System

Abstract

To provide a system capable of providing an interface which allows a user to interact with a large-scale language model using voice.SOLUTION: A system according to an embodiment comprises a display unit, an acceptance unit, a generation unit, and an output unit. The display unit displays a user interface through which information can be input to a large-scale language model on a wearable device. The acceptance unit accepts voice from a user. The generation unit generates a response corresponding to the voice accepted by the acceptance unit by inputting the voice into the large-scale language model. The output unit outputs the response generated by the generation unit to the wearable device.SELECTED DRAWING: Figure 1

Description

[Technical field]

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

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

[0003] [Patent Document 1] JP 2022-180282 A Summary of the Invention [Problem to be solved by the invention]

[0004] Conventional technologies have not provided a sufficient interface for users to interact with large-scale language models through voice, and have had the problem of lacking convenience.

[0005] The system according to the embodiment aims to provide an interface that allows users to interact with large-scale language models through speech. [Means for solving the problem]

[0006] A system according to an embodiment includes a display unit, a reception unit, a generation unit, and an output unit. The display unit displays a user interface on a wearable device that allows information to be input to the large-scale language model. The reception unit receives speech from a user. The generation unit inputs the speech received by the reception unit into the large-scale language model, thereby generating a response corresponding to the speech. The output unit outputs the response generated by the generation unit to the wearable device. Effect of the Invention

[0007] An embodiment of the system can provide an interface that allows a user to interact with a large language model through speech. [Brief description of the drawings]

[0008] [Figure 1] 1 is a conceptual diagram showing an example of the configuration of a data processing system according to a first embodiment. [Diagram 2] 1 is a conceptual diagram showing an example of main functions of a data processing device and a smart device according to a first embodiment. FIG. [Diagram 3] FIG. 11 is a conceptual diagram showing an example of the configuration of a data processing system according to a second embodiment. [Figure 4] FIG. 11 is a conceptual diagram showing an example of main functions of a data processing device and smart glasses according to a second embodiment. [Diagram 5] FIG. 13 is a conceptual diagram showing an example of the configuration of a data processing system according to a third embodiment. [Figure 6] FIG. 11 is a conceptual diagram showing an example of main functions of a data processing device and a headset-type terminal according to a third embodiment. [Figure 7] FIG. 13 is a conceptual diagram showing an example of the configuration of a data processing system according to a fourth embodiment. [Figure 8] FIG. 13 is a conceptual diagram showing an example of main functions of a data processing device and a robot according to a fourth embodiment. [Figure 9] 1 shows an emotion map onto which multiple emotions are mapped. [Figure 10] 1 shows an emotion map onto which multiple emotions are mapped. DETAILED DESCRIPTION OF THE PREFERRED EMBODIMENTS

[0009] 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.

[0010] First, the terms used in the following description will be explained.

[0011] In the following embodiments, a signed processor (hereinafter simply referred to as a "processor") may be one arithmetic device or a combination of multiple arithmetic devices. Furthermore, a processor may be one type of arithmetic device or a combination of multiple types of arithmetic devices. Examples of arithmetic devices include a CPU (Central Processing Unit), a GPU (Graphics Processing Unit), a GPGPU (General-Purpose computing on Graphics Processing Units), an APU (Accelerated Processing Unit), or a TPU (Tensor Processing Unit).

[0012] In the following embodiments, a signed RAM (Random Access Memory) is a memory in which information is temporarily stored and is used as a working memory by the processor.

[0013] In the following embodiments, the coded storage is one or more non-volatile storage devices that store various programs and various parameters, etc. Examples of non-volatile storage devices include flash memory (SSD (Solid State Drive)), magnetic disks (e.g., hard disks), and magnetic tapes.

[0014] In the following embodiments, a communication I / F (Interface) with a code is an interface including a communication processor and an antenna. The communication I / F controls communication between multiple computers. An example of a communication standard applied to the communication I / F is a wireless communication standard including 5G (5th Generation Mobile Communication System), Wi-Fi (registered trademark), or Bluetooth (registered trademark).

[0015] In the following embodiments, "A and / or B" is synonymous with "at least one of A and B." In other words, "A and / or B" means that it may be only A, only B, or a combination of A and B. In addition, in this specification, the same idea as "A and / or B" is also applied when three or more things are expressed by connecting them with "and / or."

[0016] [First embodiment] FIG. 1 shows an example of the configuration of a data processing system 10 according to the first embodiment.

[0017] 1, a data processing system 10 includes a data processing device 12 and a smart device 14. An example of the data processing device 12 is a server.

[0018] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, the RAM 30, and the storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0019] The smart device 14 includes a computer 36, a reception device 38, an output device 40, a camera 42, and a communication I / F 44. The computer 36 includes a processor 46, a RAM 48, and a storage 50. The processor 46, the RAM 48, and the storage 50 are connected to a bus 52. The reception device 38, the output device 40, and the camera 42 are also connected to the bus 52.

[0020] The reception device 38 includes a touch panel 38A and a microphone 38B, and receives user input. The touch panel 38A detects contact with a pointer (e.g., a pen or a finger) to receive user input by the touch of the pointer. The microphone 38B detects the user's voice to receive user input by voice. The control unit 46A transmits data indicating the user input received by the touch panel 38A and the microphone 38B to the data processing device 12. In the data processing device 12, the specific processing unit 290 (see FIG. 2) acquires the data indicating the user input.

[0021] Output device 40 includes a display 40A and a speaker 40B, and presents data to a user by outputting the data in a form of expression that the user can perceive (e.g., voice and / or text). Display 40A displays visible information such as text and images according to instructions from processor 46. Speaker 40B outputs voice according to instructions from processor 46. Camera 42 is a compact digital camera equipped with an optical system including a lens, aperture, and shutter, and an imaging element such as a Complementary Metal-Oxide-Semiconductor (CMOS) image sensor or a Charge Coupled Device (CCD) image sensor.

[0022] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 are responsible for transmitting and receiving various types of information between the processor 46 and the processor 28 via the network 54.

[0023] FIG. 2 shows an example of main functions of the data processing device 12 and the smart device 14.

[0024] As shown in Fig. 2, in the data processing device 12, a specific process is performed by the processor 28. A specific process program 56 is stored in the storage 32. The specific process program 56 is an example of a "program" according to the technology of the present disclosure. The processor 28 reads the specific process program 56 from the storage 32, and executes the read specific process program 56 on the RAM 30. The specific process is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific process program 56 executed on the RAM 30.

[0025] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290. The identification processing unit 290 can estimate the emotion of the user using the emotion identification model 59 and perform identification processing using the user's emotion. In the emotion estimation function (emotion identification function) using the emotion identification model 59, various estimations and predictions regarding the user's emotion, including estimation and prediction of the user's emotion, are performed, but are not limited to such examples. In addition, the estimation and prediction of the emotion also include, for example, analysis of the emotion.

[0026] In the smart device 14, the specific processing is performed by the processor 46. The storage 50 stores a specific processing program 60. The specific processing program 60 is used together with the specific processing program 56 by the data processing system 10. The processor 46 reads the specific processing program 60 from the storage 50 and executes the specific processing program 60 on the RAM 48. The specific processing is realized by the processor 46 operating as the control unit 46A in accordance with the specific processing program 60 executed on the RAM 48. Note that the smart device 14 has a data generation model and an emotion identification model similar to the data generation model 58 and the emotion identification model 59, and can also perform processing similar to that of the specific processing unit 290 using these models.

[0027] Note that a device other than the data processing device 12 may have the data generation model 58. For example, a server device (e.g., a generation server) may have the data generation model 58. In this case, the data processing device 12 obtains a processing result (prediction result, etc.) using the data generation model 58 by communicating with the server device having the data generation model 58. Also, the data processing device 12 may be a server device, or may be a terminal device (e.g., a mobile phone, a robot, a home appliance, etc.) owned by a user. Next, an example of processing by the data processing system 10 according to the first embodiment will be described.

[0028] (Example 1) In the system according to the embodiment of the present invention, an AI chip containing a generation AI is linked to smart glasses with an earphone microphone, and the user can talk or consult with a buddy (generation AI) displayed on the screen. This system starts when a user asks a question or asks a question by voice. This voice is received by the reception unit of the smart glasses with an earphone microphone. Next, the received voice is input into a large-scale language model (generation AI), and a corresponding response is generated. This response is generated by the generation unit and displayed on the display unit of the smart glasses. This allows the user to talk or consult with a buddy (generation AI) displayed on the screen. For example, when a user asks a question, "What's the weather like today?", the reception unit receives the voice and inputs it into the large-scale language model. The large-scale language model generates a response corresponding to the question, such as "The weather is sunny today." This response is generated by the generation unit and displayed on the display unit of the smart glasses. The user can continue the conversation with the buddy (generation AI) displayed on the screen. Furthermore, the generation unit can generate personalized responses. For example, the generation unit can learn the user's preferences and habits and provide a response tailored to the user. It is also possible to estimate the user's emotions and adjust the accuracy of voice analysis based on the estimated emotions. This allows for more natural conversations. The generation unit can also analyze the user's past voice data and select an appropriate voice recognition algorithm. This improves the accuracy of voice recognition and accurately recognizes the user's words. This system allows the user to have natural conversations and ask questions with the buddy (generative AI) displayed on the screen through the smart glasses with earphone microphone. For example, it can be used to ask small questions or ask questions about daily life, or as a work assistant. By simply wearing the smart glasses, the user can enjoy conversations with the buddy (generative AI) anytime, anywhere. This allows the user to have natural conversations and ask questions with the buddy (generative AI) displayed on the screen through the smart glasses with earphone microphone.

[0029] The system according to the embodiment includes a display unit, a reception unit, a generation unit, and an output unit. The display unit displays a user interface on the wearable device that allows information to be input to the large-scale language model. The user interface includes, for example, a graphical user interface and a voice user interface. The reception unit receives voice from the user. The voice includes, for example, a voice format and a voice quality. The generation unit generates a response corresponding to the voice by inputting the voice received by the reception unit into the large-scale language model. The generation unit generates a response using, for example, a generation AI (for example, a text generation AI or a multimodal generation AI). The generation AI can use, for example, a large-scale language model such as GPT or Gemini. The output unit outputs the response generated by the generation unit to the wearable device. The output unit can perform, for example, voice output or text output. This allows the system to allow the user to have a natural conversation or consultation through the wearable device. For example, when the user asks, "What's the weather like today?", the reception unit receives the voice and inputs it into the large-scale language model. The large-scale language model generates a response corresponding to the question, such as "The weather is sunny today." This response is generated by the generation unit and displayed on the display unit of the wearable device. The user can continue a conversation with the buddy (generative AI) displayed on the screen. This enables the system to enable the user to have a natural conversation or consultation through the wearable device.

[0030] The display unit displays a user interface on the wearable device that allows the user to input information into the large-scale language model. The user interface includes, for example, a graphical user interface and a voice user interface. Specifically, the graphical user interface is designed to support touch screen and gesture operations and to allow the user to operate intuitively. For example, the user can tap the touch screen to input a question or swipe to switch menus. The voice user interface accepts the user's voice commands using voice recognition technology. This allows the user to operate the device using only voice without using his or her hands. Furthermore, the display unit is equipped with a sensor that detects the user's gaze and facial expression, and can grasp the user's intention more accurately. For example, the user can select a specific icon by gazing at that icon. This allows the display unit to provide an interface that the user can operate intuitively and naturally, thereby improving the convenience of the wearable device.

[0031] The reception unit receives voice from the user. The voice includes, for example, the voice format and the quality of the voice. Specifically, the reception unit is equipped with a highly sensitive microphone, and can clearly capture the user's voice while removing surrounding noise. Furthermore, the reception unit converts the user's speech into text data using voice recognition technology. At this time, a common voice codec such as PCM or AAC is used as the voice format. In addition, the quality of the voice can be adjusted to obtain optimal voice data by adjusting the sampling rate and bit rate. The reception unit can analyze the user's voice command in real time and quickly obtain the required information. For example, when the user utters "Tell me about a nearby restaurant," the reception unit analyzes the voice and converts it into appropriate text data. As a result, the reception unit can accurately and quickly process the user's voice input and provide it as input data to the generation unit, which is the next step.

[0032] The generation unit generates a response corresponding to the voice by inputting the voice received by the reception unit into a large-scale language model. The generation unit generates a response using, for example, a generation AI (for example, a text generation AI or a multimodal generation AI). Specifically, the generation AI uses natural language processing technology to generate an optimal response to a user's question or request. For example, when a user asks, "What's the weather like today?", the generation AI accesses a weather forecast database to obtain the latest weather information. Then, based on the obtained information, it generates a natural response such as "It's sunny today." The generation AI is trained with a large amount of data in advance to understand the context and provide appropriate information. Furthermore, the generation unit can generate a more personalized response by taking into account the user's past speech history and the preferences of each individual user. For example, if a user has previously asked, "Please tell me the weather tomorrow," the generation unit takes that history into account and generates a response such as "It's forecast to be sunny tomorrow as well." This allows the generation unit to provide high-quality responses that meet the needs of the user and improve the user experience.

[0033] The output unit outputs the response generated by the generation unit to the wearable device. The output unit can perform, for example, voice output or text output. Specifically, in the case of voice output, a high-quality speaker is used to convey the generated response to the user in a clear voice. Natural pronunciation and intonation are realized using speech synthesis technology, so that the user can hear the response without feeling uncomfortable. In addition, in the case of text output, the response is displayed on the display of the wearable device. The display is designed to have high resolution and high visibility so that the user can easily check the information. Furthermore, the output unit can select the optimal output method according to the user's situation and environment. For example, in a noisy environment, text output is prioritized, and in a quiet environment, voice output is prioritized. In addition, the output unit can receive feedback from the user and continuously improve the output content and method. As a result, the output unit can provide information to the user in an optimal form, thereby improving the convenience and user experience of the entire system.

[0034] The generation unit can generate a personalized response. The generation unit generates a personalized response based on, for example, the user's profile information and past dialogue history. For example, the generation unit can learn the user's preferences and habits and provide a response tailored to the user. The generation unit can analyze, for example, the user's past dialogue history and identify a response pattern preferred by the user. This allows the generation unit to provide a response tailored to the user. A part or all of the above-mentioned processing in the generation unit may be performed, for example, using a generation AI, or may be performed without using a generation AI. For example, the generation unit can input the user's profile information into the generation AI and cause the generation AI to execute a personalized response. This allows the generation unit to provide a response tailored to the user.

[0035] The generation unit can learn the user's preferences and habits and provide feedback to the generation unit. The generation unit learns the user's preferences and habits based on, for example, the user's questionnaire results and usage history. For example, the generation unit analyzes the user's questionnaire results and identifies the user's preferences. The generation unit also analyzes the user's usage history and identifies the user's habits. This allows the generation unit to provide a response based on the user's preferences and habits. A part or all of the above-mentioned processing in the generation unit may be performed using, for example, a generation AI, or may be performed without using a generation AI. For example, the generation unit can input the user's questionnaire results into the generation AI and identify the user's preferences. This allows the generation unit to provide a response based on the user's preferences and habits.

[0036] The generation unit can analyze the user's past voice data and select an appropriate voice recognition algorithm. The generation unit, for example, analyzes the user's past voice data and selects a voice recognition algorithm. For example, the generation unit analyzes the user's past voice data and selects an algorithm for improving the accuracy of voice recognition. The voice recognition algorithm includes, for example, an HMM (Hidden Markov Model) and a DNN (Deep Neural Network). This allows the generation unit to improve the accuracy of voice recognition. A part or all of the above-mentioned processing in the generation unit may be performed using, for example, a generation AI, or may be performed without using a generation AI. For example, the generation unit can input the user's past voice data to the generation AI and select an appropriate voice recognition algorithm. This allows the generation unit to improve the accuracy of voice recognition.

[0037] The display unit can track the user's gaze and display information according to the position of the gaze. The display unit tracks the user's gaze using, for example, a camera-based gaze tracking technology. For example, when the user gazes at a specific icon, the display unit pops up information related to the icon. In addition, when the user gazes at a part of the screen for a long time, the display unit can also enlarge and display that part. Furthermore, when the user gazes in a specific direction, the display unit can display information related to that direction. For example, when the user gazes at the upper right of the screen, the display unit displays information related to the upper right. This allows the display unit to display information according to the user's gaze. The gaze tracking is realized using, for example, a camera-based gaze tracking technology or an infrared gaze tracking technology. A part or all of the above-mentioned processing in the display unit may be performed using, for example, a generation AI, or may be performed without using a generation AI. For example, the display unit can input the user's gaze data to the generation AI and cause the generation AI to execute information display according to the position of the gaze. This allows the display unit to display information according to the user's gaze.

[0038] The display unit can analyze the user's past usage history and select the optimal information display method. The display unit, for example, analyzes the user's past usage history and selects the optimal information display method. For example, the display unit preferentially displays information that the user frequently accessed in the past. The display unit can also analyze the user's past operation patterns and propose an optimal layout. Furthermore, the display unit can customize information to be displayed in a specific time period from the user's past usage history. For example, the display unit preferentially displays information that the user frequently accesses in the morning. This enables the display unit to display information based on the user's past usage history. A part or all of the above-mentioned processing in the display unit may be performed, for example, using a generation AI, or may be performed without using a generation AI. For example, the display unit can input the user's past usage history data to the generation AI and have the generation AI select the optimal information display method. This enables the display unit to display information based on the user's past usage history.

[0039] The display unit can display highly relevant information with priority in consideration of the geographical location information of the user. The display unit, for example, acquires the geographical location information of the user and displays highly relevant information based on the information. For example, when the user is in a specific location, the display unit displays information related to the location. In addition, when the user is traveling, the display unit can also display tourist information of the travel destination with priority. Furthermore, when the user is at home, the display unit can also display weather information around the home. This enables the display unit to display information based on the geographical location information of the user. A part or all of the above-mentioned processing in the display unit may be performed, for example, using a generation AI, or may be performed without using a generation AI. For example, the display unit inputs the geographical location information of the user to the generation AI and allows the generation AI to select highly relevant information. This enables the display unit to display information based on the geographical location information of the user.

[0040] The display unit can analyze the user's social media activity and display related information. The display unit can, for example, analyze the user's social media activity and display related information. For example, the display unit displays the latest posts of accounts that the user follows on social media. The display unit can also display news related to topics in which the user has shown interest on social media. Furthermore, the display unit can display event information of interest from the user's social media activity. This enables the display unit to display information based on the user's social media activity. A part or all of the above-mentioned processing in the display unit may be performed, for example, using a generation AI, or may be performed without using a generation AI. For example, the display unit can input the user's social media activity data to the generation AI and have the generation AI select related information. This enables the display unit to display information based on the user's social media activity.

[0041] The reception unit can analyze the user's past voice input history and select the optimal reception method. The reception unit, for example, analyzes the user's past voice input history and selects the optimal reception method. For example, the reception unit preferentially accepts voice commands that the user has frequently used in the past. The reception unit can also analyze the user's past voice input patterns and select the optimal voice recognition algorithm. Furthermore, the reception unit can predict and accept a voice command to be used in a specific time period from the user's past voice input history. For example, the reception unit preferentially accepts a voice command that the user frequently uses in the morning. This enables the reception unit to select the optimal reception method based on the user's past voice input history. A part or all of the above-mentioned processing in the reception unit may be performed using, for example, a generation AI, or may be performed without using a generation AI. For example, the reception unit can input the user's past voice input history data to the generation AI and have the generation AI select the optimal reception method. This enables the reception unit to select the optimal reception method based on the user's past voice input history.

[0042] The reception unit can filter the user's current environmental sound to improve the accuracy of the voice input. The reception unit, for example, filters the user's current environmental sound to improve the accuracy of the voice input. For example, when the user is in a noisy environment, the reception unit filters the environmental sound to improve the accuracy of the voice input. In addition, when the user is in a quiet environment, the reception unit can adjust the sensitivity of the voice input to improve the accuracy. Furthermore, when the user is moving, the reception unit can filter the wind noise to improve the accuracy of the voice input. For example, when the user is in a car, the reception unit filters the environmental sound in the car to improve the accuracy of the voice input. This allows the reception unit to improve the accuracy of the voice input based on the user's current environmental sound. Part or all of the above-mentioned processing in the reception unit may be performed, for example, using a generation AI, or may be performed without using a generation AI. For example, the reception unit can input the user's environmental sound data to the generation AI and cause the generation AI to filter the environmental sound. This allows the reception unit to improve the accuracy of the voice input based on the user's current environmental sound.

[0043] The reception unit can preferentially receive a highly relevant voice in consideration of the geographical location information of the user. The reception unit, for example, acquires the geographical location information of the user and preferentially receives a highly relevant voice based on the information. For example, when the user is in a specific location, the reception unit preferentially receives a voice command related to the location. In addition, when the user is traveling, the reception unit can also preferentially receive a voice command related to the travel destination. Furthermore, when the user is at home, the reception unit can also preferentially receive a voice command related to the surroundings of the home. This enables the reception unit to preferentially receive a voice based on the geographical location information of the user. A part or all of the above-mentioned processing in the reception unit may be performed, for example, using a generation AI, or may be performed without using a generation AI. For example, the reception unit can input the geographical location information of the user to the generation AI and have the generation AI select a highly relevant voice. This enables the reception unit to preferentially receive a voice based on the geographical location information of the user.

[0044] The reception unit can analyze the social media activity of the user and receive the related voice. The reception unit, for example, analyzes the social media activity of the user and receives the related voice. For example, the reception unit receives a voice command related to an account that the user follows on social media. The reception unit can also receive a voice command related to a topic in which the user has shown an interest on social media. Furthermore, the reception unit can also receive a voice command related to an event of interest from the social media activity of the user. This enables the reception unit to receive the voice based on the social media activity of the user. A part or all of the above-mentioned processing in the reception unit may be performed, for example, using a generation AI, or may be performed without using a generation AI. For example, the reception unit can input the social media activity data of the user to the generation AI and have the generation AI select the related voice. This enables the reception unit to receive the voice based on the social media activity of the user.

[0045] The generation unit can analyze the user's past response history and select the optimal response generation method. The generation unit, for example, analyzes the user's past response history and selects the optimal response generation method. For example, the generation unit generates an optimal response based on a response pattern that the user has preferred in the past. The generation unit can also generate a response suitable for a specific time period from the user's past response history. Furthermore, the generation unit can analyze the user's past response history and select the most effective response method. This enables the generation unit to generate an optimal response based on the user's past response history. A part or all of the above-mentioned processing in the generation unit may be performed using, for example, a generation AI, or may be performed without using a generation AI. For example, the generation unit can input the user's past response history data to the generation AI and have the generation AI select the optimal response generation method. This enables the generation unit to generate an optimal response based on the user's past response history.

[0046] The generation unit can customize the content of the response based on the user's current situation. The generation unit customizes the content of the response based on the user's current situation, for example. For example, when the user is in a specific location, the generation unit generates a response including information related to the location. Also, when the user is in a specific time period, the generation unit can generate a response including information related to the time period. Furthermore, the generation unit can generate an optimal response based on the user's current activity. For example, when the user is exercising, the generation unit generates a response including information related to exercise. This allows the generation unit to customize the response based on the user's current situation. A part or all of the above-mentioned processing in the generation unit may be performed using, for example, a generation AI, or may be performed without using a generation AI. For example, the generation unit can input the user's current situation data to the generation AI and have the generation AI customize the content of the response. This allows the generation unit to customize the response based on the user's current situation.

[0047] The generation unit can generate a highly relevant response in consideration of the geographical location information of the user. The generation unit, for example, acquires the geographical location information of the user and generates a highly relevant response based on the information. For example, when the user is in a specific location, the generation unit generates a response including information related to the location. In addition, when the user is traveling, the generation unit can also generate a response including information related to the travel destination. Furthermore, when the user is at home, the generation unit can also generate a response including information related to the surroundings of the home. This enables the generation unit to generate a response based on the geographical location information of the user. A part or all of the above-mentioned processing in the generation unit may be performed, for example, using a generation AI, or may be performed without using a generation AI. For example, the generation unit can input the geographical location information of the user to the generation AI and cause the generation AI to generate a highly relevant response. This enables the generation unit to generate a response based on the geographical location information of the user.

[0048] The generation unit can analyze the user's social media activity and generate a relevant response. The generation unit can, for example, analyze the user's social media activity and generate a relevant response. For example, the generation unit generates a response including information related to accounts that the user follows on social media. The generation unit can also generate a response including information related to topics in which the user has shown interest on social media. Furthermore, the generation unit can generate a response including information related to an event of interest from the user's social media activity. This enables the generation unit to generate a response based on the user's social media activity. A part or all of the above-mentioned processing in the generation unit may be performed, for example, using a generation AI, or may be performed without using a generation AI. For example, the generation unit can input the user's social media activity data to the generation AI and cause the generation AI to generate a relevant response. This enables the generation unit to generate a response based on the user's social media activity.

[0049] The output unit can analyze the user's past output history and select the optimal output method. The output unit, for example, analyzes the user's past output history and selects the optimal output method. For example, the output unit selects the optimal output method based on the output format that the user has preferred in the past. The output unit can also select an output method suitable for a specific time period from the user's past output history. Furthermore, the output unit can analyze the user's past output history and select the most effective output method. This enables the output unit to select the optimal output method based on the user's past output history. A part or all of the above-mentioned processing in the output unit may be performed using, for example, a generation AI, or may be performed without using a generation AI. For example, the output unit can input the user's past output history data to the generation AI and have the generation AI select the optimal output method. This enables the output unit to select the optimal output method based on the user's past output history.

[0050] The output unit can customize the means of output based on the user's current environment. The output unit customizes the means of output based on the user's current environment, for example. For example, the output unit prioritizes visual output when the user is in a noisy environment. The output unit can also prioritize audio output when the user is in a quiet environment. Furthermore, the output unit can provide a concise and highly visible output when the user is moving. For example, the output unit prioritizes visual output and refrains from audio output when the user is in a car. This enables the output unit to customize the output means based on the user's current environment. A part or all of the above-mentioned processing in the output unit may be performed, for example, using a generation AI, or may be performed without using a generation AI. For example, the output unit can input the user's current environmental data to the generation AI and have the generation AI customize the means of output. This enables the output unit to customize the output means based on the user's current environment.

[0051] The output unit can select the optimal output method in consideration of the geographical location information of the user. The output unit, for example, acquires the geographical location information of the user and selects the optimal output method based on the information. For example, when the user is in a specific location, the output unit preferentially outputs information related to the location. In addition, when the user is traveling, the output unit can also preferentially output information related to the travel destination. Furthermore, when the user is at home, the output unit can also preferentially output information related to the surroundings of the home. This enables the output unit to use the optimal output method based on the geographical location information of the user. A part or all of the above-mentioned processing in the output unit may be performed, for example, using a generation AI, or may be performed without using a generation AI. For example, the output unit can input the geographical location information of the user to the generation AI and have the generation AI select the optimal output method. This enables the output unit to use the optimal output method based on the geographical location information of the user.

[0052] The output unit can analyze the social media activity of the user and provide a related output. The output unit can, for example, analyze the social media activity of the user and provide a related output. For example, the output unit preferentially outputs information related to accounts that the user follows on social media. The output unit can also preferentially output information related to topics in which the user has shown interest on social media. Furthermore, the output unit can also preferentially output information related to events of interest from the user's social media activity. This enables the output unit to provide an output based on the user's social media activity. A part or all of the above-mentioned processing in the output unit may be performed, for example, using a generation AI, or may be performed without using a generation AI. For example, the output unit can input the user's social media activity data to the generation AI and have the generation AI select a related output. This enables the output unit to provide an output based on the user's social media activity.

[0053] The system according to the embodiment is not limited to the above-described example, and various modifications are possible, for example, as follows.

[0054] The reception unit can not only receive the user's voice, but also recognize the user's gestures and receive them as input. For example, when the user raises his / her hand, the reception unit recognizes the gesture and interprets it as a specific command. When the user points a finger, the reception unit can display information related to that direction. Furthermore, if the user repeats a specific gesture, a custom command corresponding to that gesture can be set. This allows the user to operate the system using gestures as well as voice.

[0055] The generation unit can generate a personalized response by taking into account not only the user's past dialogue history but also the user's current activity status. For example, if the user is exercising, the generation unit can provide advice and information related to exercise. Also, if the user is working, the generation unit can suggest efficient methods and tools related to work. Furthermore, during the user's time of relaxation, the generation unit can provide music and entertainment information suitable for relaxation. This allows the generation unit to provide an optimal response according to the user's current situation.

[0056] The generator can not only learn the user's preferences and habits, but also monitor the user's health condition and provide a response based thereon. For example, the generator can monitor the user's heart rate and blood pressure, and provide appropriate advice and warnings when abnormalities are detected. The generator can also analyze the user's sleep patterns and provide suggestions for improving sleep quality. Furthermore, the generator can record the user's dietary history and provide healthy dietary suggestions. This allows the generator to provide a response based on the user's health condition.

[0057] The generation unit can not only analyze the user's past voice data, but also learn the user's pronunciation and accent and adjust the voice recognition algorithm based on the learned pronunciation and accent. For example, if the user has a specific accent, the generation unit selects a voice recognition algorithm that corresponds to the accent. The generation unit can also learn the user's pronunciation habits and make adjustments to reduce misrecognition. Furthermore, the generation unit can continuously learn the user's voice data and improve the accuracy of voice recognition. This allows the generation unit to realize optimal voice recognition according to the user's pronunciation and accent.

[0058] The display unit can not only track the user's gaze, but also estimate the target of the user's interest from the movement of the user's gaze and provide information based on the estimation. For example, if the user gazes at a specific icon, detailed information related to the icon is displayed. Also, if the user gazes at a specific part of the screen for a long time, information related to that part can be preferentially displayed. Furthermore, the display unit can estimate a topic of interest from the movement of the user's gaze and provide information related to that topic. This enables the display unit to provide optimal information according to the movement of the user's gaze.

[0059] The display unit can not only analyze the user's past usage history, but also customize the information display method based on the user's learning style. For example, if the user is a visual learner, a graphical display can be prioritized. Also, if the user is an auditory learner, audio information can be prioritized. Furthermore, if the user is a practical learner, interactive content can be provided. In this way, the display unit can provide the optimal information display method according to the user's learning style.

[0060] The display unit can not only take into account the geographical location information of the user, but also analyze the user's movement pattern and provide information based on the analysis. For example, if the user frequently travels along a specific route, information related to that route is preferentially displayed. In addition, if the user travels to a new location, tourist information and restaurant information related to that location can be provided. Furthermore, the display unit can suggest optimal means of transportation and routes based on the user's movement pattern. This enables the display unit to provide optimal information according to the user's movement pattern.

[0061] The process flow of the first embodiment will be briefly described below.

[0062] Step 1: The display unit displays a user interface on the wearable device that allows input of information into the large-scale language model. The user interface may be, for example, a graphical user interface or a voice user interface. Step 2: The reception unit receives voice from the user, which includes, for example, the voice format and the voice quality. Step 3: The generation unit generates a response corresponding to the voice by inputting the voice received by the reception unit into a large-scale language model. The generation unit generates the response using, for example, a generation AI (for example, a text generation AI or a multimodal generation AI). The generation AI can use, for example, a large-scale language model such as GPT or Gemini. Step 4: The output unit outputs the response generated by the generation unit to the wearable device. The output unit can output, for example, audio or text.

[0063] (Example 2) In the system according to the embodiment of the present invention, an AI chip containing a generation AI is linked to smart glasses with an earphone microphone, and the user can talk or consult with a buddy (generation AI) displayed on the screen. This system starts when a user asks a question or asks a question by voice. This voice is received by the reception unit of the smart glasses with an earphone microphone. Next, the received voice is input into a large-scale language model (generation AI), and a corresponding response is generated. This response is generated by the generation unit and displayed on the display unit of the smart glasses. This allows the user to talk or consult with a buddy (generation AI) displayed on the screen. For example, when a user asks a question, "What's the weather like today?", the reception unit receives the voice and inputs it into the large-scale language model. The large-scale language model generates a response corresponding to the question, such as "The weather is sunny today." This response is generated by the generation unit and displayed on the display unit of the smart glasses. The user can continue the conversation with the buddy (generation AI) displayed on the screen. Furthermore, the generation unit can generate personalized responses. For example, the generation unit can learn the user's preferences and habits and provide a response tailored to the user. It is also possible to estimate the user's emotions and adjust the accuracy of voice analysis based on the estimated emotions. This allows for more natural conversations. The generation unit can also analyze the user's past voice data and select an appropriate voice recognition algorithm. This improves the accuracy of voice recognition and accurately recognizes the user's words. This system allows the user to have natural conversations and ask questions with the buddy (generative AI) displayed on the screen through the smart glasses with earphone microphone. For example, it can be used to ask small questions or ask questions about daily life, or as a work assistant. By simply wearing the smart glasses, the user can enjoy conversations with the buddy (generative AI) anytime, anywhere. This allows the user to have natural conversations and ask questions with the buddy (generative AI) displayed on the screen through the smart glasses with earphone microphone.

[0064] The system according to the embodiment includes a display unit, a reception unit, a generation unit, and an output unit. The display unit displays a user interface on the wearable device that allows information to be input to the large-scale language model. The user interface includes, for example, a graphical user interface and a voice user interface. The reception unit receives voice from the user. The voice includes, for example, a voice format and a voice quality. The generation unit generates a response corresponding to the voice by inputting the voice received by the reception unit into the large-scale language model. The generation unit generates a response using, for example, a generation AI (for example, a text generation AI or a multimodal generation AI). The generation AI can use, for example, a large-scale language model such as GPT or Gemini. The output unit outputs the response generated by the generation unit to the wearable device. The output unit can perform, for example, voice output or text output. This allows the system to allow the user to have a natural conversation or consultation through the wearable device. For example, when the user asks, "What's the weather like today?", the reception unit receives the voice and inputs it into the large-scale language model. The large-scale language model generates a response corresponding to the question, such as "The weather is sunny today." This response is generated by the generation unit and displayed on the display unit of the wearable device. The user can continue a conversation with the buddy (generative AI) displayed on the screen. This enables the system to enable the user to have a natural conversation or consultation through the wearable device.

[0065] The display unit displays a user interface on the wearable device that allows the user to input information into the large-scale language model. The user interface includes, for example, a graphical user interface and a voice user interface. Specifically, the graphical user interface is designed to support touch screen and gesture operations and to allow the user to operate intuitively. For example, the user can tap the touch screen to input a question or swipe to switch menus. The voice user interface accepts the user's voice commands using voice recognition technology. This allows the user to operate the device using only voice without using his or her hands. Furthermore, the display unit is equipped with a sensor that detects the user's gaze and facial expression, and can grasp the user's intention more accurately. For example, the user can select a specific icon by gazing at that icon. This allows the display unit to provide an interface that the user can operate intuitively and naturally, thereby improving the convenience of the wearable device.

[0066] The reception unit receives voice from the user. The voice includes, for example, the voice format and the quality of the voice. Specifically, the reception unit is equipped with a highly sensitive microphone, and can clearly capture the user's voice while removing surrounding noise. Furthermore, the reception unit converts the user's speech into text data using voice recognition technology. At this time, a common voice codec such as PCM or AAC is used as the voice format. In addition, the quality of the voice can be adjusted to obtain optimal voice data by adjusting the sampling rate and bit rate. The reception unit can analyze the user's voice command in real time and quickly obtain the required information. For example, when the user utters "Tell me about a nearby restaurant," the reception unit analyzes the voice and converts it into appropriate text data. As a result, the reception unit can accurately and quickly process the user's voice input and provide it as input data to the generation unit, which is the next step.

[0067] The generation unit generates a response corresponding to the voice by inputting the voice received by the reception unit into a large-scale language model. The generation unit generates a response using, for example, a generation AI (for example, a text generation AI or a multimodal generation AI). Specifically, the generation AI uses natural language processing technology to generate an optimal response to a user's question or request. For example, when a user asks, "What's the weather like today?", the generation AI accesses a weather forecast database to obtain the latest weather information. Then, based on the obtained information, it generates a natural response such as "It's sunny today." The generation AI is trained with a large amount of data in advance to understand the context and provide appropriate information. Furthermore, the generation unit can generate a more personalized response by taking into account the user's past speech history and the preferences of each individual user. For example, if a user has previously asked, "Please tell me the weather tomorrow," the generation unit takes that history into account and generates a response such as "It's forecast to be sunny tomorrow as well." This allows the generation unit to provide high-quality responses that meet the needs of the user and improve the user experience.

[0068] The output unit outputs the response generated by the generation unit to the wearable device. The output unit can perform, for example, voice output or text output. Specifically, in the case of voice output, a high-quality speaker is used to convey the generated response to the user in a clear voice. Natural pronunciation and intonation are realized using speech synthesis technology, so that the user can hear the response without feeling uncomfortable. In addition, in the case of text output, the response is displayed on the display of the wearable device. The display is designed to have high resolution and high visibility so that the user can easily check the information. Furthermore, the output unit can select the optimal output method according to the user's situation and environment. For example, in a noisy environment, text output is prioritized, and in a quiet environment, voice output is prioritized. In addition, the output unit can receive feedback from the user and continuously improve the output content and method. As a result, the output unit can provide information to the user in an optimal form, thereby improving the convenience and user experience of the entire system.

[0069] The generation unit can generate a personalized response. The generation unit generates a personalized response based on, for example, the user's profile information and past dialogue history. For example, the generation unit can learn the user's preferences and habits and provide a response tailored to the user. The generation unit can analyze, for example, the user's past dialogue history and identify a response pattern preferred by the user. This allows the generation unit to provide a response tailored to the user. A part or all of the above-mentioned processing in the generation unit may be performed, for example, using a generation AI, or may be performed without using a generation AI. For example, the generation unit can input the user's profile information into the generation AI and cause the generation AI to execute a personalized response. This allows the generation unit to provide a response tailored to the user.

[0070] The generation unit can learn the user's preferences and habits and provide feedback to the generation unit. The generation unit learns the user's preferences and habits based on, for example, the user's questionnaire results and usage history. For example, the generation unit analyzes the user's questionnaire results and identifies the user's preferences. The generation unit also analyzes the user's usage history and identifies the user's habits. This allows the generation unit to provide a response based on the user's preferences and habits. A part or all of the above-mentioned processing in the generation unit may be performed using, for example, a generation AI, or may be performed without using a generation AI. For example, the generation unit can input the user's questionnaire results into the generation AI and identify the user's preferences. This allows the generation unit to provide a response based on the user's preferences and habits.

[0071] The generation unit can estimate the user's emotion and adjust the accuracy of the voice analysis based on the estimated user's emotion. The generation unit estimates the user's emotion using, for example, voice analysis or facial expression recognition. For example, the generation unit analyzes the user's voice and estimates the emotion based on the tone and speed of the voice. The generation unit can also capture the user's facial expression with a camera and estimate the emotion using facial expression recognition technology. This allows the generation unit to adjust the accuracy of the voice analysis based on the user's emotion. The emotion estimation is realized using an emotion estimation function using, for example, an emotion engine or a generation AI. The generation AI is a text generation AI (for example, LLM) or a multimodal generation AI, but is not limited to such examples. A part or all of the above-mentioned processing in the generation unit may be performed using, for example, the generation AI, or may be performed without using the generation AI. For example, the generation unit can input the user's voice data to the generation AI and cause the generation AI to execute emotion estimation. This allows the generation unit to adjust the accuracy of the voice analysis based on the user's emotion.

[0072] The generation unit can analyze the user's past voice data and select an appropriate voice recognition algorithm. The generation unit, for example, analyzes the user's past voice data and selects a voice recognition algorithm. For example, the generation unit analyzes the user's past voice data and selects an algorithm for improving the accuracy of voice recognition. The voice recognition algorithm includes, for example, an HMM (Hidden Markov Model) and a DNN (Deep Neural Network). This allows the generation unit to improve the accuracy of voice recognition. A part or all of the above-mentioned processing in the generation unit may be performed using, for example, a generation AI, or may be performed without using a generation AI. For example, the generation unit can input the user's past voice data to the generation AI and select an appropriate voice recognition algorithm. This allows the generation unit to improve the accuracy of voice recognition.

[0073] The display unit can estimate the user's emotion and dynamically change the display content based on the estimated user's emotion. For example, the display unit captures the user's facial expression with a camera and estimates the emotion using an emotion estimation algorithm. For example, the display unit calculates an emotion score based on the change in facial expression and dynamically changes the display content. The display unit can also record the user's voice and estimate the emotion using a voice analysis technique. For example, the display unit analyzes the tone and speed of the voice, calculates an emotion score, and dynamically changes the display content. The display unit can also collect the user's biometric data (heart rate and electrodermal activity) with a sensor and estimate the emotion using an emotion estimation algorithm. For example, the display unit calculates an emotion score based on the fluctuation of the heart rate and dynamically changes the display content. This enables the display unit to change the display content according to the user's emotion. The emotion estimation is realized using an emotion estimation function using, for example, an emotion engine or a generation AI. The generation AI is a text generation AI (for example, LLM) or a multimodal generation AI, but is not limited to such examples. A part or all of the above-mentioned processing in the display unit may be performed, for example, using a generation AI, or may be performed without using a generation AI. For example, the display unit can input the user's facial expression data to the generation AI and have the generation AI execute emotion estimation. This enables the display unit to change the display content according to the user's emotion.

[0074] The display unit can track the user's gaze and display information according to the position of the gaze. The display unit tracks the user's gaze using, for example, a camera-based gaze tracking technology. For example, when the user gazes at a specific icon, the display unit pops up information related to the icon. In addition, when the user gazes at a part of the screen for a long time, the display unit can also enlarge and display that part. Furthermore, when the user gazes in a specific direction, the display unit can display information related to that direction. For example, when the user gazes at the upper right of the screen, the display unit displays information related to the upper right. This allows the display unit to display information according to the user's gaze. The gaze tracking is realized using, for example, a camera-based gaze tracking technology or an infrared gaze tracking technology. A part or all of the above-mentioned processing in the display unit may be performed using, for example, a generation AI, or may be performed without using a generation AI. For example, the display unit can input the user's gaze data to the generation AI and cause the generation AI to execute information display according to the position of the gaze. This allows the display unit to display information according to the user's gaze.

[0075] The display unit can analyze the user's past usage history and select the optimal information display method. The display unit, for example, analyzes the user's past usage history and selects the optimal information display method. For example, the display unit preferentially displays information that the user frequently accessed in the past. The display unit can also analyze the user's past operation patterns and propose an optimal layout. Furthermore, the display unit can customize information to be displayed in a specific time period from the user's past usage history. For example, the display unit preferentially displays information that the user frequently accesses in the morning. This enables the display unit to display information based on the user's past usage history. A part or all of the above-mentioned processing in the display unit may be performed, for example, using a generation AI, or may be performed without using a generation AI. For example, the display unit can input the user's past usage history data to the generation AI and have the generation AI select the optimal information display method. This enables the display unit to display information based on the user's past usage history.

[0076] The display unit can estimate the user's emotion and adjust the brightness and color of the display based on the estimated user's emotion. For example, the display unit captures the user's facial expression with a camera and estimates the emotion using an emotion estimation algorithm. For example, the display unit calculates an emotion score based on the change in the facial expression and adjusts the brightness and color of the display. The display unit can also record the user's voice and estimate the emotion using a voice analysis technology. For example, the display unit analyzes the tone and speed of the voice, calculates an emotion score, and adjusts the brightness and color of the display. The display unit can also collect the user's biodata (heart rate and electrodermal activity) with a sensor and estimate the emotion using an emotion estimation algorithm. For example, the display unit calculates an emotion score based on the fluctuation of the heart rate and adjusts the brightness and color of the display. This enables the display unit to adjust the brightness and color of the display according to the user's emotion. The emotion estimation is realized using an emotion estimation function using, for example, an emotion engine or a generation AI. The generation AI may be a text generation AI (e.g., LLM) or a multimodal generation AI, but is not limited to such examples. Some or all of the above-mentioned processing in the display unit may be performed, for example, using the generation AI, or may be performed without using the generation AI. For example, the display unit can input the user's facial expression data to the generation AI and cause the generation AI to estimate emotions. This enables the display unit to adjust the brightness and color tone of the display according to the user's emotions.

[0077] The display unit can display highly relevant information with priority in consideration of the geographical location information of the user. The display unit, for example, acquires the geographical location information of the user and displays highly relevant information based on the information. For example, when the user is in a specific location, the display unit displays information related to the location. In addition, when the user is traveling, the display unit can also display tourist information of the travel destination with priority. Furthermore, when the user is at home, the display unit can also display weather information around the home. This enables the display unit to display information based on the geographical location information of the user. A part or all of the above-mentioned processing in the display unit may be performed, for example, using a generation AI, or may be performed without using a generation AI. For example, the display unit can input the geographical location information of the user to the generation AI and have the generation AI select highly relevant information. This enables the display unit to display information based on the geographical location information of the user.

[0078] The display unit can analyze the user's social media activity and display related information. The display unit can, for example, analyze the user's social media activity and display related information. For example, the display unit displays the latest posts of accounts that the user follows on social media. The display unit can also display news related to topics in which the user has shown interest on social media. Furthermore, the display unit can display event information of interest from the user's social media activity. This enables the display unit to display information based on the user's social media activity. A part or all of the above-mentioned processing in the display unit may be performed, for example, using a generation AI, or may be performed without using a generation AI. For example, the display unit can input the user's social media activity data to the generation AI and have the generation AI select related information. This enables the display unit to display information based on the user's social media activity.

[0079] The reception unit can estimate the user's emotion and adjust the timing of receiving the voice based on the estimated emotion of the user. For example, the reception unit captures the user's facial expression with a camera and estimates the emotion using an emotion estimation algorithm. For example, the reception unit calculates an emotion score based on a change in facial expression and adjusts the timing of receiving the voice. The reception unit can also record the user's voice and estimate the emotion using a voice analysis technology. For example, the reception unit analyzes the tone and speed of the voice, calculates an emotion score, and adjusts the timing of receiving the voice. The reception unit can also collect the user's biometric data (heart rate and electrodermal activity) with a sensor and estimate the emotion using an emotion estimation algorithm. For example, the reception unit calculates an emotion score based on the fluctuation of the heart rate and adjusts the timing of receiving the voice. This enables the reception unit to adjust the timing of receiving the voice according to the user's emotion. The emotion estimation is realized using an emotion estimation function using, for example, an emotion engine or a generation AI. The generation AI is a text generation AI (for example, LLM) or a multimodal generation AI, but is not limited to such examples. A part or all of the above-mentioned processing in the reception unit may be performed, for example, using the generation AI, or may be performed without using the generation AI. For example, the reception unit can input the user's facial expression data to the generation AI and have the generation AI execute emotion estimation. This enables the reception unit to adjust the timing of receiving the voice according to the user's emotion.

[0080] The reception unit can analyze the user's past voice input history and select the optimal reception method. The reception unit, for example, analyzes the user's past voice input history and selects the optimal reception method. For example, the reception unit preferentially accepts voice commands that the user has frequently used in the past. The reception unit can also analyze the user's past voice input patterns and select the optimal voice recognition algorithm. Furthermore, the reception unit can predict and accept a voice command to be used in a specific time period from the user's past voice input history. For example, the reception unit preferentially accepts a voice command that the user frequently uses in the morning. This enables the reception unit to select the optimal reception method based on the user's past voice input history. A part or all of the above-mentioned processing in the reception unit may be performed using, for example, a generation AI, or may be performed without using a generation AI. For example, the reception unit can input the user's past voice input history data to the generation AI and have the generation AI select the optimal reception method. This enables the reception unit to select the optimal reception method based on the user's past voice input history.

[0081] The reception unit can filter the user's current environmental sound to improve the accuracy of the voice input. The reception unit, for example, filters the user's current environmental sound to improve the accuracy of the voice input. For example, when the user is in a noisy environment, the reception unit filters the environmental sound to improve the accuracy of the voice input. In addition, when the user is in a quiet environment, the reception unit can adjust the sensitivity of the voice input to improve the accuracy. Furthermore, when the user is moving, the reception unit can filter the wind noise to improve the accuracy of the voice input. For example, when the user is in a car, the reception unit filters the environmental sound in the car to improve the accuracy of the voice input. This allows the reception unit to improve the accuracy of the voice input based on the user's current environmental sound. Part or all of the above-mentioned processing in the reception unit may be performed, for example, using a generation AI, or may be performed without using a generation AI. For example, the reception unit can input the user's environmental sound data to the generation AI and cause the generation AI to filter the environmental sound. This allows the reception unit to improve the accuracy of the voice input based on the user's current environmental sound.

[0082] The reception unit can estimate the user's emotion and determine the priority of the voice to be received based on the estimated emotion of the user. For example, the reception unit captures the user's facial expression with a camera and estimates the emotion using an emotion estimation algorithm. For example, the reception unit calculates an emotion score based on the change in facial expression and determines the priority of the voice to be received. The reception unit can also record the user's voice and estimate the emotion using a voice analysis technology. For example, the reception unit analyzes the tone and speed of the voice, calculates an emotion score, and determines the priority of the voice to be received. The reception unit can also collect the user's biometric data (heart rate and electrodermal activity) with a sensor and estimate the emotion using an emotion estimation algorithm. For example, the reception unit calculates an emotion score based on the fluctuation of the heart rate and determines the priority of the voice to be received. This enables the reception unit to determine the priority of the voice according to the user's emotion. The emotion estimation is realized using an emotion estimation function using, for example, an emotion engine or a generation AI. The generation AI may be, but is not limited to, a text generation AI (e.g., LLM) or a multimodal generation AI. Some or all of the above-mentioned processing in the reception unit may be performed, for example, using the generation AI, or may be performed without using the generation AI. For example, the reception unit may input the user's facial expression data to the generation AI and cause the generation AI to estimate emotions. This enables the reception unit to determine the priority order of voices according to the user's emotions.

[0083] The reception unit can preferentially receive a highly relevant voice in consideration of the geographical location information of the user. The reception unit, for example, acquires the geographical location information of the user and preferentially receives a highly relevant voice based on the information. For example, when the user is in a specific location, the reception unit preferentially receives a voice command related to the location. In addition, when the user is traveling, the reception unit can also preferentially receive a voice command related to the travel destination. Furthermore, when the user is at home, the reception unit can also preferentially receive a voice command related to the surroundings of the home. This enables the reception unit to preferentially receive a voice based on the geographical location information of the user. A part or all of the above-mentioned processing in the reception unit may be performed, for example, using a generation AI, or may be performed without using a generation AI. For example, the reception unit can input the geographical location information of the user to the generation AI and have the generation AI select a highly relevant voice. This enables the reception unit to preferentially receive a voice based on the geographical location information of the user.

[0084] The reception unit can analyze the social media activity of the user and receive the related voice. The reception unit, for example, analyzes the social media activity of the user and receives the related voice. For example, the reception unit receives a voice command related to an account that the user follows on social media. The reception unit can also receive a voice command related to a topic in which the user has shown an interest on social media. Furthermore, the reception unit can also receive a voice command related to an event of interest from the social media activity of the user. This enables the reception unit to receive the voice based on the social media activity of the user. A part or all of the above-mentioned processing in the reception unit may be performed, for example, using a generation AI, or may be performed without using a generation AI. For example, the reception unit can input the social media activity data of the user to the generation AI and have the generation AI select the related voice. This enables the reception unit to receive the voice based on the social media activity of the user.

[0085] The generation unit can estimate the user's emotion and adjust the way of expressing the response based on the estimated emotion of the user. For example, the generation unit captures the user's facial expression with a camera and estimates the emotion using an emotion estimation algorithm. For example, the generation unit calculates an emotion score based on the change in the facial expression and adjusts the way of expressing the response. The generation unit can also record the user's voice and estimate the emotion using a voice analysis technology. For example, the generation unit analyzes the tone and speed of the voice, calculates an emotion score, and adjusts the way of expressing the response. The generation unit can also collect the user's biometric data (heart rate and electrodermal activity) with a sensor and estimate the emotion using an emotion estimation algorithm. For example, the generation unit calculates an emotion score based on the fluctuation of the heart rate and adjusts the way of expressing the response. This enables the generation unit to adjust the way of expressing the response according to the emotion of the user. The emotion estimation is realized using an emotion estimation function using, for example, an emotion engine or a generation AI. The generation AI is a text generation AI (for example, LLM) or a multimodal generation AI, but is not limited to such examples. A part or all of the above-mentioned processing in the generation unit may be performed, for example, using a generation AI, or may be performed without using a generation AI. For example, the generation unit may input the user's facial expression data to the generation AI and cause the generation AI to estimate the emotion. This enables the generation unit to adjust the way in which the response is expressed according to the user's emotion.

[0086] The generation unit can analyze the user's past response history and select the optimal response generation method. The generation unit, for example, analyzes the user's past response history and selects the optimal response generation method. For example, the generation unit generates an optimal response based on a response pattern that the user has preferred in the past. The generation unit can also generate a response suitable for a specific time period from the user's past response history. Furthermore, the generation unit can analyze the user's past response history and select the most effective response method. This enables the generation unit to generate an optimal response based on the user's past response history. A part or all of the above-mentioned processing in the generation unit may be performed using, for example, a generation AI, or may be performed without using a generation AI. For example, the generation unit can input the user's past response history data to the generation AI and have the generation AI select the optimal response generation method. This enables the generation unit to generate an optimal response based on the user's past response history.

[0087] The generation unit can customize the content of the response based on the user's current situation. The generation unit customizes the content of the response based on the user's current situation, for example. For example, when the user is in a specific location, the generation unit generates a response including information related to the location. Also, when the user is in a specific time period, the generation unit can generate a response including information related to the time period. Furthermore, the generation unit can generate an optimal response based on the user's current activity. For example, when the user is exercising, the generation unit generates a response including information related to exercise. This allows the generation unit to customize the response based on the user's current situation. A part or all of the above-mentioned processing in the generation unit may be performed using, for example, a generation AI, or may be performed without using a generation AI. For example, the generation unit can input the user's current situation data to the generation AI and have the generation AI customize the content of the response. This allows the generation unit to customize the response based on the user's current situation.

[0088] The generation unit can estimate the user's emotion and adjust the length of the response based on the estimated user's emotion. For example, the generation unit captures the user's facial expression with a camera and estimates the emotion using an emotion estimation algorithm. For example, the generation unit calculates an emotion score based on the change in facial expression and adjusts the length of the response. The generation unit can also record the user's voice and estimate the emotion using a voice analysis technique. For example, the generation unit analyzes the tone and speed of the voice, calculates an emotion score, and adjusts the length of the response. The generation unit can also collect the user's biometric data (heart rate and electrodermal activity) with a sensor and estimate the emotion using an emotion estimation algorithm. For example, the generation unit calculates an emotion score based on the fluctuation of the heart rate and adjusts the length of the response. This enables the generation unit to adjust the length of the response according to the user's emotion. The emotion estimation is realized using an emotion estimation function using, for example, an emotion engine or a generation AI. The generation AI is a text generation AI (for example, LLM) or a multimodal generation AI, but is not limited to such examples. A part or all of the above-mentioned processing in the generation unit may be performed, for example, using a generation AI, or may be performed without using a generation AI. For example, the generation unit may input the user's facial expression data to the generation AI and cause the generation AI to estimate the emotion. This enables the generation unit to adjust the length of the response according to the user's emotion.

[0089] The generation unit can generate a highly relevant response in consideration of the geographical location information of the user. The generation unit, for example, acquires the geographical location information of the user and generates a highly relevant response based on the information. For example, when the user is in a specific location, the generation unit generates a response including information related to the location. In addition, when the user is traveling, the generation unit can also generate a response including information related to the travel destination. Furthermore, when the user is at home, the generation unit can also generate a response including information related to the surroundings of the home. This enables the generation unit to generate a response based on the geographical location information of the user. A part or all of the above-mentioned processing in the generation unit may be performed, for example, using a generation AI, or may be performed without using a generation AI. For example, the generation unit can input the geographical location information of the user to the generation AI and cause the generation AI to generate a highly relevant response. This enables the generation unit to generate a response based on the geographical location information of the user.

[0090] The generation unit can analyze the social media activity of the user and generate a relevant response. The generation unit can, for example, analyze the social media activity of the user and generate a relevant response. For example, the generation unit generates a response including information related to an account that the user follows on social media. The generation unit can also generate a response including information related to a topic in which the user has shown interest on social media. Furthermore, the generation unit can generate a response including information related to an event of interest from the user's social media activity. This enables the generation unit to generate a response based on the user's social media activity. A part or all of the above-mentioned processing in the generation unit may be performed, for example, using a generation AI, or may be performed without using a generation AI. For example, the generation unit can input the user's social media activity data to the generation AI and cause the generation AI to generate a relevant response. This enables the generation unit to generate a response based on the user's social media activity.

[0091] The output unit can estimate the user's emotion and adjust the output method based on the estimated user's emotion. For example, the output unit captures the user's facial expression with a camera and estimates the emotion using an emotion estimation algorithm. For example, the output unit calculates an emotion score based on the change in the facial expression and adjusts the output method. The output unit can also record the user's voice and estimate the emotion using a voice analysis technology. For example, the output unit analyzes the tone and speed of the voice, calculates an emotion score, and adjusts the output method. The output unit can also collect the user's biometric data (heart rate and electrodermal activity) with a sensor and estimate the emotion using an emotion estimation algorithm. For example, the output unit calculates an emotion score based on the fluctuation of the heart rate and adjusts the output method. This enables the output unit to adjust the output method according to the user's emotion. The emotion estimation is realized using an emotion estimation function using, for example, an emotion engine or a generation AI. The generation AI is a text generation AI (for example, LLM) or a multimodal generation AI, but is not limited to such examples. A part or all of the above-mentioned processing in the output unit may be performed, for example, using a generation AI, or may be performed without using a generation AI. For example, the output unit can input the user's facial expression data to the generation AI and have the generation AI estimate the emotion. This enables the output unit to adjust the output method according to the user's emotion.

[0092] The output unit can analyze the user's past output history and select the optimal output method. The output unit, for example, analyzes the user's past output history and selects the optimal output method. For example, the output unit selects the optimal output method based on the output format that the user has preferred in the past. The output unit can also select an output method suitable for a specific time period from the user's past output history. Furthermore, the output unit can analyze the user's past output history and select the most effective output method. This enables the output unit to select the optimal output method based on the user's past output history. A part or all of the above-mentioned processing in the output unit may be performed using, for example, a generation AI, or may be performed without using a generation AI. For example, the output unit can input the user's past output history data to the generation AI and have the generation AI select the optimal output method. This enables the output unit to select the optimal output method based on the user's past output history.

[0093] The output unit can customize the means of output based on the user's current environment. The output unit customizes the means of output based on the user's current environment, for example. For example, the output unit prioritizes visual output when the user is in a noisy environment. The output unit can also prioritize audio output when the user is in a quiet environment. Furthermore, the output unit can provide a concise and highly visible output when the user is moving. For example, the output unit prioritizes visual output and refrains from audio output when the user is in a car. This enables the output unit to customize the output means based on the user's current environment. A part or all of the above-mentioned processing in the output unit may be performed, for example, using a generation AI, or may be performed without using a generation AI. For example, the output unit can input the user's current environmental data to the generation AI and have the generation AI customize the means of output. This enables the output unit to customize the output means based on the user's current environment.

[0094] The output unit can estimate the user's emotion and determine the priority of output based on the estimated emotion of the user. For example, the output unit captures the user's facial expression with a camera and estimates the emotion using an emotion estimation algorithm. For example, the output unit calculates an emotion score based on the change in the facial expression and determines the priority of output. The output unit can also record the user's voice and estimate the emotion using a voice analysis technology. For example, the output unit analyzes the tone and speed of the voice, calculates an emotion score, and determines the priority of output. The output unit can also collect the user's biometric data (heart rate and electrodermal activity) with a sensor and estimate the emotion using an emotion estimation algorithm. For example, the output unit calculates an emotion score based on the fluctuation of the heart rate and determines the priority of output. This enables the output unit to determine the priority of output according to the user's emotion. The emotion estimation is realized using an emotion estimation function using, for example, an emotion engine or a generation AI. The generation AI is a text generation AI (for example, LLM) or a multimodal generation AI, but is not limited to such examples. A part or all of the above-mentioned processing in the output unit may be performed, for example, using a generation AI, or may be performed without using a generation AI. For example, the output unit can input the user's facial expression data to the generation AI and have the generation AI execute emotion estimation. This enables the output unit to determine the priority of the output according to the user's emotion.

[0095] The output unit can select the optimal output method in consideration of the geographical location information of the user. The output unit, for example, acquires the geographical location information of the user and selects the optimal output method based on the information. For example, when the user is in a specific location, the output unit preferentially outputs information related to the location. In addition, when the user is traveling, the output unit can also preferentially output information related to the travel destination. Furthermore, when the user is at home, the output unit can also preferentially output information related to the surroundings of the home. This enables the output unit to use the optimal output method based on the geographical location information of the user. A part or all of the above-mentioned processing in the output unit may be performed, for example, using a generation AI, or may be performed without using a generation AI. For example, the output unit can input the geographical location information of the user to the generation AI and have the generation AI select the optimal output method. This enables the output unit to use the optimal output method based on the geographical location information of the user.

[0096] The output unit can analyze the social media activity of the user and provide a related output. The output unit can, for example, analyze the social media activity of the user and provide a related output. For example, the output unit preferentially outputs information related to accounts that the user follows on social media. The output unit can also preferentially output information related to topics in which the user has shown interest on social media. Furthermore, the output unit can also preferentially output information related to events of interest from the user's social media activity. This enables the output unit to provide an output based on the user's social media activity. A part or all of the above-mentioned processing in the output unit may be performed, for example, using a generation AI, or may be performed without using a generation AI. For example, the output unit can input the user's social media activity data to the generation AI and have the generation AI select a related output. This enables the output unit to provide an output based on the user's social media activity.

[0097] The system according to the embodiment is not limited to the above-described example, and various modifications are possible, for example, as follows.

[0098] The reception unit can not only receive the user's voice, but also recognize the user's gestures and receive them as input. For example, when the user raises his / her hand, the reception unit recognizes the gesture and interprets it as a specific command. When the user points a finger, the reception unit can display information related to that direction. Furthermore, if the user repeats a specific gesture, a custom command corresponding to that gesture can be set. This allows the user to operate the system using gestures as well as voice.

[0099] The generation unit can generate a personalized response by taking into account not only the user's past dialogue history but also the user's current activity status. For example, if the user is exercising, the generation unit can provide advice and information related to exercise. Also, if the user is working, the generation unit can suggest efficient methods and tools related to work. Furthermore, during the user's time of relaxation, the generation unit can provide music and entertainment information suitable for relaxation. This allows the generation unit to provide an optimal response according to the user's current situation.

[0100] The generator can not only learn the user's preferences and habits, but also monitor the user's health condition and provide a response based thereon. For example, the generator can monitor the user's heart rate and blood pressure, and provide appropriate advice and warnings when abnormalities are detected. The generator can also analyze the user's sleep patterns and provide suggestions for improving sleep quality. Furthermore, the generator can record the user's dietary history and provide healthy dietary suggestions. This allows the generator to provide a response based on the user's health condition.

[0101] The generator can estimate the user's emotions, as well as evaluate the user's stress level and adjust the response based on the estimation. For example, the generator can estimate the user's stress level from the user's tone of voice and facial expression, and provide advice to relax if the user is in a high stress state. Also, if the user's stress level is low, the generator can provide challenging tasks or new information. Furthermore, the generator can adjust the tone and content of the response according to the user's stress level. This allows the generator to provide an optimal response according to the user's stress level.

[0102] The generation unit can not only analyze the user's past voice data, but also learn the user's pronunciation and accent and adjust the voice recognition algorithm based on the learned pronunciation and accent. For example, if the user has a specific accent, the generation unit selects a voice recognition algorithm that corresponds to the accent. The generation unit can also learn the user's pronunciation habits and make adjustments to reduce misrecognition. Furthermore, the generation unit can continuously learn the user's voice data and improve the accuracy of voice recognition. This allows the generation unit to realize optimal voice recognition according to the user's pronunciation and accent.

[0103] The display unit can not only estimate the user's emotions, but also evaluate the user's concentration level and adjust the display content based on the evaluation. For example, when the user is concentrating, important information can be displayed with emphasis. When the user is not concentrating, visually appealing content can be displayed to attract attention. Furthermore, the complexity and amount of information of the display content can be adjusted according to the user's concentration level. This allows the display unit to provide optimal display content according to the user's concentration level.

[0104] The display unit can not only track the user's gaze, but also estimate the target of the user's interest from the movement of the user's gaze and provide information based on the estimation. For example, if the user gazes at a specific icon, detailed information related to the icon is displayed. Also, if the user gazes at a specific part of the screen for a long time, information related to that part can be preferentially displayed. Furthermore, the display unit can estimate a topic of interest from the movement of the user's gaze and provide information related to that topic. This enables the display unit to provide optimal information according to the movement of the user's gaze.

[0105] The display unit can not only analyze the user's past usage history, but also customize the information display method based on the user's learning style. For example, if the user is a visual learner, a graphical display can be prioritized. Also, if the user is an auditory learner, audio information can be prioritized. Furthermore, if the user is a practical learner, interactive content can be provided. In this way, the display unit can provide the optimal information display method according to the user's learning style.

[0106] The display unit can not only estimate the user's emotion, but also evaluate the user's energy level and adjust the brightness and color tone of the display based on the evaluation. For example, when the user's energy level is high, the display can be made using bright and vivid colors. When the user's energy level is low, the display can be made using subdued colors. Furthermore, the brightness of the display can be adjusted according to the user's energy level. This allows the display unit to provide an optimal display according to the user's energy level.

[0107] The display unit can not only take into account the geographical location information of the user, but also analyze the user's movement pattern and provide information based on the analysis. For example, if the user frequently travels along a specific route, information related to that route is preferentially displayed. In addition, if the user travels to a new location, tourist information and restaurant information related to that location can be provided. Furthermore, the display unit can suggest optimal means of transportation and routes based on the user's movement pattern. This enables the display unit to provide optimal information according to the user's movement pattern.

[0108] The process flow of the second embodiment will be briefly described below.

[0109] Step 1: The display unit displays a user interface on the wearable device that allows input of information into the large-scale language model. The user interface may be, for example, a graphical user interface or a voice user interface. Step 2: The reception unit receives voice from the user, which includes, for example, the voice format and the voice quality. Step 3: The generation unit generates a response corresponding to the voice by inputting the voice received by the reception unit into a large-scale language model. The generation unit generates the response using, for example, a generation AI (for example, a text generation AI or a multimodal generation AI). The generation AI can use, for example, a large-scale language model such as GPT or Gemini. Step 4: The output unit outputs the response generated by the generation unit to the wearable device. The output unit can output, for example, audio or text.

[0110] 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 a voice indicating a user input for the result of the specific processing. The control unit 46A transmits the voice data indicating the user input acquired by the microphone 38B to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the voice data.

[0111] The data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of the data generation model 58 is ChatGPT (registered trademark) (Internet search<URL: https: / / openai.com / blog / chatgpt> ) and other generation AIs. The data generation model 58 is obtained by performing deep learning on a neural network. A prompt including an instruction is input to the data generation model 58, and inference data such as voice data indicating a voice, text data indicating a text, and image data indicating an image (e.g., still image data or video data) are input. The data generation model 58 infers the input inference data according to the instruction indicated by the prompt, and outputs the inference result in one or more data formats of voice data, text data, and image data. The data generation model 58 includes, for example, a text generation AI, an image generation AI, and a multimodal generation AI. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The specification processing unit 290 performs the above-mentioned specification processing while using the data generation model 58. The data generation model 58 may be a fine-tuned model so as to output an inference result from a prompt that does not include an instruction, and in this case, the data generation model 58 can output an inference result from a prompt that does not include an instruction. In the data processing device 12 and the like, the data generation model 58 includes a plurality of types, and the data generation model 58 includes an AI other than the generation AI. The AI ​​other than the generation AI is, for example, a linear regression, a logistic regression, a decision tree, a random forest, a support vector machine (SVM), a k-means clustering, a convolutional neural network (CNN), a recurrent neural network (RNN), a generative adversarial network (GAN), or a naive Bayes, and can perform various processes, but is not limited to such examples. The AI ​​may also be an AI agent. In addition, when the processes of each of the above-mentioned parts are performed by an AI, the processes are performed in part or in whole by the AI, but are not limited to such examples.In addition, processing performed by AI including the generation AI may be replaced with rule-based processing, and rule-based processing may be replaced with processing performed by AI including the generation AI.

[0112] Furthermore, the above-described processing by the data processing system 10 is executed by the specific processing unit 290 of the data processing device 12 or the control unit 46A of the smart device 14, but may also be executed by the specific processing unit 290 of the data processing device 12 and the control unit 46A of the smart device 14. Furthermore, the specific processing unit 290 of the data processing device 12 acquires or collects information required for processing from the smart device 14 or an external device, and the smart device 14 acquires or collects information required for processing from the data processing device 12 or an external device.

[0113] For example, the display unit is realized by the display 40A of the smart device 14. For example, the reception unit is realized by the touch panel 38A and microphone 38B of the smart device 14. For example, the generation unit is realized by the specific processing unit 290 of the data processing device 12. For example, the output unit is realized by the speaker 40B and display 40A of the smart device 14. The correspondence between each unit and the device or control unit is not limited to the above example, and various changes are possible.

[0114] [Second embodiment] FIG. 3 shows an example of the configuration of a data processing system 210 according to the second embodiment.

[0115] 3, the data processing system 210 includes the data processing device 12 and smart glasses 214. An example of the data processing device 12 is a server.

[0116] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, the RAM 30, and the storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN and / or a LAN.

[0117] The smart glasses 214 include a computer 36, a microphone 238, a speaker 240, a camera 42, and a communication I / F 44. The computer 36 includes a processor 46, a RAM 48, and a storage 50. The processor 46, the RAM 48, and the storage 50 are connected to a bus 52. The microphone 238, the speaker 240, and the camera 42 are also connected to the bus 52.

[0118] The microphone 238 receives instructions and the like from the user by receiving voice uttered by the user. The microphone 238 captures the voice uttered by the user, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs the voice according to instructions from the processor 46.

[0119] Camera 42 is a small digital camera equipped with an optical system including a lens, an aperture, and a shutter, and an imaging element such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the user's surroundings (e.g., an imaging range defined by an angle of view equivalent to the width of the field of vision of an average healthy person).

[0120] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 are responsible for the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is performed in a secure state.

[0121] Fig. 4 shows an example of main functions of the data processing device 12 and the smart glasses 214. As shown in Fig. 4, in the data processing device 12, a specific process is performed by the processor 28. A specific process program 56 is stored in the storage 32.

[0122] 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.

[0123] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290. The identification processing unit 290 can estimate the emotion of the user using the emotion identification model 59 and perform identification processing using the user's emotion. In the emotion estimation function (emotion identification function) using the emotion identification model 59, various estimations and predictions regarding the user's emotion, including estimation and prediction of the user's emotion, are performed, but are not limited to such examples. In addition, the estimation and prediction of the emotion also include, for example, analysis of the emotion.

[0124] In the smart glasses 214, the specific processing is performed by the processor 46. The storage 50 stores a specific processing program 60. The processor 46 reads the specific processing program 60 from the storage 50 and executes the read specific processing program 60 on the RAM 48. The specific processing is realized by the processor 46 operating as the control unit 46A in accordance with the specific processing program 60 executed on the RAM 48. Note that the smart glasses 214 have a data generation model and an emotion identification model similar to the data generation model 58 and the emotion identification model 59, and can also perform processing similar to that of the specific processing unit 290 using these models.

[0125] Note that a device other than the data processing device 12 may have the data generation model 58. For example, a server device may have the data generation model 58. In this case, the data processing device 12 obtains a processing result (such as a prediction result) using the data generation model 58 by communicating with the server device having the data generation model 58. In addition, the data processing device 12 may be a server device, or may be a terminal device (such as a mobile phone, a robot, or a home appliance) owned by a user.

[0126] 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 a voice indicating a user input for the result of the specific processing. The control unit 46A transmits the voice data indicating the user input acquired by the microphone 238 to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the voice data.

[0127] The data generation model 58 is a so-called generative AI. An example of the data generation model 58 is a generative AI such as ChatGPT. The data generation model 58 is obtained by performing deep learning on a neural network. A prompt including an instruction is input to the data generation model 58, and inference data such as voice data indicating a voice, text data indicating a text, and image data indicating an image (e.g., still image data or video data) is input. The data generation model 58 infers the input inference data according to the instruction indicated by the prompt, and outputs the inference result in one or more data formats of voice data, text data, and image data. The data generation model 58 includes, for example, a text generation AI, an image generation AI, and a multimodal generation AI. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The specification processing unit 290 performs the above-mentioned specification processing while using the data generation model 58. The data generation model 58 may be a fine-tuned model so as to output an inference result from a prompt that does not include an instruction, and in this case, the data generation model 58 can output an inference result from a prompt that does not include an instruction. In the data processing device 12 and the like, the data generation model 58 includes a plurality of types, and the data generation model 58 includes an AI other than the generation AI. The AI ​​other than the generation AI is, for example, a linear regression, a logistic regression, a decision tree, a random forest, a support vector machine (SVM), a k-means clustering, a convolutional neural network (CNN), a recurrent neural network (RNN), a generative adversarial network (GAN), or a naive Bayes, and can perform various processes, but is not limited to such examples. The AI ​​may be an AI agent. In addition, when the processes of each part described above are performed by an AI, the processes are performed in part or in whole by the AI, but are not limited to such examples. In addition, the processes performed by the AI ​​including the generation AI may be replaced with rule-based processes, and the rule-based processes may be replaced with processes performed by the AI ​​including the generation AI.

[0128] The data processing system 210 according to the second embodiment performs the same processing as the data processing system 10 according to the first embodiment. The processing by the data processing system 210 is executed by the specific processing unit 290 of the data processing device 12 or the control unit 46A of the smart glasses 214, but may be executed by the specific processing unit 290 of the data processing device 12 and the control unit 46A of the smart glasses 214. In addition, the specific processing unit 290 of the data processing device 12 acquires or collects information required for processing from the smart glasses 214 or an external device, and the smart glasses 214 acquires or collects information required for processing from the data processing device 12 or an external device.

[0129] For example, the display unit is realized by the display of the smart glasses 214. For example, the reception unit is realized by the microphone 238 of the smart glasses 214. For example, the generation unit is realized by the specific processing unit 290 of the data processing device 12. For example, the output unit is realized by the speaker 240 and display of the smart glasses 214. The correspondence between each unit and the device or control unit is not limited to the above example, and various changes are possible.

[0130] [Third embodiment] FIG. 5 shows an example of the configuration of a data processing system 310 according to the third embodiment.

[0131] 5, the data processing system 310 includes the data processing device 12 and a headset type terminal 314. An example of the data processing device 12 is a server.

[0132] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, the RAM 30, and the storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN and / or a LAN.

[0133] The headset type terminal 314 includes a computer 36, a microphone 238, a speaker 240, a camera 42, a communication I / F 44, and a display 343. The computer 36 includes a processor 46, a RAM 48, and a storage 50. The processor 46, the RAM 48, and the storage 50 are connected to a bus 52. The microphone 238, the speaker 240, the camera 42, and the display 343 are also connected to the bus 52.

[0134] The microphone 238 receives instructions and the like from the user by receiving voice uttered by the user. The microphone 238 captures the voice uttered by the user, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs the voice according to instructions from the processor 46.

[0135] Camera 42 is a small digital camera equipped with an optical system including a lens, an aperture, and a shutter, and an imaging element such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the user's surroundings (e.g., an imaging range defined by an angle of view equivalent to the width of the field of vision of an average healthy person).

[0136] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 are responsible for the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is performed in a secure state.

[0137] Fig. 6 shows an example of the main functions of the data processing device 12 and the headset type terminal 314. As shown in Fig. 6, in the data processing device 12, a specific process is performed by the processor 28. A specific process program 56 is stored in the storage 32.

[0138] 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.

[0139] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290. The identification processing unit 290 can estimate the emotion of the user using the emotion identification model 59 and perform identification processing using the user's emotion. In the emotion estimation function (emotion identification function) using the emotion identification model 59, various estimations and predictions regarding the user's emotion, including estimation and prediction of the user's emotion, are performed, but are not limited to such examples. In addition, the estimation and prediction of the emotion also include, for example, analysis of the emotion.

[0140] In the headset type terminal 314, the specific processing is performed by the processor 46. The storage 50 stores a specific program 60. The processor 46 reads the specific program 60 from the storage 50, and executes the read specific program 60 on the RAM 48. The specific processing is realized by the processor 46 operating as the control unit 46A in accordance with the specific program 60 executed on the RAM 48. Note that the headset type terminal 314 has a data generation model and an emotion identification model similar to the data generation model 58 and the emotion identification model 59, and can also perform processing similar to that of the identification processing unit 290 using these models.

[0141] Note that a device other than the data processing device 12 may have the data generation model 58. For example, a server device may have the data generation model 58. In this case, the data processing device 12 obtains a processing result (such as a prediction result) using the data generation model 58 by communicating with the server device having the data generation model 58. In addition, the data processing device 12 may be a server device, or may be a terminal device (such as a mobile phone, a robot, or a home appliance) owned by a user.

[0142] The specific processing unit 290 transmits the result of the specific processing to the headset type terminal 314. In the headset type terminal 314, the control unit 46A causes the speaker 240 and the display 343 to output the result of the specific processing. The microphone 238 acquires voice indicating a user input for the result of the specific processing. The control unit 46A transmits voice data indicating the user input acquired by the microphone 238 to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the voice data.

[0143] The data generation model 58 is a so-called generative AI. An example of the data generation model 58 is a generative AI such as ChatGPT. The data generation model 58 is obtained by performing deep learning on a neural network. A prompt including an instruction is input to the data generation model 58, and inference data such as voice data indicating a voice, text data indicating a text, and image data indicating an image (e.g., still image data or video data) is input. The data generation model 58 infers the input inference data according to the instruction indicated by the prompt, and outputs the inference result in one or more data formats of voice data, text data, and image data. The data generation model 58 includes, for example, a text generation AI, an image generation AI, and a multimodal generation AI. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The specification processing unit 290 performs the above-mentioned specification processing while using the data generation model 58. The data generation model 58 may be a fine-tuned model so as to output an inference result from a prompt that does not include an instruction, and in this case, the data generation model 58 can output an inference result from a prompt that does not include an instruction. In the data processing device 12 and the like, the data generation model 58 includes a plurality of types, and the data generation model 58 includes an AI other than the generation AI. The AI ​​other than the generation AI is, for example, a linear regression, a logistic regression, a decision tree, a random forest, a support vector machine (SVM), a k-means clustering, a convolutional neural network (CNN), a recurrent neural network (RNN), a generative adversarial network (GAN), or a naive Bayes, and can perform various processes, but is not limited to such examples. The AI ​​may be an AI agent. In addition, when the processes of each part described above are performed by an AI, the processes are performed in part or in whole by the AI, but are not limited to such examples. In addition, the processes performed by the AI ​​including the generation AI may be replaced with rule-based processes, and the rule-based processes may be replaced with processes performed by the AI ​​including the generation AI.

[0144] The data processing system 310 according to the third embodiment performs the same processing as the data processing system 10 according to the first embodiment. The processing by the data processing system 310 is executed by the specific processing unit 290 of the data processing device 12 or the control unit 46A of the headset type terminal 314, but may be executed by the specific processing unit 290 of the data processing device 12 and the control unit 46A of the headset type terminal 314. In addition, the specific processing unit 290 of the data processing device 12 acquires or collects information required for processing from the headset type terminal 314 or an external device, and the headset type terminal 314 acquires or collects information required for processing from the data processing device 12 or an external device.

[0145] For example, the display unit is realized by the display 343 of the headset type terminal 314. For example, the reception unit is realized by the microphone 238 of the headset type terminal 314. For example, the generation unit is realized by the specific processing unit 290 of the data processing device 12. For example, the output unit is realized by the speaker 240 and display 343 of the headset type terminal 314. The correspondence between each unit and the device or control unit is not limited to the above-mentioned example, and various changes are possible.

[0146] [Fourth embodiment] FIG. 7 shows an example of the configuration of a data processing system 410 according to the fourth embodiment.

[0147] 7, a data processing system 410 includes a data processing device 12 and a robot 414. An example of the data processing device 12 is a server.

[0148] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, the RAM 30, and the storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN and / or a LAN.

[0149] The robot 414 includes a computer 36, a microphone 238, a speaker 240, a camera 42, a communication I / F 44, and a control target 443. The computer 36 includes a processor 46, a RAM 48, and a storage 50. The processor 46, the RAM 48, and the storage 50 are connected to a bus 52. In addition, the microphone 238, the speaker 240, the camera 42, and the control target 443 are also connected to the bus 52.

[0150] The microphone 238 receives instructions and the like from the user by receiving voice uttered by the user. The microphone 238 captures the voice uttered by the user, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs the voice according to instructions from the processor 46.

[0151] Camera 42 is a small digital camera equipped with an optical system including a lens, an aperture, and a shutter, and an imaging element such as a CMOS image sensor or a CCD image sensor, and captures images of the user's surroundings (e.g., an imaging range defined by an angle of view equivalent to the width of the field of vision of a typical healthy person).

[0152] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 are responsible for the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is performed in a secure state.

[0153] The control object 443 includes a display device, LEDs in the eyes, and motors for driving the arms, hands, and legs. The posture and behavior of the robot 414 are controlled by controlling the motors of the arms, hands, and legs. Some of the emotions of the robot 414 can be expressed by controlling these motors. In addition, the facial expressions of the robot 414 can also be expressed by controlling the light emission state of the LEDs in the eyes of the robot 414.

[0154] Fig. 8 shows an example of the main functions of the data processing device 12 and the robot 414. As shown in Fig. 8, in the data processing device 12, a specific process is performed by the processor 28. A specific process program 56 is stored in the storage 32.

[0155] 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.

[0156] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290. The identification processing unit 290 can estimate the emotion of the user using the emotion identification model 59 and perform identification processing using the user's emotion. In the emotion estimation function (emotion identification function) using the emotion identification model 59, various estimations and predictions regarding the user's emotion, including estimation and prediction of the user's emotion, are performed, but are not limited to such examples. In addition, the estimation and prediction of the emotion also include, for example, analysis of the emotion.

[0157] In the robot 414, the specific processing is performed by the processor 46. The storage 50 stores a specific program 60. The processor 46 reads out the specific program 60 from the storage 50, and executes the specific program 60 on the RAM 48. The specific processing is realized by the processor 46 operating as the control unit 46A in accordance with the specific program 60 executed on the RAM 48. The robot 414 has a data generation model and an emotion identification model similar to the data generation model 58 and the emotion identification model 59, and can also perform processing similar to that of the specific processing unit 290 using these models.

[0158] Note that a device other than the data processing device 12 may have the data generation model 58. For example, a server device may have the data generation model 58. In this case, the data processing device 12 obtains a processing result (such as a prediction result) using the data generation model 58 by communicating with the server device having the data generation model 58. In addition, the data processing device 12 may be a server device, or may be a terminal device (such as a mobile phone, a robot, or a home appliance) owned by a user.

[0159] The specific processing unit 290 transmits the result of the specific processing to the robot 414. In the robot 414, the control unit 46A causes the speaker 240 and the control target 443 to output the result of the specific processing. The microphone 238 acquires a voice indicating a user input for the result of the specific processing. The control unit 46A transmits voice data indicating the user input acquired by the microphone 238 to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the voice data.

[0160] The data generation model 58 is a so-called generative AI. An example of the data generation model 58 is a generative AI such as ChatGPT. The data generation model 58 is obtained by performing deep learning on a neural network. A prompt including an instruction is input to the data generation model 58, and inference data such as voice data indicating a voice, text data indicating a text, and image data indicating an image (e.g., still image data or video data) is input. The data generation model 58 infers the input inference data according to the instruction indicated by the prompt, and outputs the inference result in one or more data formats of voice data, text data, and image data. The data generation model 58 includes, for example, a text generation AI, an image generation AI, and a multimodal generation AI. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The specification processing unit 290 performs the above-mentioned specification processing while using the data generation model 58. The data generation model 58 may be a fine-tuned model so as to output an inference result from a prompt that does not include an instruction, and in this case, the data generation model 58 can output an inference result from a prompt that does not include an instruction. In the data processing device 12 and the like, the data generation model 58 includes a plurality of types, and the data generation model 58 includes an AI other than the generation AI. The AI ​​other than the generation AI is, for example, a linear regression, a logistic regression, a decision tree, a random forest, a support vector machine (SVM), a k-means clustering, a convolutional neural network (CNN), a recurrent neural network (RNN), a generative adversarial network (GAN), or a naive Bayes, and can perform various processes, but is not limited to such examples. The AI ​​may be an AI agent. In addition, when the processes of each part described above are performed by an AI, the processes are performed in part or in whole by the AI, but are not limited to such examples. In addition, the processes performed by the AI ​​including the generation AI may be replaced with rule-based processes, and the rule-based processes may be replaced with processes performed by the AI ​​including the generation AI.

[0161] The data processing system 410 according to the fourth embodiment performs the same processing as the data processing system 10 according to the first embodiment. The processing by the data processing system 410 is executed by the specific processing unit 290 of the data processing device 12 or the control unit 46A of the robot 414, but may be executed by the specific processing unit 290 of the data processing device 12 and the control unit 46A of the robot 414. In addition, the specific processing unit 290 of the data processing device 12 acquires or collects information required for processing from the robot 414 or an external device, etc., and the robot 414 acquires or collects information required for processing from the data processing device 12 or an external device, etc.

[0162] For example, the display unit is realized by a display device of the robot 414. For example, the reception unit is realized by a microphone 238 of the robot 414. For example, the generation unit is realized by a specific processing unit 290 of the data processing device 12. For example, the output unit is realized by a speaker 240 and a display device of the robot 414. The correspondence between each unit and the device or control unit is not limited to the above-mentioned example, and various changes are possible.

[0163] The emotion identification model 59 as an emotion engine may determine the emotion of the user according to a specific mapping. Specifically, the emotion identification model 59 may determine the emotion of the user according to an emotion map (see FIG. 9), which is a specific mapping. Similarly, the emotion identification model 59 may determine the emotion of the robot, and the identification processing unit 290 may perform identification processing using the emotion of the robot.

[0164] FIG. 9 is a diagram showing an emotion map 400 on which multiple emotions are mapped. In the emotion map 400, emotions are arranged in concentric circles radiating from the center. The closer to the center of the concentric circles, the more primitive emotions are arranged. The more outside the concentric circles, the more emotions that represent states and actions that arise from a state of mind are arranged. Emotions are a concept that includes emotions and mental states. On the left side of the concentric circles, emotions that are generally generated from reactions that occur in the brain are arranged. On the right side of the concentric circles, emotions that are generally induced by situational judgment are arranged. On the upper and lower sides of the concentric circles, emotions that are generally generated from reactions that occur in the brain and are induced by situational judgment are arranged. In addition, on the upper side of the concentric circles, emotions of "pleasure" are arranged, and on the lower side, emotions of "discomfort" are arranged. In this way, in the emotion map 400, multiple emotions are mapped based on the structure in which emotions are generated, and emotions that tend to occur simultaneously are mapped close to each other.

[0165] These emotions are distributed in the 3 o'clock direction of emotion map 400 and usually fluctuate between relief and anxiety. In the right half of emotion map 400, situational awareness dominates over internal sensations, resulting in a sense of calm.

[0166] The inside of emotion map 400 represents what is going on inside one's mind, and the outside of emotion map 400 represents behavior, so the further out you go on emotion map 400, the more visible the emotions become (the more they are expressed in behavior).

[0167] Here, human emotions are based on various balances such as posture and blood sugar level, and when these balances are far from the ideal, it indicates an unpleasant state, and when they are close to the ideal, it indicates a pleasant state. Emotions can also be created for robots, cars, motorcycles, etc., based on various balances such as posture and battery level, so that when these balances are far from the ideal, it indicates an unpleasant state, and when they are close to the ideal, it indicates a pleasant state. The emotion map may be generated, for example, based on the emotion map of Dr. Mitsuyoshi (Research on speech emotion recognition and emotion brain physiological signal analysis system, Tokushima University, doctoral dissertation: https: / / ci.nii.ac.jp / naid / 500000375379). On the left half of the emotion map, emotions belonging to an area called "reaction" where sensation is dominant are lined up. On the right half of the emotion map, emotions belonging to an area called "situation" where situation recognition is dominant are lined up.

[0168] The emotion map defines two emotions that promote learning. The first is the negative emotion around the middle of "repentance" or "remorse" on the situation side. In other words, this 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 positive emotion around "desire" on the response side. In other words, this is when the robot has positive feelings such as "I want more" or "I want to know more."

[0169] The emotion identification model 59 inputs the user input to a pre-trained neural network, obtains emotion values ​​indicating each emotion shown in the emotion map 400, and determines the emotion of the user. This neural network is pre-trained based on multiple learning data that are combinations of the user input and emotion values ​​indicating each emotion shown in the emotion map 400. Furthermore, this neural network is trained so that emotions that are located close to each other have similar values, as in the emotion map 900 shown in Fig. 10. Fig. 10 shows an example in which multiple emotions, "relief," "calm," and "encouraging," have similar emotion values.

[0170] In the above embodiment, an example was given in which a specific process is performed by one computer 22, but the technology disclosed herein is not limited to this, and distributed processing of the specific process may be performed by multiple computers, including computer 22.

[0171] In the above embodiment, an example in which the specific processing program 56 is stored in the storage 32 has been described, but the technology of the present disclosure is not limited to this. For example, the specific processing program 56 may be stored in a portable computer-readable non-transitory storage medium such as a Universal Serial Bus (USB) memory. The specific processing program 56 stored in the non-transitory storage medium is installed in the computer 22 of the data processing device 12. The processor 28 executes the specific processing in accordance with the specific processing program 56.

[0172] In addition, 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 upon request from the data processing device 12.

[0173] It is not necessary to store all of the specific processing program 56 in a storage device such as a server connected to the data processing device 12 via the network 54, or to store all of the specific processing program 56 in the storage 32; only a portion of the specific processing program 56 may be stored.

[0174] As the hardware resource for executing the specific process, various processors as shown below can be used. An example of the processor is a CPU, which is a general-purpose processor that functions as a hardware resource for executing the specific process by executing software, i.e., a program. Another example of the processor is a dedicated electric circuit, which is a processor having a circuit configuration designed exclusively for executing a specific process, such as a Field-Programmable Gate Array (FPGA), a Programmable Logic Device (PLD), or an Application Specific Integrated Circuit (ASIC). Each processor has a built-in or connected memory, and each processor executes the specific process by using the memory.

[0175] The hardware resource that executes the specific process may be one of these various processors, or may be a combination of two or more processors of the same or different types (for example, a combination of multiple FPGAs, or a combination of a CPU and an FPGA). Also, the hardware resource that executes the specific process may be a single processor.

[0176] As an example of a configuration using one processor, first, one processor is configured by combining one or more CPUs and software, and this processor functions as a hardware resource that executes a specific process. Second, there is a configuration using a processor that realizes the functions of the entire system including multiple hardware resources that execute a specific process on a single IC chip, as typified by SoC (System-on-a-chip). In this way, a specific process is realized using one or more of the above-mentioned various processors as hardware resources.

[0177] Furthermore, more specifically, the hardware structure of these various processors can be an electric circuit that combines circuit elements such as semiconductor elements. The specific processes described above are merely examples. It goes without saying that unnecessary steps may be deleted, new steps may be added, or the order of processes may be changed without departing from the spirit of the invention.

[0178] In the above example, the first to fourth embodiments are described separately, but some or all of these embodiments may be combined. The smart device 14, the smart glasses 214, the headset terminal 314, and the robot 414 are only examples, and they may be combined with each other, or may be other devices. In the above example, the first and second embodiments are described separately, but they may be combined.

[0179] The above description and illustrations are detailed descriptions of the parts related to the technology of the present disclosure, and are merely an example of the technology of the present disclosure. For example, the above description of the configuration, function, action, and effect is an example of the configuration, function, action, and effect of the parts related to the technology of the present disclosure. Therefore, it goes without saying that unnecessary parts may be deleted, new elements may be added, or replaced with respect to the description and illustrations shown above, within the scope of the gist of the technology of the present disclosure. In addition, in order to avoid confusion and to facilitate understanding of the parts related to the technology of the present disclosure, the description and illustrations shown above omit explanations of technical common sense that do not require particular explanation in enabling the implementation of the technology of the present disclosure.

[0180] All publications, patent applications, and standards mentioned in this specification are herein incorporated by reference to the same extent as if each individual publication, patent application, and standard was specifically and individually indicated to be incorporated by reference.

[0181] (Appendix 1) a display unit that displays on a wearable device a user interface that enables input of information into the large-scale language model; A reception unit that receives voice from a user; a generation unit that generates a response corresponding to the speech by inputting the speech received by the reception unit into the large-scale language model; An output unit that outputs the response generated by the generation unit to the wearable device. A system characterized by: (Appendix 2) The generation unit is Generate personalized responses 2. The system of claim 1, (Appendix 3) The generation unit is Learns user preferences and habits and provides feedback to the generator 2. The system of claim 1, (Appendix 4) The generation unit is Estimate user emotions and adjust the accuracy of voice analysis based on the estimated user emotions 2. The system of claim 1, (Appendix 5) The generation unit is Analyze the user's past voice data and select the appropriate voice recognition algorithm 2. The system of claim 1, (Appendix 6) The display unit is Estimate the user's emotions and dynamically change the display content based on the estimated user emotions. 2. The system of claim 1, (Appendix 7) The display unit is Tracks the user's gaze and displays information according to the position of the gaze 2. The system of claim 1, (Appendix 8) The display unit is Analyze the user's past usage history and select the optimal information display method 2. The system of claim 1, (Appendix 9) The display unit is Estimate the user's emotions and adjust the brightness and color of the display based on the estimated user's emotions. 2. The system of claim 1, (Appendix 10) The display unit is Prioritize the display of relevant information by taking into account the user's geographic location 2. The system of claim 1, (Appendix 11) The display unit is Analyze your social media activity and display relevant information 2. The system of claim 1, (Appendix 12) The reception unit is A method for estimating a user's emotion and adjusting the timing of voice reception based on the estimated user's emotion 2. The system of claim 1, (Appendix 13) The reception unit is Analyze the user's past voice input history and select the optimal reception method 2. The system of claim 1, (Appendix 14) The reception unit is Filters the user's current ambient sounds to improve the accuracy of voice input 2. The system of claim 1, (Appendix 15) The reception unit is Estimate the user's emotions and prioritize the voices to be received based on the estimated user's emotions. 2. The system of claim 1, (Appendix 16) The reception unit is Prioritize relevant voice based on the user's geographic location 2. The system of claim 1, (Appendix 17) The reception unit is Analyze your social media activity and receive relevant audio 2. The system of claim 1, (Appendix 18) The generation unit is Inferring a user's emotions and adjusting the way responses are expressed based on the inferred user emotions 2. The system of claim 1, (Appendix 19) The generation unit is Analyze the user's past response history and select the optimal response generation method 2. The system of claim 1, (Appendix 20) The generation unit is Customize the content of your response based on the user's current situation 2. The system of claim 1, (Appendix 21) The generation unit is Inferring a user's emotion and adjusting the length of a response based on the estimated user's emotion 2. The system of claim 1, (Appendix 22) The generation unit is Generate relevant responses by taking into account the user's geographic location 2. The system of claim 1, (Appendix 23) The generation unit is Analyze users' social media activity and generate relevant responses 2. The system of claim 1, (Appendix 24) The output unit is Infer user emotions and adjust output methods based on the estimated user emotions 2. The system of claim 1, (Appendix 25) The output unit is Analyze the user's past output history and select the optimal output method 2. The system of claim 1, (Appendix 26) The output unit is Customize the output method based on the user's current environment 2. The system of claim 1, (Appendix 27) The output unit is Estimate user emotions and prioritize outputs based on the estimated user emotions. 2. The system of claim 1, (Appendix 28) The output unit is Select the optimal output method based on the user's geographic location 2. The system of claim 1, (Appendix 29) The output unit is Analyze your social media activity and provide relevant output 2. The system of claim 1, [Explanation of symbols]

[0182] 10, 210, 310, 410 Data Processing Systems 12 Data Processing Device 14 Smart Devices 214 Smart Glasses 314 Headset-type terminal 414 Robot

Claims

1. a display unit that displays on a wearable device a user interface that enables input of information into the large-scale language model; A reception unit that receives voice from a user; a generation unit that generates a response corresponding to the speech by inputting the speech received by the reception unit into the large-scale language model; An output unit that outputs the response generated by the generation unit to the wearable device. A system characterized by:

2. The generation unit is Generate personalized responses 2. The system of claim 1 .

3. The generation unit is Learn user preferences and habits and provide feedback to the generator 2. The system of claim 1 .

4. The generation unit is Estimate user emotions and adjust the accuracy of voice analysis based on the estimated user emotions 2. The system of claim 1 .

5. The generation unit is Analyze the user's past voice data and select the appropriate voice recognition algorithm 2. The system of claim 1 .

6. The display unit is Estimate the user's emotions and dynamically change the display content based on the estimated user emotions.

2. The system of claim 1 .

7. The display unit is Tracks the user's gaze and displays information according to the position of the gaze 2. The system of claim 1 .

8. The display unit is Analyze the user's past usage history and select the optimal information display method 2. The system of claim 1 .

9. The display unit is Estimate the user's emotions and adjust the brightness and color of the display based on the estimated user's emotions.

2. The system of claim 1 .

Images