System

Abstract

An object of a system according to an embodiment is to automate work and support decision making by utilizing user's behavior data.SOLUTION: A system according to an embodiment includes an action data collection unit, a learning unit, a task automation unit, and a decision-making support unit. The action data collection unit collects action data of a user. The learning unit performs learning based on the action data collected by the action data collection unit. The task automation unit automates a task based on the data learned by the learning unit. The decision-making support unit supports decision making by the user on the basis of the data learned by the learning unit.SELECTED DRAWING: Figure 1

Description

[Technical Field]

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

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

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

[0004] Conventional technologies do not adequately provide systems that utilize user behavioral data to automate tasks and support decision-making, and there is room for improvement.

[0005] The system according to the embodiment aims to utilize user behavior data to automate tasks and support decision-making. [Means for solving the problem]

[0006] The system according to the embodiment includes a behavioral data collection unit, a learning unit, a task automation unit, and a decision-making support unit. The behavioral data collection unit collects user behavioral data. The learning unit performs learning based on the behavioral data collected by the behavioral data collection unit. The task automation unit automates tasks based on the data learned by the learning unit. The decision-making support unit supports user decision-making based on the data learned by the learning unit. [Effects of the Invention]

[0007] The system according to the embodiment can utilize user behavior data to automate tasks and support decision-making. [Brief explanation of the drawings]

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

[0025] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290. The identification processing unit 290 can estimate the user's emotion using the emotion identification model 59 and perform identification processing using the user's emotion.

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

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

[0028] (Example 1) The secretary system according to the embodiment of the present invention is a system that collects user behavior data, has a generation AI that learns, automates tasks, and supports decision-making. This allows the secretary system to learn based on the user behavior data, automate tasks, and support decision-making.

[0029] The secretary system according to the embodiment includes a behavioral data collection unit, a learning unit, a task automation unit, and a decision-making support unit. The behavioral data collection unit collects user behavioral data. For example, it collects website browsing history. The behavioral data collection unit can also collect app usage history. The behavioral data collection unit can also collect location information. For example, the behavioral data collection unit collects a history of places visited by the user. The app usage history records which apps the user used and for how long. The location information records the user's movement history using GPS. The learning unit performs learning based on the behavioral data collected by the behavioral data collection unit. For example, the learning unit analyzes the behavioral data using a machine learning algorithm. The learning unit can also analyze the behavioral data using deep learning. The learning unit can also analyze the behavioral data using reinforcement learning. For example, the machine learning algorithm extracts patterns from the behavioral data and builds a predictive model. Deep learning uses a neural network to learn complex patterns. Reinforcement learning learns optimal behavior through trial and error. The business automation unit automates business processes based on the data learned by the learning unit. For example, the business automation unit automates data entry. The business automation unit can also automate report generation. The business automation unit can also automate email sending. For example, data entry automates tasks that users must perform manually. Report generation automatically creates reports based on data. Email sending automatically creates and sends emails to be sent by users. The decision support unit supports user decision making based on the data learned by the learning unit. For example, the decision support unit supports purchasing decisions. The decision support unit can also support strategic decisions. The decision support unit can also support risk assessment. For example, purchasing decisions suggest optimal options when users select products or services to purchase. Strategic decisions provide optimal advice when deciding on business directions and plans. Risk assessment evaluates the risks of investments and projects and supports optimal decisions.As a result, the secretary system according to the embodiment can learn from the user's behavioral data and automate tasks and support decision-making. For example, the output unit provides feedback to the user on the progress of tasks and the results of decisions. The notification function notifies the user of important information in real time. The dashboard visually displays the progress of tasks and the results of decisions.

[0030] The behavioral data collection unit collects the user's biometric data and can learn the relationship between the behavioral data and physiological responses. The behavioral data collection unit, for example, monitors the user's heart rate and electrodermal activity in real time and integrates the data with the behavioral data to learn. For example, it analyzes heart rate fluctuations in situations where the user feels stressed and makes suggestions for stress reduction. The behavioral data collection unit also analyzes the user's behavioral patterns in detail based on the biometric data. For example, it learns the user's heart rate and electrodermal activity when the user is concentrating and identifies times when concentration is at its peak. The behavioral data collection unit also collects the user's biometric data and combines it with the behavioral data to learn, thereby making more accurate behavioral predictions. For example, it suggests optimal times to take a break based on the user's physiological responses. In this way, by collecting the user's biometric data and learning the relationship between behavior and physiological responses, more accurate behavioral predictions are possible.

[0031] The behavioral data collection unit collects environmental data of the user and can learn the association between the behavioral data and environmental factors. The behavioral data collection unit, for example, collects environmental data such as weather, location, and time of day along with the user's behavioral data, and analyzes the impact of environmental factors on decision-making. For example, it learns what behavior the user will exhibit on a rainy day. The behavioral data collection unit also analyzes the user's behavioral patterns in detail based on the environmental data. For example, it learns behavioral tendencies in specific locations and time periods and suggests optimal behavior. The behavioral data collection unit also collects the user's environmental data and learns by combining it with the behavioral data, thereby making more accurate behavioral predictions. For example, it suggests an optimal schedule depending on the weather and location. In this way, by collecting the user's environmental data and learning the association between the behavioral data and environmental factors, more accurate behavioral predictions are possible.

[0032] The behavioral data collection unit can collect voice data and image data of the user and perform learning based on the multimodal data. The behavioral data collection unit, for example, collects voice data and image data along with the user's behavioral data and learns behavioral patterns based on the multimodal data. For example, the user's utterances and facial expressions are analyzed and used for behavior prediction. The behavioral data collection unit also performs detailed analysis of the user's behavioral patterns based on the voice data and image data. For example, the user's emotional state is estimated from the user's tone of voice and facial expressions and reflected in behavior prediction. The behavioral data collection unit also performs more accurate behavior prediction by collecting multimodal data and combining it with the behavioral data for learning. For example, optimal behavior suggestions are made based on the user's utterances and facial expressions. As a result, more accurate behavior prediction is possible by collecting voice data and image data and performing learning based on multimodal data.

[0033] The behavioral data collection unit compares the behavioral data of different users and extracts common and different patterns, thereby constructing a general-purpose judgment criterion. The behavioral data collection unit, for example, collects the behavioral data of different users and analyzes the common and different patterns. For example, it compares the behaviors that multiple users exhibit in the same situation. The behavioral data collection unit also constructs a general-purpose judgment criterion based on the behavioral data of different users. For example, it analyzes whether a specific behavioral pattern is common to many users. The behavioral data collection unit also compares the behavioral data of different users and extracts common and different patterns, thereby making more accurate behavior predictions. For example, it makes optimal behavior suggestions based on the common behavioral patterns. In this way, by comparing the behavioral data of different users and extracting common and different patterns, a more general-purpose judgment criterion can be constructed.

[0034] The task automation unit can automatically determine the priority of tasks and execute them in the optimal order when automating a user's tasks. For example, the task automation unit develops an algorithm that automatically determines the priority of tasks when automating a user's tasks. For example, it determines the order of tasks based on importance and urgency. The task automation unit also builds a system that automatically determines the priority of tasks and executes them in the optimal order. For example, it adjusts the order of tasks based on the user's schedule and the importance of tasks. Furthermore, when automating a user's tasks, the task automation unit determines the priority in real time and executes the tasks in the optimal order. For example, it reevaluates the priority based on the progress and changes in the tasks. In this way, the efficiency of tasks is improved by automatically determining the priority of tasks and executing them in the optimal order.

[0035] When automating a user's tasks, the task automation department can monitor the progress of the tasks in real time and make adjustments as necessary. For example, when automating a user's tasks, the task automation department builds a system that monitors the progress of the tasks in real time. For example, it displays the completion status and progress of tasks in real time. The task automation department also develops an algorithm that monitors the progress of the tasks in real time and makes adjustments as necessary. For example, it automatically adjusts the schedule if a delay occurs. The task automation department also builds a system that monitors the progress of the tasks in real time and makes adjustments as necessary when automating a user's tasks. For example, it changes the priority of tasks. In this way, the progress of the tasks can be monitored in real time and adjustments made as necessary, thereby improving the efficiency of the tasks.

[0036] The task automation unit can automatically detect the relationships between different tasks and build an efficient task flow. For example, when automating a user's task, the task automation unit develops an algorithm that automatically detects the relationships between different tasks. For example, it groups related tasks and builds an efficient task flow. The task automation unit also builds a system that automatically detects the relationships between different tasks and builds an efficient task flow. For example, it executes related tasks consecutively. Furthermore, when automating a user's task, the task automation unit detects the relationships between different tasks in real time and builds an efficient task flow. For example, it analyzes task dependencies and executes them in the optimal order. In this way, the relationship between different tasks is automatically detected and an efficient task flow is built, thereby improving task efficiency.

[0037] The task automation unit can automatically adjust cooperation and collaboration with other users to improve the efficiency of the entire team. For example, the task automation unit builds a system that automatically adjusts cooperation and collaboration with other users when automating a user's task. For example, it optimizes task allocation among team members. The task automation unit also develops algorithms that automatically adjust cooperation and collaboration with other users to improve the efficiency of the entire team. For example, it shares task progress and promotes cooperation. The task automation unit also adjusts cooperation and collaboration with other users in real time when automating a user's task to improve the efficiency of the entire team. For example, it analyzes task dependencies and builds an optimal cooperation system. This automatically adjusts cooperation and collaboration with other users to improve the efficiency of the entire team, thereby improving the efficiency of the work.

[0038] The decision support unit incorporates the results of the user's past decisions as feedback, allowing it to provide more accurate advice. For example, the decision support unit stores the results of the user's past decisions in a database and builds a system to improve the accuracy of decision-making based on that feedback. For example, it analyzes past success and failure cases and provides optimal advice. The decision support unit also incorporates the results of past decisions as feedback and develops an algorithm to improve the accuracy of decision-making. For example, it predicts the probability of success based on past data and reflects that result in advice. The decision support unit also incorporates the results of the user's past decisions as feedback and builds a system to provide more accurate advice. For example, it analyzes past decision-making patterns and presents optimal options. In this way, more accurate advice can be provided by incorporating the results of past decisions as feedback.

[0039] The decision support unit can refer to the opinions and data of external experts and provide advice from a more multifaceted perspective. For example, the decision support unit builds a system that references the opinions and data of external experts when supporting user decision-making. For example, it provides optimal advice based on the opinions of experts. The decision support unit also develops an algorithm that supports user decision-making based on the opinions and data of external experts. For example, it analyzes the opinions of experts and presents optimal options. The decision support unit also builds a system that references the opinions and data of external experts when supporting user decision-making and provides advice from a more multifaceted perspective. For example, it obtains the opinions of experts in real time and reflects them in the advice. In this way, by referring to the opinions and data of external experts, advice can be provided from a more multifaceted perspective.

[0040] The decision support unit can simulate different scenarios and present the optimal option. For example, when supporting a user's decision-making, the decision support unit builds a system that simulates different scenarios. For example, it compares multiple scenarios and presents the optimal option. The decision support unit also develops an algorithm that simulates different scenarios and presents the optimal option. For example, it analyzes the risks and benefits of each scenario and presents the optimal option. The decision support unit also builds a system that simulates different scenarios in real time and presents the optimal option when supporting a user's decision-making. For example, it predicts the results of each scenario and presents the optimal option. In this way, the decision support unit supports the user's decision-making by simulating different scenarios and presenting the optimal option.

[0041] The decision support unit can provide best practices by referring to the decision-making patterns of other users. For example, the decision support unit collects the decision-making patterns of other users and builds a system that provides best practices. For example, it provides optimal advice based on success stories and failure stories. The decision support unit also references the decision-making patterns of other users and develops an algorithm that provides best practices. For example, it analyzes decision-making patterns in similar situations and presents optimal options. The decision support unit also references the decision-making patterns of other users when supporting user decision-making and builds a system that provides best practices. For example, it obtains success stories of other users in real time and reflects them in advice. In this way, best practices are provided by referring to the decision-making patterns of other users and supports user decision-making.

[0042] The customization unit incorporates the user's past feedback to perform more accurate customization. For example, the customization unit stores the user's past feedback in a database and builds a system that improves the accuracy of customization based on that data. For example, the customization unit learns the user's preferred formats and styles and performs customization based on that. The customization unit also incorporates the user's past feedback and develops an algorithm that improves the accuracy of customization. For example, the customization unit analyzes the user's preferences and requests and provides optimal customization. The customization unit also incorporates the user's past feedback to build a system that performs more accurate customization. For example, the customization unit obtains the user's feedback in real time and reflects it in the customization. In this way, more accurate customization is performed by incorporating the past feedback.

[0043] The customization unit can make personalized suggestions by taking into account the user's lifestyle, hobbies, and preferences. The customization unit, for example, stores the user's lifestyle, hobbies, and preferences in a database and builds a system that makes personalized suggestions based on that data. For example, it learns the user's preferred time periods and activities and makes suggestions based on that. The customization unit also develops an algorithm that makes personalized suggestions by taking into account the user's lifestyle, hobbies, and preferences. For example, it analyzes the user's preferences and requests and provides optimal suggestions. The customization unit also builds a system that makes personalized suggestions by taking into account the user's lifestyle, hobbies, and preferences. For example, it proposes schedules and activities that match the user's lifestyle. In this way, personalized suggestions are made by taking into account the user's lifestyle, hobbies, and preferences.

[0044] The customization unit can compare the preferences of different users and extract common patterns. The customization unit, for example, builds a system that collects the preferences of different users and analyzes common patterns. For example, it compares formats and styles preferred by multiple users and extracts common patterns. The customization unit also develops an algorithm that extracts common patterns based on the preferences of different users. For example, it analyzes whether specific preferences or requests are common to many users. The customization unit also builds a system that performs more accurate customization by comparing the preferences of different users and extracting common patterns. For example, it makes optimal suggestions based on common preferences. In this way, more accurate customization is performed by comparing the preferences of different users and extracting common patterns.

[0045] The customization unit can make new suggestions by referring to the preferences and trends of other users. For example, the customization unit collects the preferences and trends of other users and builds a system that makes new suggestions based on them. For example, suggestions are made by referring to popular formats and styles. The customization unit also analyzes the preferences and trends of other users and develops an algorithm that makes new suggestions. For example, it provides optimal suggestions based on trend data. The customization unit also builds a system that makes new suggestions by referring to the preferences and trends of other users when customizing based on user preferences. For example, it obtains the latest trends in real time and reflects them in suggestions. In this way, new suggestions are made by referring to the preferences and trends of other users.

[0046] The learning unit can incorporate not only new user behavior data but also external data sources to perform extensive learning. The learning unit, for example, builds a system that collects new user behavior data as well as external data sources (news, social media, etc.) and incorporates them into learning. For example, learning is performed based on the latest news and trends. The learning unit also develops algorithms that perform more extensive learning based on external data sources. For example, it analyzes social media posts and news articles and reflects them in the learning data. The learning unit also builds a system that performs more extensive learning when performing continuous learning, incorporating not only new user behavior data but also external data sources. For example, it obtains external data in real time and reflects it in learning. In this way, more extensive learning is performed by incorporating external data sources.

[0047] The learning unit can incorporate user feedback in real time and instantly update the learning content. For example, the learning unit builds a system that collects user feedback in real time and instantly updates the learning content based on that data. For example, learning is performed by reflecting user opinions and requests. The learning unit also develops an algorithm that instantly updates the learning content based on user feedback. For example, it analyzes user feedback and reflects it in learning data. The learning unit also builds a system that incorporates user feedback in real time and instantly updates the learning content when continuous learning is performed. For example, it obtains user feedback in real time and reflects it in learning. In this way, by incorporating user feedback in real time and instantly updating the learning content, more accurate learning is achieved.

[0048] The learning unit can integrate data from different users and extract common and different patterns. The learning unit, for example, collects data from different users and builds a system that analyzes common and different patterns. For example, it compares how multiple users behave in the same situation. The learning unit also develops an algorithm that extracts common and different patterns based on the data from different users. For example, it analyzes whether a specific behavioral pattern is common to many users. The learning unit also builds a system that performs more accurate learning by integrating data from different users and extracting common and different patterns. For example, it performs optimal learning based on common behavioral patterns. In this way, more accurate learning is performed by integrating data from different users and extracting common and different patterns.

[0049] The learning unit can cooperate with other AI systems and share learning content with each other. The learning unit, for example, cooperates with other AI systems and builds a system for sharing learning content. For example, it integrates data from different AI systems and reflects it in learning. The learning unit also develops an algorithm for sharing learning content based on cooperation with other AI systems. For example, it learns based on feedback from different AI systems. The learning unit also cooperates with other AI systems when performing continuous learning and builds a system for mutually sharing learning content. For example, it obtains data from other AI systems in real time and reflects it in learning. In this way, cooperation with other AI systems and mutual sharing of learning content enables more extensive learning.

[0050] The system according to the embodiment is not limited to the above-described example, and various modifications are possible, for example, as follows.

[0051] The behavioral data collection unit compares the behavioral data of different users and extracts common and different patterns, thereby constructing a general-purpose judgment criterion. For example, the behavioral data collection unit collects the behavioral data of different users and analyzes the common and different patterns. For example, it compares the behaviors that multiple users exhibit in the same situation. The behavioral data collection unit also constructs a general-purpose judgment criterion based on the behavioral data of different users. For example, it analyzes whether a specific behavioral pattern is common to many users. The behavioral data collection unit also compares the behavioral data of different users and extracts common and different patterns, thereby making more accurate behavior predictions. For example, it makes optimal behavior suggestions based on the common behavioral patterns. In this way, by comparing the behavioral data of different users and extracting common and different patterns, a more general-purpose judgment criterion can be constructed.

[0052] When automating a user's tasks, the task automation department can automatically determine the priority of the tasks and execute them in the optimal order. For example, when automating a user's tasks, the department develops an algorithm that automatically determines the priority of the tasks. For example, the department determines the order of tasks based on importance and urgency. The task automation department also builds a system that automatically determines the priority of tasks and executes them in the optimal order. For example, the department adjusts the order of tasks based on the user's schedule and the importance of tasks. When automating a user's tasks, the task automation department also determines the priority in real time and executes the tasks in the optimal order. For example, the department reevaluates the priority based on the progress and changes in the tasks. In this way, the efficiency of the tasks is improved by automatically determining the priority of tasks and executing them in the optimal order.

[0053] The decision support unit can incorporate the results of the user's past decisions as feedback and provide more accurate advice. For example, a system can be built that stores the results of the user's past decisions in a database and improves the accuracy of decision-making based on that feedback. For example, it can analyze past success and failure cases and provide optimal advice. The decision support unit can also incorporate the results of past decisions as feedback and develop algorithms that improve the accuracy of decision-making. For example, it can predict the probability of success based on past data and reflect that result in advice. The decision support unit can also incorporate the results of the user's past decisions as feedback and build a system that provides more accurate advice. For example, it can analyze past decision-making patterns and present optimal options. In this way, more accurate advice can be provided by incorporating the results of past decisions as feedback.

[0054] The customization unit can make personalized suggestions by taking into account the user's lifestyle, hobbies, and preferences. For example, a system is constructed that stores the user's lifestyle, hobbies, and preferences in a database and makes personalized suggestions based on that data. For example, the system learns the user's preferred time periods and activities and makes suggestions based on that. The customization unit also develops an algorithm that makes personalized suggestions by taking into account the user's lifestyle, hobbies, and preferences. For example, the system analyzes the user's preferences and requests and provides optimal suggestions. The customization unit also builds a system that makes personalized suggestions by taking into account the user's lifestyle, hobbies, and preferences. For example, the system proposes schedules and activities that match the user's lifestyle. In this way, personalized suggestions are made by taking into account the user's lifestyle, hobbies, and preferences.

[0055] The learning unit can incorporate not only new user behavior data but also external data sources to perform extensive learning. For example, a system can be built that collects new user behavior data as well as external data sources (news, social media, etc.) and incorporates them into learning. For example, learning is performed based on the latest news and trends. The learning unit can also develop algorithms that perform more extensive learning based on external data sources. For example, it can analyze social media posts and news articles and reflect them in the learning data. The learning unit can also build a system that performs more extensive learning when performing continuous learning, incorporating not only new user behavior data but also external data sources. For example, it can obtain external data in real time and reflect it in learning. In this way, more extensive learning is performed by incorporating external data sources.

[0056] The processing flow of the first embodiment will be briefly explained below.

[0057] Step 1: The behavioral data collection unit collects user behavioral data. For example, it collects website browsing history, app usage history, location information, etc. The app usage history records which apps the user used and for how long, and the location information records the user's movement history using GPS. Step 2: The learning unit performs learning based on the behavioral data collected by the behavioral data collection unit. For example, it analyzes the behavioral data using machine learning algorithms, deep learning, or reinforcement learning, extracts patterns, and builds a predictive model. Step 3: The process automation unit automates processes based on the data learned by the learning unit. For example, it automates tasks such as data entry, report generation, and email sending. Step 4: The decision support unit supports user decision-making based on the data learned by the learning unit, such as purchasing decisions, strategic judgments, and risk assessments.

[0058] (Example 2) The secretary system according to the embodiment of the present invention is a system that collects user behavior data, has a generation AI that learns, automates tasks, and supports decision-making. This allows the secretary system to learn based on the user behavior data, automate tasks, and support decision-making.

[0059] The secretary system according to the embodiment includes a behavioral data collection unit, a learning unit, a task automation unit, and a decision-making support unit. The behavioral data collection unit collects user behavioral data. For example, it collects website browsing history. The behavioral data collection unit can also collect app usage history. The behavioral data collection unit can also collect location information. For example, the behavioral data collection unit collects a history of places visited by the user. The app usage history records which apps the user used and for how long. The location information records the user's movement history using GPS. The learning unit performs learning based on the behavioral data collected by the behavioral data collection unit. For example, the learning unit analyzes the behavioral data using a machine learning algorithm. The learning unit can also analyze the behavioral data using deep learning. The learning unit can also analyze the behavioral data using reinforcement learning. For example, the machine learning algorithm extracts patterns from the behavioral data and builds a predictive model. Deep learning uses a neural network to learn complex patterns. Reinforcement learning learns optimal behavior through trial and error. The business automation unit automates business processes based on the data learned by the learning unit. For example, the business automation unit automates data entry. The business automation unit can also automate report generation. The business automation unit can also automate email sending. For example, data entry automates tasks that users must perform manually. Report generation automatically creates reports based on data. Email sending automatically creates and sends emails to be sent by users. The decision support unit supports user decision making based on the data learned by the learning unit. For example, the decision support unit supports purchasing decisions. The decision support unit can also support strategic decisions. The decision support unit can also support risk assessment. For example, purchasing decisions suggest optimal options when users select products or services to purchase. Strategic decisions provide optimal advice when deciding on business directions and plans. Risk assessment evaluates the risks of investments and projects and supports optimal decisions.As a result, the secretary system according to the embodiment can learn from the user's behavioral data and automate tasks and support decision-making. For example, the output unit provides feedback to the user on the progress of tasks and the results of decisions. The notification function notifies the user of important information in real time. The dashboard visually displays the progress of tasks and the results of decisions.

[0060] The behavioral data collection unit collects the user's biometric data and can learn the relationship between the behavioral data and physiological responses. The behavioral data collection unit, for example, monitors the user's heart rate and electrodermal activity in real time and integrates the data with the behavioral data to learn. For example, it analyzes heart rate fluctuations in situations where the user feels stressed and makes suggestions for stress reduction. The behavioral data collection unit also analyzes the user's behavioral patterns in detail based on the biometric data. For example, it learns the user's heart rate and electrodermal activity when the user is concentrating and identifies times when concentration is at its peak. The behavioral data collection unit also collects the user's biometric data and combines it with the behavioral data to learn, thereby making more accurate behavioral predictions. For example, it suggests optimal times to take a break based on the user's physiological responses. In this way, by collecting the user's biometric data and learning the relationship between behavior and physiological responses, more accurate behavioral predictions are possible.

[0061] The behavioral data collection unit collects environmental data of the user and can learn the association between the behavioral data and environmental factors. The behavioral data collection unit, for example, collects environmental data such as weather, location, and time of day along with the user's behavioral data, and analyzes the impact of environmental factors on decision-making. For example, it learns what behavior the user will exhibit on a rainy day. The behavioral data collection unit also analyzes the user's behavioral patterns in detail based on the environmental data. For example, it learns behavioral tendencies in specific locations and time periods and suggests optimal behavior. The behavioral data collection unit also collects the user's environmental data and learns by combining it with the behavioral data, thereby making more accurate behavioral predictions. For example, it suggests an optimal schedule depending on the weather and location. In this way, by collecting the user's environmental data and learning the association between the behavioral data and environmental factors, more accurate behavioral predictions are possible.

[0062] The behavioral data collection unit can use the emotion estimation function to estimate the emotional state from the user's behavioral data and learn the association between emotions and behavior. The behavioral data collection unit, for example, performs emotion estimation based on the user's behavioral data and analyzes the association between the emotional state and behavior. For example, it learns behavioral patterns in situations where the user feels stressed. The behavioral data collection unit also uses the emotion estimation function to estimate the emotional state from the user's behavioral data in real time and predicts behavior based on that data. For example, it learns behavior patterns when the user is relaxed. The behavioral data collection unit also estimates the user's emotional state and learns by combining it with the behavioral data to perform more accurate behavior prediction. For example, it suggests optimal behavior according to the user's emotional state. As a result, more accurate behavior prediction is possible by using the emotion estimation function to estimate the user's emotional state and learning the association between emotions and behavior.

[0063] The behavioral data collection unit can collect voice data and image data of the user and perform learning based on the multimodal data. The behavioral data collection unit, for example, collects voice data and image data along with the user's behavioral data and learns behavioral patterns based on the multimodal data. For example, the user's utterances and facial expressions are analyzed and used for behavior prediction. The behavioral data collection unit also performs detailed analysis of the user's behavioral patterns based on the voice data and image data. For example, the user's emotional state is estimated from the user's tone of voice and facial expressions and reflected in behavior prediction. The behavioral data collection unit also performs more accurate behavior prediction by collecting multimodal data and combining it with the behavioral data for learning. For example, optimal behavior suggestions are made based on the user's utterances and facial expressions. As a result, more accurate behavior prediction is possible by collecting voice data and image data and performing learning based on multimodal data.

[0064] The behavioral data collection unit compares the behavioral data of different users and extracts common and different patterns, thereby constructing a general-purpose judgment criterion. The behavioral data collection unit, for example, collects the behavioral data of different users and analyzes the common and different patterns. For example, it compares the behaviors that multiple users exhibit in the same situation. The behavioral data collection unit also constructs a general-purpose judgment criterion based on the behavioral data of different users. For example, it analyzes whether a specific behavioral pattern is common to many users. The behavioral data collection unit also compares the behavioral data of different users and extracts common and different patterns, thereby making more accurate behavior predictions. For example, it makes optimal behavior suggestions based on the common behavioral patterns. In this way, by comparing the behavioral data of different users and extracting common and different patterns, a more general-purpose judgment criterion can be constructed.

[0065] The behavioral data collection unit can use the emotion estimation function to estimate the emotion of the user when inputting behavioral data in real time and make suggestions to elicit positive emotions. For example, when the user inputs behavioral data, the behavioral data collection unit uses the emotion estimation function to estimate the emotion in real time and make suggestions to elicit positive emotions. For example, if the user is feeling stressed, the behavioral data collection unit makes suggestions to relax. The behavioral data collection unit also uses the emotion estimation function to analyze the emotion of the user when inputting behavioral data and makes suggestions to elicit positive emotions based on the data. For example, if the user is tired, the behavioral data collection unit also estimates the user's emotional state in real time and provides an interface for eliciting positive emotions when inputting behavioral data. For example, it displays encouraging messages or positive feedback. In this way, the emotion estimation function is used to estimate the user's emotion in real time and make suggestions to elicit positive emotions, thereby improving user satisfaction.

[0066] The task automation unit can automatically determine the priority of tasks and execute them in the optimal order when automating a user's tasks. For example, the task automation unit develops an algorithm that automatically determines the priority of tasks when automating a user's tasks. For example, it determines the order of tasks based on importance and urgency. The task automation unit also builds a system that automatically determines the priority of tasks and executes them in the optimal order. For example, it adjusts the order of tasks based on the user's schedule and the importance of tasks. Furthermore, when automating a user's tasks, the task automation unit determines the priority in real time and executes the tasks in the optimal order. For example, it reevaluates the priority based on the progress and changes in the tasks. In this way, the efficiency of tasks is improved by automatically determining the priority of tasks and executing them in the optimal order.

[0067] When automating a user's tasks, the task automation department can monitor the progress of the tasks in real time and make adjustments as necessary. For example, when automating a user's tasks, the task automation department builds a system that monitors the progress of the tasks in real time. For example, it displays the completion status and progress of tasks in real time. The task automation department also develops an algorithm that monitors the progress of the tasks in real time and makes adjustments as necessary. For example, it automatically adjusts the schedule if a delay occurs. The task automation department also builds a system that monitors the progress of the tasks in real time and makes adjustments as necessary when automating a user's tasks. For example, it changes the priority of tasks. In this way, the progress of the tasks can be monitored in real time and adjustments made as necessary, thereby improving the efficiency of the tasks.

[0068] The task automation unit can use the emotion estimation function to adjust the speed and method of task progress according to the user's emotional state. For example, the task automation unit uses the emotion estimation function to analyze the user's emotional state in real time and build a system that adjusts the speed and method of task progress. For example, the task automation unit slows down the speed of task progress when the user is feeling stressed. The task automation unit also develops an algorithm that adjusts the speed and method of task progress according to the user's emotional state. For example, the task automation unit increases the speed of task progress when the user is relaxed. The task automation unit also uses the emotion estimation function to build a system that adjusts the speed and method of task progress based on the user's emotional state. For example, the task automation unit changes task allocation according to the user's emotional state. In this way, by using the emotion estimation function to adjust the speed and method of task progress according to the user's emotional state, the user's stress is reduced and task efficiency is improved.

[0069] The task automation unit can automatically detect the relationships between different tasks and build an efficient task flow. For example, when automating a user's task, the task automation unit develops an algorithm that automatically detects the relationships between different tasks. For example, it groups related tasks and builds an efficient task flow. The task automation unit also builds a system that automatically detects the relationships between different tasks and builds an efficient task flow. For example, it executes related tasks consecutively. Furthermore, when automating a user's task, the task automation unit detects the relationships between different tasks in real time and builds an efficient task flow. For example, it analyzes task dependencies and executes them in the optimal order. In this way, the relationship between different tasks is automatically detected and an efficient task flow is built, thereby improving task efficiency.

[0070] The task automation unit can automatically adjust cooperation and collaboration with other users to improve the efficiency of the entire team. For example, the task automation unit builds a system that automatically adjusts cooperation and collaboration with other users when automating a user's task. For example, it optimizes task allocation among team members. The task automation unit also develops algorithms that automatically adjust cooperation and collaboration with other users to improve the efficiency of the entire team. For example, it shares task progress and promotes cooperation. The task automation unit also adjusts cooperation and collaboration with other users in real time when automating a user's task to improve the efficiency of the entire team. For example, it analyzes task dependencies and builds an optimal cooperation system. This automatically adjusts cooperation and collaboration with other users to improve the efficiency of the entire team, thereby improving the efficiency of the work.

[0071] The task automation unit can use the emotion estimation function to monitor the emotions of a user when performing work in real time and make suggestions to reduce stress. For example, the task automation unit uses the emotion estimation function to build a system that monitors the emotions of a user when performing work in real time and makes suggestions to reduce stress. For example, if the user is feeling stressed, the task automation unit suggests taking a break to relax. The task automation unit also analyzes the user's emotional state in real time and makes specific suggestions to reduce stress. For example, if the user is tired, the task automation unit suggests light exercise or stretching. The task automation unit also uses the emotion estimation function to provide an interface for stress reduction based on the user's emotional state. For example, if the user is feeling stressed, the task automation unit provides music or a meditation guide to help the user relax. In this way, by using the emotion estimation function to monitor the user's emotions in real time and making suggestions to reduce stress, the user's stress is reduced and task efficiency is improved.

[0072] The decision support unit incorporates the results of the user's past decisions as feedback, allowing it to provide more accurate advice. For example, the decision support unit stores the results of the user's past decisions in a database and builds a system to improve the accuracy of decision-making based on that feedback. For example, it analyzes past success and failure cases and provides optimal advice. The decision support unit also incorporates the results of past decisions as feedback and develops an algorithm to improve the accuracy of decision-making. For example, it predicts the probability of success based on past data and reflects that result in advice. The decision support unit also incorporates the results of the user's past decisions as feedback and builds a system to provide more accurate advice. For example, it analyzes past decision-making patterns and presents optimal options. In this way, more accurate advice can be provided by incorporating the results of past decisions as feedback.

[0073] The decision support unit can refer to the opinions and data of external experts and provide advice from a more multifaceted perspective. For example, the decision support unit builds a system that references the opinions and data of external experts when supporting user decision-making. For example, it provides optimal advice based on the opinions of experts. The decision support unit also develops an algorithm that supports user decision-making based on the opinions and data of external experts. For example, it analyzes the opinions of experts and presents optimal options. The decision support unit also builds a system that references the opinions and data of external experts when supporting user decision-making and provides advice from a more multifaceted perspective. For example, it obtains the opinions of experts in real time and reflects them in the advice. In this way, by referring to the opinions and data of external experts, advice can be provided from a more multifaceted perspective.

[0074] The decision-making support unit uses the emotion estimation function to provide advice according to the user's emotional state, thereby reducing emotional bias. The decision-making support unit, for example, uses the emotion estimation function to build a system that analyzes the user's emotional state in real time and provides advice to reduce emotional bias. For example, when a user is feeling stressed, the decision-making support unit provides advice according to the user's emotional state and develops an algorithm that reduces emotional bias. For example, when a user is relaxed, the algorithm presents the optimal option. The decision-making support unit also uses the emotion estimation function to build a system that provides advice based on the user's emotional state and reduces emotional bias. For example, the content of the advice is adjusted according to the user's emotional state. In this way, the emotion estimation function is used to provide advice according to the user's emotional state, reducing emotional bias and supporting more calm decision-making.

[0075] The decision support unit can simulate different scenarios and present the optimal option. For example, when supporting a user's decision-making, the decision support unit builds a system that simulates different scenarios. For example, it compares multiple scenarios and presents the optimal option. The decision support unit also develops an algorithm that simulates different scenarios and presents the optimal option. For example, it analyzes the risks and benefits of each scenario and presents the optimal option. The decision support unit also builds a system that simulates different scenarios in real time and presents the optimal option when supporting a user's decision-making. For example, it predicts the results of each scenario and presents the optimal option. In this way, the decision support unit supports the user's decision-making by simulating different scenarios and presenting the optimal option.

[0076] The decision support unit can provide best practices by referring to the decision-making patterns of other users. For example, the decision support unit collects the decision-making patterns of other users and builds a system that provides best practices. For example, it provides optimal advice based on success stories and failure stories. The decision support unit also references the decision-making patterns of other users and develops an algorithm that provides best practices. For example, it analyzes decision-making patterns in similar situations and presents optimal options. The decision support unit also references the decision-making patterns of other users when supporting user decision-making and builds a system that provides best practices. For example, it obtains success stories of other users in real time and reflects them in advice. In this way, best practices are provided by referring to the decision-making patterns of other users and supports user decision-making.

[0077] The decision support unit can use the emotion estimation function to monitor the emotions of a user when making a decision in real time and make suggestions to elicit positive emotions. The decision support unit, for example, uses the emotion estimation function to build a system that monitors the emotions of a user when making a decision in real time and makes suggestions to elicit positive emotions. For example, if the user is feeling anxious, it makes suggestions to give the user a sense of security. The decision support unit also analyzes the user's emotional state in real time and makes specific suggestions to elicit positive emotions. For example, if the user is feeling nervous, it makes suggestions to help the user relax. The decision support unit also uses the emotion estimation function to provide an interface for eliciting positive emotions based on the user's emotional state. For example, it displays encouraging messages or positive feedback when the user makes a decision. In this way, the emotion estimation function is used to monitor the user's emotions in real time and make suggestions to elicit positive emotions, thereby supporting the user's decision-making.

[0078] The customization unit incorporates the user's past feedback to perform more accurate customization. For example, the customization unit stores the user's past feedback in a database and builds a system that improves the accuracy of customization based on that data. For example, the customization unit learns the user's preferred formats and styles and performs customization based on that. The customization unit also incorporates the user's past feedback and develops an algorithm that improves the accuracy of customization. For example, the customization unit analyzes the user's preferences and requests and provides optimal customization. The customization unit also incorporates the user's past feedback to build a system that performs more accurate customization. For example, the customization unit obtains the user's feedback in real time and reflects it in the customization. In this way, more accurate customization is performed by incorporating the past feedback.

[0079] The customization unit can make personalized suggestions by taking into account the user's lifestyle, hobbies, and preferences. The customization unit, for example, stores the user's lifestyle, hobbies, and preferences in a database and builds a system that makes personalized suggestions based on that data. For example, it learns the user's preferred time periods and activities and makes suggestions based on that. The customization unit also develops an algorithm that makes personalized suggestions by taking into account the user's lifestyle, hobbies, and preferences. For example, it analyzes the user's preferences and requests and provides optimal suggestions. The customization unit also builds a system that makes personalized suggestions by taking into account the user's lifestyle, hobbies, and preferences. For example, it proposes schedules and activities that match the user's lifestyle. In this way, personalized suggestions are made by taking into account the user's lifestyle, hobbies, and preferences.

[0080] The customization unit uses the emotion estimation function to perform customization according to the user's emotional state, thereby improving user satisfaction. The customization unit, for example, uses the emotion estimation function to analyze the user's emotional state in real time and build a system that performs customization according to the emotional state. For example, when the user is relaxed, the customization unit suggests a relaxing environment. The customization unit also develops an algorithm that performs customization according to the user's emotional state and improves satisfaction. For example, when the user is feeling stressed, the customization unit makes suggestions for stress reduction. The customization unit also uses the emotion estimation function to perform customization based on the user's emotional state and build a system that improves satisfaction. For example, the design and functions of the interface are adjusted according to the user's emotional state. In this way, user satisfaction is improved by using the emotion estimation function to perform customization according to the user's emotional state.

[0081] The customization unit can compare the preferences of different users and extract common patterns. The customization unit, for example, builds a system that collects the preferences of different users and analyzes common patterns. For example, it compares formats and styles preferred by multiple users and extracts common patterns. The customization unit also develops an algorithm that extracts common patterns based on the preferences of different users. For example, it analyzes whether specific preferences or requests are common to many users. The customization unit also builds a system that performs more accurate customization by comparing the preferences of different users and extracting common patterns. For example, it makes optimal suggestions based on common preferences. In this way, more accurate customization is performed by comparing the preferences of different users and extracting common patterns.

[0082] The customization unit can make new suggestions by referring to the preferences and trends of other users. For example, the customization unit collects the preferences and trends of other users and builds a system that makes new suggestions based on them. For example, suggestions are made by referring to popular formats and styles. The customization unit also analyzes the preferences and trends of other users and develops an algorithm that makes new suggestions. For example, it provides optimal suggestions based on trend data. The customization unit also builds a system that makes new suggestions by referring to the preferences and trends of other users when customizing based on user preferences. For example, it obtains the latest trends in real time and reflects them in suggestions. In this way, new suggestions are made by referring to the preferences and trends of other users.

[0083] The customization unit can use the emotion estimation function to monitor the emotions of the user when customizing in real time and make suggestions to elicit positive emotions. The customization unit, for example, uses the emotion estimation function to build a system that monitors the emotions of the user when customizing in real time and makes suggestions to elicit positive emotions. For example, if the user is enjoying themselves, the customization unit makes suggestions to make the experience even more enjoyable. The customization unit also analyzes the user's emotional state in real time and makes specific suggestions to elicit positive emotions. For example, if the user is relaxed, the customization unit suggests a relaxing environment. The customization unit also uses the emotion estimation function to provide an interface for eliciting positive emotions based on the user's emotional state. For example, the customization unit displays encouraging messages or positive feedback when the user customizes. In this way, the emotion estimation function is used to monitor the user's emotions in real time and makes suggestions to elicit positive emotions, thereby improving user satisfaction.

[0084] The learning unit can incorporate not only new user behavior data but also external data sources to perform extensive learning. The learning unit, for example, builds a system that collects new user behavior data as well as external data sources (news, social media, etc.) and incorporates them into learning. For example, learning is performed based on the latest news and trends. The learning unit also develops algorithms that perform more extensive learning based on external data sources. For example, it analyzes social media posts and news articles and reflects them in the learning data. The learning unit also builds a system that performs more extensive learning when performing continuous learning, incorporating not only new user behavior data but also external data sources. For example, it obtains external data in real time and reflects it in learning. In this way, more extensive learning is performed by incorporating external data sources.

[0085] The learning unit can incorporate user feedback in real time and instantly update the learning content. For example, the learning unit builds a system that collects user feedback in real time and instantly updates the learning content based on that data. For example, learning is performed by reflecting user opinions and requests. The learning unit also develops an algorithm that instantly updates the learning content based on user feedback. For example, it analyzes user feedback and reflects it in learning data. The learning unit also builds a system that incorporates user feedback in real time and instantly updates the learning content when continuous learning is performed. For example, it obtains user feedback in real time and reflects it in learning. In this way, by incorporating user feedback in real time and instantly updating the learning content, more accurate learning is achieved.

[0086] The learning unit uses the emotion estimation function to learn according to the user's emotional state and reduce emotional bias. The learning unit, for example, uses the emotion estimation function to analyze the user's emotional state in real time and build a system that learns to reduce emotional bias. For example, learning is performed to encourage calm judgment when the user is feeling stressed. The learning unit also learns according to the user's emotional state and develops an algorithm that reduces emotional bias. For example, optimal learning is performed when the user is relaxed. The learning unit also uses the emotion estimation function to learn based on the user's emotional state and build a system that reduces emotional bias. For example, the learning content is adjusted according to the user's emotional state. In this way, emotional bias is reduced by using the emotion estimation function to learn according to the user's emotional state.

[0087] The learning unit can integrate data from different users and extract common and different patterns. The learning unit, for example, collects data from different users and builds a system that analyzes common and different patterns. For example, it compares how multiple users behave in the same situation. The learning unit also develops an algorithm that extracts common and different patterns based on the data from different users. For example, it analyzes whether a specific behavioral pattern is common to many users. The learning unit also builds a system that performs more accurate learning by integrating data from different users and extracting common and different patterns. For example, it performs optimal learning based on common behavioral patterns. In this way, more accurate learning is performed by integrating data from different users and extracting common and different patterns.

[0088] The learning unit can cooperate with other AI systems and share learning content with each other. The learning unit, for example, cooperates with other AI systems and builds a system for sharing learning content. For example, it integrates data from different AI systems and reflects it in learning. The learning unit also develops an algorithm for sharing learning content based on cooperation with other AI systems. For example, it learns based on feedback from different AI systems. The learning unit also cooperates with other AI systems when performing continuous learning and builds a system for mutually sharing learning content. For example, it obtains data from other AI systems in real time and reflects it in learning. In this way, cooperation with other AI systems and mutual sharing of learning content enables more extensive learning.

[0089] The learning unit can use the emotion estimation function to monitor the emotions of a user when performing a new behavior in real time and make suggestions to elicit positive emotions. The learning unit, for example, uses the emotion estimation function to build a system that monitors the emotions of a user when performing a new behavior in real time and makes suggestions to elicit positive emotions. For example, if the user is feeling anxious, the learning unit makes suggestions to give the user a sense of security. The learning unit also analyzes the user's emotional state in real time and makes specific suggestions to elicit positive emotions. For example, if the user is feeling nervous, the learning unit makes suggestions to help the user relax. The learning unit also uses the emotion estimation function to provide an interface for eliciting positive emotions based on the user's emotional state. For example, the learning unit displays encouraging messages or positive feedback when the user performs a new behavior. In this way, the emotion estimation function is used to monitor the user's emotions in real time and makes suggestions to elicit positive emotions, thereby improving user satisfaction.

[0090] The system according to the embodiment is not limited to the above-described example, and various modifications are possible, for example, as follows.

[0091] The behavioral data collection unit can collect voice data and image data of the user and perform learning based on the multimodal data. For example, voice data and image data are collected along with the user's behavioral data, and behavioral patterns are learned based on the multimodal data. For example, the user's remarks and facial expressions are analyzed and used for behavior prediction. The behavioral data collection unit also performs detailed analysis of the user's behavioral patterns based on the voice data and image data. For example, the user's emotional state is estimated from the user's tone of voice and facial expressions and reflected in behavior prediction. The behavioral data collection unit also performs more accurate behavior prediction by collecting multimodal data and combining it with the behavioral data for learning. For example, optimal behavior suggestions are made based on the user's remarks and facial expressions. As a result, more accurate behavior prediction is possible by collecting voice data and image data and performing learning based on multimodal data.

[0092] The behavioral data collection unit compares the behavioral data of different users and extracts common and different patterns, thereby constructing a general-purpose judgment criterion. For example, the behavioral data collection unit collects the behavioral data of different users and analyzes the common and different patterns. For example, it compares the behaviors that multiple users exhibit in the same situation. The behavioral data collection unit also constructs a general-purpose judgment criterion based on the behavioral data of different users. For example, it analyzes whether a specific behavioral pattern is common to many users. The behavioral data collection unit also compares the behavioral data of different users and extracts common and different patterns, thereby making more accurate behavior predictions. For example, it makes optimal behavior suggestions based on the common behavioral patterns. In this way, by comparing the behavioral data of different users and extracting common and different patterns, a more general-purpose judgment criterion can be constructed.

[0093] When automating a user's tasks, the task automation department can automatically determine the priority of the tasks and execute them in the optimal order. For example, when automating a user's tasks, the department develops an algorithm that automatically determines the priority of the tasks. For example, the department determines the order of tasks based on importance and urgency. The task automation department also builds a system that automatically determines the priority of tasks and executes them in the optimal order. For example, the department adjusts the order of tasks based on the user's schedule and the importance of tasks. When automating a user's tasks, the task automation department also determines the priority in real time and executes the tasks in the optimal order. For example, the department reevaluates the priority based on the progress and changes in the tasks. In this way, the efficiency of the tasks is improved by automatically determining the priority of tasks and executing them in the optimal order.

[0094] The task automation unit can use the emotion estimation function to adjust the speed and method of task progress according to the user's emotional state. For example, the emotion estimation function is used to build a system that analyzes the user's emotional state in real time and adjusts the speed and method of task progress. For example, the speed of task progress is slowed down when the user is feeling stressed. The task automation unit also develops an algorithm that adjusts the speed and method of task progress according to the user's emotional state. For example, the speed of task progress is increased when the user is relaxed. The task automation unit also uses the emotion estimation function to build a system that adjusts the speed and method of task progress based on the user's emotional state. For example, task allocation is changed according to the user's emotional state. In this way, the emotion estimation function is used to adjust the speed and method of task progress according to the user's emotional state, thereby reducing user stress and improving work efficiency.

[0095] The decision support unit can incorporate the results of the user's past decisions as feedback and provide more accurate advice. For example, a system can be built that stores the results of the user's past decisions in a database and improves the accuracy of decision-making based on that feedback. For example, it can analyze past success and failure cases and provide optimal advice. The decision support unit can also incorporate the results of past decisions as feedback and develop algorithms that improve the accuracy of decision-making. For example, it can predict the probability of success based on past data and reflect that result in advice. The decision support unit can also incorporate the results of the user's past decisions as feedback and build a system that provides more accurate advice. For example, it can analyze past decision-making patterns and present optimal options. In this way, more accurate advice can be provided by incorporating the results of past decisions as feedback.

[0096] The decision-making support unit uses the emotion estimation function to provide advice according to the user's emotional state and reduce emotional bias. For example, a system is constructed using the emotion estimation function to analyze the user's emotional state in real time and provide advice to reduce emotional bias. For example, advice is provided to encourage calm decision-making when the user is feeling stressed. The decision-making support unit also develops an algorithm that provides advice according to the user's emotional state and reduces emotional bias. For example, the algorithm presents the optimal option when the user is relaxed. The decision-making support unit also uses the emotion estimation function to provide advice based on the user's emotional state and build a system that reduces emotional bias. For example, the content of the advice is adjusted according to the user's emotional state. In this way, the emotion estimation function is used to provide advice according to the user's emotional state and reduce emotional bias, thereby supporting calmer decision-making.

[0097] The customization unit can make personalized suggestions by taking into account the user's lifestyle, hobbies, and preferences. For example, a system is constructed that stores the user's lifestyle, hobbies, and preferences in a database and makes personalized suggestions based on that data. For example, the system learns the user's preferred time periods and activities and makes suggestions based on that. The customization unit also develops an algorithm that makes personalized suggestions by taking into account the user's lifestyle, hobbies, and preferences. For example, the system analyzes the user's preferences and requests and provides optimal suggestions. The customization unit also builds a system that makes personalized suggestions by taking into account the user's lifestyle, hobbies, and preferences. For example, the system proposes schedules and activities that match the user's lifestyle. In this way, personalized suggestions are made by taking into account the user's lifestyle, hobbies, and preferences.

[0098] The customization unit uses the emotion estimation function to perform customization according to the user's emotional state, thereby improving user satisfaction. For example, the emotion estimation function is used to build a system that analyzes the user's emotional state in real time and performs customization according to the emotional state. For example, when the user is relaxed, the system suggests a relaxing environment. The customization unit also develops an algorithm that performs customization according to the user's emotional state and improves satisfaction. For example, when the user is feeling stressed, the system suggests ways to reduce stress. The customization unit also uses the emotion estimation function to perform customization based on the user's emotional state and build a system that improves satisfaction. For example, the design and functions of the interface are adjusted according to the user's emotional state. In this way, the emotion estimation function is used to perform customization according to the user's emotional state, thereby improving user satisfaction.

[0099] The learning unit can incorporate not only new user behavior data but also external data sources to perform extensive learning. For example, a system can be built that collects new user behavior data as well as external data sources (news, social media, etc.) and incorporates them into learning. For example, learning is performed based on the latest news and trends. The learning unit can also develop algorithms that perform more extensive learning based on external data sources. For example, it can analyze social media posts and news articles and reflect them in the learning data. The learning unit can also build a system that performs more extensive learning when performing continuous learning, incorporating not only new user behavior data but also external data sources. For example, it can obtain external data in real time and reflect it in learning. In this way, more extensive learning is performed by incorporating external data sources.

[0100] The learning unit can use the emotion estimation function to monitor the emotions of a user when performing a new behavior in real time and make suggestions to elicit positive emotions. For example, a system can be constructed that uses the emotion estimation function to monitor the emotions of a user when performing a new behavior in real time and make suggestions to elicit positive emotions. For example, if the user is feeling anxious, the system can make suggestions to give the user a sense of security. The learning unit can also analyze the user's emotional state in real time and make specific suggestions to elicit positive emotions. For example, if the user is feeling nervous, the system can make suggestions to help the user relax. The learning unit can also use the emotion estimation function to provide an interface for eliciting positive emotions based on the user's emotional state. For example, the learning unit can display encouraging messages or positive feedback when the user performs a new behavior. In this way, the emotion estimation function can be used to monitor the user's emotions in real time and make suggestions to elicit positive emotions, thereby improving user satisfaction.

[0101] The processing flow of the second embodiment will be briefly explained below.

[0102] Step 1: The behavioral data collection unit collects user behavioral data. For example, it collects website browsing history, app usage history, location information, etc. The app usage history records which apps the user used and for how long, and the location information records the user's movement history using GPS. Step 2: The learning unit performs learning based on the behavioral data collected by the behavioral data collection unit. For example, it analyzes the behavioral data using machine learning algorithms, deep learning, or reinforcement learning, extracts patterns, and builds a predictive model. Step 3: The process automation unit automates processes based on the data learned by the learning unit. For example, it automates tasks such as data entry, report generation, and email sending. Step 4: The decision support unit supports user decision-making based on the data learned by the learning unit, such as purchasing decisions, strategic judgments, and risk assessments.

[0103] The specific processing unit 290 transmits the result of the specific processing to the smart device 14. In the smart device 14, the control unit 46A causes the output device 40 to output the result of the specific processing. The microphone 38B acquires audio indicating a user input regarding the result of the specific processing. The control unit 46A transmits audio data indicating the user input acquired by the microphone 38B to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the audio data.

[0104] The data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of the data generation model 58 is ChatGPT (Internet Search<URL: https: / / openai.com / blog / chatgpt> Examples of generative AIs include the data generation model 58, such as a neural network model (e.g., a neural network model), and a neural network model (e.g., a neural network model). The data generation model 58 is obtained by performing deep learning on a neural network. A prompt including an instruction is input to the data generation model 58, and inference data such as voice data indicating speech, text data indicating text, and image data indicating an image is also input to the data generation model 58. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The specification processing unit 290 performs the above-mentioned specification processing using the data generation model 58. The data generation model 58 may be a fine-tuned model so as to output an inference result from a prompt that does not include an instruction. In this case, the data generation model 58 can output an inference result from a prompt that does not include an instruction. The data processing device 12 and the like include multiple types of data generation models 58, and the data generation model 58 includes AIs other than the generative AI. The AI ​​other than the generative AI may be, for example, linear regression, logistic regression, decision tree, random forest, support vector machine (SVM), k-means clustering, convolutional neural network (CNN), recurrent neural network (RNN), generative adversarial network (GAN), or naive Bayes, and can perform various processes, but is not limited to these examples. The AI ​​may also be an AI agent. When the processes of each of the above-mentioned parts are performed by AI, the processes may be performed in part or entirely by AI, but are not limited to these examples. The processes performed by AI, including the generative AI, may be replaced with rule-based processes.

[0105] Furthermore, the processing by the data processing system 10 described above is executed by the specific processing unit 290 of the data processing device 12 or the control unit 46A of the smart device 14, but may also be executed by the specific processing unit 290 of the data processing device 12 and the control unit 46A of the smart device 14. Furthermore, the specific processing unit 290 of the data processing device 12 acquires or collects information necessary for processing from the smart device 14 or an external device, and the smart device 14 acquires or collects information necessary for processing from the data processing device 12 or an external device.

[0106] [Second embodiment] FIG. 3 shows an example of the configuration of a data processing system 210 according to the second embodiment.

[0107] 3, the data processing system 210 includes the data processing device 12 and smart glasses 214. An example of the data processing device 12 is a server.

[0108] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN and / or a LAN.

[0109] The smart glasses 214 include a computer 36, a microphone 238, a speaker 240, a camera 42, and a communication I / F 44. The computer 36 includes a processor 46, a RAM 48, and a storage 50. The processor 46, the RAM 48, and the storage 50 are connected to a bus 52. The microphone 238, the speaker 240, and the camera 42 are also connected to the bus 52.

[0110] The microphone 238 receives instructions and the like from the user by receiving voice uttered by the user. The microphone 238 captures the voice uttered by the user, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to instructions from the processor 46.

[0111] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an imaging element such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the user's surroundings (for example, an imaging range defined by an angle of view equivalent to the field of vision of a typical healthy person).

[0112] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 are responsible for the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is carried out in a secure state.

[0113] Fig. 4 shows an example of the main functions of the data processing device 12 and the smart glasses 214. As shown in Fig. 4, in the data processing device 12, a specific process is performed by the processor 28. A specific process program 56 is stored in the storage 32.

[0114] The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[0115] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290. The identification processing unit 290 can estimate the user's emotion using the emotion identification model 59 and perform identification processing using the user's emotion.

[0116] In the smart glasses 214, the specific processing is performed by the processor 46. A specific processing program 60 is stored in the storage 50. The processor 46 reads the specific processing program 60 from the storage 50 and executes the read specific processing program 60 on the RAM 48. The specific processing is realized by the processor 46 operating as the control unit 46A in accordance with the specific processing program 60 executed on the RAM 48. Note that the smart glasses 214 may have a data generation model and an emotion identification model similar to the data generation model 58 and the emotion identification model 59.

[0117] Note that a device other than the data processing device 12 may have the data generation model 58. For example, a server device may have the data generation model 58. In this case, the data processing device 12 communicates with the server device having the data generation model 58 to obtain a processing result (such as a prediction result) using the data generation model 58. Furthermore, the data processing device 12 may be a server device, or may be a terminal device (for example, a mobile phone, a robot, a home appliance, etc.) owned by a user.

[0118] The specific processing unit 290 transmits the result of the specific processing to the smart glasses 214. In the smart glasses 214, the control unit 46A causes the speaker 240 to output the result of the specific processing. The microphone 238 acquires audio indicating a user input regarding the result of the specific processing. The control unit 46A transmits audio data indicating the user input acquired by the microphone 238 to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the audio data.

[0119] The data generation model 58 is a so-called generative AI. An example of the data generation model 58 is a generative AI such as ChatGPT. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 receives a prompt containing an instruction, as well as inference data such as voice data representing speech, text data representing text, and image data representing an image. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The identification processing unit 290 performs the above-mentioned identification processing using the data generation model 58. The data generation model 58 may be a fine-tuned model so as to output an inference result from a prompt that does not include an instruction. In this case, the data generation model 58 can output an inference result from a prompt that does not include an instruction. The data processing device 12 and the like include multiple types of data generation models 58, and the data generation model 58 includes AIs other than the generative AI. The AI ​​other than the generative AI may be, for example, linear regression, logistic regression, decision tree, random forest, support vector machine (SVM), k-means clustering, convolutional neural network (CNN), recurrent neural network (RNN), generative adversarial network (GAN), or naive Bayes, and can perform various processes, but is not limited to these examples. The AI ​​may also be an AI agent. When the processes of each of the above-mentioned parts are performed by AI, the processes may be performed in part or entirely by AI, but are not limited to these examples. The processes performed by AI, including the generative AI, may be replaced with rule-based processes.

[0120] The data processing system 210 according to the second embodiment performs the same processing as the data processing system 10 according to the first embodiment. The processing by the data processing system 210 is executed by the specific processing unit 290 of the data processing device 12 or the control unit 46A of the smart glasses 214, but may also be executed by the specific processing unit 290 of the data processing device 12 and the control unit 46A of the smart glasses 214. Furthermore, the specific processing unit 290 of the data processing device 12 acquires or collects information required for processing from the smart glasses 214 or an external device, etc., and the smart glasses 214 acquires or collects information required for processing from the data processing device 12 or an external device, etc.

[0121] [Third embodiment] FIG. 5 shows an example of the configuration of a data processing system 310 according to the third embodiment.

[0122] 5, the data processing system 310 includes the data processing device 12 and a headset type terminal 314. An example of the data processing device 12 is a server.

[0123] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN and / or a LAN.

[0124] The headset type terminal 314 includes a computer 36, a microphone 238, a speaker 240, a camera 42, a communication I / F 44, and a display 343. The computer 36 includes a processor 46, a RAM 48, and a storage 50. The processor 46, the RAM 48, and the storage 50 are connected to a bus 52. The microphone 238, the speaker 240, the camera 42, and the display 343 are also connected to the bus 52.

[0125] The microphone 238 receives instructions and the like from the user by receiving voice uttered by the user. The microphone 238 captures the voice uttered by the user, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to instructions from the processor 46.

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

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

[0128] Fig. 6 shows an example of the main functions of the data processing device 12 and the headset type terminal 314. As shown in Fig. 6, in the data processing device 12, a specific process is performed by the processor 28. A specific process program 56 is stored in the storage 32.

[0129] The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[0130] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290. The identification processing unit 290 can estimate the user's emotion using the emotion identification model 59 and perform identification processing using the user's emotion.

[0131] In the headset type terminal 314, the identification process is performed by the processor 46. A identification program 60 is stored in the storage 50. The processor 46 reads the identification program 60 from the storage 50 and executes the read identification program 60 on the RAM 48. The identification process is realized by the processor 46 operating as a control unit 46A in accordance with the identification program 60 executed on the RAM 48. Note that the headset type terminal 314 may also have a data generation model and an emotion identification model similar to the data generation model 58 and the emotion identification model 59.

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

[0133] The specific processing unit 290 transmits the result of the specific processing to the headset type terminal 314. In the headset type terminal 314, the control unit 46A causes the speaker 240 and the display 343 to output the result of the specific processing. The microphone 238 acquires audio indicating a user input regarding the result of the specific processing. The control unit 46A transmits audio data indicating the user input acquired by the microphone 238 to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the audio data.

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

[0135] The data processing system 310 according to the third embodiment performs the same processing as the data processing system 10 according to the first embodiment. The processing by the data processing system 310 is executed by the specific processing unit 290 of the data processing device 12 or the control unit 46A of the headset type terminal 314, but may also be executed by the specific processing unit 290 of the data processing device 12 and the control unit 46A of the headset type terminal 314. Furthermore, the specific processing unit 290 of the data processing device 12 acquires or collects information required for processing from the headset type terminal 314 or an external device, etc., and the headset type terminal 314 acquires or collects information required for processing from the data processing device 12 or an external device, etc.

[0136] [Fourth embodiment] FIG. 7 shows an example of the configuration of a data processing system 410 according to the fourth embodiment.

[0137] 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.

[0138] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN and / or a LAN.

[0139] The robot 414 includes a computer 36, a microphone 238, a speaker 240, a camera 42, a communication I / F 44, and a control target 443. The computer 36 includes a processor 46, a RAM 48, and a storage 50. The processor 46, the RAM 48, and the storage 50 are connected to a bus 52. The microphone 238, the speaker 240, the camera 42, and the control target 443 are also connected to the bus 52.

[0140] The microphone 238 receives instructions and the like from the user by receiving voice uttered by the user. The microphone 238 captures the voice uttered by the user, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to instructions from the processor 46.

[0141] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an imaging element such as a CMOS image sensor or a CCD image sensor, and captures images of the user's surroundings (for example, an imaging range defined by an angle of view equivalent to the field of vision of a typical healthy person).

[0142] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 are responsible for the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is carried out in a secure state.

[0143] The control object 443 includes a display device, LEDs in the eyes, and motors that drive the arms, hands, and feet. The posture and gestures of the robot 414 are controlled by controlling the motors of the arms, hands, and feet. Some of the emotions of the robot 414 can be expressed by controlling these motors. In addition, the facial expressions of the robot 414 can also be expressed by controlling the light emission state of the LEDs in the eyes of the robot 414.

[0144] Fig. 8 shows an example of the main functions of the data processing device 12 and the robot 414. As shown in Fig. 8, in the data processing device 12, a specific process is performed by the processor 28. A specific process program 56 is stored in the storage 32.

[0145] The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[0146] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290. The identification processing unit 290 can estimate the user's emotion using the emotion identification model 59 and perform identification processing using the user's emotion.

[0147] In the robot 414, the processor 46 performs the identification process. A identification program 60 is stored in the storage 50. The processor 46 reads the identification program 60 from the storage 50 and executes the read identification program 60 on the RAM 48. The identification process is realized by the processor 46 operating as a control unit 46A in accordance with the identification program 60 executed on the RAM 48. The robot 414 may have a data generation model and an emotion identification model similar to the data generation model 58 and the emotion identification model 59.

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

[0149] The specific processing unit 290 transmits the result of the specific processing to the robot 414. In the robot 414, the control unit 46A causes the speaker 240 and the control target 443 to output the result of the specific processing. The microphone 238 acquires voice indicating a user input regarding the result of the specific processing. The control unit 46A transmits voice data indicating the user input acquired by the microphone 238 to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the voice data.

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

[0151] The data processing system 410 according to the fourth embodiment performs the same processing as the data processing system 10 according to the first embodiment. The processing by the data processing system 410 is executed by the specific processing unit 290 of the data processing device 12 or the control unit 46A of the robot 414, but may also be executed by the specific processing unit 290 of the data processing device 12 and the control unit 46A of the robot 414. Furthermore, the specific processing unit 290 of the data processing device 12 acquires or collects information required for processing from the robot 414 or an external device, etc., and the robot 414 acquires or collects information required for processing from the data processing device 12 or an external device, etc.

[0152] The emotion identification model 59 as an emotion engine may determine the user's emotion according to a specific mapping. Specifically, the emotion identification model 59 may determine the user's emotion according to an emotion map (see FIG. 9), which is a specific mapping. Similarly, the emotion identification model 59 may determine the robot's emotion, and the identification processing unit 290 may perform identification processing using the robot's emotion.

[0153] FIG. 9 illustrates an emotion map 400 on which multiple emotions are mapped. In the emotion map 400, emotions are arranged in concentric circles radiating from the center. Emotions closer to the center of the concentric circles are more primitive. Emotions representing states and behaviors arising from a state of mind are arranged on the outer edges of the concentric circles. The concept of emotion encompasses both emotions and mental states. Emotions generally generated from reactions occurring in the brain are arranged on the left side of the concentric circles. Emotions generally induced by situational judgment are arranged on the right side of the concentric circles. Emotions generally generated from reactions occurring in the brain and induced by situational judgment are arranged on the upper and lower sides of the concentric circles. Furthermore, the emotion of "pleasure" is arranged on the upper side of the concentric circles, and the emotion of "discomfort" is arranged on the lower side. In this way, in the emotion map 400, multiple emotions are mapped based on the structure by which emotions are generated, and emotions that tend to occur simultaneously are mapped close to each other.

[0154] These emotions are distributed in the 3 o'clock direction on emotion map 400, and typically fluctuate between relief and anxiety. In the right half of emotion map 400, situational awareness dominates over internal sensations, resulting in a sense of calm.

[0155] The inside of emotion map 400 represents what is going on in the mind, and the outside of emotion map 400 represents behavior, so the further you go outside emotion map 400, the more visible the emotions become (the more they are expressed in behavior).

[0156] Human emotions are based on various balances, such as posture and blood sugar levels. When these balances deviate from the ideal, a state of discomfort is expressed, and when they approach the ideal, a state of pleasure is expressed. Emotions can also be created for robots, cars, and motorcycles, based on various balances, such as posture and remaining battery life. When these balances deviate from the ideal, a state of discomfort is expressed, and when they approach the ideal, a state of pleasure is expressed. An emotion map can be generated, for example, based on Dr. Mitsuyoshi's emotion map (Research on speech emotion recognition and brain physiological signal analysis systems for emotions, Tokushima University, doctoral dissertation: https: / / ci.nii.ac.jp / naid / 500000375379). The left half of the emotion map lists emotions belonging to the area called "reaction," where sensation is dominant. The right half of the emotion map lists emotions belonging to the area called "situation," where situational awareness is dominant.

[0157] The emotion map defines two emotions that promote learning. One is a negative emotion on the situation side, around the middle of "repentance" or "reflection." In other words, this occurs when the robot experiences negative emotions such as "I never want to feel this way again" or "I don't want to be scolded again." The other is a positive emotion on the response side, around "desire." In other words, this occurs when the robot experiences positive feelings such as "I want more" or "I want to know more."

[0158] The emotion identification model 59 inputs user input into a pre-trained neural network, obtains emotion values ​​indicating each emotion shown in the emotion map 400, and determines the user's emotion. This neural network is pre-trained based on multiple pieces of training data that are combinations of user input and emotion values ​​indicating each emotion shown in the emotion map 400. Furthermore, this neural network is trained so that emotions that are located close to each other have similar values, as in the emotion map 900 shown in FIG. 10. FIG. 10 shows an example in which multiple emotions, "relieved," "calm," and "reassuring," have similar emotion values.

[0159] In the above embodiment, an example was given in which a specific process is performed by one computer 22, but the technology disclosed herein is not limited to this, and distributed processing of the specific process may be performed by multiple computers including computer 22.

[0160] In the above embodiment, an example in which the specific processing program 56 is stored in the storage 32 has been described, but the technology of the present disclosure is not limited to this. For example, the specific processing program 56 may be stored in a portable, computer-readable, non-transitory storage medium such as a USB (Universal Serial Bus) memory. The specific processing program 56 stored in the non-transitory storage medium is installed in the computer 22 of the data processing device 12. The processor 28 executes the specific processing in accordance with the specific processing program 56.

[0161] 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.

[0162] It is not necessary to store all of the specific processing program 56 in a storage device such as a server connected to the data processing device 12 via the network 54, or to store all of the specific processing program 56 in the storage 32; only a portion of the specific processing program 56 may be stored.

[0163] The hardware resource for executing a specific process can be any of the following types of processors: A processor, for example, is a CPU, which is a general-purpose processor that functions as a hardware resource for executing a specific process by executing software, i.e., a program. A processor also includes a dedicated electrical circuit, such as an FPGA (Field-Programmable Gate Array), a PLD (Programmable Logic Device), or an ASIC (Application Specific Integrated Circuit), which is a processor with a circuit configuration designed specifically for executing a specific process. Each processor has built-in or connected memory, and each processor uses the memory to execute the specific process.

[0164] The hardware resource that executes the specific process may be configured with one of these various processors, or may be configured with a combination of two or more processors of the same or different types (for example, a combination of multiple FPGAs, or a combination of a CPU and an FPGA). Also, the hardware resource that executes the specific process may be a single processor.

[0165] As an example of a system configured with a single processor, first, one processor is configured by combining one or more CPUs and software, and this processor functions as a hardware resource that executes a specific process. Second, there is a system that uses a processor that realizes the functions of an entire system including multiple hardware resources that execute a specific process on a single IC chip, as typified by SoC (System-on-a-chip). In this way, a specific process is realized using one or more of the above-mentioned various processors as hardware resources.

[0166] Furthermore, the hardware structure of these various processors can be, more specifically, an electric circuit that combines circuit elements such as semiconductor devices. The specific processing described above is merely an example. Therefore, it goes without saying that unnecessary steps may be deleted, new steps may be added, or the processing order may be rearranged, without departing from the spirit of the invention.

[0167] In the above example, the first to fourth embodiments have been described separately, but some or all of these embodiments may be combined. The smart device 14, smart glasses 214, headset terminal 314, and robot 414 are merely examples, and they may be combined, or other devices may be used. In the above example, the first and second embodiments have been described separately, but they may be combined.

[0168] The above-described description and illustrations are a detailed explanation of the parts related to the technology of the present disclosure and are merely an example of the technology of the present disclosure. For example, the above description of the configuration, functions, actions, and effects is an explanation of an example of the configuration, functions, actions, and effects of the parts related to the technology of the present disclosure. Therefore, it goes without saying that unnecessary parts may be deleted, new elements may be added, or replacements may be made to the above-described description and illustrations within the scope of the gist of the technology of the present disclosure. Furthermore, in order to avoid confusion and to facilitate understanding of the parts related to the technology of the present disclosure, the above-described description and illustrations omit explanations of common technical knowledge that do not require particular explanation to enable the implementation of the technology of the present disclosure.

[0169] All publications, patent applications, and technical standards mentioned in this specification are herein incorporated by reference to the same extent as if each individual publication, patent application, or technical standard was specifically and individually indicated to be incorporated by reference. [Explanation of symbols]

[0170] 10, 210, 310, 410 Data Processing Systems 12 Data Processing Device 14 Smart Devices 214 Smart Glasses 314 Headset-type terminal 414 Robot

Claims

1. a behavioral data collection unit that collects user behavioral data; a learning unit that performs learning based on the behavioral data collected by the behavioral data collecting unit; a task automation unit that automates tasks based on the data learned by the learning unit; a decision-making support unit that supports a user in making decisions based on the data learned by the learning unit. A system characterized by:

2. The behavioral data collection unit Collecting biometric data of the user and learning the relationship between the behavioral data and physiological responses.

2. The system of claim 1.

3. The business automation unit When automating the user's tasks, the priority of the tasks is automatically determined and the tasks are carried out in the optimal order.

2. The system of claim 1.

4. The decision support unit Incorporating feedback from the user's past decisions to provide more accurate advice 2. The system of claim 1.

5. The customization section is To improve the satisfaction of the user by customizing the content in accordance with the emotional state of the user.

2. The system of claim 1.

6. The learning unit Learning according to the user's emotional state to reduce emotional bias 2. The system of claim 1.

7. The behavioral data collection unit The emotional state of the user is estimated from the behavioral data, and the relationship between emotions and behavior is learned.

2. The system of claim 1.

Images