joy, surprise, and boredom. This information, along with historical data, is stored as a user-specific emotion pattern.

[0624] Step 4:

[0625] The device analyzes its current location information and surrounding video using a VPS to identify landmarks and buildings. It then extracts environmental information and sends it to the server.

[0626] Step 5:

[0627] The server integrates received environmental information and sentiment data, and uses a large-scale language model to generate appropriate conversation topics and advice. Past conversation logs are also referenced in this process.

[0628] Step 6:

[0629] The generated conversation topics and advice are sent to the terminal in short text format. The terminal then displays them appropriately in the user's field of view.

[0630] Step 7:

[0631] The user takes the advice into consideration, continues the conversation, and observes the other person's reactions. If necessary, they return to step 1 and repeat the process.

[0632] Step 8:

[0633] After the conversation ends, the user provides feedback to the system. The server receives this feedback and uses it as training data to improve the accuracy of sentiment estimation and advice generation.

[0634] (Example 1)

[0635] 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".

[0636] In modern social settings, individuals face the challenge of generating appropriate conversations that are responsive to the other person's emotions and the surrounding environment. Finding the right timing to naturally advance conversation within diverse social interactions is also a challenge. This can sometimes lead to interactions not proceeding smoothly.

[0637] 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.

[0638] In this invention, the server includes information processing means for receiving video and audio data acquired from the user's device and estimating the other party's emotions based on that data; information recognition means for identifying environmental information based on location data and surrounding information acquired from the user's device; and information generation means for generating optimal topics and behavioral advice using a large-scale language model based on the estimated emotions and identified environmental information. This enables the user to engage in natural conversations that are appropriate to the other party's emotions and environment, and to facilitate smooth communication.

[0639] "User's device" refers to a terminal device that a user wears or operates to input video and audio data.

[0640] "Video and audio data" refers to digital data of visual and audio information acquired through the user's device.

[0641] "Information processing means" refers to means of analyzing received video and audio data and performing calculations and analyses to estimate the emotions of the other party.

[0642] "Location data and surrounding information" refers to geographical and physical information related to the user's current location, which is acquired through the device.

[0643] "Information recognition means" refers to means for analyzing location data and surrounding information to extract specific environmental information.

[0644] "Environmental information" refers to data about the user's current location and surroundings, which functions as background and supplementary information for conversations.

[0645] A "large-scale language model" is a model that learns from a large amount of language data and generates diverse conversation topics and texts.

[0646] An "information generation method" is a means of generating optimal topics and behavioral advice based on estimated emotions and identified environmental information.

[0647] "Information display means" refers to a display device or method for visually presenting generated topics or advice to a user.

[0648] The embodiment of this invention primarily uses a system in which a terminal and a server work together. The user wears a wearable device, such as AR glasses equipped with a camera and microphone, which functions as the terminal. This terminal captures the facial expressions and voices of people within the user's field of view in real time and transmits them to the server via a communication network.

[0649] The server processes information based on the received video and audio data. Specifically, it uses image recognition software to analyze the facial features of the other person and estimate various emotions from their expressions. Furthermore, it uses speech recognition technology to analyze the tone and volume of the voice and grasp the nuances of emotion. The terminal also acquires location data and surrounding information using GPS and nearby Wi-Fi signals, and provides this information to the server as well.

[0650] The server uses a large-scale language model to generate optimal conversation topics and behavioral advice based on estimated sentiment data and environmental information. This process involves feeding prompt sentences into the generative AI model. An example of a prompt sentence might be: "Generate advice to liven up the conversation based on the user's current situation. For example, if the user is on a date at a cafe and their date seems bored, suggest some topics to bring up."

[0651] Ultimately, the device visually displays topics and advice received from the server in an easy-to-understand format for the user. This allows users to engage in natural conversations and make informed choices based on the situation. For example, if a user is on a date at a cafe, the system can provide appropriate small talk topics and information about nearby places that might be relevant, based on the other person's facial expressions. In this way, the system provides a mechanism to enhance the user's interaction experience.

[0652] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0653] Step 1:

[0654] The device uses the camera and microphone of the AR glasses being worn to capture the other person's facial expressions and voice in real time. It receives video and audio signals captured through the camera and microphone as input. These signals are processed as data, converted into image and audio data, and output.

[0655] Step 2:

[0656] The terminal transmits the acquired image and audio data to the server via the network. Data compression and encryption may be performed during transmission. The input is the image and audio data generated in step 1, and the output is the transmission of data to the server.

[0657] Step 3:

[0658] The server analyzes the image data received from the terminal. Using image processing algorithms, it extracts facial features and estimates emotion labels (such as joy, surprise, or boredom). The input is image data sent from the terminal, and the output is a set of emotion labels.

[0659] Step 4:

[0660] Simultaneously, the server analyzes the audio data, using speech recognition technology to analyze the tone and volume of the voice and grasp the nuances of emotion. The input is the audio data transmitted from the terminal, and the output is an emotion index based on the voice.

[0661] Step 5:

[0662] The device acquires location data and surrounding information from GPS and Wi-Fi information, and transmits this data to the server. The input is data obtained from location sensors, and the output is the transmission of location data and surrounding information to the server.

[0663] Step 6:

[0664] The server integrates received sentiment data and environmental information, and uses a generative AI model to generate optimal conversation topics and behavioral advice. This process uses the prompt, "Generate advice to liven up the conversation based on the user's current situation." The input is sentiment labels and environmental information, and the output is the generated conversation topics and advice.

[0665] Step 7:

[0666] Ultimately, the terminal visually displays the advice sent from the server, allowing the user to review it. The input is the advice data from the server, and the output is the display of information on the user interface. This step helps the user to move the conversation forward at the appropriate time.

[0667] (Application Example 1)

[0668] 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".

[0669] In the work performed by workers, there is a need for a means to quickly and accurately provide appropriate work advice tailored to the individual worker's emotions and surrounding circumstances. However, conventional methods have made it difficult to estimate emotions in real time or identify environmental conditions, making it difficult to improve work efficiency and worker satisfaction. Therefore, the present invention aims to provide a device that accurately grasps the worker's emotions and surrounding circumstances and provides optimal work advice based on that.

[0670] 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.

[0671] In this invention, the server includes emotion estimation means that receives image and audio information acquired from the user's terminal and estimates the emotions of others based on this information; situation recognition means that identifies the surrounding situation based on the current location and surrounding conditions acquired from the user's terminal; and information generation means that generates optimal work advice or action instructions using a language generation model based on the estimated emotions and identified surrounding conditions. This makes it possible to provide optimal advice in real time according to the worker's emotions and surrounding conditions.

[0672] "Emotion estimation means" is a technology that estimates the emotions of others, taking into account various possibilities, based on image and audio information acquired from the user's device.

[0673] "Situation recognition means" refers to a technology that uses the user's current location and surrounding situation information sent from their terminal to identify the surrounding situation in real time.

[0674] "Information generation means" refers to a technology that uses language generation models to create optimal work advice and behavioral instructions based on estimated emotions and identified surrounding circumstances.

[0675] An "advice display means" is a device or technology that visually presents generated work advice or action instructions to the worker in an easily understandable manner.

[0676] "Reaction processing means" refers to a technology that analyzes the reactions received from workers and uses that analysis to improve the accuracy of information generation means.

[0677] A "language generation model" is an artificial intelligence model that generates diverse texts and information based on large amounts of data.

[0678] A system for implementing this invention requires a user-worn terminal and a server connected to it. The terminal is equipped with a camera and microphone to acquire image and audio information of the user's surroundings. This enables real-time emotion estimation and situational awareness. The acquired data is immediately transmitted to the server.

[0679] The server analyzes transmitted image and audio information using emotion estimation means to estimate the worker's emotions with high accuracy. This process incorporates emotion analysis algorithms that utilize image recognition and natural language processing technologies. In addition, situation recognition means are used to identify the user's current location and surrounding environment, and to obtain information appropriate to the surrounding situation.

[0680] Next, the information generation system uses a language generation model to generate optimal work advice and action instructions based on estimated emotions and identified surrounding circumstances. This provides a beneficial and efficient work environment for the worker. The generated advice is presented in real time to the worker through the advice display system on the terminal.

[0681] For example, if the system determines that a factory worker is not concentrating on their work, it will generate and visually display advice such as "Take a short break" or "Try changing the order of your tasks." An example of a prompt message might be: "Generate the best advice for a worker who is tired. Current environmental data is a temperature of 25 degrees Celsius, humidity of 60%, and noise level of 80 decibels."

[0682] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0683] Step 1:

[0684] The device collects image and audio information from the user's surroundings in real time. Using the camera and microphone, it generates image and audio files from the acquired data. These are then sent to the server as a data stream.

[0685] Step 2:

[0686] The server processes image and audio files sent from the terminal using emotion estimation methods. It extracts facial features from image files using image processing algorithms and analyzes voice tone from audio files using speech recognition technology. Based on these analysis results, it quantifies and outputs the user's emotional state.

[0687] Step 3:

[0688] The server uses situational awareness to identify the user's current location and surrounding environment. It obtains location data using location services and collects environmental information about the user's surroundings. Based on this data, it analyzes the surrounding environment and outputs information about the user's work environment.

[0689] Step 4:

[0690] The server uses information generation means to utilize the emotional state obtained in step 2 and the surrounding situation information obtained in step 3 as input data. A generative AI model is then used to generate optimal work advice and action instructions based on this input data. In this generation process, the generative AI model forms various advice patterns based on prompt sentences and outputs them in text format.

[0691] Step 5:

[0692] The terminal visually displays the generated advice received from the server. It presents the advice clearly to the user via a display device, providing interaction that encourages them to act according to the advice. This display is designed to enhance user efficiency while maintaining a natural workflow.

[0693] 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.

[0694] This invention is a system that effectively supports communication using a device worn by the user, and is particularly characterized by its incorporation of an emotion engine. This system comprises emotion recognition means, environment recognition means, content generation means, and advice display means, and further integrates the emotion engine to analyze and utilize the emotions of both the user and the other party.

[0695] The device is implemented as AR glasses or other wearable devices and is equipped with a camera and microphone. The device first captures the other person's facial expressions and voice in real time, converts this data, and sends it to a server. This allows the system to constantly acquire information about the other person's emotions.

[0696] The server has emotion recognition capabilities to analyze received video and audio data, and uses deep learning technology to estimate emotions. It analyzes the state of joy, anger, sadness, and other emotions from facial expressions and voice, and in parallel builds a user emotion model based on this using an emotion engine. This emotion model learns the user's unique emotion patterns and is used in subsequent conversations.

[0697] Simultaneously, the terminal uses VPS technology to acquire surrounding geographical information and characteristics of the surrounding environment, and sends this information to the server as environmental data. This allows the entire system to understand the user's current location and its characteristics.

[0698] Based on this emotional and environmental information, the server uses a large-scale language model to generate conversation topics and behavioral advice. In this process, it can refer to the user's emotional model via the emotion engine to provide more personalized content. For example, if the user is feeling stressed, it will suggest topics that help them relax.

[0699] The device visually displays the final generated information and prompts the user for action. This facilitates a smoother conversation flow and helps build better communication.

[0700] For example, if a user is feeling nervous during a business meeting, the emotion engine will detect this and display advice on the device such as "advice on relaxing deep breathing" or "talking about a shared hobby with meeting participants." The user can then use this advice to ease the atmosphere. This invention allows users to not only receive information but also receive personalized support, thereby improving the quality of their communication.

[0701] The following describes the processing flow.

[0702] Step 1:

[0703] The device uses AR glasses worn by the user to capture surrounding video and audio in real time. It records the other person's facial expressions through the camera and collects audio with the microphone. The acquired data is immediately transmitted to the server.

[0704] Step 2:

[0705] The server performs facial recognition on the received video data and analyzes facial landmarks using emotion recognition technology. This allows it to detect subtle changes in the other person's facial expressions and generate emotion labels such as joy, anger, sadness, and happiness.

[0706] Step 3:

[0707] Similarly, the server analyzes the audio data and extracts speech features. It evaluates the tone, pitch, and speaking speed of the voice and uses this information to further reinforce the emotional state.

[0708] Step 4:

[0709] The terminal uses VPS technology to determine the user's current location and surrounding environment. The acquired geographical information is transmitted to an environmental recognition system to understand the surrounding landmarks and characteristics of the location.

[0710] Step 5:

[0711] The server integrates collected emotional and environmental information and uses an emotion engine to diagnose the user's emotional state. It then compares this with the user's past emotional history to build a individually tailored emotional model.

[0712] Step 6:

[0713] The server leverages a large-scale language model to generate personalized conversation topics and behavioral advice based on the user's emotion model. For example, if the user is feeling anxious, it will suggest small talk to help them calm down.

[0714] Step 7:

[0715] The generated advice is sent to the device and efficiently displayed within the user's field of view. This visual presentation allows users to quickly understand the information and immediately utilize it in subsequent interactions.

[0716] Step 8:

[0717] Based on the advice provided, users advance the conversation and improve the quality of communication. After the conversation ends, users provide feedback to the system, contributing to its further optimization.

[0718] (Example 2)

[0719] 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".

[0720] In modern communication, it is essential to appropriately understand the emotions of the person you are talking to and the surrounding environment, and to conduct the conversation accordingly. However, achieving this requires advanced emotion analysis and environmental awareness, making it difficult for users to engage in high-quality communication simply by receiving what the other person says. There is a need to improve this situation and provide personalized support that responds to the other person's emotions and environment in real time.

[0721] 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.

[0722] In this invention, the server includes emotion analysis means for receiving video and audio data acquired from the user's information processing device and estimating the emotions of others; environmental analysis means for identifying environmental data based on geographical data and surrounding conditions; content generation means for generating appropriate conversation topics and action instructions based on emotions and environmental data; and emotion engine means for integrating emotion engines to analyze emotions. This makes it possible to analyze the emotions of the user and the person they are talking to in real time and provide personalized support accordingly.

[0723] The term "user" refers to an individual or group that operates a device or technology.

[0724] "Information processing equipment" is a general term for electronic devices used to collect, transmit, and analyze data.

[0725] "Video data" refers to visual information acquired by visual sensors such as cameras.

[0726] "Audio data" refers to sound information acquired by acoustic sensors such as microphones.

[0727] "Emotional analysis means" refers to a technology or device for estimating another person's emotional state based on acquired data.

[0728] "Geographic data" refers to information about the user's location and the surrounding geographical characteristics.

[0729] "Surrounding circumstances" is a concept that includes information about the environment and conditions of the user's location.

[0730] "Environmental analysis means" refers to technologies or devices for identifying environmental data based on acquired geographical data and surrounding condition information.

[0731] "Content generation means" refers to a technology or device for generating appropriate conversation topics and action instructions using analyzed emotion data and environmental data.

[0732] An "emotion engine" is a technology or device used to analyze the emotions of users and others, and to build an emotion model based on that analysis.

[0733] This invention is a system that supports communication by acquiring and analyzing emotional and environmental data in real time via a device worn by the user. Specifically, it uses AR glasses or other wearable devices to acquire video and audio data through a camera and microphone. The device transmits this data to a server, which analyzes it to recognize emotions and the surrounding environment.

[0734] The server uses deep learning-based sentiment analysis to estimate the emotions of others from acquired data. Furthermore, environmental analysis identifies environmental data based on geographical data and surrounding conditions. Based on this information, the server uses a large-scale data model to generate optimal conversation topics and behavioral advice via content generation.

[0735] The generated information is visually displayed on the user's device, allowing the user to communicate more effectively. The emotion engine can learn from the user's past emotional data and build an emotion model that can be used in future interactions.

[0736] For example, if a user is feeling nervous during a business meeting, the device might offer information such as "advice on relaxing deep breathing" or "suggestions for conversations about shared hobbies with other participants." This system combines advanced sentiment analysis and environmental awareness to provide users with personalized communication support.

[0737] As an example of a prompt, using the question, "What conversation topics are effective when the user is feeling nervous?", the generative AI model generates appropriate advice. In this way, users can achieve smoother and higher-quality communication.

[0738] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0739] Step 1:

[0740] The device uses its camera and microphone to capture video and audio data of the person it is talking to in real time. The input consists of the other person's facial expressions and voice, which are converted into digital data. This digital data is temporarily stored on the device for later analysis.

[0741] Step 2:

[0742] The terminal transmits the collected video and audio data to the server via wireless communication. The input is the digital data acquired in step 1, and the output is the data received on the server for analysis. The terminal maintains real-time capabilities by performing high-speed and stable data transmission.

[0743] Step 3:

[0744] The server analyzes the received video and audio data using emotion analysis tools. The input is the data received in step 2, and the output is information about the identified emotional state of another person. The server uses a deep learning model to identify each emotion (joy, anger, sadness, pleasure) and sends the analysis results to the emotion engine.

[0745] Step 4:

[0746] Simultaneously, the device utilizes VPS technology to acquire geographical data and environmental characteristics of the user's surroundings. The input is sensor information from the device, and the output is environmental data for the identified user. This data reflects the user's location and the surrounding sound and light conditions.

[0747] Step 5:

[0748] The terminal sends the acquired geographical data and environmental characteristics to the server. The input is the environmental data from step 4, and the output is the data received for processing on the server. The server analyzes this data to understand the details of the environment.

[0749] Step 6:

[0750] The server integrates sentiment data and environmental data and uses content generation tools to generate conversation topics and behavioral advice. The input is the output results from steps 3 and 5, and the output is optimized content to be provided to the user. The server uses a generative AI model to refine and personalize the generated advice with a sentiment engine.

[0751] Step 7:

[0752] The device displays the final generated content to the user in a visual format. The input is the content generated in step 6, and the output is information that can be visually interpreted by the user. For example, the display can show advice or conversation topics that the user can use in actual communication.

[0753] (Application Example 2)

[0754] 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".

[0755] In today's commercial spaces, increasing customer satisfaction requires more than just providing products and services; it demands personalized service that addresses individual needs and emotions. However, traditional customer service has struggled to accurately grasp customers' emotions and respond appropriately on an immediate basis. Therefore, there is a need for a system that can flexibly respond to different emotional states and environments of customers and effectively support customer service.

[0756] 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.

[0757] In this invention, the server includes emotion recognition means that receive video and audio information acquired from the user's device and estimate the emotions of others based on that information; environment recognition means that identify environmental information based on the user's current location and surrounding information acquired from the user's device; and content generation means that use a language model to generate optimal dialogue topics and behavioral advice based on the estimated emotions and identified environmental information. This enables flexible and precise customer service that is in line with the customer's emotions.

[0758] "User's device" refers to a terminal device used for acquiring and displaying data, and includes smart glasses and other wearable devices.

[0759] "Visual information" refers to visual data acquired through a camera, and is primarily used to analyze the facial expressions of others.

[0760] "Audio information" refers to sound data acquired through a microphone, which is used to analyze other people's voices for emotion estimation.

[0761] "Emotion recognition means" refers to a technical function that estimates the emotions of others based on video and audio information, and is mainly realized through deep learning technology.

[0762] "Environmental information" refers to data about the user's current location and surrounding environment, and is used to provide feedback in a specific context.

[0763] "Environmental recognition means" refers to a function that identifies the user's current location and surrounding conditions based on information from the user's device.

[0764] A "language model" refers to an algorithm that uses natural language processing technology to generate optimal dialogue based on emotional and environmental information.

[0765] A "dialogue topic" is a topic suggested in the generated language content to enable users to have natural conversations with others.

[0766] "Behavioral advice" refers to suggestions regarding actions that users should follow to achieve better communication.

[0767] The system that realizes this invention is operated primarily through smart glasses worn by the user. The device has a built-in camera and microphone, which allow it to acquire video and audio information in real time. The device has the function to transmit this data to a server. The server uses emotion recognition means to analyze and estimate the emotions of others from the received video information using deep learning technology. Specifically, it estimates emotions from facial expressions and voice using APIs such as Microsoft's Face API and Google's Speech-to-Text.

[0768] Next, the server uses environmental recognition means to identify environmental information based on the user's current location and surrounding conditions obtained from their smart glasses. For example, by using VPS technology, it can grasp detailed location information and understand the physical characteristics of the surroundings.

[0769] Furthermore, the server uses a language model to generate optimal dialogue topics and behavioral advice based on received emotional and environmental information. In this process, a generative AI model such as OpenAI GPT-3 is used to create personalized content that reflects the user's individual emotional patterns.

[0770] The generated content is displayed visually on the device's display, providing users with advice on specific customer service methods and conversation flow. For example, if a store detects that a customer has a stern expression, the smart glasses might display "Ask if they have any questions about the products." This allows users to respond flexibly to the situation.

[0771] An example of a prompt message is: "Provide advice to display when the customer's expression is stern. The options should be friendly and stress-reducing."

[0772] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0773] Step 1:

[0774] The device acquires real-time video and audio information of the customer through its camera and microphone. This information, including the customer's facial expressions and voice, is sent to the server as input data for estimating their emotions.

[0775] Step 2:

[0776] The server analyzes the received video and audio information using emotion recognition technology. Specifically, it analyzes facial expression data using Microsoft's Face API and estimates emotions from audio data using Google's Speech-to-Text. This identifies the customer's emotional state and outputs it as emotion parameters.

[0777] Step 3:

[0778] The server uses environmental recognition capabilities to identify environmental information based on the current location information and surrounding conditions received from the terminal. Utilizing VPS technology, it understands the physical characteristics of the space where the user is located and outputs data related to those characteristics.

[0779] Step 4:

[0780] The server inputs estimated emotion parameters and identified environmental information into a language model. At this time, it uses a generative AI model such as OpenAI GPT-3 to generate optimal dialogue topics and behavioral advice. It determines what to provide to the user in the form of prompt statements and outputs personalized content.

[0781] Step 5:

[0782] The generated dialogue topics and behavioral advice are visually displayed on the terminal's display device. Users can review the presented information and utilize it in actual customer interactions. This creates opportunities to improve the quality of service and increase customer satisfaction.

[0783] 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.

[0784] 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.

[0785] In the above embodiment, an example was given in which the specific processing is performed by the data processing device 12, but the technology of this disclosure is not limited thereto, and the specific processing may also be performed by the robot 414.

[0786] 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.

[0787] 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. In the upper and lower directions of the concentric circles, emotions that are generally generated from reactions occurring in the brain and induced by situational judgment are located. Also, the upper side of the concentric circles is where "pleasant" emotions are located, and the lower side is where "unpleasant" emotions are located. In this way, 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.

[0788] 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.

[0789] 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.

[0790] 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.

[0791] 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."

[0792] 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.

[0793] 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.

[0794] 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.

[0795] 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.

[0796] 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.

[0797] 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.

[0798] 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.

[0799] 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.

[0800] 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.

[0801] 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.

[0802] 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.

[0803] 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 to be incorporated by reference.

[0804] The following is further disclosed regarding the embodiments described above.

[0805] (Claim 1)

[0806] An emotion recognition means that receives video and audio data acquired from the user's device and estimates the other party's emotions based on said data,

[0807] An environmental recognition means that identifies environmental information based on the current location and surrounding information acquired from the user's device,

[0808] A content generation method that uses a large-scale language model to generate optimal conversation topics and behavioral advice based on estimated emotions and identified environmental information,

[0809] An advice display means that visually outputs the generated information to the user's display device,

[0810] A system that includes this.

[0811] (Claim 2)

[0812] The system according to claim 1, further comprising a feedback processing means for receiving user feedback and processing said feedback to improve the accuracy of the content generation means.

[0813] (Claim 3)

[0814] The system according to claim 1, which includes instructions indicating the timing for displaying generated information in order to maintain a natural flow of conversation.

[0815] "Example 1"

[0816] (Claim 1)

[0817] Information processing means that receives video data and audio data acquired from the user's device and estimates the other party's emotions based on said data,

[0818] An information recognition means that identifies environmental information based on location data and surrounding information acquired from the user's device,

[0819] An information generation means that generates optimal topics and behavioral advice using a large-scale language model based on estimated emotions and identified environmental information,

[0820] Information display means that visually outputs the generated information to the user's display device,

[0821] A system that includes this.

[0822] (Claim 2)

[0823] The system according to claim 1, comprising information processing means for receiving data from a user and processing said data to improve the accuracy of the information generation means.

[0824] (Claim 3)

[0825] The system according to claim 1, including instructions for maintaining a natural flow of information when displaying generated information.

[0826] "Application Example 1"

[0827] (Claim 1)

[0828] An emotion estimation means that receives image and audio information acquired from the user's terminal and estimates the emotions of others based on that information,

[0829] A situation recognition means that identifies the surrounding situation based on the current location and surrounding conditions obtained from the user's terminal,

[0830] Information generation means that generates optimal work advice or action instructions using a language generation model based on estimated emotions and identified surrounding circumstances,

[0831] An advice display means that visually outputs the generated information to the worker's display device,

[0832] A device that includes this.

[0833] (Claim 2)

[0834] The apparatus according to claim 1, comprising a reaction processing means that receives a response from an operator, processes the response, and reflects it in improving the accuracy of the information generation means.

[0835] (Claim 3)

[0836] The apparatus according to claim 1, which includes instructions indicating the timing for displaying generated information in order to maintain a natural workflow.

[0837] "Example 2 of combining an emotion engine"

[0838] (Claim 1)

[0839] An emotion analysis means that receives video data and audio data acquired from a user's information processing device and estimates the emotions of others based on said data,

[0840] An environmental analysis means that identifies environmental data based on geographical data and surrounding conditions acquired from the user's information processing device,

[0841] A content generation means that generates appropriate conversation topics and action instructions using a large-scale data model based on estimated emotions and identified environmental data,

[0842] An instruction display means that visually outputs the generated information to the user's display device,

[0843] An emotion engine means that integrates emotion engines to analyze the emotions of the user and others, learns the user's emotion patterns, and utilizes them in subsequent interactions,

[0844] A system that includes this.

[0845] (Claim 2)

[0846] The system according to claim 1, comprising a feedback processing means that receives feedback from users, processes the feedback, and reflects it in improving the accuracy of the content generation means, thereby updating the user's emotional model.

[0847] (Claim 3)

[0848] The system according to claim 1, which includes instructions indicating the timing for displaying generated information in order to maintain a natural flow of conversation, and personalizes the information according to the user's emotional state.

[0849] "Application example 2 when combining with an emotional engine"

[0850] (Claim 1)

[0851] An emotion recognition means that receives video and audio information acquired from the user's device and estimates the emotions of others based on that information,

[0852] An environmental recognition means that identifies environmental information based on the current location and surrounding information acquired from the user's device,

[0853] A content generation method that uses a language model to generate optimal dialogue topics and behavioral advice based on estimated emotions and identified environmental information,

[0854] An advisory display means that visually outputs the generated information to the user's display device,

[0855] A means of analyzing the emotions of others within a specific space and providing behavioral advice to improve the quality of customer service,

[0856] A system that includes this.

[0857] (Claim 2)

[0858] The system according to claim 1, further comprising an evaluation processing means for receiving user evaluations, processing those evaluations, and reflecting them in improving the performance of the content generation means.

[0859] (Claim 3)

[0860] The system according to claim 1, which includes instructions indicating when to display the generated information in order to maintain a natural flow of dialogue. [Explanation of Symbols]

[0861] 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. An emotion recognition means that receives video and audio data acquired from the user's device and estimates the other party's emotions based on said data, An environmental recognition means that identifies environmental information based on the current location and surrounding information acquired from the user's device, A content generation method that uses a large-scale language model to generate optimal conversation topics and behavioral advice based on estimated emotions and identified environmental information, An advice display means that visually outputs the generated information to the user's display device, A system that includes this.

2. The system according to claim 1, further comprising a feedback processing means for receiving user feedback and processing said feedback to improve the accuracy of the content generation means.

3. The system according to claim 1, which includes instructions indicating the timing for displaying generated information in order to maintain a natural flow of conversation.

Images