System

Abstract

An object of a system according to an embodiment is to acquire information on surroundings when going out in real time and appropriately notify the information.SOLUTION: A system includes a sensor part, an analysis part, a notification part, and a confirmation part. The sensor unit acquires real-time information of surroundings. The analysis unit analyzes the information acquired by the sensor unit and detects supplementary information and danger information of the surroundings. The notification unit notifies the user of the information detected by the analysis unit. The confirmation unit recognizes the direction in which the user points the finger at the time of the route guidance, and determines whether or not the direction is correct.SELECTED DRAWING: Figure 1

Description

[Technical Field]

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

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

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

[0004] Conventional technologies have not adequately acquired information about the surroundings in real time when the user is out and provided appropriate notification, and there is room for improvement.

[0005] The system according to the embodiment aims to obtain information about the surroundings in real time when the user is out and to notify the user appropriately. [Means for solving the problem]

[0006] The system according to the embodiment includes a sensor unit, an analysis unit, a notification unit, and a confirmation unit. The sensor unit acquires real-time information about the surroundings. The analysis unit analyzes the information acquired by the sensor unit and detects supplemental information and danger information about the surroundings. The notification unit notifies the user of the information detected by the analysis unit. The confirmation unit recognizes the direction the user points when receiving route guidance and determines whether the direction is correct. [Effects of the Invention]

[0007] The system according to the embodiment can obtain information about the surroundings in real time when the user is out and can provide appropriate notification. [Brief explanation 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. [Figure 2] 1 is a conceptual diagram showing an example of main functions of a data processing device and a smart device according to a first embodiment. [Figure 3] FIG. 10 is a conceptual diagram showing an example of the configuration of a data processing system according to a second embodiment. [Figure 4] FIG. 10 is a conceptual diagram showing an example of main functions of a data processing device and smart glasses according to a second embodiment. [Figure 5] FIG. 10 is a conceptual diagram showing an example of the configuration of a data processing system according to a third embodiment. [Figure 6] FIG. 11 is a conceptual diagram showing an example of main functions of a data processing device and a headset-type terminal according to a third embodiment. [Figure 7] FIG. 10 is a conceptual diagram showing an example of the configuration of a data processing system according to a fourth embodiment. [Figure 8] FIG. 10 is a conceptual diagram showing an example of main functions of a data processing device and a robot according to a fourth embodiment. [Figure 9] 1 shows an emotion map onto which multiple emotions are mapped. [Figure 10] 1 shows an emotion map onto which multiple emotions are mapped. DETAILED DESCRIPTION OF THE INVENTION

[0009] An example of an embodiment of a system according to the technology of the present disclosure will be described below with reference to the accompanying drawings.

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

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

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

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

[0014] In the following embodiments, a communication I / F (Interface) with a symbol is an interface including a communication processor, an antenna, etc. The communication I / F controls communication between multiple computers. Examples of communication standards applied to the communication I / F include wireless communication standards including 5G (5th Generation Mobile Communication System), Wi-Fi (registered trademark), and 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. Furthermore, in this specification, the same concept as "A and / or B" is also applied when three or more things are expressed connected by "and / or."

[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, RAM 30, and 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 (for example, 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., audio and / or text). Display 40A displays visible information such as text and images in accordance with instructions from processor 46. Speaker 40B outputs audio in accordance with 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 CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor.

[0022] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 control the exchange of various information between the processor 46 and the processor 28 via the network 54.

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

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

[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 a user's emotion using the emotion identification model 59 and perform identification processing using the user's emotion. The emotion estimation function (emotion identification function) using the emotion identification model 59 performs various estimations and predictions regarding the user's emotion, including estimation and prediction of the user's emotion, but is not limited to these examples. Furthermore, the estimation and prediction of emotion also includes, for example, emotion analysis.

[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 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 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. Furthermore, the data processing device 12 may be a server device, or may be a terminal device owned by a user (e.g., a mobile phone, a robot, a home appliance, etc.). Next, an example of processing by the data processing system 10 according to the first embodiment will be described.

[0028] (Example 1) An assistant system according to an embodiment of the present invention uses a mobile device or wearable device to acquire real-time images, videos, and audio of the surrounding environment, which are then analyzed by a multimodal generation AI to detect supplementary information and hazard information about the surrounding area and notify the user. The assistant system acquires real-time information about the surrounding environment, analyzes it using a generation AI, detects the supplementary information and hazard information, and notifies the user. When providing directions, the system also has a double-check function that recognizes the direction the user points and determines whether the direction is correct. For example, the assistant system uses a mobile device to capture images of the user's field of view with a camera and collects surrounding audio with a microphone. This information is input into the multimodal generation AI. The generation AI then analyzes the acquired information and detects supplementary information and hazard information about the surrounding area. For example, the generation AI analyzes images to identify the locations of pedestrians and vehicles and detect dangerous situations. It can also analyze audio to detect sirens and warning sounds from emergency vehicles. The detected information is then notified to the user. For example, the supplementary information and hazard information may be displayed on the mobile device's display or may also be notified by audio. Furthermore, when providing directions, the camera recognizes the direction the user points, and the generating AI determines whether that direction is correct. This allows users to receive accurate directions and supports the smooth completion of tasks. This allows the assistant system to improve safety when going out and support the smooth completion of tasks. By obtaining information about the user's surroundings in real time and analyzing, notifying, and confirming it, the assistant system can support the user's safety and the smooth completion of tasks. For example, even if people with visual or hearing impairments have difficulty understanding their surroundings, they can use this assistant to go out safely. The route guidance function also helps them reach their destination without getting lost.

[0029] The assistant system according to the embodiment includes a sensor unit, an analysis unit, a notification unit, and a confirmation unit. The sensor unit acquires real-time information about the surroundings. Examples of the real-time information about the surroundings include, but are not limited to, environmental data, location information, and audio data. The sensor unit acquires real-time images and audio information about the surroundings using, for example, a camera and a microphone. The sensor unit can also acquire environmental data using a temperature sensor and a humidity sensor. For example, the sensor unit acquires high-resolution images using a camera and collects high-sensitivity audio data using a microphone. The temperature sensor measures the surrounding temperature in real time, and the humidity sensor measures the surrounding humidity in real time. The analysis unit analyzes the information acquired by the sensor unit using a generation AI. The analysis unit detects supplementary information and danger information about the surroundings using, for example, image recognition technology and voice recognition technology. For example, the generation AI identifies the locations of pedestrians and vehicles and detects dangerous situations using image recognition technology. The generation AI can also detect sirens and warning sounds of emergency vehicles using voice recognition technology. The analysis unit can also use the generation AI to detect detailed information about surrounding objects and weather information. For example, the generation AI can use object detection technology to identify the location and type of surrounding objects and analyze weather information to understand the current weather. The notification unit notifies the user of the information detected by the analysis unit. The notification unit can notify the user of supplementary information and danger information using, for example, a display or an audio output device. For example, the notification unit can display the supplementary information or danger information on a display and notify the user by voice using an audio output device. The notification unit can also notify the user by vibration using a vibration device. For example, the notification unit can display text information on a display and play an audio message using an audio output device. The vibration device can be worn in the user's pocket or on the user's arm and notify the user by vibration. The confirmation unit recognizes the direction the user points their finger when receiving directions and determines whether that direction is correct. For example, the confirmation unit can recognize the direction of the user's finger using a camera, and the analysis unit can determine whether that direction is correct. For example, the confirmation unit can track the user's finger movement using a camera, and the generation AI can determine whether that direction is correct.The confirmation unit can also analyze the user's finger movements in real time and provide feedback indicating the correct direction. For example, the confirmation unit recognizes the user's finger movements using a camera, and the generation AI determines whether the direction is correct and displays the feedback on the display. As a result, the assistant system according to the embodiment can obtain information about the user's surroundings in real time and analyze, notify, and confirm the information, thereby supporting the user's safety and smooth task execution.

[0030] The sensor unit can acquire real-time images or audio information of the surroundings using a camera or a microphone. Examples of real-time images include, but are not limited to, the resolution and frame rate of the camera. The sensor unit can acquire high-resolution images using, for example, a camera. For example, the sensor unit can acquire images at 30 frames per second using a 4K resolution camera. The sensor unit can also collect highly sensitive audio data using a microphone. For example, the sensor unit can clearly collect surrounding audio using a directional microphone. This allows accurate acquisition of real-time information of the surroundings using a camera or microphone. Some or all of the above-described processing in the sensor unit may be performed using, for example, AI, or may be performed without using AI. For example, the sensor unit can input image data acquired by a camera to a generation AI and have the generation AI analyze the image data.

[0031] The analysis unit can detect supplementary information or danger information about the surroundings using image recognition technology or voice recognition technology. Image recognition technology includes, but is not limited to, object detection, face recognition, pattern recognition, etc. The analysis unit can, for example, use object detection technology to identify the location and type of surrounding objects. For example, the analysis unit can use generation AI to detect objects in an image and identify their location and type. The analysis unit can also use face recognition technology to identify specific people. For example, the analysis unit can use generation AI to detect faces in an image and identify specific people. The analysis unit can also detect specific patterns using pattern recognition technology. For example, the analysis unit can use generation AI to detect specific patterns in an image and detect supplementary information or danger information based on the patterns. Voice recognition technology includes, but is not limited to, voice command recognition and voice transcription. The analysis unit can, for example, use voice command recognition technology to recognize a user's voice commands. For example, the analysis unit can use generation AI to analyze a user's voice commands and detect supplementary information or danger information based on the content of the commands. The analysis unit can also convert voice data into text data using voice transcription technology. For example, the analysis unit can use a generation AI to convert voice data into text data and detect supplementary information or danger information based on the content of the text. This allows for accurate detection of surrounding supplementary information or danger information using image recognition technology or voice recognition technology. Some or all of the above-described processing in the analysis unit may be performed using AI, for example, or may be performed without using AI. For example, the analysis unit can input image data or voice data into the generation AI and have the generation AI detect supplementary information or danger information.

[0032] The notification unit may notify the user of the supplemental information or danger information using a display or an audio output device. Examples of displays include, but are not limited to, a liquid crystal display, an LED display, etc. The notification unit may display the supplemental information or danger information using, for example, an LCD display. For example, the notification unit may display text information or graphic information on an LCD display. The notification unit may also display the supplemental information or danger information using an LED display. For example, the notification unit may display a warning message or an icon on an LED display. Examples of audio output devices include, but are not limited to, a speaker, earphones, etc. The notification unit may notify the user of the supplemental information or danger information by audio, for example, using a speaker. For example, the notification unit may play an audio message using a speaker. The notification unit may also notify the user of the supplemental information or danger information by audio using earphones. For example, the notification unit may provide a private audio message to the user using earphones. This allows the user to be effectively notified of the supplemental information or danger information using a display or an audio output device. Some or all of the above-described processing in the notification unit may be performed using, for example, AI, or may be performed without using AI. For example, the notification unit can use a generation AI to generate supplementary information or danger information and notify it via a display or audio output device.

[0033] The confirmation unit can recognize the direction of the user's finger using a camera and determine whether the direction is correct using an analysis unit. The finger direction can include, but is not limited to, the camera usage method and the recognition algorithm. The confirmation unit can recognize the direction of the user's finger using a camera. For example, the confirmation unit can track the movement of the user's finger using a camera and recognize its direction. The confirmation unit can also determine whether the direction of the user's finger is correct using a recognition algorithm. For example, the confirmation unit can analyze the direction of the user's finger using a generation AI and determine whether the direction is correct. This enables accurate route guidance by recognizing the direction of the user's finger using a camera and determining whether the direction is correct using an analysis unit. Some or all of the above-described processing in the confirmation unit can be performed using, for example, AI, or without AI. For example, the confirmation unit can input the user's finger movement data acquired by a camera into the generation AI and have the generation AI recognize the finger direction and determine its accuracy.

[0034] The sensor unit can switch the sensor's operating mode based on the surrounding environmental conditions. The sensor unit detects environmental conditions such as weather and time of day. For example, the sensor unit can detect weather using a temperature sensor or humidity sensor. The sensor unit can also detect time of day using a light sensor. For example, the sensor unit can analyze the surrounding environmental conditions and identify the weather and time of day using a generation AI. Based on the detected environmental conditions, the sensor unit switches the sensor's operating mode. For example, when it rains, the sensor unit adjusts the camera's sensitivity to minimize obstruction of visibility caused by raindrops. At night, the sensor unit can use an infrared sensor to acquire information about the surroundings even in dark places. Furthermore, during bright daytime hours, the sensor unit can acquire information about the surroundings in normal camera mode. This enables optimal information acquisition by switching the sensor's operating mode according to the surrounding environmental conditions. Some or all of the above-described processing in the sensor unit may be performed using AI, for example, or without AI. For example, the sensor unit can input data acquired by a temperature sensor or light sensor into the generation AI and have the generation AI switch the operating mode.

[0035] The sensor unit can change the type of information it acquires based on the user's current task. For example, the sensor unit identifies the user's current task. For example, the sensor unit can analyze the user's schedule and location information to identify the current task. For example, the sensor unit can use a generation AI to analyze the user's schedule data and location data to identify the current task. Based on the identified task, the sensor unit changes the type of information it acquires. For example, if the user needs directions, it can prioritize acquiring map information and surrounding landmark information. Also, if the user is shopping, it can prioritize acquiring store information and product location information. Furthermore, if the user is exercising, it can prioritize acquiring information about surrounding obstacles and pedestrians. This allows the type of information to be dynamically changed depending on the user's current task, thereby prioritizing the acquisition of necessary information. Some or all of the above-described processing in the sensor unit may be performed using, for example, AI, or may be performed without AI. For example, the sensor unit can input the user's schedule data and location data into the generation AI and cause the generation AI to change the type of information it acquires.

[0036] The sensor unit can adjust the accuracy of the acquired information based on the user's past behavioral history. The sensor unit, for example, analyzes the user's past behavioral history. For example, the sensor unit can analyze the user's movement route and usage history to identify the user's past behavioral history. For example, the sensor unit can use a generation AI to analyze the user's movement data and usage data to identify the user's past behavioral history. Based on the identified behavioral history, the sensor unit adjusts the accuracy of the acquired information. For example, if the user has previously been lost in a specific location, the accuracy of information acquisition for that location can be increased. Also, if the user has previously felt unsafe during a specific time period, the accuracy of information acquisition for that time period can be increased. Furthermore, if the user has frequently performed a specific task in the past, the accuracy of information acquisition related to that task can be increased. This enables more accurate information acquisition by optimizing the accuracy of the information based on the user's past behavioral history. Some or all of the above-described processing in the sensor unit may be performed using, for example, AI, or without AI. For example, the sensor unit can input the user's movement data and usage data into the generation AI and have the generation AI adjust the accuracy of the information.

[0037] The sensor unit can select the information to be acquired based on the user's geographical location information. The sensor unit can acquire the user's geographical location information, for example, using GPS data or a location information service. For example, the sensor unit can identify the user's current location using a GPS device. The sensor unit can also acquire the user's geographical location information using a location information service. For example, the sensor unit can analyze the user's location data and identify the user's current geographical location using a generation AI. The sensor unit selects the information to be acquired based on the acquired geographical location information. For example, if the user is in a specific area, information related to that area can be preferentially acquired. Also, if the user is in a tourist destination, information about tourist spots and famous places can be preferentially acquired. Furthermore, if the user is near their home, information about nearby stores and facilities can be preferentially acquired. This allows necessary information to be preferentially acquired by filtering information based on the user's geographical location information. Some or all of the above-described processing in the sensor unit may be performed using AI, for example, or may be performed without using AI. For example, the sensor unit can input GPS data or data obtained from location information services into the generation AI, allowing the generation AI to select the information.

[0038] The sensor unit can adjust the information it acquires based on the user's social media activity. For example, the sensor unit analyzes the user's social media posts and like history. For example, the sensor unit can analyze the user's social media account and identify past posts and like history. For example, the sensor unit can use a generation AI to analyze the user's social media data and identify past activity history. Based on the identified social media activity, the sensor unit adjusts the information it acquires. For example, the sensor unit can prioritize acquiring information about locations where the user has checked in on social media. The sensor unit can also analyze the user's social media posts and prioritize acquiring related information. Furthermore, the sensor unit can prioritize acquiring related information based on the activity of the user's friends on social media. This allows the information to be customized based on the user's social media activity, thereby acquiring highly relevant information. Some or all of the above-described processing by the sensor unit may be performed using, for example, AI, or may be performed without using AI. For example, the sensor unit can input the user's social media data into a generation AI and have the generation AI adjust the information.

[0039] The sensor unit can change the information to be acquired based on the user's past feedback. The sensor unit, for example, analyzes the user's past feedback. For example, the sensor unit can analyze the user's ratings and comments to identify past feedback. For example, the sensor unit can use a generation AI to analyze the user's feedback data and identify past feedback. Based on the identified feedback, the sensor unit changes the information to be acquired. For example, if the user has placed importance on specific information in the past, the sensor unit can prioritize acquisition of that information. Also, if the user has ignored specific information in the past, the sensor unit can reduce the frequency of acquisition of that information. Furthermore, the sensor unit can analyze the user's past feedback and suggest an optimal information acquisition method. This enables more appropriate information acquisition by adjusting the information based on the user's past feedback. Some or all of the above-described processing in the sensor unit may be performed using, for example, AI, or may be performed without using AI. For example, the sensor unit can input the user's feedback data to the generation AI and have the generation AI change the information.

[0040] The analysis unit can change the algorithm to be used based on the type of acquired information. The analysis unit, for example, identifies the type of acquired information. For example, the analysis unit can analyze image data or audio data to identify the type of information. For example, the analysis unit can use a generation AI to analyze the acquired data and identify the type of information. Based on the identified type of information, the analysis unit changes the algorithm to be used. For example, if there is a lot of image information, an image recognition algorithm can be used preferentially. Also, if there is a lot of audio information, a voice recognition algorithm can be used preferentially. Furthermore, if there is a lot of both image and audio, a multimodal analysis algorithm can be used. This enables more accurate analysis by dynamically changing the algorithm depending on the type of acquired information. Some or all of the above-mentioned processing in the analysis unit can be performed using, for example, AI, or without AI. For example, the analysis unit can input the acquired data to the generation AI and cause the generation AI to change the algorithm to be used.

[0041] The analysis unit can prioritize the information to be analyzed based on the user's current task. The analysis unit, for example, identifies the user's current task. For example, the analysis unit can analyze the user's schedule and location information to identify the current task. For example, the analysis unit can use a generation AI to analyze the user's schedule data and location data to identify the current task. Based on the identified task, the analysis unit determines the priority of the information to be analyzed. For example, if the user needs directions, map information and landmark information can be analyzed preferentially. Also, if the user is shopping, store information and product location information can be analyzed preferentially. Furthermore, if the user is exercising, surrounding obstacle information and pedestrian information can be analyzed preferentially. Thus, by determining the priority of information based on the user's current task, necessary information can be analyzed preferentially. Some or all of the above-described processing in the analysis unit may be performed using, for example, AI, or without AI. For example, the analysis unit can input the user's schedule data and location data into the generation AI and have the generation AI determine the priority of the information.

[0042] The analysis unit can adjust the accuracy of the analyzed information based on the user's past behavioral history. The analysis unit, for example, analyzes the user's past behavioral history. For example, the analysis unit can analyze the user's travel route and usage history to identify the user's past behavioral history. For example, the analysis unit can use a generation AI to analyze the user's travel data and usage data to identify the user's past behavioral history. Based on the identified behavioral history, the analysis unit adjusts the accuracy of the analyzed information. For example, if the user has previously been lost in a specific location, the accuracy of the information analysis for that location can be improved. Also, if the user has previously felt unsafe during a specific time period, the accuracy of the information analysis for that time period can be improved. Furthermore, if the user has frequently performed a specific task in the past, the accuracy of the information analysis related to that task can be improved. This enables more accurate analysis by optimizing the accuracy of the information based on the user's past behavioral history. Some or all of the above-described processing in the analysis unit may be performed using AI, for example, or without AI. For example, the analysis unit can input the user's travel data and usage data into the generation AI and have the generation AI adjust the accuracy of the information.

[0043] The analysis unit can select information to analyze based on the user's geographical location information. The analysis unit can acquire the user's geographical location information, for example, using GPS data or a location information service. For example, the analysis unit can identify the user's current location using a GPS device. The analysis unit can also acquire the user's geographical location information using a location information service. For example, the analysis unit can analyze the user's location data and identify the user's current geographical location using a generating AI. The analysis unit selects information to analyze based on the acquired geographical location information. For example, if the user is in a specific area, information related to that area can be prioritized for analysis. Also, if the user is in a tourist destination, information about tourist spots and famous places can be prioritized for analysis. Furthermore, if the user is near their home, information about nearby stores and facilities can be prioritized for analysis. This allows necessary information to be prioritized for analysis by filtering information based on the user's geographical location information. Some or all of the above-described processing in the analysis unit can be performed, for example, using AI or without AI. For example, the analysis unit can input GPS data or data obtained from location information services into the generation AI and have the generation AI select the information.

[0044] The analysis unit can adjust the information to be analyzed based on the user's social media activity. The analysis unit, for example, analyzes the user's social media posts and like history. For example, the analysis unit can analyze the user's social media accounts and identify past posts and like history. For example, the analysis unit can use a generation AI to analyze the user's social media data and identify past activity history. Based on the identified social media activity, the analysis unit adjusts the information to be analyzed. For example, the analysis unit can prioritize analysis of information related to the user's check-in locations on social media. The analysis unit can also analyze the user's social media posts and prioritize analysis of related information. Furthermore, the analysis unit can prioritize analysis of related information based on the user's social media activities. This allows for customization of information based on the user's social media activity, thereby enabling analysis of highly relevant information. Some or all of the above-described processing by the analysis unit can be performed using, for example, AI, or without AI. For example, the analysis unit can input the user's social media data into the generation AI and have the generation AI adjust the information.

[0045] The analysis unit can change the information to be analyzed based on the user's past feedback. The analysis unit, for example, analyzes the user's past feedback. For example, the analysis unit can analyze the user's ratings and comments to identify past feedback. For example, the analysis unit can use the generation AI to analyze the user's feedback data and identify past feedback. Based on the identified feedback, the analysis unit changes the information to be analyzed. For example, if the user has placed importance on specific information in the past, the analysis unit can prioritize the analysis of that information. Also, if the user has ignored specific information in the past, the analysis unit can reduce the frequency of analysis of that information. Furthermore, the analysis unit can analyze the user's past feedback and propose an optimal information analysis method. This enables more appropriate information analysis by adjusting the information based on the user's past feedback. Some or all of the above-described processing in the analysis unit can be performed using, for example, AI, or without AI. For example, the analysis unit can input the user's feedback data into the generation AI and have the generation AI change the information.

[0046] The notification unit can change the notification means to be used based on the user's current situation. The notification unit, for example, identifies the user's current situation. For example, the notification unit can analyze the user's location information and activity data to identify the current situation. For example, the notification unit can use a generation AI to analyze the user's location data and activity data to identify the current situation. Based on the identified situation, the notification unit changes the notification means to be used. For example, when the user is walking, audio notification can be used preferentially. Also, when the user is driving a car, visual notification can be used preferentially. Furthermore, when the user is in a quiet place, vibration notification can be used preferentially. This enables more appropriate information to be provided by dynamically changing the notification means according to the user's current situation. Some or all of the above-mentioned processing in the notification unit may be performed using AI, for example, or may be performed without using AI. For example, the notification unit can input the user's location data and activity data into the generation AI and cause the generation AI to change the notification means.

[0047] The notification unit can determine the priority of information to be notified based on the user's current task. The notification unit, for example, identifies the user's current task. For example, the notification unit can analyze the user's schedule and location information to identify the current task. For example, the notification unit can use a generation AI to analyze the user's schedule data and location data to identify the current task. Based on the identified task, the notification unit determines the priority of information to be notified. For example, if the user needs directions, map information and landmark information can be prioritized. Also, if the user is shopping, store information and product location information can be prioritized. Furthermore, if the user is exercising, information about surrounding obstacles and pedestrians can be prioritized. In this way, by determining the priority of information based on the user's current task, necessary information can be prioritized. Some or all of the above-described processing in the notification unit may be performed using, for example, AI, or may be performed without using AI. For example, the notification unit can input the user's schedule data and location data into the generation AI and have the generation AI determine the priority of information.

[0048] The notification unit can adjust the level of detail of the information to be notified based on the user's past behavioral history. The notification unit, for example, analyzes the user's past behavioral history. For example, the notification unit can analyze the user's travel route and usage history to identify the user's past behavioral history. For example, the notification unit can use a generation AI to analyze the user's travel data and usage data to identify the user's past behavioral history. Based on the identified behavioral history, the notification unit adjusts the level of detail of the information to be notified. For example, if the user has previously been lost in a specific location, the level of detail of the information notification for that location can be increased. Also, if the user has previously felt unsafe during a specific time period, the level of detail of the information notification for that time period can be increased. Furthermore, if the user has frequently performed a specific task in the past, the level of detail of the information notification related to that task can be increased. This enables more appropriate information to be provided by optimizing the level of detail of the information based on the user's past behavioral history. Some or all of the above-described processing in the notification unit may be performed using, for example, AI, or may be performed without AI. For example, the notification unit can input the user's travel data and usage data into the generation AI and cause the generation AI to adjust the level of detail of the information.

[0049] The notification unit can select information to be notified based on the user's geographical location information. The notification unit can acquire the user's geographical location information, for example, using GPS data or a location information service. For example, the notification unit can identify the user's current location using a GPS device. The notification unit can also acquire the user's geographical location information using a location information service. For example, the notification unit can analyze the user's location data using a generation AI to identify the user's current geographical location. The notification unit selects information to be notified based on the acquired geographical location information. For example, if the user is in a specific area, information related to that area can be prioritized. Also, if the user is in a tourist destination, information about tourist spots and famous places can be prioritized. Furthermore, if the user is near their home, information about nearby stores and facilities can be prioritized. In this way, by filtering information based on the user's geographical location information, necessary information can be prioritized. Some or all of the above-described processing in the notification unit can be performed, for example, using AI or without AI. For example, the notification unit can input GPS data or data obtained from location information services into the generation AI and have the generation AI select the information.

[0050] The notification unit can adjust the information to be notified based on the user's social media activity. The notification unit, for example, analyzes the user's social media posts and like history. For example, the notification unit can analyze the user's social media account and identify past posts and like history. For example, the notification unit can use a generation AI to analyze the user's social media data and identify past activity history. Based on the identified social media activity, the notification unit adjusts the information to be notified. For example, the notification unit can prioritize information about places the user has checked in on social media. The notification unit can also analyze the user's social media posts and prioritize related information. Furthermore, the notification unit can prioritize related information based on the activity of the user's friends on social media. This allows the notification of highly relevant information by customizing the information based on the user's social media activity. Some or all of the above-described processing by the notification unit may be performed using, for example, AI, or may be performed without using AI. For example, the notification unit can input the user's social media data into a generation AI and have the generation AI adjust the information.

[0051] The notification unit can change the information to be notified based on the user's past feedback. The notification unit, for example, analyzes the user's past feedback. For example, the notification unit can analyze the user's ratings and comments to identify past feedback. For example, the notification unit can use a generation AI to analyze the user's feedback data and identify past feedback. Based on the identified feedback, the notification unit changes the information to be notified. For example, if the user has previously placed importance on specific information, the notification unit can prioritize notifying that information. Also, if the user has previously ignored specific information, the notification frequency of that information can be reduced. Furthermore, the user's past feedback can be analyzed and an optimal information notification method can be proposed. This enables more appropriate information to be provided by adjusting the information based on the user's past feedback. Some or all of the above-described processing in the notification unit can be performed using, for example, AI, or without AI. For example, the notification unit can input the user's feedback data into the generation AI and have the generation AI change the information.

[0052] The confirmation unit can change the algorithm to be used based on the type of user's finger movement. The confirmation unit, for example, identifies the type of user's finger movement. For example, the confirmation unit can analyze the user's finger movement using a camera to identify the type of movement. For example, the confirmation unit can analyze the user's finger movement data using a generation AI to identify the type of movement. Based on the identified type of movement, the confirmation unit changes the algorithm to be used. For example, if the user performs a pointing motion, an algorithm that recognizes that motion can be used. Also, if the user performs a hand-waving motion, an algorithm that recognizes that motion can be used. Furthermore, if the user performs a specific gesture, an algorithm that recognizes that gesture can be used. This enables more accurate information to be provided by dynamically changing the algorithm according to the type of user's finger movement. Some or all of the above-described processing in the confirmation unit may be performed using, for example, AI, or may be performed without using AI. For example, the confirmation unit can input the user's finger movement data to the generation AI and cause the generation AI to change the algorithm to be used.

[0053] The confirmation unit can determine the priority of information to be confirmed based on the user's current task. The confirmation unit, for example, identifies the user's current task. For example, the confirmation unit can analyze the user's schedule and location information to identify the current task. For example, the confirmation unit can use a generation AI to analyze the user's schedule data and location data to identify the current task. Based on the identified task, the confirmation unit determines the priority of information to be confirmed. For example, if the user needs directions, map information and landmark information can be checked with priority. Also, if the user is shopping, store information and product location information can be checked with priority. Furthermore, if the user is exercising, information about surrounding obstacles and pedestrians can be checked with priority. Thus, by determining the priority of information based on the user's current task, necessary information can be checked with priority. Some or all of the above-described processing in the confirmation unit may be performed using, for example, AI, or may be performed without using AI. For example, the confirmation unit can input the user's schedule data and location data into the generation AI and have the generation AI determine the priority of information.

[0054] The confirmation unit can adjust the accuracy of the information to be confirmed based on the user's past behavioral history. The confirmation unit, for example, analyzes the user's past behavioral history. For example, the confirmation unit can analyze the user's travel route and usage history to identify the user's past behavioral history. For example, the confirmation unit can use a generation AI to analyze the user's travel data and usage data to identify the user's past behavioral history. Based on the identified behavioral history, the confirmation unit adjusts the accuracy of the information to be confirmed. For example, if the user has previously been lost in a specific location, the accuracy of information confirmation for that location can be increased. Also, if the user has previously felt unsafe during a specific time period, the accuracy of information confirmation for that time period can be increased. Furthermore, if the user has frequently performed a specific task in the past, the accuracy of information confirmation related to that task can be increased. This enables the provision of more accurate information by optimizing the accuracy of the information based on the user's past behavioral history. Some or all of the above-described processing in the confirmation unit may be performed using, for example, AI, or may be performed without AI. For example, the confirmation unit can input the user's travel data and usage data into the generation AI and cause the generation AI to adjust the accuracy of the information.

[0055] The confirmation unit can select information to be confirmed based on the user's geographical location information. The confirmation unit can acquire the user's geographical location information, for example, using GPS data or a location information service. For example, the confirmation unit can identify the user's current location using a GPS device. The confirmation unit can also acquire the user's geographical location information using a location information service. For example, the confirmation unit can analyze the user's location data using a generation AI to identify the user's current geographical location. The confirmation unit selects information to be confirmed based on the acquired geographical location information. For example, if the user is in a specific area, information related to that area can be prioritized for confirmation. Also, if the user is in a tourist destination, information about tourist spots and famous places can be prioritized for confirmation. Furthermore, if the user is near their home, information about nearby stores and facilities can be prioritized for confirmation. In this way, by filtering information based on the user's geographical location information, necessary information can be prioritized for confirmation. Some or all of the above-described processing in the confirmation unit may be performed, for example, using AI or without using AI. For example, the verification unit can input GPS data or data obtained from location information services into the generation AI and have the generation AI select the information.

[0056] The verification unit can adjust the information to be verified based on the user's social media activity. The verification unit, for example, analyzes the user's social media posts and like history. For example, the verification unit can analyze the user's social media accounts and identify past posts and like history. For example, the verification unit can use a generation AI to analyze the user's social media data and identify past activity history. Based on the identified social media activity, the verification unit adjusts the information to be verified. For example, the verification unit can prioritize checking information related to locations where the user has checked in on social media. The verification unit can also analyze the user's social media posts and prioritize checking related information. Furthermore, the verification unit can prioritize checking related information based on the user's social media friends' activities. This allows the verification unit to customize the information based on the user's social media activity, thereby verifying highly relevant information. Some or all of the above-described processing in the verification unit may be performed using, for example, AI, or may be performed without using AI. For example, the verification unit can input the user's social media data into the generation AI and have the generation AI adjust the information.

[0057] The confirmation unit can change the information to be confirmed based on the user's past feedback. The confirmation unit, for example, analyzes the user's past feedback. For example, the confirmation unit can analyze the user's ratings and comments to identify past feedback. For example, the confirmation unit can use the generation AI to analyze the user's feedback data and identify past feedback. Based on the identified feedback, the confirmation unit changes the information to be confirmed. For example, if the user has previously placed importance on specific information, the confirmation unit can prioritize checking that information. Also, if the user has previously ignored specific information, the confirmation unit can reduce the frequency of checking that information. Furthermore, the confirmation unit can analyze the user's past feedback and suggest an optimal information confirmation method. This enables more appropriate information to be provided by adjusting the information based on the user's past feedback. Some or all of the above-described processing in the confirmation unit may be performed using, for example, AI, or may be performed without using AI. For example, the confirmation unit can input the user's feedback data into the generation AI and have the generation AI change the information.

[0058] The system according to the embodiment is not limited to the above-described example, and various modifications are possible, for example, as follows.

[0059] The analysis unit can learn the user's past behavioral patterns and adjust the analysis priority based on predicted behavior. For example, if the user commutes via a specific route every morning, information related to that route can be analyzed with priority. Also, if the user performs a specific activity on a specific day of the week, information related to that activity can be analyzed with priority. Furthermore, if the user is in a specific location at a specific time, information related to that location can be analyzed with priority. In this way, by adjusting the analysis priority based on the user's past behavioral patterns, necessary information can be analyzed with priority.

[0060] The confirmation unit can adjust the display speed of the confirmation result based on the speed of the user's finger movement. For example, if the user moves their finger quickly, the confirmation result can be displayed immediately. If the user moves their finger slowly, the confirmation result can be displayed slowly. Furthermore, if the user moves their finger at a constant speed, the confirmation result can be displayed at a display speed corresponding to that speed. This makes it possible to provide more appropriate information by adjusting the display speed of the confirmation result according to the speed of the user's finger movement.

[0061] The analysis unit can adjust the accuracy of analysis based on the user's current activity level. For example, when the user is exercising, the analysis accuracy can be increased to analyze information about surrounding obstacles and pedestrians in detail. When the user is resting, the analysis accuracy can be returned to normal, and only the minimum necessary information can be analyzed. Furthermore, when the user is concentrating, the analysis accuracy can be optimized, and important information can be prioritized. This allows the provision of more appropriate information by adjusting the analysis accuracy according to the user's current activity level.

[0062] The sensor unit can predict the sensor's operating mode based on the user's past behavioral history and switch to the optimal mode in advance. For example, if the user has previously been active in a specific location at a specific time, the sensor will automatically switch to the optimal mode for that activity when the user approaches that location at that time. Also, if the user has previously engaged in a specific activity under specific weather conditions, the sensor can automatically switch to the optimal mode for that activity when those weather conditions are reproduced. This allows the sensor's operating mode to be predicted based on the user's past behavioral history and switched to the optimal mode in advance, enabling more appropriate information to be acquired.

[0063] The notification unit can dynamically change the priority of notifications based on the user's current task. For example, if the user is in a meeting, only important notifications can be displayed with priority. If the user is exercising, notifications related to exercise can be displayed with priority. Furthermore, if the user is taking a break, all notifications can be displayed as usual. This allows for more appropriate information to be provided by dynamically changing the priority of notifications according to the user's current task.

[0064] The processing flow of the first embodiment will be briefly explained below.

[0065] Step 1: The sensor unit acquires real-time information about the surroundings. The real-time information about the surroundings includes environmental data, location information, and audio data. The sensor unit acquires real-time images and audio information about the surroundings using a camera and microphone, and can also acquire environmental data using a temperature sensor and humidity sensor. For example, a camera is used to acquire high-resolution images, and a microphone is used to collect highly sensitive audio data. The temperature sensor measures the surrounding temperature in real time, and the humidity sensor measures the surrounding humidity in real time. Step 2: The analysis unit uses the generation AI to analyze the information acquired by the sensor unit. The analysis unit uses image recognition and voice recognition technologies to detect supplementary information and danger information about the surrounding area. For example, the generation AI uses image recognition technology to identify the location of pedestrians and vehicles and detect dangerous situations. The generation AI can also use voice recognition technology to detect sirens and warning sounds from emergency vehicles. Furthermore, the generation AI uses object detection technology to identify the location and type of surrounding objects and analyzes weather information to understand the current weather. Step 3: The notification unit notifies the user of the information detected by the analysis unit. The notification unit notifies the user of supplementary information or danger information using a display or an audio output device. For example, the supplementary information or danger information can be displayed on the display and the audio output device can be used to notify the user by voice. It is also possible to notify the user by vibration using a vibration device. For example, text information can be displayed on the display and an audio message can be played using the audio output device. The vibration device is worn in the user's pocket or on their arm and notifies by vibration. Step 4: The confirmation unit recognizes the direction the user points their finger when receiving directions and determines whether that direction is correct. The confirmation unit uses a camera to recognize the direction of the user's finger, and the analysis unit determines whether that direction is correct. For example, a camera can be used to track the movement of the user's finger, and the generation AI determines whether that direction is correct. The confirmation unit can also analyze the movement of the user's finger in real time and provide feedback indicating the correct direction. For example, the camera can recognize the movement of the user's finger, and the generation AI determines whether that direction is correct and displays the feedback on the display.

[0066] (Example 2) An assistant system according to an embodiment of the present invention uses a mobile device or wearable device to acquire real-time images, videos, and audio of the surrounding environment, which are then analyzed by a multimodal generation AI to detect supplementary information and hazard information about the surrounding area and notify the user. The assistant system acquires real-time information about the surrounding environment, analyzes it using a generation AI, detects the supplementary information and hazard information, and notifies the user. When providing directions, the system also has a double-check function that recognizes the direction the user points and determines whether the direction is correct. For example, the assistant system uses a mobile device to capture images of the user's field of view with a camera and collects surrounding audio with a microphone. This information is input into the multimodal generation AI. The generation AI then analyzes the acquired information and detects supplementary information and hazard information about the surrounding area. For example, the generation AI analyzes images to identify the locations of pedestrians and vehicles and detect dangerous situations. It can also analyze audio to detect sirens and warning sounds from emergency vehicles. The detected information is then notified to the user. For example, the supplementary information and hazard information may be displayed on the mobile device's display or may also be notified by audio. Furthermore, when providing directions, the camera recognizes the direction the user points, and the generating AI determines whether that direction is correct. This allows users to receive accurate directions and supports the smooth completion of tasks. This allows the assistant system to improve safety when going out and support the smooth completion of tasks. By obtaining information about the user's surroundings in real time and analyzing, notifying, and confirming it, the assistant system can support the user's safety and the smooth completion of tasks. For example, even if people with visual or hearing impairments have difficulty understanding their surroundings, they can use this assistant to go out safely. The route guidance function also helps them reach their destination without getting lost.

[0067] The assistant system according to the embodiment includes a sensor unit, an analysis unit, a notification unit, and a confirmation unit. The sensor unit acquires real-time information about the surroundings. Examples of the real-time information about the surroundings include, but are not limited to, environmental data, location information, and audio data. The sensor unit acquires real-time images and audio information about the surroundings using, for example, a camera and a microphone. The sensor unit can also acquire environmental data using a temperature sensor and a humidity sensor. For example, the sensor unit acquires high-resolution images using a camera and collects high-sensitivity audio data using a microphone. The temperature sensor measures the surrounding temperature in real time, and the humidity sensor measures the surrounding humidity in real time. The analysis unit analyzes the information acquired by the sensor unit using a generation AI. The analysis unit detects supplementary information and danger information about the surroundings using, for example, image recognition technology and voice recognition technology. For example, the generation AI identifies the locations of pedestrians and vehicles and detects dangerous situations using image recognition technology. The generation AI can also detect sirens and warning sounds of emergency vehicles using voice recognition technology. The analysis unit can also use the generation AI to detect detailed information about surrounding objects and weather information. For example, the generation AI can use object detection technology to identify the location and type of surrounding objects and analyze weather information to understand the current weather. The notification unit notifies the user of the information detected by the analysis unit. The notification unit can notify the user of supplementary information and danger information using, for example, a display or an audio output device. For example, the notification unit can display the supplementary information or danger information on a display and notify the user by voice using an audio output device. The notification unit can also notify the user by vibration using a vibration device. For example, the notification unit can display text information on a display and play an audio message using an audio output device. The vibration device can be worn in the user's pocket or on the user's arm and notify the user by vibration. The confirmation unit recognizes the direction the user points their finger when receiving directions and determines whether that direction is correct. For example, the confirmation unit can recognize the direction of the user's finger using a camera, and the analysis unit can determine whether that direction is correct. For example, the confirmation unit can track the user's finger movement using a camera, and the generation AI can determine whether that direction is correct.The confirmation unit can also analyze the user's finger movements in real time and provide feedback indicating the correct direction. For example, the confirmation unit recognizes the user's finger movements using a camera, and the generation AI determines whether the direction is correct and displays the feedback on the display. As a result, the assistant system according to the embodiment can obtain information about the user's surroundings in real time and analyze, notify, and confirm the information, thereby supporting the user's safety and smooth task execution.

[0068] The sensor unit can acquire real-time images or audio information of the surroundings using a camera or a microphone. Examples of real-time images include, but are not limited to, the resolution and frame rate of the camera. The sensor unit can acquire high-resolution images using, for example, a camera. For example, the sensor unit can acquire images at 30 frames per second using a 4K resolution camera. The sensor unit can also collect highly sensitive audio data using a microphone. For example, the sensor unit can clearly collect surrounding audio using a directional microphone. This allows accurate acquisition of real-time information of the surroundings using a camera or microphone. Some or all of the above-described processing in the sensor unit may be performed using, for example, AI, or may be performed without using AI. For example, the sensor unit can input image data acquired by a camera to a generation AI and have the generation AI analyze the image data.

[0069] The analysis unit can detect supplementary information or danger information about the surroundings using image recognition technology or voice recognition technology. Image recognition technology includes, but is not limited to, object detection, face recognition, pattern recognition, etc. The analysis unit can, for example, use object detection technology to identify the location and type of surrounding objects. For example, the analysis unit can use generation AI to detect objects in an image and identify their location and type. The analysis unit can also use face recognition technology to identify specific people. For example, the analysis unit can use generation AI to detect faces in an image and identify specific people. The analysis unit can also detect specific patterns using pattern recognition technology. For example, the analysis unit can use generation AI to detect specific patterns in an image and detect supplementary information or danger information based on the patterns. Voice recognition technology includes, but is not limited to, voice command recognition and voice transcription. The analysis unit can, for example, use voice command recognition technology to recognize a user's voice commands. For example, the analysis unit can use generation AI to analyze a user's voice commands and detect supplementary information or danger information based on the content of the commands. The analysis unit can also convert voice data into text data using voice transcription technology. For example, the analysis unit can use a generation AI to convert voice data into text data and detect supplementary information or danger information based on the content of the text. This allows for accurate detection of surrounding supplementary information or danger information using image recognition technology or voice recognition technology. Some or all of the above-described processing in the analysis unit may be performed using AI, for example, or may be performed without using AI. For example, the analysis unit can input image data or voice data into the generation AI and have the generation AI detect supplementary information or danger information.

[0070] The notification unit may notify the user of the supplemental information or danger information using a display or an audio output device. Examples of displays include, but are not limited to, a liquid crystal display, an LED display, etc. The notification unit may display the supplemental information or danger information using, for example, an LCD display. For example, the notification unit may display text information or graphic information on an LCD display. The notification unit may also display the supplemental information or danger information using an LED display. For example, the notification unit may display a warning message or an icon on an LED display. Examples of audio output devices include, but are not limited to, a speaker, earphones, etc. The notification unit may notify the user of the supplemental information or danger information by audio, for example, using a speaker. For example, the notification unit may play an audio message using a speaker. The notification unit may also notify the user of the supplemental information or danger information by audio using earphones. For example, the notification unit may provide a private audio message to the user using earphones. This allows the user to be effectively notified of the supplemental information or danger information using a display or an audio output device. Some or all of the above-described processing in the notification unit may be performed using, for example, AI, or may be performed without using AI. For example, the notification unit can use a generation AI to generate supplementary information or danger information and notify it via a display or audio output device.

[0071] The confirmation unit can recognize the direction of the user's finger using a camera and determine whether the direction is correct using an analysis unit. The finger direction can include, but is not limited to, the camera usage method and the recognition algorithm. The confirmation unit can recognize the direction of the user's finger using a camera. For example, the confirmation unit can track the movement of the user's finger using a camera and recognize its direction. The confirmation unit can also determine whether the direction of the user's finger is correct using a recognition algorithm. For example, the confirmation unit can analyze the direction of the user's finger using a generation AI and determine whether the direction is correct. This enables accurate route guidance by recognizing the direction of the user's finger using a camera and determining whether the direction is correct using an analysis unit. Some or all of the above-described processing in the confirmation unit can be performed using, for example, AI, or without AI. For example, the confirmation unit can input the user's finger movement data acquired by a camera into the generation AI and have the generation AI recognize the finger direction and determine its accuracy.

[0072] The sensor unit can estimate the user's emotions and adjust the sensitivity of the sensor based on the estimated user emotions. The sensor unit estimates the user's emotions using, for example, facial expression recognition technology or voice analysis technology. For example, the sensor unit can analyze the user's facial expressions using a camera to estimate emotions. The sensor unit can also analyze the user's voice using a microphone to estimate emotions. For example, the sensor unit can estimate emotions from the user's facial expressions and voice using generative AI. Based on the estimated emotions, the sensor unit adjusts the sensitivity of the sensor. For example, if the user is nervous, the sensor sensitivity can be increased to obtain more detailed information about the surroundings. Alternatively, if the user is relaxed, the sensor sensitivity can be returned to normal to obtain the minimum necessary information. Furthermore, if the user is in a hurry, the sensor sensitivity can be optimized to prioritize obtaining important information. This allows for more appropriate information acquisition by adjusting the sensor sensitivity according to the user's emotions. Emotion estimation is achieved using an emotion estimation function, for example, an emotion engine or generative 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-described processing in the sensor unit may be performed using AI, for example, or may be performed without using AI. For example, the sensor unit may input facial expression data of a user acquired by a camera into the generation AI, and cause the generation AI to estimate emotions and adjust sensor sensitivity.

[0073] The sensor unit can switch the sensor's operating mode based on the surrounding environmental conditions. The sensor unit detects environmental conditions such as weather and time of day. For example, the sensor unit can detect weather using a temperature sensor or humidity sensor. The sensor unit can also detect time of day using a light sensor. For example, the sensor unit can analyze the surrounding environmental conditions and identify the weather and time of day using a generation AI. Based on the detected environmental conditions, the sensor unit switches the sensor's operating mode. For example, when it rains, the sensor unit adjusts the camera's sensitivity to minimize obstruction of visibility caused by raindrops. At night, the sensor unit can use an infrared sensor to acquire information about the surroundings even in dark places. Furthermore, during bright daytime hours, the sensor unit can acquire information about the surroundings in normal camera mode. This enables optimal information acquisition by switching the sensor's operating mode according to the surrounding environmental conditions. Some or all of the above-described processing in the sensor unit may be performed using AI, for example, or without AI. For example, the sensor unit can input data acquired by a temperature sensor or light sensor into the generation AI and have the generation AI switch the operating mode.

[0074] The sensor unit can change the type of information it acquires based on the user's current task. For example, the sensor unit identifies the user's current task. For example, the sensor unit can analyze the user's schedule and location information to identify the current task. For example, the sensor unit can use a generation AI to analyze the user's schedule data and location data to identify the current task. Based on the identified task, the sensor unit changes the type of information it acquires. For example, if the user needs directions, it can prioritize acquiring map information and surrounding landmark information. Also, if the user is shopping, it can prioritize acquiring store information and product location information. Furthermore, if the user is exercising, it can prioritize acquiring information about surrounding obstacles and pedestrians. This allows the type of information to be dynamically changed depending on the user's current task, thereby prioritizing the acquisition of necessary information. Some or all of the above-described processing in the sensor unit may be performed using, for example, AI, or may be performed without AI. For example, the sensor unit can input the user's schedule data and location data into the generation AI and cause the generation AI to change the type of information it acquires.

[0075] The sensor unit can adjust the accuracy of the acquired information based on the user's past behavioral history. The sensor unit, for example, analyzes the user's past behavioral history. For example, the sensor unit can analyze the user's movement route and usage history to identify the user's past behavioral history. For example, the sensor unit can use a generation AI to analyze the user's movement data and usage data to identify the user's past behavioral history. Based on the identified behavioral history, the sensor unit adjusts the accuracy of the acquired information. For example, if the user has previously been lost in a specific location, the accuracy of information acquisition for that location can be increased. Also, if the user has previously felt unsafe during a specific time period, the accuracy of information acquisition for that time period can be increased. Furthermore, if the user has frequently performed a specific task in the past, the accuracy of information acquisition related to that task can be increased. This enables more accurate information acquisition by optimizing the accuracy of the information based on the user's past behavioral history. Some or all of the above-described processing in the sensor unit may be performed using, for example, AI, or without AI. For example, the sensor unit can input the user's movement data and usage data into the generation AI and have the generation AI adjust the accuracy of the information.

[0076] The sensor unit can estimate the user's emotions and adjust the sensor operation timing based on the estimated user emotions. The sensor unit estimates the user's emotions using, for example, facial expression recognition technology or voice analysis technology. For example, the sensor unit can analyze the user's facial expressions using a camera to estimate emotions. The sensor unit can also analyze the user's voice using a microphone to estimate emotions. For example, the sensor unit can estimate emotions from the user's facial expressions and voice using a generative AI. Based on the estimated emotions, the sensor unit adjusts the sensor operation timing. For example, if the user is nervous, the sensor operation frequency can be increased to acquire information in real time. Alternatively, if the user is relaxed, the sensor operation frequency can be returned to normal to acquire the minimum necessary information. Furthermore, if the user is in a hurry, the sensor operation frequency can be optimized to prioritize the acquisition of important information. This allows for more appropriate information acquisition by adjusting the sensor operation timing according to the user's emotions. Emotion estimation is realized using an emotion estimation function, for example, an emotion engine or generative 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-described processing in the sensor unit may be performed using AI, for example, or may be performed without using AI. For example, the sensor unit may input facial expression data of a user acquired by a camera into the generation AI, and cause the generation AI to estimate emotions and adjust the timing of sensor operation.

[0077] The sensor unit can select the information to be acquired based on the user's geographical location information. The sensor unit can acquire the user's geographical location information, for example, using GPS data or a location information service. For example, the sensor unit can identify the user's current location using a GPS device. The sensor unit can also acquire the user's geographical location information using a location information service. For example, the sensor unit can analyze the user's location data and identify the user's current geographical location using a generation AI. The sensor unit selects the information to be acquired based on the acquired geographical location information. For example, if the user is in a specific area, information related to that area can be preferentially acquired. Also, if the user is in a tourist destination, information about tourist spots and famous places can be preferentially acquired. Furthermore, if the user is near their home, information about nearby stores and facilities can be preferentially acquired. This allows necessary information to be preferentially acquired by filtering information based on the user's geographical location information. Some or all of the above-described processing in the sensor unit may be performed using AI, for example, or may be performed without using AI. For example, the sensor unit can input GPS data or data obtained from location information services into the generation AI, allowing the generation AI to select the information.

[0078] The sensor unit can adjust the information it acquires based on the user's social media activity. For example, the sensor unit analyzes the user's social media posts and like history. For example, the sensor unit can analyze the user's social media account and identify past posts and like history. For example, the sensor unit can use a generation AI to analyze the user's social media data and identify past activity history. Based on the identified social media activity, the sensor unit adjusts the information it acquires. For example, the sensor unit can prioritize acquiring information about locations where the user has checked in on social media. The sensor unit can also analyze the user's social media posts and prioritize acquiring related information. Furthermore, the sensor unit can prioritize acquiring related information based on the activity of the user's friends on social media. This allows the information to be customized based on the user's social media activity, thereby acquiring highly relevant information. Some or all of the above-described processing by the sensor unit may be performed using, for example, AI, or may be performed without using AI. For example, the sensor unit can input the user's social media data into a generation AI and have the generation AI adjust the information.

[0079] The sensor unit can change the information to be acquired based on the user's past feedback. The sensor unit, for example, analyzes the user's past feedback. For example, the sensor unit can analyze the user's ratings and comments to identify past feedback. For example, the sensor unit can use a generation AI to analyze the user's feedback data and identify past feedback. Based on the identified feedback, the sensor unit changes the information to be acquired. For example, if the user has placed importance on specific information in the past, the sensor unit can prioritize acquisition of that information. Also, if the user has ignored specific information in the past, the sensor unit can reduce the frequency of acquisition of that information. Furthermore, the sensor unit can analyze the user's past feedback and suggest an optimal information acquisition method. This enables more appropriate information acquisition by adjusting the information based on the user's past feedback. Some or all of the above-described processing in the sensor unit may be performed using, for example, AI, or may be performed without using AI. For example, the sensor unit can input the user's feedback data to the generation AI and have the generation AI change the information.

[0080] The analysis unit can estimate the user's emotions and adjust the presentation method of the analysis results based on the estimated user emotions. The analysis unit estimates the user's emotions using, for example, facial expression recognition technology or voice analysis technology. For example, the analysis unit can analyze the user's facial expressions using a camera to estimate emotions. The analysis unit can also analyze the user's voice using a microphone to estimate emotions. For example, the analysis unit can estimate emotions from the user's facial expressions and voice using a generation AI. Based on the estimated emotions, the analysis unit adjusts the presentation method of the analysis results. For example, if the user is nervous, a simple and highly visible analysis result can be displayed. On the other hand, if the user is relaxed, a detailed analysis result can be displayed. Furthermore, if the user is in a hurry, an analysis result that focuses on the main points can be displayed. This enables more appropriate information to be provided by adjusting the presentation method of the analysis results according to the user's emotions. Emotion estimation is realized using an emotion estimation function, for example, using an emotion engine or generation AI. The generation AI can 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 analysis unit may be performed using, for example, AI, or may be performed without using AI. For example, the analysis unit may input facial expression data of a user acquired by a camera into the generation AI, and have the generation AI estimate emotions and adjust the way the analysis results are expressed.

[0081] The analysis unit can change the algorithm to be used based on the type of acquired information. The analysis unit, for example, identifies the type of acquired information. For example, the analysis unit can analyze image data or audio data to identify the type of information. For example, the analysis unit can use a generation AI to analyze the acquired data and identify the type of information. Based on the identified type of information, the analysis unit changes the algorithm to be used. For example, if there is a lot of image information, an image recognition algorithm can be used preferentially. Also, if there is a lot of audio information, a voice recognition algorithm can be used preferentially. Furthermore, if there is a lot of both image and audio, a multimodal analysis algorithm can be used. This enables more accurate analysis by dynamically changing the algorithm depending on the type of acquired information. Some or all of the above-mentioned processing in the analysis unit can be performed using, for example, AI, or without AI. For example, the analysis unit can input the acquired data to the generation AI and cause the generation AI to change the algorithm to be used.

[0082] The analysis unit can prioritize the information to be analyzed based on the user's current task. The analysis unit, for example, identifies the user's current task. For example, the analysis unit can analyze the user's schedule and location information to identify the current task. For example, the analysis unit can use a generation AI to analyze the user's schedule data and location data to identify the current task. Based on the identified task, the analysis unit determines the priority of the information to be analyzed. For example, if the user needs directions, map information and landmark information can be analyzed preferentially. Also, if the user is shopping, store information and product location information can be analyzed preferentially. Furthermore, if the user is exercising, surrounding obstacle information and pedestrian information can be analyzed preferentially. Thus, by determining the priority of information based on the user's current task, necessary information can be analyzed preferentially. Some or all of the above-described processing in the analysis unit may be performed using, for example, AI, or without AI. For example, the analysis unit can input the user's schedule data and location data into the generation AI and have the generation AI determine the priority of the information.

[0083] The analysis unit can adjust the accuracy of the analyzed information based on the user's past behavioral history. The analysis unit, for example, analyzes the user's past behavioral history. For example, the analysis unit can analyze the user's travel route and usage history to identify the user's past behavioral history. For example, the analysis unit can use a generation AI to analyze the user's travel data and usage data to identify the user's past behavioral history. Based on the identified behavioral history, the analysis unit adjusts the accuracy of the analyzed information. For example, if the user has previously been lost in a specific location, the accuracy of the information analysis for that location can be improved. Also, if the user has previously felt unsafe during a specific time period, the accuracy of the information analysis for that time period can be improved. Furthermore, if the user has frequently performed a specific task in the past, the accuracy of the information analysis related to that task can be improved. This enables more accurate analysis by optimizing the accuracy of the information based on the user's past behavioral history. Some or all of the above-described processing in the analysis unit may be performed using AI, for example, or without AI. For example, the analysis unit can input the user's travel data and usage data into the generation AI and have the generation AI adjust the accuracy of the information.

[0084] The analysis unit can estimate the user's emotion and adjust the level of detail of the analysis results based on the estimated user's emotion. The analysis unit estimates the user's emotion using, for example, facial expression recognition technology or voice analysis technology. For example, the analysis unit can analyze the user's facial expression using a camera to estimate the emotion. The analysis unit can also analyze the user's voice using a microphone to estimate the emotion. For example, the analysis unit can estimate the emotion from the user's facial expression or voice using a generation AI. Based on the estimated emotion, the analysis unit adjusts the level of detail of the analysis results. For example, if the user is nervous, a simple, highly visible analysis result can be displayed. On the other hand, if the user is relaxed, a detailed analysis result can be displayed. Furthermore, if the user is in a hurry, an analysis result that focuses on the main points can be displayed. This allows for more appropriate information to be provided by adjusting the level of detail of the analysis results according to the user's emotion. Emotion estimation is realized using an emotion estimation function, for example, using an emotion engine or generation AI. The generation AI can be, but is not limited to, a text generation AI (e.g., LLM) or a multimodal generation AI. Some or all of the above-described processing in the analysis unit may be performed using, for example, AI, or may be performed without using AI. For example, the analysis unit may input facial expression data of a user acquired by a camera into the generation AI, and have the generation AI estimate emotions and adjust the level of detail of the analysis results.

[0085] The analysis unit can select information to analyze based on the user's geographical location information. The analysis unit can acquire the user's geographical location information, for example, using GPS data or a location information service. For example, the analysis unit can identify the user's current location using a GPS device. The analysis unit can also acquire the user's geographical location information using a location information service. For example, the analysis unit can analyze the user's location data and identify the user's current geographical location using a generating AI. The analysis unit selects information to analyze based on the acquired geographical location information. For example, if the user is in a specific area, information related to that area can be prioritized for analysis. Also, if the user is in a tourist destination, information about tourist spots and famous places can be prioritized for analysis. Furthermore, if the user is near their home, information about nearby stores and facilities can be prioritized for analysis. This allows necessary information to be prioritized for analysis by filtering information based on the user's geographical location information. Some or all of the above-described processing in the analysis unit can be performed, for example, using AI or without AI. For example, the analysis unit can input GPS data or data obtained from location information services into the generation AI and have the generation AI select the information.

[0086] The analysis unit can adjust the information to be analyzed based on the user's social media activity. The analysis unit, for example, analyzes the user's social media posts and like history. For example, the analysis unit can analyze the user's social media accounts and identify past posts and like history. For example, the analysis unit can use a generation AI to analyze the user's social media data and identify past activity history. Based on the identified social media activity, the analysis unit adjusts the information to be analyzed. For example, the analysis unit can prioritize analysis of information related to the user's check-in locations on social media. The analysis unit can also analyze the user's social media posts and prioritize analysis of related information. Furthermore, the analysis unit can prioritize analysis of related information based on the user's social media activities. This allows for customization of information based on the user's social media activity, thereby enabling analysis of highly relevant information. Some or all of the above-described processing by the analysis unit can be performed using, for example, AI, or without AI. For example, the analysis unit can input the user's social media data into the generation AI and have the generation AI adjust the information.

[0087] The analysis unit can change the information to be analyzed based on the user's past feedback. The analysis unit, for example, analyzes the user's past feedback. For example, the analysis unit can analyze the user's ratings and comments to identify past feedback. For example, the analysis unit can use the generation AI to analyze the user's feedback data and identify past feedback. Based on the identified feedback, the analysis unit changes the information to be analyzed. For example, if the user has placed importance on specific information in the past, the analysis unit can prioritize the analysis of that information. Also, if the user has ignored specific information in the past, the analysis unit can reduce the frequency of analysis of that information. Furthermore, the analysis unit can analyze the user's past feedback and propose an optimal information analysis method. This enables more appropriate information analysis by adjusting the information based on the user's past feedback. Some or all of the above-described processing in the analysis unit can be performed using, for example, AI, or without AI. For example, the analysis unit can input the user's feedback data into the generation AI and have the generation AI change the information.

[0088] The notification unit can estimate the user's emotion and adjust the notification presentation method based on the estimated user's emotion. The notification unit can estimate the user's emotion using, for example, facial expression recognition technology or voice analysis technology. For example, the notification unit can analyze the user's facial expression using a camera to estimate the emotion. The notification unit can also analyze the user's voice using a microphone to estimate the emotion. For example, the notification unit can estimate the emotion from the user's facial expression or voice using a generation AI. Based on the estimated emotion, the notification unit adjusts the notification presentation method. For example, if the user is nervous, a simple, highly visible notification can be provided. If the user is relaxed, a detailed notification can be provided. Furthermore, if the user is in a hurry, a notification that focuses on the main points can be provided. This allows for more appropriate information provision by adjusting the notification presentation method according to the user's emotion. Emotion estimation is realized using an emotion estimation function, for example, using an emotion engine or generation AI. The generation AI can be, but is not limited to, a text generation AI (e.g., LLM) or a multimodal generation AI. Some or all of the above-described processing in the notification unit may be performed using, for example, AI, or may be performed without using AI. For example, the notification unit may input facial expression data of the user acquired by a camera into the generation AI, and have the generation AI estimate the emotion and adjust the notification expression method.

[0089] The notification unit can change the notification means to be used based on the user's current situation. The notification unit, for example, identifies the user's current situation. For example, the notification unit can analyze the user's location information and activity data to identify the current situation. For example, the notification unit can use a generation AI to analyze the user's location data and activity data to identify the current situation. Based on the identified situation, the notification unit changes the notification means to be used. For example, when the user is walking, audio notification can be used preferentially. Also, when the user is driving a car, visual notification can be used preferentially. Furthermore, when the user is in a quiet place, vibration notification can be used preferentially. This enables more appropriate information to be provided by dynamically changing the notification means according to the user's current situation. Some or all of the above-mentioned processing in the notification unit may be performed using AI, for example, or may be performed without using AI. For example, the notification unit can input the user's location data and activity data into the generation AI and cause the generation AI to change the notification means.

[0090] The notification unit can determine the priority of information to be notified based on the user's current task. The notification unit, for example, identifies the user's current task. For example, the notification unit can analyze the user's schedule and location information to identify the current task. For example, the notification unit can use a generation AI to analyze the user's schedule data and location data to identify the current task. Based on the identified task, the notification unit determines the priority of information to be notified. For example, if the user needs directions, map information and landmark information can be prioritized. Also, if the user is shopping, store information and product location information can be prioritized. Furthermore, if the user is exercising, information about surrounding obstacles and pedestrians can be prioritized. In this way, by determining the priority of information based on the user's current task, necessary information can be prioritized. Some or all of the above-described processing in the notification unit may be performed using, for example, AI, or may be performed without using AI. For example, the notification unit can input the user's schedule data and location data into the generation AI and have the generation AI determine the priority of information.

[0091] The notification unit can adjust the level of detail of the information to be notified based on the user's past behavioral history. The notification unit, for example, analyzes the user's past behavioral history. For example, the notification unit can analyze the user's travel route and usage history to identify the user's past behavioral history. For example, the notification unit can use a generation AI to analyze the user's travel data and usage data to identify the user's past behavioral history. Based on the identified behavioral history, the notification unit adjusts the level of detail of the information to be notified. For example, if the user has previously been lost in a specific location, the level of detail of the information notification for that location can be increased. Also, if the user has previously felt unsafe during a specific time period, the level of detail of the information notification for that time period can be increased. Furthermore, if the user has frequently performed a specific task in the past, the level of detail of the information notification related to that task can be increased. This enables more appropriate information to be provided by optimizing the level of detail of the information based on the user's past behavioral history. Some or all of the above-described processing in the notification unit may be performed using, for example, AI, or may be performed without AI. For example, the notification unit can input the user's travel data and usage data into the generation AI and cause the generation AI to adjust the level of detail of the information.

[0092] The notification unit can estimate the user's emotion and adjust the timing of notifications based on the estimated user emotion. The notification unit can estimate the user's emotion using, for example, facial expression recognition technology or voice analysis technology. For example, the notification unit can analyze the user's facial expression using a camera to estimate the emotion. The notification unit can also analyze the user's voice using a microphone to estimate the emotion. For example, the notification unit can estimate the emotion from the user's facial expression or voice using a generation AI. The notification unit adjusts the timing of notifications based on the estimated emotion. For example, if the user is nervous, important information can be notified immediately. If the user is relaxed, the timing of notifications can be returned to normal. Furthermore, if the user is in a hurry, important information can be notified preferentially. This allows for more appropriate information provision by adjusting the timing of notifications according to the user's emotion. Emotion estimation is realized using an emotion estimation function, for example, using an emotion engine or generation AI. The generation AI can be, but is not limited to, a text generation AI (e.g., LLM) or a multimodal generation AI. Some or all of the above-described processing in the notification unit may be performed using, for example, AI, or may be performed without using AI. For example, the notification unit may input facial expression data of the user acquired by a camera to the generation AI, and have the generation AI estimate the emotion and adjust the timing of the notification.

[0093] The notification unit can select information to be notified based on the user's geographical location information. The notification unit can acquire the user's geographical location information, for example, using GPS data or a location information service. For example, the notification unit can identify the user's current location using a GPS device. The notification unit can also acquire the user's geographical location information using a location information service. For example, the notification unit can analyze the user's location data using a generation AI to identify the user's current geographical location. The notification unit selects information to be notified based on the acquired geographical location information. For example, if the user is in a specific area, information related to that area can be prioritized. Also, if the user is in a tourist destination, information about tourist spots and famous places can be prioritized. Furthermore, if the user is near their home, information about nearby stores and facilities can be prioritized. In this way, by filtering information based on the user's geographical location information, necessary information can be prioritized. Some or all of the above-described processing in the notification unit can be performed, for example, using AI or without AI. For example, the notification unit can input GPS data or data obtained from location information services into the generation AI and have the generation AI select the information.

[0094] The notification unit can adjust the information to be notified based on the user's social media activity. The notification unit, for example, analyzes the user's social media posts and like history. For example, the notification unit can analyze the user's social media account and identify past posts and like history. For example, the notification unit can use a generation AI to analyze the user's social media data and identify past activity history. Based on the identified social media activity, the notification unit adjusts the information to be notified. For example, the notification unit can prioritize information about places the user has checked in on social media. The notification unit can also analyze the user's social media posts and prioritize related information. Furthermore, the notification unit can prioritize related information based on the activity of the user's friends on social media. This allows the notification of highly relevant information by customizing the information based on the user's social media activity. Some or all of the above-described processing by the notification unit may be performed using, for example, AI, or may be performed without using AI. For example, the notification unit can input the user's social media data into a generation AI and have the generation AI adjust the information.

[0095] The notification unit can change the information to be notified based on the user's past feedback. The notification unit, for example, analyzes the user's past feedback. For example, the notification unit can analyze the user's ratings and comments to identify past feedback. For example, the notification unit can use a generation AI to analyze the user's feedback data and identify past feedback. Based on the identified feedback, the notification unit changes the information to be notified. For example, if the user has previously placed importance on specific information, the notification unit can prioritize notifying that information. Also, if the user has previously ignored specific information, the notification frequency of that information can be reduced. Furthermore, the user's past feedback can be analyzed and an optimal information notification method can be proposed. This enables more appropriate information to be provided by adjusting the information based on the user's past feedback. Some or all of the above-described processing in the notification unit can be performed using, for example, AI, or without AI. For example, the notification unit can input the user's feedback data into the generation AI and have the generation AI change the information.

[0096] The confirmation unit can estimate the user's emotions and adjust the presentation method of the confirmation result based on the estimated user emotions. The confirmation unit can estimate the user's emotions using, for example, facial expression recognition technology or voice analysis technology. For example, the confirmation unit can analyze the user's facial expressions using a camera to estimate emotions. The confirmation unit can also analyze the user's voice using a microphone to estimate emotions. For example, the confirmation unit can estimate emotions from the user's facial expressions and voice using a generation AI. Based on the estimated emotions, the confirmation unit adjusts the presentation method of the confirmation result. For example, if the user is nervous, a simple and highly visible confirmation result can be displayed. If the user is relaxed, a detailed confirmation result can be displayed. Furthermore, if the user is in a hurry, a confirmation result that focuses on the main points can be displayed. This enables more appropriate information to be provided by adjusting the presentation method of the confirmation result according to the user's emotions. Emotion estimation is realized using an emotion estimation function, for example, using an emotion engine or generation AI. The generation AI can be, but is not limited to, a text generation AI (e.g., LLM) or a multimodal generation AI. Some or all of the above-described processing in the confirmation unit may be performed using, for example, AI, or may be performed without using AI. For example, the confirmation unit may input facial expression data of the user acquired by a camera into the generation AI, and cause the generation AI to estimate emotions and adjust the way the confirmation results are expressed.

[0097] The confirmation unit can change the algorithm to be used based on the type of user's finger movement. The confirmation unit, for example, identifies the type of user's finger movement. For example, the confirmation unit can analyze the user's finger movement using a camera to identify the type of movement. For example, the confirmation unit can analyze the user's finger movement data using a generation AI to identify the type of movement. Based on the identified type of movement, the confirmation unit changes the algorithm to be used. For example, if the user performs a pointing motion, an algorithm that recognizes that motion can be used. Also, if the user performs a hand-waving motion, an algorithm that recognizes that motion can be used. Furthermore, if the user performs a specific gesture, an algorithm that recognizes that gesture can be used. This enables more accurate information to be provided by dynamically changing the algorithm according to the type of user's finger movement. Some or all of the above-described processing in the confirmation unit may be performed using, for example, AI, or may be performed without using AI. For example, the confirmation unit can input the user's finger movement data to the generation AI and cause the generation AI to change the algorithm to be used.

[0098] The confirmation unit can determine the priority of information to be confirmed based on the user's current task. The confirmation unit, for example, identifies the user's current task. For example, the confirmation unit can analyze the user's schedule and location information to identify the current task. For example, the confirmation unit can use a generation AI to analyze the user's schedule data and location data to identify the current task. Based on the identified task, the confirmation unit determines the priority of information to be confirmed. For example, if the user needs directions, map information and landmark information can be checked with priority. Also, if the user is shopping, store information and product location information can be checked with priority. Furthermore, if the user is exercising, information about surrounding obstacles and pedestrians can be checked with priority. Thus, by determining the priority of information based on the user's current task, necessary information can be checked with priority. Some or all of the above-described processing in the confirmation unit may be performed using, for example, AI, or may be performed without using AI. For example, the confirmation unit can input the user's schedule data and location data into the generation AI and have the generation AI determine the priority of information.

[0099] The confirmation unit can adjust the accuracy of the information to be confirmed based on the user's past behavioral history. The confirmation unit, for example, analyzes the user's past behavioral history. For example, the confirmation unit can analyze the user's travel route and usage history to identify the user's past behavioral history. For example, the confirmation unit can use a generation AI to analyze the user's travel data and usage data to identify the user's past behavioral history. Based on the identified behavioral history, the confirmation unit adjusts the accuracy of the information to be confirmed. For example, if the user has previously been lost in a specific location, the accuracy of information confirmation for that location can be increased. Also, if the user has previously felt unsafe during a specific time period, the accuracy of information confirmation for that time period can be increased. Furthermore, if the user has frequently performed a specific task in the past, the accuracy of information confirmation related to that task can be increased. This enables the provision of more accurate information by optimizing the accuracy of the information based on the user's past behavioral history. Some or all of the above-described processing in the confirmation unit may be performed using, for example, AI, or may be performed without AI. For example, the confirmation unit can input the user's travel data and usage data into the generation AI and cause the generation AI to adjust the accuracy of the information.

[0100] The confirmation unit can estimate the user's emotion and adjust the level of detail of the confirmation result based on the estimated user's emotion. The confirmation unit can estimate the user's emotion using, for example, facial expression recognition technology or voice analysis technology. For example, the confirmation unit can analyze the user's facial expression using a camera to estimate the emotion. The confirmation unit can also analyze the user's voice using a microphone to estimate the emotion. For example, the confirmation unit can estimate the emotion from the user's facial expression or voice using a generation AI. The confirmation unit adjusts the level of detail of the confirmation result based on the estimated emotion. For example, if the user is nervous, a simple and highly visible confirmation result can be displayed. On the other hand, if the user is relaxed, a detailed confirmation result can be displayed. Furthermore, if the user is in a hurry, a confirmation result that focuses on the main points can be displayed. This allows for more appropriate information to be provided by adjusting the level of detail of the confirmation result according to the user's emotion. Emotion estimation is realized using an emotion estimation function, for example, using an emotion engine or generation AI. The generation AI can be, but is not limited to, a text generation AI (e.g., LLM) or a multimodal generation AI. Some or all of the above-described processing in the confirmation unit may be performed using, for example, AI, or may be performed without using AI. For example, the confirmation unit may input facial expression data of the user acquired by a camera to the generation AI, and cause the generation AI to estimate emotions and adjust the level of detail of the confirmation result.

[0101] The confirmation unit can select information to be confirmed based on the user's geographical location information. The confirmation unit can acquire the user's geographical location information, for example, using GPS data or a location information service. For example, the confirmation unit can identify the user's current location using a GPS device. The confirmation unit can also acquire the user's geographical location information using a location information service. For example, the confirmation unit can analyze the user's location data using a generation AI to identify the user's current geographical location. The confirmation unit selects information to be confirmed based on the acquired geographical location information. For example, if the user is in a specific area, information related to that area can be prioritized for confirmation. Also, if the user is in a tourist destination, information about tourist spots and famous places can be prioritized for confirmation. Furthermore, if the user is near their home, information about nearby stores and facilities can be prioritized for confirmation. In this way, by filtering information based on the user's geographical location information, necessary information can be prioritized for confirmation. Some or all of the above-described processing in the confirmation unit may be performed, for example, using AI or without using AI. For example, the verification unit can input GPS data or data obtained from location information services into the generation AI and have the generation AI select the information.

[0102] The verification unit can adjust the information to be verified based on the user's social media activity. The verification unit, for example, analyzes the user's social media posts and like history. For example, the verification unit can analyze the user's social media accounts and identify past posts and like history. For example, the verification unit can use a generation AI to analyze the user's social media data and identify past activity history. Based on the identified social media activity, the verification unit adjusts the information to be verified. For example, the verification unit can prioritize checking information related to locations where the user has checked in on social media. The verification unit can also analyze the user's social media posts and prioritize checking related information. Furthermore, the verification unit can prioritize checking related information based on the user's social media friends' activities. This allows the verification unit to customize the information based on the user's social media activity, thereby verifying highly relevant information. Some or all of the above-described processing in the verification unit may be performed using, for example, AI, or may be performed without using AI. For example, the verification unit can input the user's social media data into the generation AI and have the generation AI adjust the information.

[0103] The confirmation unit can change the information to be confirmed based on the user's past feedback. The confirmation unit, for example, analyzes the user's past feedback. For example, the confirmation unit can analyze the user's ratings and comments to identify past feedback. For example, the confirmation unit can use the generation AI to analyze the user's feedback data and identify past feedback. Based on the identified feedback, the confirmation unit changes the information to be confirmed. For example, if the user has previously placed importance on specific information, the confirmation unit can prioritize checking that information. Also, if the user has previously ignored specific information, the confirmation unit can reduce the frequency of checking that information. Furthermore, the confirmation unit can analyze the user's past feedback and suggest an optimal information confirmation method. This enables more appropriate information to be provided by adjusting the information based on the user's past feedback. Some or all of the above-described processing in the confirmation unit may be performed using, for example, AI, or may be performed without using AI. For example, the confirmation unit can input the user's feedback data into the generation AI and have the generation AI change the information. === Hard Collateral 1-1 === Each of the multiple elements, including the sensor unit, analysis unit, notification unit, and confirmation unit, described above, is realized, for example, by at least one of the smart device 14 and the data processing device 12. For example, the sensor unit can acquire real-time images and audio information of the surroundings using the camera 42 and microphone 38B of the smart device 14. The analysis unit is realized by the specific processing unit 290 of the data processing device 12 and analyzes the acquired information using a generation AI. The notification unit notifies the user of supplementary information and danger information using the display 40A and speaker 40B of the smart device 14. The confirmation unit recognizes the direction of the user's finger using the camera 42 of the smart device 14, and determines whether the direction is correct using the specific processing unit 290 of the data processing device 12. === Hard Collateral 1-2 === Each of the multiple elements, including the sensor unit, analysis unit, notification unit, and confirmation unit, described above, is realized, for example, by at least one of the smart glasses 214 and the data processing device 12. For example, the sensor unit can acquire real-time images and audio information of the surroundings using the camera 42 and microphone 238 of the smart glasses 214. The analysis unit is realized by the specific processing unit 290 of the data processing device 12 and analyzes the acquired information using a generation AI. The notification unit notifies the user of supplementary information and danger information using the display and speaker 240 of the smart glasses 214. The confirmation unit recognizes the direction of the user's finger using the camera 42 of the smart glasses 214, and determines whether the direction is correct using the specific processing unit 290 of the data processing device 12. === Hard Collateral 1-3 === Each of the multiple elements including the sensor unit, analysis unit, notification unit, and confirmation unit described above is realized, for example, by at least one of the headset-type terminal 314 and the data processing device 12. For example, the sensor unit can acquire real-time images and audio information of the surroundings using the camera 42 and microphone 238 of the headset-type terminal 314. The analysis unit is realized by the specific processing unit 290 of the data processing device 12 and analyzes the acquired information using a generation AI. The notification unit notifies the user of supplementary information and danger information using the display 343 and speaker 240 of the headset-type terminal 314. The confirmation unit recognizes the direction of the user's finger using the camera 42 of the headset-type terminal 314, and determines whether the direction is correct using the specific processing unit 290 of the data processing device 12. === Hard Collateral 1-4 === Each of the multiple elements including the sensor unit, analysis unit, notification unit, and confirmation unit described above is realized, for example, by at least one of the robot 414 and the data processing device 12. For example, the sensor unit can acquire real-time images and audio information of the surroundings using the camera 42 and microphone 238 of the robot 414. The analysis unit is realized by the specific processing unit 290 of the data processing device 12 and analyzes the acquired information using a generation AI. The notification unit notifies the user of supplementary information and danger information using the display and speaker 240 of the robot 414. The confirmation unit recognizes the direction of the user's finger using the camera 42 of the robot 414, and determines whether the direction is correct using the specific processing unit 290 of the data processing device 12.

[0104] The system according to the embodiment is not limited to the above-described example, and various modifications are possible, for example, as follows.

[0105] The sensor unit can monitor the user's health condition and adjust the sensor's operating mode based on the health condition. For example, the sensor unit measures heart rate and blood pressure, and if the user is feeling stressed, it increases the sensor's sensitivity to acquire more detailed information about the surroundings. If the user is relaxed, it returns the sensor's sensitivity to normal to acquire the minimum necessary information. Furthermore, if the user is exercising, it can optimize the sensor's operating mode to prioritize the acquisition of information related to exercise. This allows for more appropriate information acquisition by adjusting the sensor's operating mode according to the user's health condition.

[0106] The analysis unit can learn the user's past behavioral patterns and adjust the analysis priority based on predicted behavior. For example, if the user commutes via a specific route every morning, information related to that route can be analyzed with priority. Also, if the user performs a specific activity on a specific day of the week, information related to that activity can be analyzed with priority. Furthermore, if the user is in a specific location at a specific time, information related to that location can be analyzed with priority. In this way, by adjusting the analysis priority based on the user's past behavioral patterns, necessary information can be analyzed with priority.

[0107] The notification unit can estimate the user's emotions and customize the notification content based on the estimated emotions. For example, if the user is feeling stressed, notification content that helps the user relax can be provided. If the user is happy, positive notification content that further enhances the user's emotions can be provided. Furthermore, if the user is sad, notification content that includes an encouraging message can be provided. In this way, by customizing the notification content according to the user's emotions, more appropriate information can be provided.

[0108] The confirmation unit can adjust the display speed of the confirmation result based on the speed of the user's finger movement. For example, if the user moves their finger quickly, the confirmation result can be displayed immediately. If the user moves their finger slowly, the confirmation result can be displayed slowly. Furthermore, if the user moves their finger at a constant speed, the confirmation result can be displayed at a display speed corresponding to that speed. This makes it possible to provide more appropriate information by adjusting the display speed of the confirmation result according to the speed of the user's finger movement.

[0109] The sensor unit can estimate the user's emotions and dynamically change the placement of the sensors based on the estimated emotions. For example, if the user is nervous, the sensors can be placed closer to the user's field of vision to obtain more detailed information about the surroundings. If the user is relaxed, the sensors can be returned to their normal positions to obtain the minimum necessary information. Furthermore, if the user is in a hurry, the sensors can be placed in the optimal positions to prioritize obtaining important information. This allows for more appropriate information acquisition by dynamically changing the placement of the sensors according to the user's emotions.

[0110] The analysis unit can adjust the accuracy of analysis based on the user's current activity level. For example, when the user is exercising, the analysis accuracy can be increased to analyze information about surrounding obstacles and pedestrians in detail. When the user is resting, the analysis accuracy can be returned to normal, and only the minimum necessary information can be analyzed. Furthermore, when the user is concentrating, the analysis accuracy can be optimized, and important information can be prioritized. This allows the provision of more appropriate information by adjusting the analysis accuracy according to the user's current activity level.

[0111] The notification unit can estimate the user's emotions and adjust the frequency of notifications based on the estimated emotions. For example, if the user is feeling stressed, the notification frequency can be reduced to reduce the burden on the user. If the user is relaxed, the notification frequency can be returned to normal. Furthermore, if the user is in a hurry, the notification frequency can be increased to prioritize the notification of important information. In this way, by adjusting the notification frequency according to the user's emotions, more appropriate information can be provided.

[0112] The sensor unit can predict the sensor's operating mode based on the user's past behavioral history and switch to the optimal mode in advance. For example, if the user has previously been active in a specific location at a specific time, the sensor will automatically switch to the optimal mode for that activity when the user approaches that location at that time. Also, if the user has previously engaged in a specific activity under specific weather conditions, the sensor can automatically switch to the optimal mode for that activity when those weather conditions are reproduced. This allows the sensor's operating mode to be predicted based on the user's past behavioral history and switched to the optimal mode in advance, enabling more appropriate information to be acquired.

[0113] The analysis unit can estimate the user's emotions and adjust the method of feedback of the analysis results based on the estimated emotions. For example, if the user is nervous, simple, highly visible feedback can be provided. If the user is relaxed, detailed feedback can be provided. Furthermore, if the user is in a hurry, feedback that focuses on the main points can be provided. In this way, by adjusting the method of feedback of the analysis results according to the user's emotions, more appropriate information can be provided.

[0114] The notification unit can dynamically change the priority of notifications based on the user's current task. For example, if the user is in a meeting, only important notifications can be displayed with priority. If the user is exercising, notifications related to exercise can be displayed with priority. Furthermore, if the user is taking a break, all notifications can be displayed as usual. This allows for more appropriate information to be provided by dynamically changing the priority of notifications according to the user's current task.

[0115] The processing flow of the second embodiment will be briefly explained below.

[0116] Step 1: The sensor unit acquires real-time information about the surroundings. The real-time information about the surroundings includes environmental data, location information, and audio data. The sensor unit acquires real-time images and audio information about the surroundings using a camera and microphone, and can also acquire environmental data using a temperature sensor and humidity sensor. For example, a camera is used to acquire high-resolution images, and a microphone is used to collect highly sensitive audio data. The temperature sensor measures the surrounding temperature in real time, and the humidity sensor measures the surrounding humidity in real time. Step 2: The analysis unit uses the generation AI to analyze the information acquired by the sensor unit. The analysis unit uses image recognition and voice recognition technologies to detect supplementary information and danger information about the surrounding area. For example, the generation AI uses image recognition technology to identify the location of pedestrians and vehicles and detect dangerous situations. The generation AI can also use voice recognition technology to detect sirens and warning sounds from emergency vehicles. Furthermore, the generation AI uses object detection technology to identify the location and type of surrounding objects and analyzes weather information to understand the current weather. Step 3: The notification unit notifies the user of the information detected by the analysis unit. The notification unit notifies the user of supplementary information or danger information using a display or an audio output device. For example, the supplementary information or danger information can be displayed on the display and the audio output device can be used to notify the user by voice. It is also possible to notify the user by vibration using a vibration device. For example, text information can be displayed on the display and an audio message can be played using the audio output device. The vibration device is worn in the user's pocket or on their arm and notifies by vibration. Step 4: The confirmation unit recognizes the direction the user points their finger when receiving directions and determines whether that direction is correct. The confirmation unit uses a camera to recognize the direction of the user's finger, and the analysis unit determines whether that direction is correct. For example, a camera can be used to track the movement of the user's finger, and the generation AI determines whether that direction is correct. The confirmation unit can also analyze the movement of the user's finger in real time and provide feedback indicating the correct direction. For example, the camera can recognize the movement of the user's finger, and the generation AI determines whether that direction is correct and displays the feedback on the display.

[0117] The specific processing unit 290 transmits the result of the specific processing to the smart device 14. In the smart device 14, the control unit 46A causes the output device 40 to output the result of the specific processing. The microphone 38B acquires audio indicating a user input regarding the result of the specific processing. The control unit 46A transmits audio data indicating the user input acquired by the microphone 38B to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the audio data.

[0118] 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 engine).<URL: https: / / openai.com / blog / chatgpt> Examples of generative AIs include the data generation model 58, such as a neural network model (e.g., a neural network model), and a neural network model (e.g., a neural network model). 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 speech, text data indicating text, and image data indicating an image is also input to the data generation model 58. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The specification processing unit 290 performs the above-mentioned specification processing 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. In this case, the data generation model 58 can output an inference result from a prompt that does not include an instruction. The data processing device 12 and the like include multiple types of data generation models 58, and the data generation model 58 includes AIs other than the generative AI. The AI ​​other than the generative AI may be, for example, linear regression, logistic regression, decision tree, random forest, support vector machine (SVM), k-means clustering, convolutional neural network (CNN), recurrent neural network (RNN), generative adversarial network (GAN), or naive Bayes, and can perform various processes, but is not limited to these examples. The AI ​​may also be an AI agent. When the processes of each of the above-mentioned parts are performed by AI, the processes may be performed in part or entirely by AI, but are not limited to these examples. The processes performed by AI, including the generative AI, may be replaced with rule-based processes.

[0119] Furthermore, the processing by the data processing system 10 described above 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 necessary for processing from the smart device 14 or an external device, and the smart device 14 acquires or collects information necessary for processing from the data processing device 12 or an external device.

[0120] The correspondence between each part and the device or control part is not limited to the above example, and various modifications are possible.

[0121] [Second embodiment] FIG. 3 shows an example of the configuration of a data processing system 210 according to the second embodiment.

[0122] 3, the data processing system 210 includes a data processing device 12 and smart glasses 214. An example of the data processing device 12 is a server.

[0123] 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, RAM 30, and 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.

[0124] 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.

[0125] 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 audio according to instructions from the processor 46.

[0126] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an imaging element such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the user's surroundings (for example, an imaging range defined by an angle of view equivalent to the field of vision of a typical healthy person).

[0127] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 are responsible for the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is carried out in a secure state.

[0128] Fig. 4 shows an example of the main functions of the data processing device 12 and the smart glasses 214. As shown in Fig. 4, in the data processing device 12, a specific process is performed by the processor 28. A specific process program 56 is stored in the storage 32.

[0129] 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.

[0130] 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 a user's emotion using the emotion identification model 59 and perform identification processing using the user's emotion. The emotion estimation function (emotion identification function) using the emotion identification model 59 performs various estimations and predictions regarding the user's emotion, including estimation and prediction of the user's emotion, but is not limited to these examples. Furthermore, the estimation and prediction of emotion also includes, for example, emotion analysis.

[0131] In the smart glasses 214, the specific processing is performed by the processor 46. A specific processing program 60 is stored in the storage 50. 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. The smart glasses 214 also 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 perform processing similar to that of the specific processing unit 290 using these models.

[0132] 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 communicates with the server device having the data generation model 58 to obtain a processing result (such as a prediction result) using the data generation model 58. Furthermore, the data processing device 12 may be a server device, or may be a terminal device (for example, a mobile phone, a robot, a home appliance, etc.) owned by a user.

[0133] The specific processing unit 290 transmits the result of the specific processing to the smart glasses 214. In the smart glasses 214, the control unit 46A causes the speaker 240 to output the result of the specific processing. The microphone 238 acquires audio indicating a user input regarding the result of the specific processing. The control unit 46A transmits audio data indicating the user input acquired by the microphone 238 to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the audio data.

[0134] 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. The data generation model 58 receives a prompt containing an instruction, as well as inference data such as voice data representing speech, text data representing text, and image data representing an image. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The identification processing unit 290 performs the above-mentioned identification processing 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. In this case, the data generation model 58 can output an inference result from a prompt that does not include an instruction. The data processing device 12 and the like include multiple types of data generation models 58, and the data generation model 58 includes AI other than the generative AI. The AI ​​other than the generative AI may be, for example, linear regression, logistic regression, decision tree, random forest, support vector machine (SVM), k-means clustering, convolutional neural network (CNN), recurrent neural network (RNN), generative adversarial network (GAN), or naive Bayes, and can perform various processes, but is not limited to these examples. The AI ​​may also be an AI agent. When the processes of each of the above-mentioned parts are performed by AI, the processes may be performed in part or entirely by AI, but are not limited to these examples. The processes performed by AI, including the generative AI, may be replaced with rule-based processes.

[0135] 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 also be executed by the specific processing unit 290 of the data processing device 12 and the control unit 46A of the smart glasses 214. Furthermore, 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, etc., and the smart glasses 214 acquires or collects information required for processing from the data processing device 12 or an external device, etc.

[0136] The correspondence between each part and the device or control part is not limited to the above example, and various modifications are possible.

[0137] [Third embodiment] FIG. 5 shows an example of the configuration of a data processing system 310 according to the third embodiment.

[0138] 5, the data processing system 310 includes the data processing device 12 and a headset terminal 314. An example of the data processing device 12 is a server.

[0139] 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, RAM 30, and 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.

[0140] 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.

[0141] 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 audio according to instructions from the processor 46.

[0142] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an imaging element such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the user's surroundings (for example, an imaging range defined by an angle of view equivalent to the field of vision of a typical healthy person).

[0143] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 are responsible for the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is carried out in a secure state.

[0144] Fig. 6 shows an example of the main functions of the data processing device 12 and the headset 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.

[0145] 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.

[0146] 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 a user's emotion using the emotion identification model 59 and perform identification processing using the user's emotion. The emotion estimation function (emotion identification function) using the emotion identification model 59 performs various estimations and predictions regarding the user's emotion, including estimation and prediction of the user's emotion, but is not limited to these examples. Furthermore, the estimation and prediction of emotion also includes, for example, emotion analysis.

[0147] In the headset type terminal 314, the identification process is performed by the processor 46. A identification program 60 is stored in the storage 50. The processor 46 reads the identification program 60 from the storage 50 and executes the read identification program 60 on the RAM 48. The identification process is realized by the processor 46 operating as a control unit 46A in accordance with the identification 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.

[0148] 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 communicates with the server device having the data generation model 58 to obtain a processing result (such as a prediction result) using the data generation model 58. Furthermore, the data processing device 12 may be a server device, or may be a terminal device (for example, a mobile phone, a robot, a home appliance, etc.) owned by a user.

[0149] The specific processing unit 290 transmits the result of the specific processing to the headset type terminal 314. In the headset type terminal 314, the control unit 46A causes the speaker 240 and the display 343 to output the result of the specific processing. The microphone 238 acquires audio indicating a user input regarding the result of the specific processing. The control unit 46A transmits audio data indicating the user input acquired by the microphone 238 to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the audio data.

[0150] 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. The data generation model 58 receives a prompt containing an instruction, as well as inference data such as voice data representing speech, text data representing text, and image data representing an image. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The identification processing unit 290 performs the above-mentioned identification processing 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. In this case, the data generation model 58 can output an inference result from a prompt that does not include an instruction. The data processing device 12 and the like include multiple types of data generation models 58, and the data generation model 58 includes AI other than the generative AI. The AI ​​other than the generative AI may be, for example, linear regression, logistic regression, decision tree, random forest, support vector machine (SVM), k-means clustering, convolutional neural network (CNN), recurrent neural network (RNN), generative adversarial network (GAN), or naive Bayes, and can perform various processes, but is not limited to these examples. The AI ​​may also be an AI agent. When the processes of each of the above-mentioned parts are performed by AI, the processes may be performed in part or entirely by AI, but are not limited to these examples. The processes performed by AI, including the generative AI, may be replaced with rule-based processes.

[0151] 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 also 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. Furthermore, 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, etc., and the headset type terminal 314 acquires or collects information required for processing from the data processing device 12 or an external device, etc.

[0152] The correspondence between each part and the device or control part is not limited to the above example, and various modifications are possible.

[0153] [Fourth embodiment] FIG. 7 shows an example of the configuration of a data processing system 410 according to the fourth embodiment.

[0154] 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.

[0155] 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, RAM 30, and 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.

[0156] The robot 414 includes a computer 36, a microphone 238, a speaker 240, a camera 42, a communication I / F 44, and a control target 443. The computer 36 includes a processor 46, a RAM 48, and a storage 50. The processor 46, the RAM 48, and the storage 50 are connected to a bus 52. The microphone 238, the speaker 240, the camera 42, and the control target 443 are also connected to the bus 52.

[0157] 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 audio according to instructions from the processor 46.

[0158] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an imaging element such as a CMOS image sensor or a CCD image sensor, and captures images of the user's surroundings (for example, an imaging range defined by an angle of view equivalent to the field of vision of a typical healthy person).

[0159] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 are responsible for the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is carried out in a secure state.

[0160] The control object 443 includes a display device, LEDs in the eyes, and motors that drive the arms, hands, and feet. The posture and gestures of the robot 414 are controlled by controlling the motors of the arms, hands, and feet. Some of the 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.

[0161] 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.

[0162] 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.

[0163] 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 a user's emotion using the emotion identification model 59 and perform identification processing using the user's emotion. The emotion estimation function (emotion identification function) using the emotion identification model 59 performs various estimations and predictions regarding the user's emotion, including estimation and prediction of the user's emotion, but is not limited to these examples. Furthermore, the estimation and prediction of emotion also includes, for example, emotion analysis.

[0164] In the robot 414, the processor 46 performs the identification process. The storage 50 stores the identification program 60. The processor 46 reads the identification program 60 from the storage 50 and executes the read identification program 60 on the RAM 48. The identification process is realized by the processor 46 operating as the control unit 46A in accordance with the identification program 60 executed on the RAM 48. The robot 414 also 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 perform the same process as the identification processing unit 290 using these models.

[0165] 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 communicates with the server device having the data generation model 58 to obtain a processing result (such as a prediction result) using the data generation model 58. Furthermore, the data processing device 12 may be a server device, or may be a terminal device (for example, a mobile phone, a robot, a home appliance, etc.) owned by a user.

[0166] The specific processing unit 290 transmits the result of the specific processing to the robot 414. In the robot 414, the control unit 46A causes the speaker 240 and the control target 443 to output the result of the specific processing. The microphone 238 acquires voice indicating a user input regarding the result of the specific processing. The control unit 46A transmits voice data indicating the user input acquired by the microphone 238 to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the voice data.

[0167] 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. The data generation model 58 receives a prompt containing an instruction, as well as inference data such as voice data representing speech, text data representing text, and image data representing an image. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The identification processing unit 290 performs the above-mentioned identification processing 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. In this case, the data generation model 58 can output an inference result from a prompt that does not include an instruction. The data processing device 12 and the like include multiple types of data generation models 58, and the data generation model 58 includes AI other than the generative AI. The AI ​​other than the generative AI may be, for example, linear regression, logistic regression, decision tree, random forest, support vector machine (SVM), k-means clustering, convolutional neural network (CNN), recurrent neural network (RNN), generative adversarial network (GAN), or naive Bayes, and can perform various processes, but is not limited to these examples. The AI ​​may also be an AI agent. When the processes of each of the above-mentioned parts are performed by AI, the processes may be performed in part or entirely by AI, but are not limited to these examples. The processes performed by AI, including the generative AI, may be replaced with rule-based processes.

[0168] 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 also be executed by the specific processing unit 290 of the data processing device 12 and the control unit 46A of the robot 414. Furthermore, 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.

[0169] The correspondence between each part and the device or control part is not limited to the above example, and various modifications are possible.

[0170] The emotion identification model 59 as an emotion engine may determine the user's emotion according to a specific mapping. Specifically, the emotion identification model 59 may determine the user's emotion according to an emotion map (see FIG. 9), which is a specific mapping. Similarly, the emotion identification model 59 may determine the robot's emotion, and the identification processing unit 290 may perform identification processing using the robot's emotion.

[0171] FIG. 9 illustrates an emotion map 400 on which multiple emotions are mapped. In the emotion map 400, emotions are arranged in concentric circles radiating from the center. Emotions closer to the center of the concentric circles are more primitive. Emotions representing states and behaviors arising from a state of mind are arranged on the outer edges of the concentric circles. The concept of emotion encompasses both emotions and mental states. Emotions generally generated from reactions occurring in the brain are arranged on the left side of the concentric circles. Emotions generally induced by situational judgment are arranged on the right side of the concentric circles. Emotions generally generated from reactions occurring in the brain and induced by situational judgment are arranged on the upper and lower sides of the concentric circles. Furthermore, the emotion of "pleasure" is arranged on the upper side of the concentric circles, and the emotion of "discomfort" is arranged on the lower side. In this way, in the emotion map 400, multiple emotions are mapped based on the structure by which emotions are generated, and emotions that tend to occur simultaneously are mapped close to each other.

[0172] These emotions are distributed in the 3 o'clock direction on emotion map 400, and typically fluctuate between relief and anxiety. In the right half of emotion map 400, situational awareness dominates over internal sensations, resulting in a sense of calm.

[0173] The inside of emotion map 400 represents what is going on in the mind, and the outside of emotion map 400 represents behavior, so the further you go outside emotion map 400, the more visible the emotions become (the more they are expressed in behavior).

[0174] Human emotions are based on various balances, such as posture and blood sugar levels. When these balances deviate from the ideal, a state of discomfort is expressed, and when they approach the ideal, a state of pleasure is expressed. Emotions can also be created for robots, cars, and motorcycles, based on various balances, such as posture and remaining battery life. When these balances deviate from the ideal, a state of discomfort is expressed, and when they approach the ideal, a state of pleasure is expressed. An emotion map can be generated, for example, based on Dr. Mitsuyoshi's emotion map (Research on speech emotion recognition and brain physiological signal analysis systems for emotions, Tokushima University, doctoral dissertation: https: / / ci.nii.ac.jp / naid / 500000375379). The left half of the emotion map lists emotions belonging to the area called "reaction," where sensation is dominant. The right half of the emotion map lists emotions belonging to the area called "situation," where situational awareness is dominant.

[0175] The emotion map defines two emotions that promote learning. One is a negative emotion on the situation side, around the middle of "repentance" or "reflection." In other words, this occurs when the robot experiences negative emotions such as "I never want to feel this way again" or "I don't want to be scolded again." The other is a positive emotion on the response side, around "desire." In other words, this occurs when the robot experiences positive feelings such as "I want more" or "I want to know more."

[0176] The emotion identification model 59 inputs user input into a pre-trained neural network, obtains emotion values ​​indicating each emotion shown in the emotion map 400, and determines the user's emotion. This neural network is pre-trained based on multiple pieces of training data that are combinations of user input and emotion values ​​indicating each emotion shown in the emotion map 400. Furthermore, this neural network is trained so that emotions that are located close to each other have similar values, as in the emotion map 900 shown in FIG. 10. FIG. 10 shows an example in which multiple emotions, "relieved," "calm," and "reassuring," have similar emotion values.

[0177] 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.

[0178] In the above embodiment, an example in which the specific processing program 56 is stored in the storage 32 has been described, but the technology of the present disclosure is not limited to this. For example, the specific processing program 56 may be stored in a portable, computer-readable, non-transitory storage medium such as a USB (Universal Serial Bus) memory. The specific processing program 56 stored in the non-transitory storage medium is installed in the computer 22 of the data processing device 12. The processor 28 executes the specific processing in accordance with the specific processing program 56.

[0179] Alternatively, the specific processing program 56 may be stored in a storage device such as a server connected to the data processing device 12 via the network 54, and the specific processing program 56 may be downloaded and installed on the computer 22 in response to a request from the data processing device 12.

[0180] 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.

[0181] The hardware resource for executing a specific process can be any of the following types of processors: A processor, for example, is a CPU, which is a general-purpose processor that functions as a hardware resource for executing a specific process by executing software, i.e., a program. A processor also includes a dedicated electrical circuit, such as an FPGA (Field-Programmable Gate Array), a PLD (Programmable Logic Device), or an ASIC (Application Specific Integrated Circuit), which is a processor with a circuit configuration designed specifically for executing a specific process. Each processor has built-in or connected memory, and each processor uses the memory to execute the specific process.

[0182] The hardware resource that executes the specific process may be configured with one of these various processors, or may be configured with a combination of two or more processors of the same or different types (for example, a combination of multiple FPGAs, or a combination of a CPU and an FPGA). Also, the hardware resource that executes the specific process may be a single processor.

[0183] As an example of a system configured with a single processor, first, one processor is configured by combining one or more CPUs and software, and this processor functions as a hardware resource that executes a specific process. Second, there is a system that uses a processor that realizes the functions of an entire system including multiple hardware resources that execute a specific process on a single IC chip, as typified by SoC (System-on-a-chip). In this way, a specific process is realized using one or more of the above-mentioned various processors as hardware resources.

[0184] Furthermore, the hardware structure of these various processors can be, more specifically, an electric circuit that combines circuit elements such as semiconductor devices. The specific processing described above is merely an example. Therefore, it goes without saying that unnecessary steps may be deleted, new steps may be added, or the processing order may be rearranged, without departing from the spirit of the invention.

[0185] In the above example, the first to fourth embodiments have been described separately, but some or all of these embodiments may be combined. The smart device 14, smart glasses 214, headset terminal 314, and robot 414 are merely examples, and they may be combined, or other devices may be used. In the above example, the first and second embodiments have been described separately, but they may be combined.

[0186] The above-described description and illustrations are a detailed explanation of the parts related to the technology of the present disclosure and are merely an example of the technology of the present disclosure. For example, the above description of the configuration, functions, actions, and effects is an explanation of an example of the configuration, functions, actions, and effects of the parts related to the technology of the present disclosure. Therefore, it goes without saying that unnecessary parts may be deleted, new elements may be added, or replacements may be made to the above-described description and illustrations within the scope of the gist of the technology of the present disclosure. Furthermore, in order to avoid confusion and to facilitate understanding of the parts related to the technology of the present disclosure, the above-described description and illustrations omit explanations of common technical knowledge that do not require particular explanation to enable the implementation of the technology of the present disclosure.

[0187] All publications, patent applications, and technical standards mentioned in this specification are herein incorporated by reference to the same extent as if each individual publication, patent application, or technical standard was specifically and individually indicated to be incorporated by reference.

[0188] [Explanation of symbols]

[0189] 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 sensor unit that acquires real-time information about the surrounding area; an analysis unit that analyzes the information acquired by the sensor unit and detects supplementary information and danger information about the surroundings; a notification unit that notifies a user of the information detected by the analysis unit; and a confirmation unit that recognizes the direction the user points when giving directions and determines whether the direction is correct. A system characterized by:

2. The sensor unit Capture real-time images or audio information of the surroundings using a camera or microphone 2. The system of claim 1.

3. The analysis unit Uses image or voice recognition technology to detect supplementary or dangerous information about the surrounding area 2. The system of claim 1.

4. The notification unit Use a display or audio output device to notify the user of supplementary or dangerous information 2. The system of claim 1.

5. The confirmation unit The camera recognizes the direction of the user's finger, and the analysis unit determines whether the direction is correct.

2. The system of claim 1.

6. The sensor unit The user's emotion is estimated, and the sensitivity of the sensor is adjusted based on the estimated user's emotion.

2. The system of claim 1.

7. The sensor unit Switching the sensor's operating mode based on the surrounding environmental conditions 2. The system of claim 1.

8. The sensor unit Vary the type of information retrieved based on the user's current task 2. The system of claim 1.

Images