system

Abstract

The system according to this embodiment aims to efficiently record, organize, and recall important moments and information in daily life. [Solution] The system according to the embodiment comprises a capture unit, a classification unit, and a dialogue unit. The capture unit captures data according to the user's actions and environment. The classification unit classifies and organizes the data captured by the capture unit on the cloud. The dialogue unit generates answers to the user's questions based on the data classified and organized by the classification unit.

Description

Technical Field

[0006] , , ,

[0005] , ,

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

Background Art

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

Prior Art Documents

Patent Documents

[0003]

Patent Document 1

Summary of the Invention

Problems to be Solved by the Invention

[0004] In the conventional technology, there is a problem that it is difficult to efficiently record, organize, and retrieve important moments and information in daily life.

[0005] The system according to the embodiment aims to efficiently record, organize, and retrieve important moments and information in daily life.

Means for Solving the Problems

[0006] The system according to this embodiment comprises a capture unit, a classification unit, and a dialogue unit. The capture unit captures data according to the user's actions and environment. The classification unit classifies and organizes the data captured by the capture unit on the cloud. The dialogue unit generates answers to the user's questions based on the data classified and organized by the classification unit. [Effects of the Invention]

[0007] The system according to this embodiment can efficiently record, organize, and recall important moments and information in daily life. [Brief explanation of the drawing]

[0008] [Figure 1] This is a conceptual diagram showing an example of the configuration of a data processing system according to the first embodiment. [Figure 2] This is a conceptual diagram showing an example of the essential functions of a data processing device and a smart device according to the first embodiment. [Figure 3] This is a conceptual diagram showing an example of the configuration of a data processing system according to the second embodiment. [Figure 4] This is a conceptual diagram showing an example of the main functions of a data processing device and smart glasses according to the second embodiment. [Figure 5] This is a conceptual diagram showing an example of the configuration of a data processing system according to the third embodiment. [Figure 6] This is a conceptual diagram showing an example of the main functions of a data processing device and a headset-type terminal according to the third embodiment. [Figure 7] This is a conceptual diagram showing an example of the configuration of a data processing system according to the fourth embodiment. [Figure 8] This is a conceptual diagram showing an example of the main functions of a data processing device and a robot according to the fourth embodiment. [Figure 9] This shows an emotion map where multiple emotions are mapped. [Figure 10] This shows an emotion map where multiple emotions are mapped. [Modes for carrying out the invention]

[0009] Hereinafter, an example of an embodiment of the system relating to the technology of this disclosure will be described with reference to the attached drawings.

[0010] First, let's explain the terminology used in the following explanation.

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

[0012] In the following embodiments, signed RAM (Random Access Memory) is a memory that temporarily stores information and is used as work memory by the processor.

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

[0014] In the following embodiments, the labeled communication I / F (Interface) is an interface including a communication processor, an antenna, etc. The communication I / F manages communication between multiple computers. Examples of communication standards applied to the communication I / F include wireless communication standards such as 5G (5th Generation Mobile Communication System), Wi-Fi (registered trademark), or Bluetooth (registered trademark).

[0015] In the following embodiments, "A and / or B" is synonymous with "at least one of A and B". That is, "A and / or B" means that it may be only A, only B, or a combination of A and B. Also, in this specification, when expressing three or more matters connected by "and / or", the same concept as "A and / or B" is applied.

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

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

[0018] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, the RAM 30, and the storage 32 are connected to a bus 34. Also, the database 24 and the communication I / F 26 are 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 comprises a computer 36, a receiving device 38, an output device 40, a camera 42, and a communication interface 44. The computer 36 comprises a processor 46, RAM 48, and storage 50. The processor 46, RAM 48, and storage 50 are connected to a bus 52. The receiving device 38, output device 40, and camera 42 are also connected to the bus 52.

[0020] The reception device 38 is equipped with a touch panel 38A and a microphone 38B, and accepts user input. The touch panel 38A accepts user input via touch by detecting contact with an object (e.g., a pen or finger). The microphone 38B accepts user input via voice by detecting the user's voice. The control unit 46A transmits data indicating the user input received by the touch panel 38A and microphone 38B to the data processing unit 12. In the data processing unit 12, the specific processing unit 290 (see Figure 2) acquires the data indicating the user input.

[0021] The output device 40 includes a display 40A and a speaker 40B, and presents data to the user by outputting the data in a form perceptible to the user (e.g., audio and / or text). The display 40A displays visible information such as text and images according to instructions from the processor 46. The speaker 40B outputs audio according to instructions from the processor 46. The camera 42 is a small digital camera equipped with an optical system such as a lens, aperture, and shutter, and an image sensor such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor.

[0022] Communication interface 44 is connected to network 54. Communication interfaces 44 and 26 are responsible for the exchange of various types of information between processor 46 and processor 28 via network 54.

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

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

[0025] Storage 32 stores the data generation model 58 and the emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290. The identification processing unit 290 can estimate the user's emotions using the emotion identification model 59 and perform identification processing using the user's emotions. The emotion estimation function (emotion identification function) using the emotion identification model 59 performs various estimations and predictions regarding the user's emotions, including but not limited to these examples. Furthermore, emotion estimation and prediction also include, for example, emotion analysis.

[0026] In the smart device 14, specific processing is performed by the processor 46. The storage 50 stores a specific processing program 60. The specific processing program 60 is used in conjunction 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 a control unit 46A according to the specific processing program 60 executed on the RAM 48. The smart device 14 also has a data generation model 58 and an emotion identification model 59, similar to the data generation model and emotion identification model 59, and can perform processing similar to that of the specific processing unit 290 using these models.

[0027] Furthermore, other devices besides the data processing device 12 may also 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 processing results (such as prediction results) using the data generation model 58 by communicating with the server device having the data generation model 58. The data processing device 12 may also be a server device or a terminal device owned by a user (e.g., a mobile phone, robot, home appliance, etc.). Next, an example of processing by the data processing system 10 according to the first embodiment will be described.

[0028] (Example of form 1) The memory assist system according to an embodiment of the present invention is a system that utilizes a wearable device capable of automatically recording, organizing, and recalling important moments and information in daily life. This system captures images and data according to the user's actions and environment, and classifies and organizes them on the cloud. The user can easily search for information later using the conversational function of the generative AI, and access it immediately when needed. For example, there is a function to record special moments. For example, it automatically captures a smile that a child suddenly shows and organizes and saves it on the cloud. This allows parents to record special moments without missing them and easily review them later. There are also functions for meal management and calorie management. When a user eats, the wearable device automatically captures the contents of the meal, and the AI ​​analyzes it to record calories and nutrients. This allows the user to achieve accurate health management without stress. Furthermore, it predicts health risks from the recorded data and suggests meals to eat next. There is also a memory support function for people with early-stage dementia. Using conversational generative AI, it answers questions such as "Where did I put my smartphone?" based on past behavioral data. This helps to support memory decline and reduce difficulties in daily life. The system automatically captures data based on the user's actions and environment, classifying and organizing it in the cloud, allowing users to easily search and access necessary information. This ensures that special moments are recorded, enabling health management and memory support. Thus, the memory assist system can automatically record, organize, and recall important moments and information of the user.

[0029] The memory assist system according to this embodiment comprises a capture unit, a classification unit, and a dialogue unit. The capture unit captures data according to the user's actions and environment. For example, the capture unit can capture images while the user is moving. The capture unit can also capture audio data while the user is working. Furthermore, the capture unit can capture sensor data when the user is in a specific location. For example, the capture unit can capture the surrounding scenery when the user is in a park. The classification unit classifies and organizes the data captured by the capture unit on the cloud. For example, the classification unit classifies image data into categories. The classification unit can also convert audio data into text data and organize it. Furthermore, the classification unit can organize sensor data chronologically. For example, the classification unit classifies image data into categories such as scenery, people, and objects. The dialogue unit generates answers to user questions based on the data classified and organized by the classification unit. For example, if the user asks, "What was for dinner yesterday?", the dialogue unit generates an answer based on past data. The dialogue unit can also generate an answer considering health risks if the user asks, "What should I eat next?" Furthermore, the dialogue unit can also generate an answer based on past behavioral data when the user asks, "Where did I put my smartphone?" For example, the dialogue unit searches past data in response to the user's question and generates an appropriate answer. As a result, the memory assist system according to the embodiment can capture data according to the user's behavior and environment, classify and organize it in the cloud, and generate answers to the user's questions.

[0030] The capture unit captures data according to the user's actions and environment. For example, the capture unit can capture images while the user is on the move. Specifically, if the user is carrying a smartphone or wearable device, it can use the camera and microphone on these devices to automatically record the surrounding scenery and sounds. For example, when a user visits a tourist spot while traveling, the capture unit can automatically take pictures of the place and record voice memos. The capture unit can also capture audio data while the user is working. For example, it can record what the user says in a meeting or ideas that come to mind while working. Furthermore, the capture unit can capture sensor data when the user is in a specific location. For example, when a user is in a park, it can not only capture the surrounding scenery but also simultaneously record environmental data such as temperature, humidity, and location information. In this way, the capture unit collects diverse data about the user's actions and environment for later reference. In addition, to protect user privacy, the capture unit allows users to set the scope and frequency of data collection. For example, it can provide settings to stop data capture in specific locations or time periods, or to capture only specific data types. This allows the capture unit to achieve flexible data collection tailored to user needs, efficiently collecting necessary information while respecting user privacy.

[0031] The classification unit classifies and organizes data captured by the capture unit on the cloud. For example, the classification unit classifies image data into categories. Specifically, it can automatically classify images into categories such as landscapes, people, and objects using image recognition technology. For example, it can classify photos taken by a user during a trip into landscape photos, people photos, food photos, etc., making them easy to search later. The classification unit can also convert and organize audio data into text data. Using speech recognition technology, it can convert audio data from meeting recordings and notes into text and organize it by keyword or topic. This allows users to search the text data later and quickly find the information they need. Furthermore, the classification unit can organize sensor data chronologically. For example, it can organize environmental data such as location information, temperature, and humidity chronologically, making it easy to refer to data for specific times of day or locations. This allows users to review past actions and environmental changes chronologically and quickly obtain the information they need. In addition, because the classification unit manages data on the cloud, users can access the data from any internet-connected device. This allows users to check and use the data from anywhere, such as at home, in the office, or while traveling. The classification unit can protect data using encryption technology to ensure data security and protect user privacy. This allows the classification unit to efficiently and securely classify and organize data, enabling users to quickly retrieve the information they need.

[0032] The dialogue unit generates answers to user questions based on data classified and organized by the classification unit. For example, if a user asks, "What was for dinner yesterday?", the dialogue unit generates an answer based on past data. Specifically, it searches for images, audio data, and text notes previously captured by the user, extracts the relevant information, and generates an answer. For example, if the user took a picture of their dinner, it can answer, "Yesterday's dinner was pasta," based on that picture. The dialogue unit can also generate an answer considering health risks if the user asks, "What should I eat next?" For example, it can suggest a nutritionally balanced meal based on the user's past meal data and health status. Furthermore, if the user asks, "Where did I put my smartphone?", the dialogue unit can generate an answer based on past behavioral data. For example, it can identify the last place and time the user used their smartphone and answer, "You last used it in the living room." The dialogue unit uses natural language processing technology to understand user questions and generate appropriate answers. This allows users to easily obtain the necessary information in a conversational format. In addition, the dialogue unit can continuously improve the accuracy of its answers based on user feedback. For example, by providing feedback such as "correct" or "incorrect" to the answers provided by the user, the dialogue unit can learn from that feedback and improve the accuracy of its answers in the future. This allows the dialogue unit to provide flexible and highly accurate answers that meet the user's needs, thereby improving user convenience.

[0033] The meal analysis unit can capture meal content and analyze calories and nutrients. For example, the meal analysis unit captures meal content when a user eats. The meal analysis unit can also analyze calories based on the captured meal content. Furthermore, the meal analysis unit can analyze nutrients based on the captured meal content. For example, the meal analysis unit calculates the calories of the food the user ate. In this way, the meal analysis unit can capture meal content and analyze calories and nutrients. Some or all of the above processing in the meal analysis unit may be performed using AI, for example, or without AI. For example, the meal analysis unit can input the captured meal content into AI and have the AI ​​perform the calorie and nutrient analysis.

[0034] The risk prediction unit can predict health risks and suggest the next meal to eat. For example, the risk prediction unit predicts health risks based on the user's health data. The risk prediction unit can also suggest the next meal to eat based on the predicted health risks. Furthermore, the risk prediction unit can make meal suggestions considering the user's eating history. For example, the risk prediction unit may suggest a low-sodium diet based on the user's blood pressure data. In this way, the risk prediction unit can predict health risks and suggest the next meal to eat. Some or all of the above processing in the risk prediction unit may be performed using AI, for example, or without AI. For example, the risk prediction unit can input the user's health data into AI and have the AI ​​perform health risk prediction and meal suggestions.

[0035] The memory assistance unit can assist the user's memory. For example, if the user asks, "Where did I put my smartphone?", the memory assistance unit can generate an answer based on past behavioral data. Similarly, if the user asks, "I forgot where I put my keys," the memory assistance unit can generate an answer based on past behavioral data. Furthermore, if the user asks, "Tell me what happened at yesterday's meeting," the memory assistance unit can generate an answer based on past behavioral data. For example, the memory assistance unit searches past data in response to the user's question and generates an appropriate answer. In this way, the memory assistance unit can assist the user's memory. Some or all of the above-described processes in the memory assistance unit may be performed using, for example, a generative AI, or without a generative AI. For example, the memory assistance unit can input the user's question into a generative AI and have the generative AI perform the process of generating an answer based on past behavioral data.

[0036] The capture unit can analyze the user's past behavior history and select the optimal capture method. For example, if the user has taken many photos at a particular location in the past, the capture unit can automatically activate the camera when the user arrives at that location. The capture unit can also automatically capture voice memos during a particular event if the user has taken many notes at that event in the past. Furthermore, if the capture unit has captured a large amount of data during a specific time period in the past, it can automatically start capturing during that time period. For example, the capture unit can automatically take photos at tourist destinations the user has visited in the past. This allows the capture unit to analyze the user's past behavior history and select the optimal capture method. Some or all of the above processing in the capture unit may be performed using AI, or not. For example, the capture unit can input the user's past behavior data into AI and have the AI ​​select the optimal capture method.

[0037] The capture unit can filter data based on the user's current activities and areas of interest during capture. For example, if the user is playing sports, the capture unit will capture only data related to that activity. It can also capture information related to the book's title and content if the user is reading. Furthermore, if the user is traveling, the capture unit can prioritize capturing information and photos related to the travel destination. For example, if the user is participating in a sporting event, the capture unit will capture photos and videos related to that event. This allows the capture unit to filter data based on the user's current activities and areas of interest. Some or all of the above processing in the capture unit may be performed using AI, for example, or without AI. For example, the capture unit can input the user's current activity data into an AI and have the AI ​​perform the filtering.

[0038] The capture unit can prioritize capturing highly relevant data by considering the user's geographical location during the capture process. For example, if the user is in a tourist destination, the capture unit will prioritize capturing information and photos related to that location. Similarly, if the user is at home, the capture unit can prioritize capturing information related to daily life. Furthermore, if the user is at work, the capture unit can prioritize capturing work-related information. For example, when the user is in a tourist destination, the capture unit will prioritize capturing landmarks and scenery of that location. This allows the capture unit to prioritize capturing highly relevant data by considering the user's geographical location. Some or all of the above processing in the capture unit may be performed using AI, or without AI. For example, the capture unit can input the user's geographical location data into an AI and have the AI ​​perform the capture of highly relevant data.

[0039] The capture unit can analyze the user's social media activity and capture relevant data during the capture process. For example, if the user posts about a specific event on social media, the capture unit can capture information related to that event. It can also capture information related to a specific location if the user posts about that location on social media. Furthermore, if the user posts about a specific topic on social media, the capture unit can capture information related to that topic. For example, the capture unit can capture photos of events shared by the user on social media. This allows the capture unit to analyze the user's social media activity and capture relevant data. Some or all of the above processing in the capture unit may be performed using AI, for example, or without AI. For example, the capture unit can input the user's social media data into an AI and have the AI ​​perform the capture of relevant data.

[0040] The classification unit can adjust the level of detail in classification based on the importance of the data. For example, the classification unit can classify important data in detail and assign many relevant tags. Alternatively, it can classify less important data simply and assign only basic tags. Furthermore, the classification unit can change the data classification method and adjust the level of detail according to importance. For example, the classification unit can classify important meeting records in detail. This allows the classification unit to adjust the level of detail in classification based on the importance of the data. Some or all of the above processes in the classification unit may be performed using AI, for example, or not. For example, the classification unit can input the importance of the data into the AI ​​and have the AI ​​perform the adjustment of the level of detail in classification.

[0041] The classification unit can apply different classification algorithms depending on the data category during classification. For example, the classification unit can apply an image recognition algorithm to image data and classify it based on its content. It can also apply a speech recognition algorithm to audio data and classify it based on its content. Furthermore, it can apply a natural language processing algorithm to text data and classify it based on its content. For example, the classification unit can classify image data into categories such as landscapes, people, and objects. This allows the classification unit to apply different classification algorithms depending on the data category. Some or all of the above processing in the classification unit may be performed using AI, for example, or without AI. For example, the classification unit can input the data categories into the AI ​​and have the AI ​​apply an appropriate classification algorithm.

[0042] The classification unit can adjust the classification order based on when the data was submitted. For example, the classification unit may prioritize the classification of the most recent data and postpone the classification of older data. It can also prioritize the classification of data submitted during a specific period. Furthermore, the classification unit can adjust the classification order of the data according to the submission date. For example, the classification unit may prioritize the classification of the most recent meeting record data. This allows the classification unit to adjust the classification order based on when the data was submitted. Some or all of the above processes in the classification unit may be performed using AI, for example, or not. For example, the classification unit can input the data submission date into the AI ​​and have the AI ​​perform the adjustment of the classification order.

[0043] The classification unit can adjust the order of classification based on the relevance of the data during the classification process. For example, the classification unit may prioritize classifying highly relevant data and postpone classifying less relevant data. It can also prioritize classifying data related to specific categories. Furthermore, the classification unit can adjust the order of classification according to the relevance of the data. For example, the classification unit may prioritize classifying highly relevant project data. This allows the classification unit to adjust the order of classification based on the relevance of the data. Some or all of the above processes in the classification unit may be performed using AI, for example, or not. For example, the classification unit can input the data relevance into the AI ​​and have the AI ​​perform the adjustment of the classification order.

[0044] The dialogue unit can adjust the level of detail in its answers based on the importance of the questions during the conversation. For example, the dialogue unit can provide detailed answers to important questions. It can also provide concise answers to less important questions. Furthermore, the dialogue unit can adjust the level of detail in its answers according to the importance of the questions. For example, the dialogue unit can generate detailed answers to important technical questions. This allows the dialogue unit to adjust the level of detail in its answers based on the importance of the questions. Some or all of the above processing in the dialogue unit may be performed using, for example, a generative AI, or without a generative AI. For example, the dialogue unit can input the importance of the questions into the generative AI and have the generative AI adjust the level of detail in its answers.

[0045] The dialogue unit can apply different answer algorithms depending on the category of the question during the dialogue. For example, the dialogue unit can apply a specialized answer algorithm to technical questions. It can also apply a concise answer algorithm to general questions. Furthermore, it can apply a friendly answer algorithm to personal questions. For example, the dialogue unit generates a specialized answer to a technical question. This allows the dialogue unit to apply different answer algorithms depending on the category of the question. Some or all of the above processing in the dialogue unit may be performed using, for example, a generative AI, or not using a generative AI. For example, the dialogue unit can input the category of the question into a generative AI and have the generative AI apply an appropriate answer algorithm.

[0046] The dialogue unit can determine the priority of answers based on when the questions were submitted during the dialogue. For example, the dialogue unit may prioritize answering the most recent questions and postpone older questions. It can also prioritize answering questions submitted within a specific period. Furthermore, the dialogue unit can adjust the order in which questions are answered according to the submission date. For example, the dialogue unit may prioritize answering the most recent questions. This allows the dialogue unit to determine the priority of answers based on when the questions were submitted. Some or all of the above processing in the dialogue unit may be performed using, for example, a generative AI, or not using a generative AI. For example, the dialogue unit can input the submission date of the questions into a generative AI and have the generative AI determine the priority of the answers.

[0047] The dialogue unit can adjust the order of answers based on the relevance of the questions during the conversation. For example, the dialogue unit may prioritize answering highly relevant questions and postpone answering less relevant ones. It can also prioritize answering questions related to a specific category. Furthermore, the dialogue unit can adjust the order of answers according to the relevance of the questions. For example, the dialogue unit may prioritize answering highly relevant technical questions. In this way, the dialogue unit can adjust the order of answers based on the relevance of the questions. Some or all of the above processing in the dialogue unit may be performed using, for example, a generative AI, or not using a generative AI. For example, the dialogue unit can input the relevance of the questions into a generative AI and have the generative AI perform the adjustment of the order of answers.

[0048] The meal analysis unit can analyze the user's past eating history and select the optimal analysis method during meal analysis. For example, the meal analysis unit can select the optimal meal analysis method based on the user's past meal data. The meal analysis unit can also select an analysis method that considers nutritional balance based on the user's past meal history. Furthermore, the meal analysis unit can analyze the user's past meal history and select an analysis method to compensate for deficiencies in specific nutrients. For example, the meal analysis unit can select the optimal meal analysis method based on the user's past meal data. This allows the meal analysis unit to analyze the user's past meal history and select the optimal analysis method. Some or all of the above processes in the meal analysis unit may be performed using AI, or not. For example, the meal analysis unit can input the user's past meal data into AI and have AI select the optimal analysis method.

[0049] The dietary analysis unit can adjust its analysis method during dietary analysis, taking into account the user's current health condition. For example, the dietary analysis unit can select an analysis method that emphasizes specific nutrients based on the user's health checkup results. Furthermore, if the user has a specific illness, the dietary analysis unit can select a dietary analysis method appropriate for that illness. In addition, the dietary analysis unit can select the optimal dietary analysis method considering the user's current physical condition. For example, the dietary analysis unit can select an analysis method that emphasizes specific nutrients based on the user's health checkup results. This allows the dietary analysis unit to adjust its analysis method considering the user's current health condition. Some or all of the above processes in the dietary analysis unit may be performed using AI, or not. For example, the dietary analysis unit can input the user's health data into AI and have AI perform the adjustment of the analysis method.

[0050] The meal analysis unit can select the optimal analysis method when analyzing a meal, taking into account the user's geographical location information. For example, if the user is in a specific region, the meal analysis unit will select an analysis method that takes into account the ingredients of that region. Furthermore, if the user is traveling, the meal analysis unit can select an analysis method that takes into account the food culture of the travel destination. Additionally, if the user is at home, the meal analysis unit can select an analysis method that takes into account everyday ingredients. For example, if the user is in a specific region, the meal analysis unit will select an analysis method that takes into account the ingredients of that region. This allows the meal analysis unit to select the optimal analysis method while considering the user's geographical location information. Some or all of the above processing in the meal analysis unit may be performed using AI, or not. For example, the meal analysis unit can input the user's geographical location data into AI and have the AI ​​select the optimal analysis method.

[0051] The meal analysis unit can adjust its analysis method while considering the user's dietary preferences. For example, if the user prefers a particular ingredient, the meal analysis unit can select an analysis method that emphasizes that ingredient. Furthermore, if the user prefers a particular dish, the meal analysis unit can select an analysis method suitable for that dish. In addition, the meal analysis unit can select the optimal meal analysis method considering the user's dietary preferences. For example, if the user prefers a particular ingredient, the meal analysis unit can select an analysis method that emphasizes that ingredient. This allows the meal analysis unit to adjust its analysis method while considering the user's dietary preferences. Some or all of the above processes in the meal analysis unit may be performed using AI, or not. For example, the meal analysis unit can input the user's dietary preference data into AI and have the AI ​​adjust the analysis method.

[0052] The risk prediction unit can analyze the user's past health data to select the optimal prediction method when predicting risk. For example, the risk prediction unit can select the optimal risk prediction method based on the user's past health checkup data. The risk prediction unit can also select a risk prediction method considering the user's past medical history. Furthermore, the risk prediction unit can analyze the user's past health data to select a method for predicting a specific risk. For example, the risk prediction unit can select the optimal risk prediction method based on the user's past health checkup data. This allows the risk prediction unit to analyze the user's past health data and select the optimal prediction method. Some or all of the above processing in the risk prediction unit may be performed using AI, for example, or without AI. For example, the risk prediction unit can input the user's past health data into AI and have AI select the optimal prediction method.

[0053] The risk prediction unit can adjust its prediction method when predicting risks, taking into account the user's current health condition. For example, the risk prediction unit can select a method to predict a specific risk based on the user's current health check results. Furthermore, if the user has a specific illness, the risk prediction unit can also select a method to predict risks associated with that illness. In addition, the risk prediction unit can select the optimal risk prediction method considering the user's current physical condition. For example, the risk prediction unit can select a method to predict a specific risk based on the user's health check results. This allows the risk prediction unit to adjust its prediction method considering the user's current health condition. Some or all of the above processing in the risk prediction unit may be performed using AI, or not. For example, the risk prediction unit can input the user's health data into AI and have the AI ​​adjust the prediction method.

[0054] The risk prediction unit can select the optimal prediction method when predicting risks, taking into account the user's geographical location information. For example, if the user is in a specific region, the risk prediction unit can select a prediction method that takes into account the health risks of that region. Furthermore, if the user is traveling, the risk prediction unit can select a prediction method that takes into account the health risks of the travel destination. Additionally, if the user is at home, the risk prediction unit can select a prediction method that takes into account everyday health risks. For example, if the user is in a specific region, the risk prediction unit can select a prediction method that takes into account the health risks of that region. This allows the risk prediction unit to select the optimal prediction method by taking into account the user's geographical location information. Some or all of the above processing in the risk prediction unit may be performed using AI, or without AI. For example, the risk prediction unit can input the user's geographical location data into AI and have the AI ​​select the optimal prediction method.

[0055] The risk prediction unit can adjust its prediction method when predicting risks, taking into account the user's lifestyle. For example, if the user is a smoker, the risk prediction unit will select a method to predict risks related to smoking. The risk prediction unit can also select a method to predict risks related to lack of exercise if the user is sedentary. Furthermore, the risk prediction unit can select the optimal risk prediction method by considering the user's lifestyle. For example, if the user is a smoker, the risk prediction unit will select a method to predict risks related to smoking. This allows the risk prediction unit to adjust its prediction method to account for the user's lifestyle. Some or all of the above processing in the risk prediction unit may be performed using AI, for example, or without AI. For example, the risk prediction unit can input user lifestyle data into AI and have the AI ​​adjust the prediction method.

[0056] The memory assistance unit can analyze the user's past behavioral history and select the optimal assistance method when providing memory assistance. For example, the memory assistance unit can select the optimal memory assistance method based on places where the user has frequently forgotten things in the past. The memory assistance unit can also select a method for providing memory assistance during specific time periods based on the user's past behavioral history. Furthermore, the memory assistance unit can analyze the user's past behavioral history and select a memory assistance method for specific actions. For example, the memory assistance unit can select the optimal memory assistance method based on places where the user has frequently forgotten things in the past. This allows the memory assistance unit to analyze the user's past behavioral history and select the optimal assistance method. Some or all of the above processing in the memory assistance unit may be performed using, for example, a generative AI, or without a generative AI. For example, the memory assistance unit can input the user's past behavioral data into a generative AI and have the generative AI select the optimal assistance method.

[0057] The memory assistance unit can adjust its assistance methods when providing memory assistance, taking into account the user's current activities. For example, if the user is at work, the memory assistance unit can provide memory assistance methods related to work. It can also provide memory assistance methods related to home activities if the user is at home. Furthermore, the memory assistance unit can provide the optimal memory assistance method by considering the user's current activities. For example, if the user is at work, the memory assistance unit can provide memory assistance methods related to work. This allows the memory assistance unit to adjust its assistance methods considering the user's current activities. Some or all of the above processing in the memory assistance unit may be performed using, for example, a generative AI, or without a generative AI. For example, the memory assistance unit can input the user's current activity data into a generative AI and have the generative AI adjust the assistance method.

[0058] The memory assistance unit can select the optimal assistance method when providing memory assistance, taking into account the user's geographical location information. For example, if the user is in a specific location, the memory assistance unit can provide a memory assistance method related to that location. Furthermore, if the user is traveling, the memory assistance unit can provide a memory assistance method related to the travel destination. Additionally, if the user is at home, the memory assistance unit can provide a memory assistance method related to daily life. For example, if the user is in a specific location, the memory assistance unit can provide a memory assistance method related to that location. This allows the memory assistance unit to select the optimal assistance method, taking into account the user's geographical location information. Some or all of the above processing in the memory assistance unit may be performed using, for example, a generative AI, or without a generative AI. For example, the memory assistance unit can input the user's geographical location data into a generative AI and have the generative AI select the optimal assistance method.

[0059] The memory assistance unit can adjust its assistance method while providing memory assistance, taking into account the user's lifestyle habits. For example, if the user is prone to forgetting things at a particular time of day, the memory assistance unit can provide memory assistance during that time. The memory assistance unit can also provide memory assistance for a specific action if the user is prone to forgetting that action. Furthermore, the memory assistance unit can provide the optimal memory assistance method, taking into account the user's lifestyle habits. For example, if the memory assistance unit is prone to forgetting things at a particular time of day, it can provide memory assistance during that time. This allows the memory assistance unit to adjust its assistance method while considering the user's lifestyle habits. Some or all of the above processing in the memory assistance unit may be performed using, for example, a generative AI, or without a generative AI. For example, the memory assistance unit can input the user's lifestyle data into a generative AI and have the generative AI adjust the assistance method.

[0060] The memory assistance unit can make suggestions based on the user's schedule by referring to the user's calendar information during memory assistance. For example, the memory assistance unit can refer to the schedule registered in the user's calendar and perform memory assistance. The memory assistance unit can also perform memory assistance related to a specific event from the user's calendar information. Furthermore, the memory assistance unit can perform memory assistance tailored to the schedule based on the user's calendar information. For example, the memory assistance unit can refer to the schedule registered in the user's calendar and perform memory assistance. This allows the memory assistance unit to make suggestions based on the schedule by referring to the user's calendar information. Some or all of the above processing in the memory assistance unit may be performed using, for example, a generating AI, or without using a generating AI. For example, the memory assistance unit can input the user's calendar information into a generating AI and have the generating AI execute suggestions based on the schedule.

[0061] The memory assistance unit can analyze the user's social media activity and provide relevant memory assistance during memory assistance. For example, if the user posts about a specific event on social media, the memory assistance unit can provide memory assistance related to that event. It can also provide memory assistance related to a specific location if the user posts about that location on social media. Furthermore, if the user posts about a specific topic on social media, the memory assistance unit can provide memory assistance related to that topic. For example, the memory assistance unit provides memory assistance based on information about events shared by the user on social media. This allows the memory assistance unit to analyze the user's social media activity and provide relevant memory assistance. Some or all of the above processing in the memory assistance unit may be performed using, for example, a generative AI, or without a generative AI. For example, the memory assistance unit can input the user's social media data into a generative AI and have the generative AI perform the relevant memory assistance.

[0062] The memory assistance unit can select the optimal assistance method while considering the user's health condition. For example, the memory assistance unit can select a memory assistance method suitable for a specific health condition based on the user's health check results. Furthermore, if the user has a specific illness, the memory assistance unit can select a memory assistance method related to that illness. In addition, the memory assistance unit can select the optimal memory assistance method considering the user's current physical condition. For example, the memory assistance unit can select a memory assistance method suitable for a specific health condition based on the user's health check results. This allows the memory assistance unit to select the optimal assistance method while considering the user's health condition. Some or all of the above processing in the memory assistance unit may be performed using, for example, a generative AI, or without a generative AI. For example, the memory assistance unit can input the user's health data into a generative AI and have the generative AI select the optimal assistance method.

[0063] The memory assistance unit can analyze the user's past memory assistance history and select the optimal assistance method during memory assistance. For example, the memory assistance unit can select the optimal assistance method based on the memory assistance methods the user has used in the past. The memory assistance unit can also select an assistance method to use during a specific time period based on the user's past memory assistance history. Furthermore, the memory assistance unit can analyze the user's past memory assistance history and select an assistance method for a specific action. For example, the memory assistance unit can select the optimal assistance method based on the memory assistance methods the user has used in the past. In this way, the memory assistance unit can analyze the user's past memory assistance history and select the optimal assistance method. Some or all of the above processing in the memory assistance unit may be performed using, for example, a generative AI, or without a generative AI. For example, the memory assistance unit can input the user's past memory assistance data into a generative AI and have the generative AI select the optimal assistance method.

[0064] The memory assistance unit can select the optimal assistance method when providing memory assistance, taking into account the user's device information. For example, if the user is using a smartphone, the memory assistance unit can provide a memory assistance method optimized for the smartphone. It can also provide a memory assistance method optimized for a tablet if the user is using a tablet. Furthermore, if the user is using a smartwatch, the memory assistance unit can provide a memory assistance method optimized for a smartwatch. For example, when the user is using a smartphone, the memory assistance unit provides a memory assistance method optimized for the smartphone. This allows the memory assistance unit to select the optimal assistance method, taking into account the user's device information. Some or all of the above processing in the memory assistance unit may be performed using, for example, a generative AI, or without a generative AI. For example, the memory assistance unit can input the user's device information into a generative AI and have the generative AI select the optimal assistance method.

[0065] The system according to the embodiment is not limited to the example described above, and various modifications are possible, for example, as follows.

[0066] The memory assist system may further include a behavioral analysis unit that analyzes the user's past behavioral history and selects the optimal capture method. For example, if the user has taken many photos at a particular location in the past, the behavioral analysis unit can automatically activate the camera when the user arrives at that location. It can also automatically capture voice memos during a particular event if the user has taken many notes at that event in the past. Furthermore, if the user has captured a lot of data during a particular time period in the past, it can automatically start capturing during that time period. In this way, the behavioral analysis unit can analyze the user's past behavioral history and select the optimal capture method. Some or all of the above processing in the behavioral analysis unit may be performed using AI or not.

[0067] The memory assist system may further include an activity filter unit that filters data based on the user's current activities and areas of interest. For example, if the user is playing sports, the activity filter unit will capture only data related to that activity. If the user is reading, it can also capture information related to the title and content of the book. Furthermore, if the user is traveling, it can prioritize capturing information and photos related to the travel destination. In this way, the activity filter unit can filter data based on the user's current activities and areas of interest. Some or all of the processing described above in the activity filter unit may be performed using AI or not.

[0068] The memory assist system may further include a location information capture unit that prioritizes capturing highly relevant data while considering the user's geographical location. For example, if the user is in a tourist destination, the location information capture unit will prioritize capturing information and photos related to that location. If the user is at home, it can also prioritize capturing information related to daily life. Furthermore, if the user is at work, it can also prioritize capturing information related to work. In this way, the location information capture unit can prioritize capturing highly relevant data while considering the user's geographical location. Some or all of the above processing in the location information capture unit may be performed using AI or not.

[0069] The memory assist system may further include a social media capture unit that analyzes the user's social media activity and captures relevant data. For example, if the user posts about a specific event on social media, the social media capture unit can capture information related to that event. It can also capture information related to a specific location if the user posts about a specific location on social media. Furthermore, if the user posts about a specific topic on social media, it can capture information related to that topic. This allows the social media capture unit to analyze the user's social media activity and capture relevant data. Some or all of the processing described above in the social media capture unit may be performed using AI or not.

[0070] The memory-assist system may further include a importance classification unit that adjusts the level of detail of classification based on the importance of the data. For example, the importance classification unit may classify important data in detail and assign many relevant tags to it. Alternatively, it may classify less important data simply and assign only basic tags to it. Furthermore, it may change the data classification method and adjust the level of detail according to the importance of the data. In this way, the importance classification unit can adjust the level of detail of classification based on the importance of the data. Some or all of the above processing in the importance classification unit may be performed using AI or not.

[0071] The memory assist system may further include a category classification unit that applies different classification algorithms depending on the data category. For example, the category classification unit can apply an image recognition algorithm to image data and classify it based on its content. It can also apply a speech recognition algorithm to audio data and classify it based on its content. Furthermore, it can apply a natural language processing algorithm to text data and classify it based on its content. This allows the category classification unit to apply different classification algorithms depending on the data category. Some or all of the above processing in the category classification unit may be performed using AI or not.

[0072] The following briefly describes the processing flow for example form 1.

[0073] Step 1: The capture unit captures data according to the user's actions and environment. For example, it can capture images while the user is moving, capture audio data while working, and capture sensor data when the user is in a specific location. Specifically, it can capture the surrounding scenery when the user is in a park. Step 2: The classification unit classifies and organizes the data captured by the capture unit on the cloud. For example, it can classify image data by category, convert audio data into text data and organize it, and organize sensor data chronologically. Specifically, it can classify image data into categories such as landscapes, people, and objects. Step 3: The dialogue unit generates answers to user questions based on data classified and organized by the classification unit. For example, if the user asks, "What did I have for dinner yesterday?", it generates an answer based on past data; if the user asks, "What should I eat next?", it generates an answer considering health risks; and if the user asks, "Where did I put my smartphone?", it generates an answer based on past behavioral data.

[0074] (Example of form 2) The memory assist system according to an embodiment of the present invention is a system that utilizes a wearable device capable of automatically recording, organizing, and recalling important moments and information in daily life. This system captures images and data according to the user's actions and environment, and classifies and organizes them on the cloud. The user can easily search for information later using the conversational function of the generative AI, and access it immediately when needed. For example, there is a function to record special moments. For example, it automatically captures a smile that a child suddenly shows and organizes and saves it on the cloud. This allows parents to record special moments without missing them and easily review them later. There are also functions for meal management and calorie management. When a user eats, the wearable device automatically captures the contents of the meal, and the AI ​​analyzes it to record calories and nutrients. This allows the user to achieve accurate health management without stress. Furthermore, it predicts health risks from the recorded data and suggests meals to eat next. There is also a memory support function for people with early-stage dementia. Using conversational generative AI, it answers questions such as "Where did I put my smartphone?" based on past behavioral data. This helps to support memory decline and reduce difficulties in daily life. The system automatically captures data based on the user's actions and environment, classifying and organizing it in the cloud, allowing users to easily search and access necessary information. This ensures that special moments are recorded, enabling health management and memory support. Thus, the memory assist system can automatically record, organize, and recall important moments and information of the user.

[0075] The memory assist system according to this embodiment comprises a capture unit, a classification unit, and a dialogue unit. The capture unit captures data according to the user's actions and environment. For example, the capture unit can capture images while the user is moving. The capture unit can also capture audio data while the user is working. Furthermore, the capture unit can capture sensor data when the user is in a specific location. For example, the capture unit can capture the surrounding scenery when the user is in a park. The classification unit classifies and organizes the data captured by the capture unit on the cloud. For example, the classification unit classifies image data into categories. The classification unit can also convert audio data into text data and organize it. Furthermore, the classification unit can organize sensor data chronologically. For example, the classification unit classifies image data into categories such as scenery, people, and objects. The dialogue unit generates answers to user questions based on the data classified and organized by the classification unit. For example, if the user asks, "What was for dinner yesterday?", the dialogue unit generates an answer based on past data. The dialogue unit can also generate an answer considering health risks if the user asks, "What should I eat next?" Furthermore, the dialogue unit can also generate an answer based on past behavioral data when the user asks, "Where did I put my smartphone?" For example, the dialogue unit searches past data in response to the user's question and generates an appropriate answer. As a result, the memory assist system according to the embodiment can capture data according to the user's behavior and environment, classify and organize it in the cloud, and generate answers to the user's questions.

[0076] The capture unit captures data according to the user's actions and environment. For example, the capture unit can capture images while the user is on the move. Specifically, if the user is carrying a smartphone or wearable device, it can use the camera and microphone on these devices to automatically record the surrounding scenery and sounds. For example, when a user visits a tourist spot while traveling, the capture unit can automatically take pictures of the place and record voice memos. The capture unit can also capture audio data while the user is working. For example, it can record what the user says in a meeting or ideas that come to mind while working. Furthermore, the capture unit can capture sensor data when the user is in a specific location. For example, when a user is in a park, it can not only capture the surrounding scenery but also simultaneously record environmental data such as temperature, humidity, and location information. In this way, the capture unit collects diverse data about the user's actions and environment for later reference. In addition, to protect user privacy, the capture unit allows users to set the scope and frequency of data collection. For example, it can provide settings to stop data capture in specific locations or time periods, or to capture only specific data types. This allows the capture unit to achieve flexible data collection tailored to user needs, efficiently collecting necessary information while respecting user privacy.

[0077] The classification unit classifies and organizes data captured by the capture unit on the cloud. For example, the classification unit classifies image data into categories. Specifically, it can automatically classify images into categories such as landscapes, people, and objects using image recognition technology. For example, it can classify photos taken by a user during a trip into landscape photos, people photos, food photos, etc., making them easy to search later. The classification unit can also convert and organize audio data into text data. Using speech recognition technology, it can convert audio data from meeting recordings and notes into text and organize it by keyword or topic. This allows users to search the text data later and quickly find the information they need. Furthermore, the classification unit can organize sensor data chronologically. For example, it can organize environmental data such as location information, temperature, and humidity chronologically, making it easy to refer to data for specific times of day or locations. This allows users to review past actions and environmental changes chronologically and quickly obtain the information they need. In addition, because the classification unit manages data on the cloud, users can access the data from any internet-connected device. This allows users to check and use the data from anywhere, such as at home, in the office, or while traveling. The classification unit can protect data using encryption technology to ensure data security and protect user privacy. This allows the classification unit to efficiently and securely classify and organize data, enabling users to quickly retrieve the information they need.

[0078] The dialogue unit generates answers to user questions based on data classified and organized by the classification unit. For example, if a user asks, "What was for dinner yesterday?", the dialogue unit generates an answer based on past data. Specifically, it searches for images, audio data, and text notes previously captured by the user, extracts the relevant information, and generates an answer. For example, if the user took a picture of their dinner, it can answer, "Yesterday's dinner was pasta," based on that picture. The dialogue unit can also generate an answer considering health risks if the user asks, "What should I eat next?" For example, it can suggest a nutritionally balanced meal based on the user's past meal data and health status. Furthermore, if the user asks, "Where did I put my smartphone?", the dialogue unit can generate an answer based on past behavioral data. For example, it can identify the last place and time the user used their smartphone and answer, "You last used it in the living room." The dialogue unit uses natural language processing technology to understand user questions and generate appropriate answers. This allows users to easily obtain the necessary information in a conversational format. In addition, the dialogue unit can continuously improve the accuracy of its answers based on user feedback. For example, by providing feedback such as "correct" or "incorrect" to the answers provided by the user, the dialogue unit can learn from that feedback and improve the accuracy of its answers in the future. This allows the dialogue unit to provide flexible and highly accurate answers that meet the user's needs, thereby improving user convenience.

[0079] The meal analysis unit can capture meal content and analyze calories and nutrients. For example, the meal analysis unit captures meal content when a user eats. The meal analysis unit can also analyze calories based on the captured meal content. Furthermore, the meal analysis unit can analyze nutrients based on the captured meal content. For example, the meal analysis unit calculates the calories of the food the user ate. In this way, the meal analysis unit can capture meal content and analyze calories and nutrients. Some or all of the above processing in the meal analysis unit may be performed using AI, for example, or without AI. For example, the meal analysis unit can input the captured meal content into AI and have the AI ​​perform the calorie and nutrient analysis.

[0080] The risk prediction unit can predict health risks and suggest the next meal to eat. For example, the risk prediction unit predicts health risks based on the user's health data. The risk prediction unit can also suggest the next meal to eat based on the predicted health risks. Furthermore, the risk prediction unit can make meal suggestions considering the user's eating history. For example, the risk prediction unit may suggest a low-sodium diet based on the user's blood pressure data. In this way, the risk prediction unit can predict health risks and suggest the next meal to eat. Some or all of the above processing in the risk prediction unit may be performed using AI, for example, or without AI. For example, the risk prediction unit can input the user's health data into AI and have the AI ​​perform health risk prediction and meal suggestions.

[0081] The memory assistance unit can assist the user's memory. For example, if the user asks, "Where did I put my smartphone?", the memory assistance unit can generate an answer based on past behavioral data. Similarly, if the user asks, "I forgot where I put my keys," the memory assistance unit can generate an answer based on past behavioral data. Furthermore, if the user asks, "Tell me what happened at yesterday's meeting," the memory assistance unit can generate an answer based on past behavioral data. For example, the memory assistance unit searches past data in response to the user's question and generates an appropriate answer. In this way, the memory assistance unit can assist the user's memory. Some or all of the above-described processes in the memory assistance unit may be performed using, for example, a generative AI, or without a generative AI. For example, the memory assistance unit can input the user's question into a generative AI and have the generative AI perform the process of generating an answer based on past behavioral data.

[0082] The capture unit can estimate the user's emotions and adjust the timing of captures based on the estimated emotions. For example, if the user is happy, the capture unit can automatically activate the camera to capture that moment. The capture unit can also capture a voice memo to record the emotion if the user is sad. Furthermore, if the user is excited, the capture unit can take continuous shots to ensure that the moment is not missed. For example, the capture unit can capture the moment the user smiles. This allows the capture unit to adjust the timing of captures based on the user's emotions. Emotion estimation is achieved using an emotion estimation function, such as an emotion engine or generative AI. Generative AI may be, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI. Some or all of the above processing in the capture unit may be performed using AI, or not. For example, the capture unit can input user facial expression data into a generative AI and have the generative AI perform emotion estimation and adjustment of capture timing.

[0083] The capture unit can analyze the user's past behavior history and select the optimal capture method. For example, if the user has taken many photos at a particular location in the past, the capture unit can automatically activate the camera when the user arrives at that location. The capture unit can also automatically capture voice memos during a particular event if the user has taken many notes at that event in the past. Furthermore, if the capture unit has captured a large amount of data during a specific time period in the past, it can automatically start capturing during that time period. For example, the capture unit can automatically take photos at tourist destinations the user has visited in the past. This allows the capture unit to analyze the user's past behavior history and select the optimal capture method. Some or all of the above processing in the capture unit may be performed using AI, or not. For example, the capture unit can input the user's past behavior data into AI and have the AI ​​select the optimal capture method.

[0084] The capture unit can filter data based on the user's current activities and areas of interest during capture. For example, if the user is playing sports, the capture unit will capture only data related to that activity. It can also capture information related to the book's title and content if the user is reading. Furthermore, if the user is traveling, the capture unit can prioritize capturing information and photos related to the travel destination. For example, if the user is participating in a sporting event, the capture unit will capture photos and videos related to that event. This allows the capture unit to filter data based on the user's current activities and areas of interest. Some or all of the above processing in the capture unit may be performed using AI, for example, or without AI. For example, the capture unit can input the user's current activity data into an AI and have the AI ​​perform the filtering.

[0085] The capture unit can estimate the user's emotions and determine the priority of data to capture based on the estimated emotions. For example, if the user is happy, the capture unit will prioritize capturing that moment. Similarly, if the user is sad, the capture unit can prioritize capturing voice memos to record that emotion. Furthermore, if the user is excited, the capture unit can prioritize continuous shooting to ensure that the moment is not missed. For example, the capture unit will prioritize capturing the moment the user smiles. This allows the capture unit to determine the priority of data to capture based on the user's emotions. Emotion estimation is achieved using an emotion estimation function, such as an emotion engine or generative AI. Generative AI may be, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI. Some or all of the above processing in the capture unit may be performed using AI, or not. For example, the capture unit can input user facial expression data into a generative AI and have the generative AI perform emotion estimation and data priority determination.

[0086] The capture unit can prioritize capturing highly relevant data by considering the user's geographical location during the capture process. For example, if the user is in a tourist destination, the capture unit will prioritize capturing information and photos related to that location. Similarly, if the user is at home, the capture unit can prioritize capturing information related to daily life. Furthermore, if the user is at work, the capture unit can prioritize capturing work-related information. For example, when the user is in a tourist destination, the capture unit will prioritize capturing landmarks and scenery of that location. This allows the capture unit to prioritize capturing highly relevant data by considering the user's geographical location. Some or all of the above processing in the capture unit may be performed using AI, or without AI. For example, the capture unit can input the user's geographical location data into an AI and have the AI ​​perform the capture of highly relevant data.

[0087] The capture unit can analyze the user's social media activity and capture relevant data during the capture process. For example, if the user posts about a specific event on social media, the capture unit can capture information related to that event. It can also capture information related to a specific location if the user posts about that location on social media. Furthermore, if the user posts about a specific topic on social media, the capture unit can capture information related to that topic. For example, the capture unit can capture photos of events shared by the user on social media. This allows the capture unit to analyze the user's social media activity and capture relevant data. Some or all of the above processing in the capture unit may be performed using AI, for example, or without AI. For example, the capture unit can input the user's social media data into an AI and have the AI ​​perform the capture of relevant data.

[0088] The classification unit can estimate the user's emotions and adjust the classification criteria based on the estimated emotions. For example, if the user is happy, the classification unit will prioritize classifying data related to that emotion. Similarly, if the user is sad, the classification unit can prioritize classifying data related to that emotion. Furthermore, if the user is excited, the classification unit can prioritize classifying data related to that emotion. For example, the classification unit might prioritize classifying photos of the moment the user smiled. This allows the classification unit to adjust the classification criteria based on the user's emotions. Emotion estimation is achieved using an emotion estimation function, such as an emotion engine or generative AI. Generative AI may be, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI. Some or all of the above-described processes in the classification unit may be performed using AI, or not. For example, the classification unit can input user emotion data into a generative AI and have the generative AI adjust the classification criteria.

[0089] The classification unit can adjust the level of detail in classification based on the importance of the data. For example, the classification unit can classify important data in detail and assign many relevant tags. Alternatively, it can classify less important data simply and assign only basic tags. Furthermore, the classification unit can change the data classification method and adjust the level of detail according to importance. For example, the classification unit can classify important meeting records in detail. This allows the classification unit to adjust the level of detail in classification based on the importance of the data. Some or all of the above processes in the classification unit may be performed using AI, for example, or not. For example, the classification unit can input the importance of the data into the AI ​​and have the AI ​​perform the adjustment of the level of detail in classification.

[0090] The classification unit can apply different classification algorithms depending on the data category during classification. For example, the classification unit can apply an image recognition algorithm to image data and classify it based on its content. It can also apply a speech recognition algorithm to audio data and classify it based on its content. Furthermore, it can apply a natural language processing algorithm to text data and classify it based on its content. For example, the classification unit can classify image data into categories such as landscapes, people, and objects. This allows the classification unit to apply different classification algorithms depending on the data category. Some or all of the above processing in the classification unit may be performed using AI, for example, or without AI. For example, the classification unit can input the data categories into the AI ​​and have the AI ​​apply an appropriate classification algorithm.

[0091] The classification unit can estimate the user's emotions and determine classification priorities based on the estimated emotions. For example, if the user is happy, the classification unit will prioritize classifying data related to that emotion. Similarly, if the user is sad, the classification unit can prioritize classifying data related to that emotion. Furthermore, if the user is excited, the classification unit can prioritize classifying data related to that emotion. For example, the classification unit might prioritize classifying photos of the moment the user smiled. This allows the classification unit to determine classification priorities based on the user's emotions. Emotion estimation is achieved using an emotion estimation function, such as an emotion engine or generative AI. Generative AI may be, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI. Some or all of the above-described processes in the classification unit may be performed using AI, or not. For example, the classification unit can input user emotion data into a generative AI and have the generative AI determine the classification priorities.

[0092] The classification unit can adjust the classification order based on when the data was submitted. For example, the classification unit may prioritize the classification of the most recent data and postpone the classification of older data. It can also prioritize the classification of data submitted during a specific period. Furthermore, the classification unit can adjust the classification order of the data according to the submission date. For example, the classification unit may prioritize the classification of the most recent meeting record data. This allows the classification unit to adjust the classification order based on when the data was submitted. Some or all of the above processes in the classification unit may be performed using AI, for example, or not. For example, the classification unit can input the data submission date into the AI ​​and have the AI ​​perform the adjustment of the classification order.

[0093] The classification unit can adjust the order of classification based on the relevance of the data during the classification process. For example, the classification unit may prioritize classifying highly relevant data and postpone classifying less relevant data. It can also prioritize classifying data related to specific categories. Furthermore, the classification unit can adjust the order of classification according to the relevance of the data. For example, the classification unit may prioritize classifying highly relevant project data. This allows the classification unit to adjust the order of classification based on the relevance of the data. Some or all of the above processes in the classification unit may be performed using AI, for example, or not. For example, the classification unit can input the data relevance into the AI ​​and have the AI ​​perform the adjustment of the classification order.

[0094] The dialogue unit can estimate the user's emotions and adjust the way it expresses its responses based on those emotions. For example, if the user is nervous, the dialogue unit will respond in a calm manner. Conversely, if the user is relaxed, it can respond in a friendly manner. Furthermore, if the user is in a hurry, the dialogue unit can provide a concise and quick response. For example, when the user is nervous, the dialogue unit will generate a response in a calm tone. This allows the dialogue unit to adjust the way it expresses its responses based on the user's emotions. Emotion estimation is achieved using an emotion estimation function, such as an emotion engine or generative AI. Generative AI may be, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI. Some or all of the above processing in the dialogue unit may be performed using, for example, a generative AI, or not. For example, the dialogue unit can input user emotion data into a generative AI and have the generative AI adjust the way it expresses its responses.

[0095] The dialogue unit can adjust the level of detail in its answers based on the importance of the questions during the conversation. For example, the dialogue unit can provide detailed answers to important questions. It can also provide concise answers to less important questions. Furthermore, the dialogue unit can adjust the level of detail in its answers according to the importance of the questions. For example, the dialogue unit can generate detailed answers to important technical questions. This allows the dialogue unit to adjust the level of detail in its answers based on the importance of the questions. Some or all of the above processing in the dialogue unit may be performed using, for example, a generative AI, or without a generative AI. For example, the dialogue unit can input the importance of the questions into the generative AI and have the generative AI adjust the level of detail in its answers.

[0096] The dialogue unit can apply different answer algorithms depending on the category of the question during the dialogue. For example, the dialogue unit can apply a specialized answer algorithm to technical questions. It can also apply a concise answer algorithm to general questions. Furthermore, it can apply a friendly answer algorithm to personal questions. For example, the dialogue unit generates a specialized answer to a technical question. This allows the dialogue unit to apply different answer algorithms depending on the category of the question. Some or all of the above processing in the dialogue unit may be performed using, for example, a generative AI, or not using a generative AI. For example, the dialogue unit can input the category of the question into a generative AI and have the generative AI apply an appropriate answer algorithm.

[0097] The dialogue unit can estimate the user's emotions and adjust the length of its response based on the estimated emotions. For example, if the user is in a hurry, the dialogue unit will provide a short, concise response. If the user is relaxed, the dialogue unit can also provide a longer response with more detailed explanations. Furthermore, if the user is excited, the dialogue unit can provide a response with visually stimulating effects. For example, when the user is in a hurry, the dialogue unit generates a short, concise response. This allows the dialogue unit to adjust the length of its response based on the user's emotions. Emotion estimation is achieved using an emotion estimation function, for example, with an emotion engine or generative AI. Generative AI may be, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI. Some or all of the above processing in the dialogue unit may be performed using, for example, a generative AI, or not using a generative AI. For example, the dialogue unit can input user emotion data into a generative AI and have the generative AI adjust the length of the response.

[0098] The dialogue unit can determine the priority of answers based on when the questions were submitted during the dialogue. For example, the dialogue unit may prioritize answering the most recent questions and postpone older questions. It can also prioritize answering questions submitted within a specific period. Furthermore, the dialogue unit can adjust the order in which questions are answered according to the submission date. For example, the dialogue unit may prioritize answering the most recent questions. This allows the dialogue unit to determine the priority of answers based on when the questions were submitted. Some or all of the above processing in the dialogue unit may be performed using, for example, a generative AI, or not using a generative AI. For example, the dialogue unit can input the submission date of the questions into a generative AI and have the generative AI determine the priority of the answers.

[0099] The dialogue unit can adjust the order of answers based on the relevance of the questions during the conversation. For example, the dialogue unit may prioritize answering highly relevant questions and postpone answering less relevant ones. It can also prioritize answering questions related to a specific category. Furthermore, the dialogue unit can adjust the order of answers according to the relevance of the questions. For example, the dialogue unit may prioritize answering highly relevant technical questions. In this way, the dialogue unit can adjust the order of answers based on the relevance of the questions. Some or all of the above processing in the dialogue unit may be performed using, for example, a generative AI, or not using a generative AI. For example, the dialogue unit can input the relevance of the questions into a generative AI and have the generative AI perform the adjustment of the order of answers.

[0100] The meal analysis unit can estimate the user's emotions and adjust the meal analysis method based on the estimated emotions. For example, if the user is stressed, the meal analysis unit can perform a simple meal analysis and suggest meals that reduce stress. If the user is relaxed, the meal analysis unit can also perform a detailed meal analysis and suggest healthy meals. Furthermore, if the user is in a hurry, the meal analysis unit can perform a quick meal analysis and provide simple meal suggestions. For example, if the user is stressed, the meal analysis unit can suggest meals that help reduce stress. In this way, the meal analysis unit can adjust the meal analysis method based on the user's emotions. Emotion estimation is achieved using an emotion estimation function, for example, using an emotion engine or generative AI. Generative AI is, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI. Some or all of the above processing in the meal analysis unit may be performed using AI, for example, or not using AI. For example, the meal analysis unit can input the user's emotion data into the generative AI and have the generative AI adjust the meal analysis method.

[0101] The meal analysis unit can analyze the user's past eating history and select the optimal analysis method during meal analysis. For example, the meal analysis unit can select the optimal meal analysis method based on the user's past meal data. The meal analysis unit can also select an analysis method that considers nutritional balance based on the user's past meal history. Furthermore, the meal analysis unit can analyze the user's past meal history and select an analysis method to compensate for deficiencies in specific nutrients. For example, the meal analysis unit can select the optimal meal analysis method based on the user's past meal data. This allows the meal analysis unit to analyze the user's past meal history and select the optimal analysis method. Some or all of the above processes in the meal analysis unit may be performed using AI, or not. For example, the meal analysis unit can input the user's past meal data into AI and have AI select the optimal analysis method.

[0102] The dietary analysis unit can adjust its analysis method during dietary analysis, taking into account the user's current health condition. For example, the dietary analysis unit can select an analysis method that emphasizes specific nutrients based on the user's health checkup results. Furthermore, if the user has a specific illness, the dietary analysis unit can select a dietary analysis method appropriate for that illness. In addition, the dietary analysis unit can select the optimal dietary analysis method considering the user's current physical condition. For example, the dietary analysis unit can select an analysis method that emphasizes specific nutrients based on the user's health checkup results. This allows the dietary analysis unit to adjust its analysis method considering the user's current health condition. Some or all of the above processes in the dietary analysis unit may be performed using AI, or not. For example, the dietary analysis unit can input the user's health data into AI and have AI perform the adjustment of the analysis method.

[0103] The meal analysis unit can estimate the user's emotions and determine the priority of meal analysis based on the estimated emotions. For example, if the user is stressed, the meal analysis unit will prioritize meal analysis that helps reduce stress. It can also prioritize healthy meal analysis if the user is relaxed. Furthermore, if the user is in a hurry, the meal analysis unit can perform meal analysis quickly. For example, when the user is stressed, the meal analysis unit will prioritize meal analysis that helps reduce stress. This allows the meal analysis unit to determine the priority of meal analysis based on the user's emotions. Emotion estimation is achieved using an emotion estimation function, such as an emotion engine or generative AI. Generative AI may be, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI. Some or all of the above processing in the meal analysis unit may be performed using AI, or not. For example, the meal analysis unit can input user emotion data into a generative AI and have the generative AI determine the priority of meal analysis.

[0104] The meal analysis unit can select the optimal analysis method when analyzing a meal, taking into account the user's geographical location information. For example, if the user is in a specific region, the meal analysis unit will select an analysis method that takes into account the ingredients of that region. Furthermore, if the user is traveling, the meal analysis unit can select an analysis method that takes into account the food culture of the travel destination. Additionally, if the user is at home, the meal analysis unit can select an analysis method that takes into account everyday ingredients. For example, if the user is in a specific region, the meal analysis unit will select an analysis method that takes into account the ingredients of that region. This allows the meal analysis unit to select the optimal analysis method while considering the user's geographical location information. Some or all of the above processing in the meal analysis unit may be performed using AI, or not. For example, the meal analysis unit can input the user's geographical location data into AI and have the AI ​​select the optimal analysis method.

[0105] The meal analysis unit can adjust its analysis method while considering the user's dietary preferences. For example, if the user prefers a particular ingredient, the meal analysis unit can select an analysis method that emphasizes that ingredient. Furthermore, if the user prefers a particular dish, the meal analysis unit can select an analysis method suitable for that dish. In addition, the meal analysis unit can select the optimal meal analysis method considering the user's dietary preferences. For example, if the user prefers a particular ingredient, the meal analysis unit can select an analysis method that emphasizes that ingredient. This allows the meal analysis unit to adjust its analysis method while considering the user's dietary preferences. Some or all of the above processes in the meal analysis unit may be performed using AI, or not. For example, the meal analysis unit can input the user's dietary preference data into AI and have the AI ​​adjust the analysis method.

[0106] The risk prediction unit can estimate the user's emotions and adjust the risk prediction method based on the estimated user emotions. For example, if the user is feeling stressed, the risk prediction unit can select a risk prediction method that helps reduce stress. It can also select a healthy risk prediction method if the user is relaxed. Furthermore, if the user is in a hurry, the risk prediction unit can perform a rapid risk prediction. For example, if the user is feeling stressed, the risk prediction unit can select a risk prediction method that helps reduce stress. This allows the risk prediction unit to adjust the risk prediction method based on the user's emotions. Emotion estimation is achieved using an emotion estimation function, such as an emotion engine or generative AI. Generative AI may be, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI. Some or all of the above-described processes in the risk prediction unit may be performed using AI, or not. For example, the risk prediction unit can input user emotion data into the generative AI and have the generative AI adjust the risk prediction method.

[0107] The risk prediction unit can analyze the user's past health data to select the optimal prediction method when predicting risk. For example, the risk prediction unit can select the optimal risk prediction method based on the user's past health checkup data. The risk prediction unit can also select a risk prediction method considering the user's past medical history. Furthermore, the risk prediction unit can analyze the user's past health data to select a method for predicting a specific risk. For example, the risk prediction unit can select the optimal risk prediction method based on the user's past health checkup data. This allows the risk prediction unit to analyze the user's past health data and select the optimal prediction method. Some or all of the above processing in the risk prediction unit may be performed using AI, for example, or without AI. For example, the risk prediction unit can input the user's past health data into AI and have AI select the optimal prediction method.

[0108] The risk prediction unit can adjust its prediction method when predicting risks, taking into account the user's current health condition. For example, the risk prediction unit can select a method to predict a specific risk based on the user's current health check results. Furthermore, if the user has a specific illness, the risk prediction unit can also select a method to predict risks associated with that illness. In addition, the risk prediction unit can select the optimal risk prediction method considering the user's current physical condition. For example, the risk prediction unit can select a method to predict a specific risk based on the user's health check results. This allows the risk prediction unit to adjust its prediction method considering the user's current health condition. Some or all of the above processing in the risk prediction unit may be performed using AI, or not. For example, the risk prediction unit can input the user's health data into AI and have the AI ​​adjust the prediction method.

[0109] The risk prediction unit can estimate the user's emotions and determine the priority of risk predictions based on the estimated emotions. For example, if the user is stressed, the risk prediction unit will prioritize risk predictions that help reduce stress. It can also prioritize healthy risk predictions if the user is relaxed. Furthermore, if the user is in a hurry, the risk prediction unit can perform risk predictions quickly. For example, when the user is stressed, the risk prediction unit will prioritize risk predictions that help reduce stress. This allows the risk prediction unit to determine the priority of risk predictions based on the user's emotions. Emotion estimation is achieved using an emotion estimation function, such as an emotion engine or generative AI. Generative AI may be, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI. Some or all of the above-described processes in the risk prediction unit may be performed using AI, or not. For example, the risk prediction unit can input user emotion data into a generative AI and have the generative AI determine the priority of risk predictions.

[0110] The risk prediction unit can select the optimal prediction method when predicting risks, taking into account the user's geographical location information. For example, if the user is in a specific region, the risk prediction unit can select a prediction method that takes into account the health risks of that region. Furthermore, if the user is traveling, the risk prediction unit can select a prediction method that takes into account the health risks of the travel destination. Additionally, if the user is at home, the risk prediction unit can select a prediction method that takes into account everyday health risks. For example, if the user is in a specific region, the risk prediction unit can select a prediction method that takes into account the health risks of that region. This allows the risk prediction unit to select the optimal prediction method by taking into account the user's geographical location information. Some or all of the above processing in the risk prediction unit may be performed using AI, or without AI. For example, the risk prediction unit can input the user's geographical location data into AI and have the AI ​​select the optimal prediction method.

[0111] The risk prediction unit can adjust its prediction method when predicting risks, taking into account the user's lifestyle. For example, if the user is a smoker, the risk prediction unit will select a method to predict risks related to smoking. The risk prediction unit can also select a method to predict risks related to lack of exercise if the user is sedentary. Furthermore, the risk prediction unit can select the optimal risk prediction method by considering the user's lifestyle. For example, if the user is a smoker, the risk prediction unit will select a method to predict risks related to smoking. This allows the risk prediction unit to adjust its prediction method to account for the user's lifestyle. Some or all of the above processing in the risk prediction unit may be performed using AI, for example, or without AI. For example, the risk prediction unit can input user lifestyle data into AI and have the AI ​​adjust the prediction method.

[0112] The memory assistance unit can estimate the user's emotions and adjust the memory assistance method based on the estimated emotions. For example, if the user is feeling stressed, the memory assistance unit can provide a simple memory assistance method. It can also provide a more detailed memory assistance method if the user is relaxed. Furthermore, if the user is in a hurry, the memory assistance unit can provide rapid memory assistance. For example, when the user is feeling stressed, the memory assistance unit provides a simple memory assistance method. This allows the memory assistance unit to adjust the memory assistance method based on the user's emotions. Emotion estimation is achieved using an emotion estimation function, for example, using an emotion engine or a generative AI. The generative AI is, 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 memory assistance unit may be performed using a generative AI, or not. For example, the memory assistance unit can input user emotion data into a generative AI and have the generative AI adjust the memory assistance method.

[0113] The memory assistance unit can analyze the user's past behavioral history and select the optimal assistance method when providing memory assistance. For example, the memory assistance unit can select the optimal memory assistance method based on places where the user has frequently forgotten things in the past. The memory assistance unit can also select a method for providing memory assistance during specific time periods based on the user's past behavioral history. Furthermore, the memory assistance unit can analyze the user's past behavioral history and select a memory assistance method for specific actions. For example, the memory assistance unit can select the optimal memory assistance method based on places where the user has frequently forgotten things in the past. This allows the memory assistance unit to analyze the user's past behavioral history and select the optimal assistance method. Some or all of the above processing in the memory assistance unit may be performed using, for example, a generative AI, or without a generative AI. For example, the memory assistance unit can input the user's past behavioral data into a generative AI and have the generative AI select the optimal assistance method.

[0114] The memory assistance unit can adjust its assistance methods when providing memory assistance, taking into account the user's current activities. For example, if the user is at work, the memory assistance unit can provide memory assistance methods related to work. It can also provide memory assistance methods related to home activities if the user is at home. Furthermore, the memory assistance unit can provide the optimal memory assistance method by considering the user's current activities. For example, if the user is at work, the memory assistance unit can provide memory assistance methods related to work. This allows the memory assistance unit to adjust its assistance methods considering the user's current activities. Some or all of the above processing in the memory assistance unit may be performed using, for example, a generative AI, or without a generative AI. For example, the memory assistance unit can input the user's current activity data into a generative AI and have the generative AI adjust the assistance method.

[0115] The memory assistance unit can estimate the user's emotions and determine the priority of memory assistance based on the estimated emotions. For example, if the user is feeling stressed, the memory assistance unit will prioritize memory assistance that helps reduce stress. It can also prioritize detailed memory assistance if the user is relaxed. Furthermore, if the user is in a hurry, the memory assistance unit can provide rapid memory assistance. For example, when the user is feeling stressed, the memory assistance unit will prioritize memory assistance that helps reduce stress. This allows the memory assistance unit to determine the priority of memory assistance based on the user's emotions. Emotion estimation is achieved using an emotion estimation function, such as an emotion engine or a generative AI. The generative AI is, 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 memory assistance unit may be performed using a generative AI, or not. For example, the memory assistance unit can input user emotion data into a generative AI and have the generative AI determine the priority of memory assistance.

[0116] The memory assistance unit can select the optimal assistance method when providing memory assistance, taking into account the user's geographical location information. For example, if the user is in a specific location, the memory assistance unit can provide a memory assistance method related to that location. Furthermore, if the user is traveling, the memory assistance unit can provide a memory assistance method related to the travel destination. Additionally, if the user is at home, the memory assistance unit can provide a memory assistance method related to daily life. For example, if the user is in a specific location, the memory assistance unit can provide a memory assistance method related to that location. This allows the memory assistance unit to select the optimal assistance method, taking into account the user's geographical location information. Some or all of the above processing in the memory assistance unit may be performed using, for example, a generative AI, or without a generative AI. For example, the memory assistance unit can input the user's geographical location data into a generative AI and have the generative AI select the optimal assistance method.

[0117] The memory assistance unit can adjust its assistance method while providing memory assistance, taking into account the user's lifestyle habits. For example, if the user is prone to forgetting things at a particular time of day, the memory assistance unit can provide memory assistance during that time. The memory assistance unit can also provide memory assistance for a specific action if the user is prone to forgetting that action. Furthermore, the memory assistance unit can provide the optimal memory assistance method, taking into account the user's lifestyle habits. For example, if the memory assistance unit is prone to forgetting things at a particular time of day, it can provide memory assistance during that time. This allows the memory assistance unit to adjust its assistance method while considering the user's lifestyle habits. Some or all of the above processing in the memory assistance unit may be performed using, for example, a generative AI, or without a generative AI. For example, the memory assistance unit can input the user's lifestyle data into a generative AI and have the generative AI adjust the assistance method.

[0118] The memory assistance unit can make suggestions based on the user's schedule by referring to the user's calendar information during memory assistance. For example, the memory assistance unit can refer to the schedule registered in the user's calendar and perform memory assistance. The memory assistance unit can also perform memory assistance related to a specific event from the user's calendar information. Furthermore, the memory assistance unit can perform memory assistance tailored to the schedule based on the user's calendar information. For example, the memory assistance unit can refer to the schedule registered in the user's calendar and perform memory assistance. This allows the memory assistance unit to make suggestions based on the schedule by referring to the user's calendar information. Some or all of the above processing in the memory assistance unit may be performed using, for example, a generating AI, or without using a generating AI. For example, the memory assistance unit can input the user's calendar information into a generating AI and have the generating AI execute suggestions based on the schedule.

[0119] The memory assistance unit can analyze the user's social media activity and provide relevant memory assistance during memory assistance. For example, if the user posts about a specific event on social media, the memory assistance unit can provide memory assistance related to that event. It can also provide memory assistance related to a specific location if the user posts about that location on social media. Furthermore, if the user posts about a specific topic on social media, the memory assistance unit can provide memory assistance related to that topic. For example, the memory assistance unit provides memory assistance based on information about events shared by the user on social media. This allows the memory assistance unit to analyze the user's social media activity and provide relevant memory assistance. Some or all of the above processing in the memory assistance unit may be performed using, for example, a generative AI, or without a generative AI. For example, the memory assistance unit can input the user's social media data into a generative AI and have the generative AI perform the relevant memory assistance.

[0120] The memory assistance unit can select the optimal assistance method while considering the user's health condition. For example, the memory assistance unit can select a memory assistance method suitable for a specific health condition based on the user's health check results. Furthermore, if the user has a specific illness, the memory assistance unit can select a memory assistance method related to that illness. In addition, the memory assistance unit can select the optimal memory assistance method considering the user's current physical condition. For example, the memory assistance unit can select a memory assistance method suitable for a specific health condition based on the user's health check results. This allows the memory assistance unit to select the optimal assistance method while considering the user's health condition. Some or all of the above processing in the memory assistance unit may be performed using, for example, a generative AI, or without a generative AI. For example, the memory assistance unit can input the user's health data into a generative AI and have the generative AI select the optimal assistance method.

[0121] The memory assistance unit can analyze the user's past memory assistance history and select the optimal assistance method during memory assistance. For example, the memory assistance unit can select the optimal assistance method based on the memory assistance methods the user has used in the past. The memory assistance unit can also select an assistance method to use during a specific time period based on the user's past memory assistance history. Furthermore, the memory assistance unit can analyze the user's past memory assistance history and select an assistance method for a specific action. For example, the memory assistance unit can select the optimal assistance method based on the memory assistance methods the user has used in the past. In this way, the memory assistance unit can analyze the user's past memory assistance history and select the optimal assistance method. Some or all of the above processing in the memory assistance unit may be performed using, for example, a generative AI, or without a generative AI. For example, the memory assistance unit can input the user's past memory assistance data into a generative AI and have the generative AI select the optimal assistance method.

[0122] The memory assistance unit can select the optimal assistance method when providing memory assistance, taking into account the user's device information. For example, if the user is using a smartphone, the memory assistance unit can provide a memory assistance method optimized for the smartphone. It can also provide a memory assistance method optimized for a tablet if the user is using a tablet. Furthermore, if the user is using a smartwatch, the memory assistance unit can provide a memory assistance method optimized for a smartwatch. For example, when the user is using a smartphone, the memory assistance unit provides a memory assistance method optimized for the smartphone. This allows the memory assistance unit to select the optimal assistance method, taking into account the user's device information. Some or all of the above processing in the memory assistance unit may be performed using, for example, a generative AI, or without a generative AI. For example, the memory assistance unit can input the user's device information into a generative AI and have the generative AI select the optimal assistance method.

[0123] The system according to the embodiment is not limited to the example described above, and various modifications are possible, for example, as follows.

[0124] The memory assist system may further include an emotion capture unit that estimates the user's emotions and adjusts the data capture method based on the estimated emotions. For example, if the user is happy, the emotion capture unit may automatically activate the camera to capture that moment. If the user is sad, it may also capture a voice memo to record that emotion. Furthermore, if the user is excited, it may take continuous shots to ensure that the moment is not missed. This allows the emotion capture unit to adjust the timing and method of capture based on the user's emotions. Emotion estimation is achieved using an emotion engine or generative AI, etc. Generative AI may be, but is not limited to, text generation AI or multimodal generation AI. Some or all of the above processing in the emotion capture unit may be performed using AI or not.

[0125] The memory assist system may further include a behavioral analysis unit that analyzes the user's past behavioral history and selects the optimal capture method. For example, if the user has taken many photos at a particular location in the past, the behavioral analysis unit can automatically activate the camera when the user arrives at that location. It can also automatically capture voice memos during a particular event if the user has taken many notes at that event in the past. Furthermore, if the user has captured a lot of data during a particular time period in the past, it can automatically start capturing during that time period. In this way, the behavioral analysis unit can analyze the user's past behavioral history and select the optimal capture method. Some or all of the above processing in the behavioral analysis unit may be performed using AI or not.

[0126] The memory assist system may further include an activity filter unit that filters data based on the user's current activities and areas of interest. For example, if the user is playing sports, the activity filter unit will capture only data related to that activity. If the user is reading, it can also capture information related to the title and content of the book. Furthermore, if the user is traveling, it can prioritize capturing information and photos related to the travel destination. In this way, the activity filter unit can filter data based on the user's current activities and areas of interest. Some or all of the processing described above in the activity filter unit may be performed using AI or not.

[0127] The memory assist system may further include an emotion prioritization unit that estimates the user's emotions and determines the priority of data to capture based on the estimated emotions. For example, if the user is happy, the emotion prioritization unit may prioritize capturing that moment. If the user is sad, it may also prioritize capturing a voice memo to record that emotion. Furthermore, if the user is excited, it may prioritize continuous shooting to ensure that the moment is not missed. In this way, the emotion prioritization unit can determine the priority of data to capture based on the user's emotions. Emotion estimation is achieved using an emotion engine or generative AI, etc. Generative AI may be, but is not limited to, text generation AI or multimodal generation AI. Some or all of the above processing in the emotion prioritization unit may be performed using AI or not using AI.

[0128] The memory assist system may further include a location information capture unit that prioritizes capturing highly relevant data while considering the user's geographical location. For example, if the user is in a tourist destination, the location information capture unit will prioritize capturing information and photos related to that location. If the user is at home, it can also prioritize capturing information related to daily life. Furthermore, if the user is at work, it can also prioritize capturing information related to work. In this way, the location information capture unit can prioritize capturing highly relevant data while considering the user's geographical location. Some or all of the above processing in the location information capture unit may be performed using AI or not.

[0129] The memory assist system may further include a social media capture unit that analyzes the user's social media activity and captures relevant data. For example, if the user posts about a specific event on social media, the social media capture unit can capture information related to that event. It can also capture information related to a specific location if the user posts about a specific location on social media. Furthermore, if the user posts about a specific topic on social media, it can capture information related to that topic. This allows the social media capture unit to analyze the user's social media activity and capture relevant data. Some or all of the processing described above in the social media capture unit may be performed using AI or not.

[0130] The memory assist system may further include an emotion classification unit that estimates the user's emotions and adjusts the classification criteria based on the estimated emotions. For example, if the user is happy, the emotion classification unit may prioritize classifying data related to that emotion. It may also prioritize classifying data related to the user's sadness. Furthermore, if the user is excited, it may also prioritize classifying data related to that emotion. In this way, the emotion classification unit can adjust the classification criteria based on the user's emotions. Emotion estimation is achieved using an emotion engine or generative AI, etc. Generative AI may be, but is not limited to, text generation AI or multimodal generation AI. Some or all of the processing described above in the emotion classification unit may be performed using AI or not using AI.

[0131] The memory-assist system may further include a importance classification unit that adjusts the level of detail of classification based on the importance of the data. For example, the importance classification unit may classify important data in detail and assign many relevant tags to it. Alternatively, it may classify less important data simply and assign only basic tags to it. Furthermore, it may change the data classification method and adjust the level of detail according to the importance of the data. In this way, the importance classification unit can adjust the level of detail of classification based on the importance of the data. Some or all of the above processing in the importance classification unit may be performed using AI or not.

[0132] The memory assist system may further include a category classification unit that applies different classification algorithms depending on the data category. For example, the category classification unit can apply an image recognition algorithm to image data and classify it based on its content. It can also apply a speech recognition algorithm to audio data and classify it based on its content. Furthermore, it can apply a natural language processing algorithm to text data and classify it based on its content. This allows the category classification unit to apply different classification algorithms depending on the data category. Some or all of the above processing in the category classification unit may be performed using AI or not.

[0133] The memory assist system may further include an emotional dialogue unit that estimates the user's emotions and adjusts the way it expresses its responses based on those emotions. For example, if the user is nervous, the emotional dialogue unit will respond in a calm manner. If the user is relaxed, it may respond in a friendly manner. Furthermore, if the user is in a hurry, it may provide a concise and quick response. In this way, the emotional dialogue unit can adjust the way it expresses its responses based on the user's emotions. Emotion estimation is achieved using an emotion engine or generative AI, etc. Generative AI may be, but is not limited to, text generation AI or multimodal generation AI. Some or all of the processing described above in the emotional dialogue unit may be performed using AI or not using AI.

[0134] The following briefly describes the processing flow for example form 2.

[0135] Step 1: The capture unit captures data according to the user's actions and environment. For example, it can capture images while the user is moving, capture audio data while working, and capture sensor data when the user is in a specific location. Specifically, it can capture the surrounding scenery when the user is in a park. Step 2: The classification unit classifies and organizes the data captured by the capture unit on the cloud. For example, it can classify image data by category, convert audio data into text data and organize it, and organize sensor data chronologically. Specifically, it can classify image data into categories such as landscapes, people, and objects. Step 3: The dialogue unit generates answers to user questions based on data classified and organized by the classification unit. For example, if the user asks, "What did I have for dinner yesterday?", it generates an answer based on past data; if the user asks, "What should I eat next?", it generates an answer considering health risks; and if the user asks, "Where did I put my smartphone?", it generates an answer based on past behavioral data.

[0136] The specific processing unit 290 transmits the result of the specific processing to the smart device 14. In the smart device 14, the control unit 46A causes the output device 40 to output the result of the specific processing. The microphone 38B acquires audio indicating user input for the result of the specific processing. The control unit 46A transmits the audio data indicating user input acquired by the microphone 38B to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the audio data.

[0137] Data generation model 58 is a form of so-called generative AI (Artificial Intelligence). An example of data generation model 58 is ChatGPT (registered trademark) (Internet search).<URL: https: / / openai.com / blog / chatgpt> Examples of generative AI include text generation AI, image generation AI, and multimodal generation AI. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 is input with prompts containing instructions, and with inference data such as audio data representing speech, text data representing text, and image data representing images (e.g., still image data or video data). The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference result in one or more data formats from audio data, text data, and image data. The data generation model 58 includes, for example, text generation AI, image generation AI, and multimodal generation AI. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The specific processing unit 290 performs the specific processing described above using the data generation model 58. The data generation model 58 may be a fine-tuned model that outputs inference results from prompts that do not contain instructions, in which case the data generation model 58 can output inference results from prompts that do not contain instructions. In the data processing device 12, etc., there are multiple types of data generation models 58, and the data generation model 58 includes AI other than generative AI. AI other than generative AI includes, for example, linear regression, logistic regression, decision trees, random forests, support vector machines (SVMs), k-means clustering, convolutional neural networks (CNNs), recurrent neural networks (RNNs), generative adversarial networks (GANs), or naive Bayes, and can perform various processes, but is not limited to these examples. Also, the AI ​​may be an AI agent. Furthermore, when the processing of each of the above parts is performed by the AI, the processing may be performed by the AI ​​in part or in whole, but is not limited to this example.Furthermore, processing performed by AI, including generative AI, may be replaced with rule-based processing, and rule-based processing may be replaced with processing performed by AI, including generative AI.

[0138] Furthermore, the processing performed by the data processing system 10 described above is carried out by the specific processing unit 290 of the data processing device 12 or the control unit 46A of the smart device 14, but it may also be carried out by the specific processing unit 290 of the data processing device 12 and the control unit 46A of the smart device 14. In addition, 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.

[0139] Each of the multiple elements described above, including the capture unit, classification unit, dialogue unit, meal analysis unit, risk prediction unit, and memory assistance unit, is implemented in at least one of the smart device 14 and the data processing unit 12. For example, the capture unit captures the user's behavior and environment using the camera 42 and microphone 38B of the smart device 14. The classification unit classifies and organizes the captured data on the cloud using the identification processing unit 290 of the data processing unit 12. The dialogue unit generates answers to the user's questions using the identification processing unit 290 of the data processing unit 12. The meal analysis unit captures the contents of meals using the camera 42 of the smart device 14 and analyzes calories and nutrients using the identification processing unit 290 of the data processing unit 12. The risk prediction unit predicts health risks using the identification processing unit 290 of the data processing unit 12 and suggests the next meal to eat. The memory assistance unit generates answers to the user's questions based on past behavioral data using the identification processing unit 290 of the data processing unit 12. The correspondence between each unit and the device or control unit is not limited to the example described above and can be changed in various ways.

[0140] [Second Embodiment] Figure 3 shows an example of the configuration of the data processing system 210 according to the second embodiment.

[0141] As shown in Figure 3, the data processing system 210 includes a data processing device 12 and smart glasses 214. An example of the data processing device 12 is a server.

[0142] The data processing device 12 comprises a computer 22, a database 24, and a communication interface 26. The computer 22 comprises a processor 28, RAM 30, and storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication interface 26 are also connected to the bus 34. The communication interface 26 is connected to a network 54. An example of the network 54 is a WAN and / or LAN.

[0143] The smart glasses 214 include a computer 36, a microphone 238, a speaker 240, a camera 42, and a communication interface 44. The computer 36 includes a processor 46, RAM 48, and storage 50. The processor 46, RAM 48, and storage 50 are connected to a bus 52. The microphone 238, speaker 240, and camera 42 are also connected to the bus 52.

[0144] The microphone 238 receives voice signals from the user and accepts instructions from the user. The microphone 238 captures the voice signals from the user, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to the instructions from the processor 46.

[0145] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an image sensor such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, which captures images of the area around the user (for example, an imaging range defined by a field of view equivalent to the field of vision of a typical healthy person).

[0146] Communication interface 44 is connected to network 54. Communication interfaces 44 and 26 are responsible for the exchange of various information between processor 46 and processor 28 via network 54. The exchange of various information between processor 46 and processor 28 using communication interfaces 44 and 26 is performed in a secure manner.

[0147] Figure 4 shows an example of the main functions of the data processing device 12 and the smart glasses 214. As shown in Figure 4, the data processing device 12 performs specific processing by the processor 28. The storage 32 stores the specific processing program 56.

[0148] The processor 28 reads a 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 acting as a specific processing unit 290 according to the specific processing program 56 executed on the RAM 30.

[0149] Storage 32 stores the data generation model 58 and the emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290. The identification processing unit 290 can estimate the user's emotions using the emotion identification model 59 and perform identification processing using the user's emotions. The emotion estimation function (emotion identification function) using the emotion identification model 59 performs various estimations and predictions regarding the user's emotions, including but not limited to these examples. Furthermore, emotion estimation and prediction also include, for example, emotion analysis.

[0150] In the smart glasses 214, specific processing is performed by the processor 46. The storage 50 stores a specific processing program 60. The processor 46 reads the specific processing program 60 from the storage 50 and executes the read specific processing program 60 on the RAM 48. The specific processing is realized by the processor 46 acting as a control unit 46A according to the specific processing program 60 executed on the RAM 48. The smart glasses 214 also have a data generation model 58 and an emotion identification model 59, similar to the data generation model and emotion identification model 59, and can perform processing similar to that of the specific processing unit 290 using these models.

[0151] Furthermore, other devices besides the data processing device 12 may also have the data generation model 58. For example, a server device may have the data generation model 58. In this case, the data processing device 12 obtains processing results (such as prediction results) using the data generation model 58 by communicating with the server device that has the data generation model 58. Also, the data processing device 12 may be a server device or a terminal device owned by the user (for example, a mobile phone, robot, home appliance, etc.).

[0152] The specific processing unit 290 transmits the result of the specific processing to the smart glasses 214. In the smart glasses 214, the control unit 46A causes the speaker 240 to output the result of the specific processing. The microphone 238 acquires audio indicating user input for the result of the specific processing. The control unit 46A transmits the audio data indicating user input acquired by the microphone 238 to the data processing unit 12. In the data processing unit 12, the specific processing unit 290 acquires the audio data.

[0153] The data generation model 58 is a so-called generative AI. An example of a 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 is input with prompts containing instructions, and inference data such as audio data representing speech, text data representing text, and image data representing images (e.g., still image data or video data). The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference result in one or more data formats such as audio data, text data, and image data. The data generation model 58 includes, for example, text generation AI, image generation AI, and multimodal generation AI. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The specific processing unit 290 performs the specific processing described above using the data generation model 58. The data generation model 58 may be a fine-tuned model that outputs inference results from prompts that do not contain instructions, in which case the data generation model 58 can output inference results from prompts that do not contain instructions. In the data processing device 12, etc., there are multiple types of data generation models 58, and the data generation model 58 includes AI other than generative AI. AI other than generative AI includes, for example, linear regression, logistic regression, decision trees, random forests, support vector machines (SVM), k-means clustering, convolutional neural networks (CNN), recurrent neural networks (RNN), generative adversarial networks (GAN), or naive Bayes, and can perform various processes, but is not limited to these examples. Also, the AI ​​may be an AI agent. Furthermore, when the processing of each part described above is performed by the AI, the processing may be performed by the AI ​​in part or in whole, but is not limited to this example. Also, processing performed by an AI including a generative AI may be replaced by rule-based processing, and rule-based processing may be replaced by processing performed by an AI including a generative AI.

[0154] 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 performed by the specific processing unit 290 of the data processing device 12 or the control unit 46A of the smart glasses 214, but it may also be performed by the specific processing unit 290 of the data processing device 12 and the control unit 46A of the smart glasses 214. In addition, the specific processing unit 290 of the data processing device 12 acquires or collects information necessary for processing from the smart glasses 214 or an external device, and the smart glasses 214 acquires or collects information necessary for processing from the data processing device 12 or an external device.

[0155] Each of the multiple elements described above, including the capture unit, classification unit, dialogue unit, meal analysis unit, risk prediction unit, and memory assistance unit, is implemented in at least one of the smart glasses 214 and the data processing unit 12. For example, the capture unit captures the user's behavior and environment using the camera 42 and microphone 238 of the smart glasses 214. The classification unit classifies and organizes the captured data on the cloud using the identification processing unit 290 of the data processing unit 12. The dialogue unit generates answers to the user's questions using the identification processing unit 290 of the data processing unit 12. The meal analysis unit captures the contents of meals using the camera 42 of the smart glasses 214 and analyzes calories and nutrients using the identification processing unit 290 of the data processing unit 12. The risk prediction unit predicts health risks using the identification processing unit 290 of the data processing unit 12 and suggests the next meal to eat. The memory assistance unit generates answers to the user's questions based on past behavioral data using the identification processing unit 290 of the data processing unit 12. The correspondence between each unit and the device or control unit is not limited to the example described above and can be changed in various ways.

[0156] [Third Embodiment] Figure 5 shows an example of the configuration of the data processing system 310 according to the third embodiment.

[0157] As shown in Figure 5, the data processing system 310 includes a data processing device 12 and a headset terminal 314. An example of the data processing device 12 is a server.

[0158] The data processing device 12 comprises a computer 22, a database 24, and a communication interface 26. The computer 22 comprises a processor 28, RAM 30, and storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication interface 26 are also connected to the bus 34. The communication interface 26 is connected to a network 54. An example of the network 54 is a WAN and / or LAN.

[0159] The headset terminal 314 includes a computer 36, a microphone 238, a speaker 240, a camera 42, a communication interface 44, and a display 343. The computer 36 includes a processor 46, RAM 48, and storage 50. The processor 46, RAM 48, and storage 50 are connected to a bus 52. The microphone 238, speaker 240, camera 42, and display 343 are also connected to the bus 52.

[0160] The microphone 238 receives voice signals from the user and accepts instructions from the user. The microphone 238 captures the voice signals from the user, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to the instructions from the processor 46.

[0161] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an image sensor such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, which captures images of the area around the user (for example, an imaging range defined by a field of view equivalent to the field of vision of a typical healthy person).

[0162] Communication interface 44 is connected to network 54. Communication interfaces 44 and 26 are responsible for the exchange of various information between processor 46 and processor 28 via network 54. The exchange of various information between processor 46 and processor 28 using communication interfaces 44 and 26 is performed in a secure manner.

[0163] Figure 6 shows an example of the main functions of the data processing device 12 and the headset terminal 314. As shown in Figure 6, the data processing device 12 performs specific processing using the processor 28. The storage 32 stores the specific processing program 56.

[0164] The processor 28 reads a 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 acting as a specific processing unit 290 according to the specific processing program 56 executed on the RAM 30.

[0165] Storage 32 stores the data generation model 58 and the emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290. The identification processing unit 290 can estimate the user's emotions using the emotion identification model 59 and perform identification processing using the user's emotions. The emotion estimation function (emotion identification function) using the emotion identification model 59 performs various estimations and predictions regarding the user's emotions, including but not limited to these examples. Furthermore, emotion estimation and prediction also include, for example, emotion analysis.

[0166] In the headset terminal 314, specific processing is performed by the processor 46. The storage 50 stores a specific program 60. The processor 46 reads the specific program 60 from the storage 50 and executes the read specific program 60 on the RAM 48. The specific processing is realized by the processor 46 acting as a control unit 46A according to the specific program 60 executed on the RAM 48. The headset terminal 314 also has a data generation model 58 and an emotion identification model 59, similar to the data generation model and emotion identification model 59, and can perform processing similar to that of the specific processing unit 290 using these models.

[0167] Furthermore, other devices besides the data processing device 12 may also have the data generation model 58. For example, a server device may have the data generation model 58. In this case, the data processing device 12 obtains processing results (such as prediction results) using the data generation model 58 by communicating with the server device that has the data generation model 58. Also, the data processing device 12 may be a server device or a terminal device owned by the user (for example, a mobile phone, robot, home appliance, etc.).

[0168] The specific processing unit 290 transmits the result of the specific processing to the headset terminal 314. In the headset terminal 314, the control unit 46A causes the speaker 240 and display 343 to output the result of the specific processing. The microphone 238 acquires audio indicating user input for the result of the specific processing. The control unit 46A transmits the audio data indicating user input acquired by the microphone 238 to the data processing unit 12. In the data processing unit 12, the specific processing unit 290 acquires the audio data.

[0169] The data generation model 58 is a so-called generative AI. An example of a 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 is input with prompts containing instructions, and inference data such as audio data representing speech, text data representing text, and image data representing images (e.g., still image data or video data). The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference result in one or more data formats such as audio data, text data, and image data. The data generation model 58 includes, for example, text generation AI, image generation AI, and multimodal generation AI. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The specific processing unit 290 performs the specific processing described above using the data generation model 58. The data generation model 58 may be a fine-tuned model that outputs inference results from prompts that do not contain instructions, in which case the data generation model 58 can output inference results from prompts that do not contain instructions. In the data processing device 12, etc., there are multiple types of data generation models 58, and the data generation model 58 includes AI other than generative AI. AI other than generative AI includes, for example, linear regression, logistic regression, decision trees, random forests, support vector machines (SVM), k-means clustering, convolutional neural networks (CNN), recurrent neural networks (RNN), generative adversarial networks (GAN), or naive Bayes, and can perform various processes, but is not limited to these examples. Also, the AI ​​may be an AI agent. Furthermore, when the processing of each part described above is performed by the AI, the processing may be performed by the AI ​​in part or in whole, but is not limited to this example. Also, processing performed by an AI including a generative AI may be replaced by rule-based processing, and rule-based processing may be replaced by processing performed by an AI including a generative AI.

[0170] 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 performed by the specific processing unit 290 of the data processing device 12 or the control unit 46A of the headset terminal 314, but may also be performed by the specific processing unit 290 of the data processing device 12 and the control unit 46A of the headset terminal 314. In addition, the specific processing unit 290 of the data processing device 12 acquires or collects information necessary for processing from the headset terminal 314 or an external device, and the headset terminal 314 acquires or collects information necessary for processing from the data processing device 12 or an external device.

[0171] Each of the multiple elements described above, including the capture unit, classification unit, dialogue unit, meal analysis unit, risk prediction unit, and memory assistance unit, is implemented in at least one of the headset terminal 314 and the data processing unit 12. For example, the capture unit captures the user's behavior and environment using the camera 42 and microphone 238 of the headset terminal 314. The classification unit classifies and organizes the captured data on the cloud using the identification processing unit 290 of the data processing unit 12. The dialogue unit generates answers to the user's questions using the identification processing unit 290 of the data processing unit 12. The meal analysis unit captures the contents of meals using the camera 42 of the headset terminal 314 and analyzes calories and nutrients using the identification processing unit 290 of the data processing unit 12. The risk prediction unit predicts health risks using the identification processing unit 290 of the data processing unit 12 and suggests the next meal to eat. The memory assistance unit generates answers to the user's questions based on past behavioral data using the identification processing unit 290 of the data processing unit 12. The correspondence between each part and the device or control unit is not limited to the examples described above, and various modifications are possible.

[0172] [Fourth Embodiment] Figure 7 shows an example of the configuration of the data processing system 410 according to the fourth embodiment.

[0173] As shown in Figure 7, the data processing system 410 includes a data processing device 12 and a robot 414. An example of the data processing device 12 is a server.

[0174] The data processing device 12 comprises a computer 22, a database 24, and a communication interface 26. The computer 22 comprises a processor 28, RAM 30, and storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication interface 26 are also connected to the bus 34. The communication interface 26 is connected to a network 54. An example of the network 54 is a WAN and / or LAN.

[0175] The robot 414 includes a computer 36, a microphone 238, a speaker 240, a camera 42, a communication interface 44, and a controlled object 443. The computer 36 includes a processor 46, RAM 48, and storage 50. The processor 46, RAM 48, and storage 50 are connected to a bus 52. The microphone 238, speaker 240, camera 42, and controlled object 443 are also connected to the bus 52.

[0176] The microphone 238 receives voice signals from the user and accepts instructions from the user. The microphone 238 captures the voice signals from the user, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to the instructions from the processor 46.

[0177] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an image sensor such as a CMOS image sensor or CCD image sensor, which captures images of the area around the user (for example, an imaging range defined by a field of view equivalent to the field of vision of a typical healthy person).

[0178] Communication interface 44 is connected to network 54. Communication interfaces 44 and 26 are responsible for the exchange of various information between processor 46 and processor 28 via network 54. The exchange of various information between processor 46 and processor 28 using communication interfaces 44 and 26 is performed in a secure manner.

[0179] The controlled object 443 includes a display device, LEDs in the eyes, and motors that drive the arms, hands, and feet. The posture and gestures of the robot 414 are controlled by controlling the motors of the arms, hands, and feet. Some of the robot 414's emotions can be expressed by controlling these motors. The robot 414's facial expressions can also be expressed by controlling the illumination state of the LEDs in its eyes.

[0180] Figure 8 shows an example of the main functions of the data processing device 12 and the robot 414. As shown in Figure 8, the data processing device 12 performs specific processing using the processor 28. The storage 32 stores the specific processing program 56.

[0181] The processor 28 reads a 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 acting as a specific processing unit 290 according to the specific processing program 56 executed on the RAM 30.

[0182] Storage 32 stores the data generation model 58 and the emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290. The identification processing unit 290 can estimate the user's emotions using the emotion identification model 59 and perform identification processing using the user's emotions. The emotion estimation function (emotion identification function) using the emotion identification model 59 performs various estimations and predictions regarding the user's emotions, including but not limited to these examples. Furthermore, emotion estimation and prediction also include, for example, emotion analysis.

[0183] In robot 414, specific processing is performed by processor 46. A specific program 60 is stored in storage 50. Processor 46 reads the specific program 60 from storage 50 and executes it on RAM 48. The specific processing is achieved by processor 46 acting as a control unit 46A according to the specific program 60 executed on RAM 48. Robot 414 also has data generation model 58 and emotion identification model 59, similar to those of the robot, and can perform processing similar to that of the specific processing unit 290 using these models.

[0184] Furthermore, other devices besides the data processing device 12 may also have the data generation model 58. For example, a server device may have the data generation model 58. In this case, the data processing device 12 obtains processing results (such as prediction results) using the data generation model 58 by communicating with the server device that has the data generation model 58. Also, the data processing device 12 may be a server device or a terminal device owned by the user (for example, a mobile phone, robot, home appliance, etc.).

[0185] The specific processing unit 290 transmits the result of the specific processing to the robot 414. In the robot 414, the control unit 46A causes the speaker 240 and the controlled object 443 to output the result of the specific processing. The microphone 238 acquires audio indicating user input for the result of the specific processing. The control unit 46A transmits the audio data indicating user input acquired by the microphone 238 to the data processing unit 12. In the data processing unit 12, the specific processing unit 290 acquires the audio data.

[0186] The data generation model 58 is a so-called generative AI. An example of a 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 is input with prompts containing instructions, and inference data such as audio data representing speech, text data representing text, and image data representing images (e.g., still image data or video data). The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference result in one or more data formats such as audio data, text data, and image data. The data generation model 58 includes, for example, text generation AI, image generation AI, and multimodal generation AI. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The specific processing unit 290 performs the specific processing described above using the data generation model 58. The data generation model 58 may be a fine-tuned model that outputs inference results from prompts that do not contain instructions, in which case the data generation model 58 can output inference results from prompts that do not contain instructions. In the data processing device 12, etc., there are multiple types of data generation models 58, and the data generation model 58 includes AI other than generative AI. AI other than generative AI includes, for example, linear regression, logistic regression, decision trees, random forests, support vector machines (SVM), k-means clustering, convolutional neural networks (CNN), recurrent neural networks (RNN), generative adversarial networks (GAN), or naive Bayes, and can perform various processes, but is not limited to these examples. Also, the AI ​​may be an AI agent. Furthermore, when the processing of each part described above is performed by the AI, the processing may be performed by the AI ​​in part or in whole, but is not limited to this example. Also, processing performed by an AI including a generative AI may be replaced by rule-based processing, and rule-based processing may be replaced by processing performed by an AI including a generative AI.

[0187] 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 performed by the specific processing unit 290 of the data processing device 12 or the control unit 46A of the robot 414, but it may also be performed by the specific processing unit 290 of the data processing device 12 and the control unit 46A of the robot 414. In addition, the specific processing unit 290 of the data processing device 12 acquires or collects information necessary for processing from the robot 414 or an external device, and the robot 414 acquires or collects information necessary for processing from the data processing device 12 or an external device.

[0188] Each of the multiple elements described above, including the capture unit, classification unit, dialogue unit, meal analysis unit, risk prediction unit, and memory assistance unit, is implemented in at least one of the robot 414 and the data processing unit 12. For example, the capture unit captures the user's behavior and environment using the camera 42 and microphone 238 of the robot 414. The classification unit classifies and organizes the captured data on the cloud using the identification processing unit 290 of the data processing unit 12. The dialogue unit generates answers to the user's questions using the identification processing unit 290 of the data processing unit 12. The meal analysis unit captures the contents of the meal using the camera 42 of the robot 414 and analyzes calories and nutrients using the identification processing unit 290 of the data processing unit 12. The risk prediction unit predicts health risks using the identification processing unit 290 of the data processing unit 12 and suggests the next meal to eat. The memory assistance unit generates answers to the user's questions based on past behavioral data using the identification processing unit 290 of the data processing unit 12. The correspondence between each unit and the device or control unit is not limited to the example described above and can be changed in various ways.

[0189] Furthermore, the emotion identification model 59, acting as an emotion engine, may determine the user's emotion according to a specific mapping. Specifically, the emotion identification model 59 may determine the user's emotion according to a specific mapping, which is an emotion map (see Figure 9). Similarly, the emotion identification model 59 may also determine the robot's emotion, and the identification processing unit 290 may perform identification processing using the robot's emotion.

[0190] Figure 9 shows the emotion map 400, in which multiple emotions are mapped. In the emotion map 400, emotions are arranged in concentric circles radiating from the center. The closer to the center of the concentric circles, the more primitive the emotions are located. Further out of the concentric circles, emotions representing states and actions arising from mental states are located. Emotion is a concept that includes feelings and mental states. On the left side of the concentric circles, emotions that are generally generated from reactions occurring in the brain are located. On the right side of the concentric circles, emotions that are generally induced by situational judgment are located. Above and below the concentric circles, emotions that are generally generated from reactions occurring in the brain and induced by situational judgment are located. In addition, the emotion of "pleasure" is located on the upper side of the concentric circles, and the emotion of "displeasure" is located on the lower side. Thus, in the emotion map 400, multiple emotions are mapped based on the structure in which emotions arise, and emotions that are likely to occur simultaneously are mapped close together.

[0191] These emotions are distributed at the 3 o'clock position on the Emotion Map 400, and usually fluctuate between feelings of security and anxiety. In the right half of the Emotion Map 400, situational awareness takes precedence over internal feelings, resulting in a calm impression.

[0192] The inside of the Emotion Map 400 represents inner thoughts, while the outside represents actions. Therefore, the further you go from the outside of the Emotion Map 400, the more visible (expressed in actions) your emotions become.

[0193] Here, human emotions are based on various balances, such as posture and blood sugar levels. When these balances deviate from the ideal, it results in discomfort, and when they approach the ideal, it results in pleasure. Similarly, in robots, cars, and motorcycles, emotions can be created based on various balances, such as posture and battery level. When these balances deviate from the ideal, it results in discomfort, and when they approach the ideal, it results in pleasure. The emotion map can be generated based, for example, on Dr. Mitsuyoshi's emotion map (Research on a system for analyzing brain physiological signals of speech emotion recognition and emotion, Tokushima University, doctoral dissertation: https: / / ci.nii.ac.jp / naid / 500000375379). The left half of the emotion map contains emotions belonging to a region called "response," where sensation is dominant. The right half of the emotion map contains emotions belonging to a region called "situation," where situational awareness is dominant.

[0194] The emotion map defines two emotions that promote learning. One is the emotion around the middle of the negative "repentance" and "reflection" on the situation side. In other words, it is when the robot experiences negative emotions such as "I never want to feel this way again" or "I don't want to be scolded again." The other is the emotion around the positive "desire" on the reaction side. In other words, it is when the robot has positive feelings such as "I want more" or "I want to know more."

[0195] The emotion identification model 59 inputs user input into a pre-trained neural network, obtains emotion values ​​representing each emotion shown in the emotion map 400, and determines the user's emotion. This neural network is pre-trained based on multiple training data sets, which are combinations of user input and emotion values ​​representing each emotion shown in the emotion map 400. Furthermore, this neural network is trained so that emotions located close together have similar values, as shown in the emotion map 900 in Figure 10. Figure 10 shows an example where multiple emotions such as "reassured," "calm," and "confident" have similar emotion values.

[0196] In the above embodiment, an example was given in which a specific process is performed by a single computer 22. However, the technology of this disclosure is not limited thereto, and a distributed processing method for the specific process may be used, which includes computer 22 and multiple other computers.

[0197] In the above embodiment, an example was given in which the specific processing program 56 is stored in the storage 32, but the technology of this disclosure is not limited thereto. For example, the specific processing program 56 may be stored in a portable, computer-readable, non-temporary storage medium such as a USB (Universal Serial Bus) memory. The specific processing program 56 stored in the non-temporary storage medium is installed in the computer 22 of the data processing device 12. The processor 28 executes specific processing according to the specific processing program 56.

[0198] 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.

[0199] Furthermore, it is not necessary to store the entirety of the specific processing program 56 in a storage device such as a server connected to the data processing device 12 via the network 54, or to store the entirety of the specific processing program 56 in the storage 32; it is acceptable to store only a portion of the specific processing program 56.

[0200] The following types of processors can be used as hardware resources to perform specific processing. Examples of processors include a CPU, a general-purpose processor that functions as a hardware resource to perform specific processing by executing software, i.e., a program. Other examples of processors include dedicated electrical circuits, such as FPGAs (Field-Programmable Gate Arrays), PLDs (Programmable Logic Devices), or ASICs (Application Specific Integrated Circuits), which have circuit configurations specifically designed to perform specific processing. All of these processors have built-in or connected memory, and all of them perform specific processing by using memory.

[0201] The hardware resource that performs a specific process may consist of one of these various processors, or it may consist of a combination of two or more processors of the same or different types (for example, a combination of multiple FPGAs, or a combination of a CPU and an FPGA). Alternatively, the hardware resource that performs a specific process may consist of a single processor.

[0202] Examples of configurations using a single processor include, firstly, a configuration in which one or more CPUs and software are combined to form a single processor, and this processor functions as a hardware resource that performs a specific process. Secondly, there is a configuration using a processor that realizes the functions of the entire system, including multiple hardware resources that perform a specific process, on a single IC chip, as exemplified by SoCs (System-on-a-chip). In this way, a specific process is realized using one or more of the above types of processors as hardware resources.

[0203] Furthermore, the hardware structure of these various processors can more specifically utilize electrical circuits that combine circuit elements such as semiconductor devices. Also, the specific processing described above is merely an example. Therefore, it goes without saying that unnecessary steps can be deleted, new steps added, or the processing order rearranged, as long as it does not deviate from the main purpose.

[0204] Furthermore, although the above-described examples were divided into four embodiments, some or all of these embodiments may be combined. Also, the smart device 14, smart glasses 214, headset terminal 314, and robot 414 are just examples, and they may be combined, or other devices may be used. Also, although the above-described examples were divided into two embodiments, Embodiment 1 and Embodiment 2, these may be combined.

[0205] The descriptions and illustrations presented above are detailed explanations of the technical aspects of this disclosure and are merely examples of the technical aspects. For example, the above descriptions of the structure, function, operation, and effect are examples of the structure, function, operation, and effect of the technical aspects of this disclosure. Therefore, it goes without saying that you may delete unnecessary parts, add new elements, or replace elements in the descriptions and illustrations presented above, as long as you do not deviate from the essence of the technical aspects of this disclosure. Furthermore, in order to avoid confusion and facilitate understanding of the technical aspects of this disclosure, explanations of common technical knowledge and other things that do not require special explanation to enable the implementation of the technical aspects of this disclosure have been omitted from the descriptions and illustrations presented above.

[0206] All documents, patent applications, and technical standards described herein are incorporated by reference to the same extent as if each individual document, patent application, and technical standard were specifically and individually noted to be incorporated by reference.

[0207] (Note 1) A capture unit that captures data according to the user's actions and environment, A classification unit that classifies and organizes the data captured by the aforementioned capture unit on the cloud, The system includes a dialogue unit that generates answers to user questions based on data classified and organized by the classification unit. A system characterized by the following features. (Note 2) It includes a meal analysis unit that captures the contents of meals and analyzes calories and nutrients. The system described in Appendix 1, characterized by the features described herein. (Note 3) It features a risk prediction unit that predicts health risks and suggests the next meal to eat. The system described in Appendix 1, characterized by the features described herein. (Note 4) It includes a memory assistance unit to support the user's memory. The system described in Appendix 1, characterized by the features described herein. (Note 5) The aforementioned capture unit is It estimates the user's emotions and adjusts the timing of captures based on the estimated user emotions. The system described in Appendix 1, characterized by the features described herein. (Note 6) The aforementioned capture unit is Analyze the user's past behavior history and select the optimal capture method. The system described in Appendix 1, characterized by the features described herein. (Note 7) The aforementioned capture unit is During capture, filtering is performed based on the user's current activities and areas of interest. The system described in Appendix 1, characterized by the features described herein. (Note 8) The aforementioned capture unit is It estimates the user's emotions and determines the priority of data to capture based on the estimated user emotions. The system described in Appendix 1, characterized by the features described herein. (Note 9) The aforementioned capture unit is During capture, the system prioritizes capturing highly relevant data by considering the user's geographical location. The system described in Appendix 1, characterized by the features described herein. (Note 10) The aforementioned capture unit is During capture, the system analyzes the user's social media activity and captures relevant data. The system described in Appendix 1, characterized by the features described herein. (Note 11) The aforementioned classification unit is It estimates the user's emotions and adjusts the classification criteria based on the estimated user emotions. The system described in Appendix 1, characterized by the features described herein. (Note 12) The aforementioned classification unit is During classification, adjust the level of detail based on the importance of the data. The system described in Appendix 1, characterized by the features described herein. (Note 13) The aforementioned classification unit is When classifying data, apply different classification algorithms depending on the data category. The system described in Appendix 1, characterized by the features described herein. (Note 14) The aforementioned classification unit is It estimates the user's emotions and determines the classification priority based on the estimated user emotions. The system described in Appendix 1, characterized by the features described herein. (Note 15) The aforementioned classification unit is During classification, the order of classification is adjusted based on when the data was submitted. The system described in Appendix 1, characterized by the features described herein. (Note 16) The aforementioned classification unit is During classification, adjust the order of classification based on the relevance of the data. The system described in Appendix 1, characterized by the features described herein. (Note 17) The aforementioned dialogue unit, It estimates the user's emotions and adjusts the way responses are expressed based on those estimated emotions. The system described in Appendix 1, characterized by the features described herein. (Note 18) The aforementioned dialogue unit, During the conversation, adjust the level of detail in the answer based on the importance of the question. The system described in Appendix 1, characterized by the features described herein. (Note 19) The aforementioned dialogue unit, During the conversation, different answer algorithms are applied depending on the category of the question. The system described in Appendix 1, characterized by the features described herein. (Note 20) The aforementioned dialogue unit, It estimates the user's emotions and adjusts the length of the response based on the estimated emotions. The system described in Appendix 1, characterized by the features described herein. (Note 21) The aforementioned dialogue unit, During the dialogue, we will prioritize the answers based on when the questions were submitted. The system described in Appendix 1, characterized by the features described herein. (Note 22) The aforementioned dialogue unit, During the conversation, adjust the order of answers based on the relevance of the questions. The system described in Appendix 1, characterized by the features described herein. (Note 23) The aforementioned dietary analysis unit, The system estimates the user's emotions and adjusts the meal analysis method based on the estimated emotions. The system described in Appendix 2, characterized by the features described herein. (Note 24) The aforementioned dietary analysis unit, During meal analysis, the system analyzes the user's past meal history to select the optimal analysis method. The system described in Appendix 2, characterized by the features described herein. (Note 25) The aforementioned dietary analysis unit, When analyzing meals, the analysis method is adjusted to take into account the user's current health status. The system described in Appendix 2, characterized by the features described herein. (Note 26) The aforementioned dietary analysis unit, The system estimates the user's emotions and determines the priority of meal analysis based on the estimated emotions. The system described in Appendix 2, characterized by the features described herein. (Note 27) The aforementioned dietary analysis unit, When analyzing meals, the optimal analysis method is selected considering the user's geographical location. The system described in Appendix 2, characterized by the features described herein. (Note 28) The aforementioned dietary analysis unit, When analyzing meals, the analysis method is adjusted to take into account the user's dietary preferences. The system described in Appendix 2, characterized by the features described herein. (Note 29) The aforementioned risk prediction unit, We estimate user sentiment and adjust risk prediction methods based on the estimated user sentiment. The system described in Appendix 3, characterized by the features described herein. (Note 30) The aforementioned risk prediction unit, When predicting risk, the system analyzes the user's past health data to select the optimal prediction method. The system described in Appendix 3, characterized by the features described herein. (Note 31) The aforementioned risk prediction unit, When predicting risk, the prediction method is adjusted to take into account the user's current health status. The system described in Appendix 3, characterized by the features described herein. (Note 32) The aforementioned risk prediction unit, It estimates user sentiment and prioritizes risk predictions based on the estimated user sentiment. The system described in Appendix 3, characterized by the features described herein. (Note 33) The aforementioned risk prediction unit, When predicting risk, the optimal prediction method is selected by considering the user's geographical location information. The system described in Appendix 3, characterized by the features described herein. (Note 34) The aforementioned risk prediction unit, When predicting risk, the prediction method is adjusted to take into account the user's lifestyle. The system described in Appendix 3, characterized by the features described herein. (Note 35) The aforementioned memory auxiliary unit is It estimates the user's emotions and adjusts the memory assistance method based on the estimated user emotions. The system described in Appendix 4, characterized by the features described herein. (Note 36) The aforementioned memory auxiliary unit is When providing memory assistance, the system analyzes the user's past behavioral history to select the most suitable assistance method. The system described in Appendix 4, characterized by the features described herein. (Note 37) The aforementioned memory auxiliary unit is When providing memory assistance, the assistance method is adjusted based on the user's current activity. The system described in Appendix 4, characterized by the features described herein. (Note 38) The aforementioned memory auxiliary unit is It estimates the user's emotions and determines the priority of memory aids based on the estimated emotions. The system described in Appendix 4, characterized by the features described herein. (Note 39) The aforementioned memory auxiliary unit is When providing memory assistance, the optimal assistance method is selected by considering the user's geographical location. The system described in Appendix 4, characterized by the features described herein. (Note 40) The aforementioned memory auxiliary unit is When providing memory assistance, the assistance method is adjusted to take into account the user's lifestyle. The system described in Appendix 4, characterized by the features described herein. (Note 41) The aforementioned memory auxiliary unit is When assisting with memory, the system references the user's calendar information to provide schedule-based suggestions. The system described in Appendix 4, characterized by the features described herein. (Note 42) The aforementioned memory auxiliary unit is During memory assistance, the system analyzes the user's social media activity and provides relevant memory support. The system described in Appendix 4, characterized by the features described herein. (Note 43) The aforementioned memory auxiliary unit is When providing memory assistance, the optimal assistance method is selected considering the user's health condition. The system described in Appendix 4, characterized by the features described herein. (Note 44) The aforementioned memory auxiliary unit is When providing memory assistance, the system analyzes the user's past memory assistance history to select the most suitable assistance method. The system described in Appendix 4, characterized by the features described herein. (Note 45) The aforementioned memory auxiliary unit is When providing memory assistance, the optimal assistance method is selected by considering the user's device information. The system described in Appendix 4, characterized by the features described herein. [Explanation of Symbols]

[0208] 10, 210, 310, 410 Data Processing Systems 12 Data Processing Devices 14 Smart Devices 214 Smart Glasses 314 Headset-type terminal 414 Robots

Claims

1. A capture unit that captures data according to the user's actions and environment, A classification unit that classifies and organizes the data captured by the aforementioned capture unit on the cloud, The system comprises: an interactive unit that generates answers to user questions based on data classified and organized by the aforementioned classification unit; and A system characterized by the following features.

2. It includes a meal analysis unit that captures the contents of meals and analyzes calories and nutrients. The system according to feature 1.

3. It features a risk prediction unit that predicts health risks and suggests the next meal to eat. The system according to feature 1.

4. It includes a memory assistance unit to support the user's memory. The system according to feature 1.

5. The aforementioned capture unit is It estimates the user's emotions and adjusts the timing of captures based on the estimated user emotions. The system according to feature 1.

6. The aforementioned capture unit is Analyze the user's past behavior history and select the optimal capture method. The system according to feature 1.

7. The aforementioned capture unit is During capture, filtering is performed based on the user's current activities and areas of interest. The system according to feature 1.

8. The aforementioned capture unit is It estimates the user's emotions and determines the priority of data to capture based on the estimated user emotions. The system according to feature 1.

9. The aforementioned capture unit is During capture, the system prioritizes capturing highly relevant data by considering the user's geographical location. The system according to feature 1.

Images