System

Abstract

To provide a system capable of properly proposing a next action of a user on the basis of the past information of the user.SOLUTION: A system according to an embodiment comprises a learning unit, an inference unit, and a proposal unit. The learning unit learns past information of a user. The inference unit analyzes information before and after the behaviors of the user on the basis of the information learned by the learning unit and infers the next behavior of the user. The proposal unit proposes the next behavior inferred by the inference unit to the user.SELECTED DRAWING: Figure 1

Description

[Technical field]

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

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

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

[0004] Conventional techniques do not adequately suggest appropriate next actions based on a user's past information, and there is room for improvement.

[0005] The system according to the embodiment aims to appropriately suggest the next action to be taken by the user based on the user's past information. [Means for solving the problem]

[0006] The system according to the embodiment includes a learning unit, an estimation unit, and a suggestion unit. The learning unit learns past information of a user. The estimation unit analyzes information before and after the user's behavior based on the information learned by the learning unit, and estimates the user's next behavior. The suggestion unit suggests to the user the next behavior estimated by the estimation unit. Effect of the Invention

[0007] The system according to the embodiment can appropriately suggest the next action to be taken by the user based on the user's past information. [Brief description of the drawings]

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

[0028] (Example 1) The system according to the embodiment of the present invention is a generative AI system in which AI complements memory and supports the next action. This generative AI system learns the user's past information, analyzes information before and after the action, and predicts the next action. For example, information such as the user's past actions, remarks, and schedules is collected, and the AI ​​learns it. This makes it possible to grasp the user's behavioral patterns. Next, based on the learned information, the information before and after the user's action is analyzed. For example, the AI ​​analyzes what information is related before and after the user takes a specific action. This builds a foundation for predicting the next action. Furthermore, the predicted next action is suggested to the user. For example, when the user says, "What should I do next?", the AI ​​suggests the next action. This allows the user to move smoothly to the next step without being confused about what to do. It also has a function to collect visual information. For example, it grasps the situation around the user through a camera and predicts the next action based on that. This makes it possible to make more accurate suggestions. In this way, the generative AI system supports memory and functions as a partner to make life smoother. It is a reliable presence when the user is confused about what to do or forgets information. This allows the generative AI system to support the user's actions and make life smoother.

[0029] The generation AI system according to the embodiment includes a learning unit, an inference unit, and a suggestion unit. The learning unit learns the user's past information. The user's past information includes, for example, past behavior history, purchase history, browsing history, etc., but is not limited to such examples. The learning unit collects information such as the user's past actions, remarks, schedules, etc., and the AI ​​learns it. This makes it possible to grasp the user's behavioral pattern. The inference unit analyzes information before and after the user's action based on the information learned by the learning unit, and infers the next action. The information before and after the action includes, for example, the situation immediately before the action, the result after the action, etc., but is not limited to such examples. For example, the inference unit uses the AI ​​to analyze what information is related before and after the user takes a specific action. This lays the foundation for inferring the next action. The suggestion unit suggests the next action inferred by the inference unit to the user. The next action includes, for example, the next action to be taken, a predicted behavior pattern, etc., but is not limited to such examples. For example, when the user says, "What should I do next?", the AI ​​suggests the next action. This allows the user to smoothly proceed to the next step without being confused about what to do. As a result, the generative AI system according to the embodiment supports the user's actions and makes life smoother.

[0030] The learning unit learns the user's past information. The user's past information includes, but is not limited to, past behavioral history, purchase history, browsing history, etc. The learning unit collects information such as the user's past actions, remarks, and schedules, and the AI ​​learns it. Specifically, data is collected from the devices and applications used by the user and stored in a database on the cloud. For example, the user's location information and app usage history are collected from smartphone applications, browsing history and search queries are collected from web browsers, and communication content is collected from emails and messaging apps. These data are anonymized to protect privacy and are managed in a secure environment. The AI ​​uses these data to analyze the user's behavioral patterns and interests. For example, if a user tends to visit a specific place at a specific time of day, the AI ​​learns the pattern and predicts the next visit. In addition, the AI ​​uses the purchase history to understand what products the user is interested in and uses it to suggest related products. Furthermore, the learning unit updates the user's behavioral patterns over time and performs analysis based on the latest information. This makes it possible to respond appropriately even if the user's behavior or interests change. The learning department uses this data to create a profile of the user, laying the foundation for providing services tailored to individual needs and preferences.

[0031] The prediction unit analyzes information before and after the user's behavior based on the information learned by the learning unit, and predicts the next behavior. The information before and after the behavior includes, for example, the situation immediately before the behavior and the result after the behavior, but is not limited to such examples. In the prediction unit, for example, the AI ​​analyzes what information is related before and after the user takes a specific behavior. Specifically, the user's past behavior and its result are extracted from the database, and the AI ​​analyzes it. For example, information such as what behavior the user took after participating in a specific event, or what review the user left after purchasing a specific product is analyzed. The AI ​​uses these data to model the causal relationship of the behavior and predict the next action to be taken. Furthermore, the prediction unit grasps the user's current situation based on data collected in real time and predicts the next action. For example, the prediction unit predicts the next action to be taken taking into account the user's current location, time of day, surrounding environmental information, etc. In addition, the prediction unit can make more accurate predictions by referring to not only the user's past behavior patterns, but also the behavioral data of other users. This allows the prediction unit to predict the user's next action with high accuracy and lay the foundation for making appropriate suggestions.

[0032] The suggestion unit suggests the next action predicted by the prediction unit to the user. The next action includes, for example, the next action to be taken, a predicted behavior pattern, and the like, but is not limited to such examples. When the user says, for example, "What should I do next?", the suggestion unit uses the AI ​​to suggest the next action. Specifically, the AI ​​suggests the optimal action based on the user's current situation and past behavior patterns. For example, if the user wants to relax between work, the AI ​​suggests an appropriate relaxation method, taking into account past relaxation methods, the current time of day, and the surrounding environment. Also, if the user is shopping, the AI ​​suggests the optimal product based on the past purchase history and the current store inventory information. The suggestion unit collects user feedback and continuously improves the accuracy of the suggestions. For example, the AI ​​collects the satisfaction and results after the user performs the suggested action as feedback, and learns from this to improve the accuracy of the next suggestion. The suggestion unit can also customize the suggestions according to the user's preferences and needs. For example, if the user likes movies of a particular genre, the AI ​​preferentially suggests movies related to that genre. This allows the suggestion unit to suggest optimal actions to the user and smoothly support their life.

[0033] The voice reception unit receives the user's voice, and the estimation unit can estimate the user's next action when the voice reception unit receives the user's voice. The voice reception unit, for example, receives the user's voice with a microphone and converts it into text data using voice recognition technology. For example, the voice reception unit uses voice recognition software to automatically analyze the voice and save it as text. The voice reception unit can also build a system that recognizes the user's voice in real time and displays it as text data. For example, text is displayed on a screen at the same time as voice input. The voice reception unit also uses voice input to convert the contents dictated by the user into text and saves the text data. For example, voice recognition technology can also be used to perform highly accurate text conversion. This allows the voice reception unit to estimate the next action by receiving the user's voice. A part or all of the above-mentioned processing in the voice reception unit may be performed using AI, for example, or may be performed without using AI. For example, the voice reception unit can input voice data acquired by a microphone to a generation AI and have the generation AI execute conversion from voice data to text data.

[0034] The collection unit collects visual information, and the estimation unit can estimate the user's next behavior based on the information learned by the learning unit and the visual information collected by the collection unit. The visual information includes, for example, images, videos, real-time videos, etc., but is not limited to such examples. The collection unit, for example, uses a camera to capture the situation around the user and collects visual information. For example, the collection unit analyzes the images and videos captured by the camera to grasp the user's behavior pattern. The collection unit can also analyze the real-time video to grasp the user's current situation. For example, the collection unit analyzes the real-time video captured by the camera and monitors the user's behavior in real time. In this way, the collection unit can estimate the next behavior by collecting visual information. A part or all of the above-mentioned processing in the collection unit may be performed, for example, using AI, or may be performed without using AI. For example, the collection unit can input image data captured by a camera to the generation AI and cause the generation AI to execute analysis of visual information from the image data.

[0035] The learning unit can classify the user's past behavior history by time period and learn behavior patterns in specific time periods. For example, the learning unit classifies the user's past behavior history by time period and learns behavior patterns in specific time periods. Time periods include, for example, morning, afternoon, night, and specific time ranges, but are not limited to such examples. For example, the learning unit learns the behavior patterns performed by the user in the morning time period and optimizes the morning routine. The learning unit can also learn the behavior patterns performed by the user in the lunch break time period and optimize how to spend the lunch break. The learning unit can also learn the behavior patterns performed by the user in the evening time period and optimize how to relax in the evening. As a result, by learning behavior patterns for each time period, it is possible to suggest optimal behavior for a specific time period. Part or all of the above-mentioned processing in the learning unit may be performed using, for example, AI, or may be performed without using AI. For example, the learning unit can input the user's behavior history data to the generation AI and cause the generation AI to execute learning of behavior patterns for each time period.

[0036] The learning unit can learn the user's health data in addition to the user's behavior history and improve the accuracy of the behavior pattern. The learning unit can learn the user's health data (e.g., heart rate, sleep pattern) in addition to the user's behavior history, for example, and improve the accuracy of the behavior pattern. The health data includes, for example, heart rate, number of steps, sleep data, etc., but is not limited to such examples. The learning unit can learn, for example, the user's heart rate data and optimize the behavior pattern during periods of high stress. The learning unit can also learn the user's sleep pattern and optimize the behavior pattern during lack of sleep. The learning unit can also learn the user's exercise data and optimize the behavior pattern after exercise. As a result, the accuracy of the behavior pattern is improved by learning the health data. Part or all of the above-mentioned processing in the learning unit may be performed, for example, using AI, or may be performed without using AI. For example, the learning unit can input the user's health data to the generation AI and cause the generation AI to execute the improvement of the accuracy of the behavior pattern.

[0037] The learning unit can analyze the user's social media activity and reflect it in the learning of the behavioral pattern. The learning unit, for example, analyzes the user's social media activity and reflects it in the learning of the behavioral pattern. The social media activity includes, for example, the content of the post, the number of likes, and comments, but is not limited to such examples. The learning unit, for example, learns the activity shared by the user on social media and reflects it in the behavioral pattern. The learning unit can also analyze the content of the user's social media post and learn the interests and concerns. The learning unit can also analyze the user's social media friendships and learn the factors that affect the behavioral pattern. In this way, the analysis of the social media activity can be reflected in the learning of the behavioral pattern. A part or all of the above-mentioned processing in the learning unit may be performed, for example, using AI, or may be performed without using AI. For example, the learning unit can input the user's social media data to the generation AI and cause the generation AI to execute the learning of the behavioral pattern.

[0038] The learning unit can learn a behavior pattern in a specific location by taking into account the geographical location information of the user. The learning unit, for example, learns a behavior pattern in a specific location by taking into account the geographical location information of the user. The geographical location information includes, for example, GPS data, Wi-Fi location information, and the like, but is not limited to such examples. The learning unit, for example, learns a behavior pattern when the user is in a specific location and proposes an optimal behavior in that location. The learning unit can also learn a behavior pattern when the user is traveling and propose an optimal behavior at the travel destination. The learning unit can also learn a behavior pattern when the user is at work and propose an behavior that improves work efficiency. In this way, the behavior pattern in a specific location can be learned by taking into account the geographical location information. A part or all of the above-mentioned processing in the learning unit may be performed, for example, using AI, or may be performed without using AI. For example, the learning unit can input the geographical location information of the user to the generation AI and cause the generation AI to execute learning of the behavior pattern.

[0039] The estimation unit can compare the user's past behavior pattern with the current situation in real time and estimate the next behavior. The estimation unit, for example, compares the user's past behavior pattern with the current situation in real time and estimates the next behavior. The current situation includes, for example, a current location, a current activity, a surrounding environment, and the like, but is not limited to such examples. The estimation unit, for example, estimates the next behavior based on the behavior the user performed in the same situation in the past. The estimation unit can also analyze the user's current situation in real time and estimate the optimal behavior. The estimation unit can also compare the user's past behavior pattern with the current situation and estimate the next behavior. As a result, the next behavior can be estimated by comparing the past behavior pattern with the current situation. A part or all of the above-mentioned processing in the estimation unit may be performed, for example, using AI, or may be performed without using AI. For example, the estimation unit can input the user's past behavior pattern data and current situation data to the generation AI and cause the generation AI to execute estimation of the next behavior.

[0040] The estimation unit can estimate the next behavior based on the environmental information around the user in addition to the information before and after the user's behavior. The estimation unit estimates the next behavior by considering the environmental information around the user (e.g., weather, traffic conditions) in addition to the information before and after the user's behavior. The environmental information around the user includes, but is not limited to, weather information, surrounding sounds, temperature, and the like. The estimation unit estimates the next behavior based on, for example, weather information. The estimation unit can also estimate the next behavior based on traffic conditions. The estimation unit can also comprehensively analyze the environmental information around the user and estimate the next behavior. This allows the next behavior to be more accurately estimated by considering the environmental information around the user. A part or all of the above-mentioned processing in the estimation unit may be performed using, for example, an AI, or may be performed without using an AI. For example, the estimation unit can input weather information and traffic condition data to the generation AI and cause the generation AI to execute estimation of the next behavior.

[0041] The estimation unit can estimate the next action by taking into account the schedule information of the user. The estimation unit estimates the next action by taking into account the schedule information of the user, for example. The schedule information includes, but is not limited to, calendar events, reminders, task management information, and the like. The estimation unit estimates the next action based on the schedule of the user, for example. The estimation unit can also estimate the optimal action by taking into account the schedule of the user. The estimation unit can also estimate the next action based on the schedule information of the user. As a result, the next action can be more accurately estimated by taking into account the schedule information. A part or all of the above-mentioned processing in the estimation unit may be performed, for example, using AI, or may be performed without using AI. For example, the estimation unit can input the schedule information of the user to the generation AI and cause the generation AI to execute estimation of the next action.

[0042] The estimation unit can analyze the user's past purchase history and estimate the next behavior. The estimation unit, for example, analyzes the user's past purchase history and estimates the next behavior. The purchase history includes, for example, online shopping history, purchase history at a store, and the like, but is not limited to such examples. The estimation unit estimates, for example, the next purchase behavior based on the user's past purchase history. The estimation unit can also analyze the user's purchase pattern and estimate the next behavior. The estimation unit can also comprehensively analyze the user's purchase history and estimate the next behavior. In this way, the next behavior can be estimated by analyzing the purchase history. A part or all of the above-mentioned processing in the estimation unit may be performed, for example, using AI, or may be performed without using AI. For example, the estimation unit can input the user's purchase history data to the generation AI and cause the generation AI to execute estimation of the next behavior.

[0043] The suggestion unit can adjust the level of detail of the proposal based on the user's past behavior history at the time of proposal. The suggestion unit adjusts the level of detail of the proposal based on the user's past behavior history, for example. The past behavior history includes, but is not limited to, for example, a movement history, a history of used apps, and a web browsing history. The suggestion unit makes a detailed proposal based on, for example, a user's past behavior. The suggestion unit can also analyze the user's past behavior history and make an optimal proposal. The suggestion unit can also adjust the level of detail of the proposal based on the user's behavior pattern. As a result, a more appropriate proposal can be made by adjusting the level of detail of the proposal based on the past behavior history. A part or all of the above-mentioned processing in the suggestion unit may be performed, for example, using AI, or may be performed without using AI. For example, the suggestion unit can input the user's past behavior history data to the generation AI and cause the generation AI to adjust the level of detail of the proposal.

[0044] The suggestion unit can apply different proposal algorithms depending on the user's current situation at the time of proposal. The suggestion unit applies different proposal algorithms depending on the user's current situation (e.g., location, time), for example. The current situation includes, but is not limited to, the current location, current activity, and surrounding environment, for example. For example, when the user is in a specific location, the suggestion unit makes a proposal suitable for that location. In addition, when the user is in a specific time period, the suggestion unit can also make a proposal suitable for that time period. In addition, the suggestion unit can comprehensively analyze the user's current situation and make an optimal proposal. This makes it possible to make a more appropriate proposal by applying different proposal algorithms depending on the current situation. Part or all of the above-mentioned processing in the suggestion unit may be performed, for example, using AI, or may be performed without using AI. For example, the suggestion unit can input the user's current situation data to the generation AI and cause the generation AI to apply different proposal algorithms.

[0045] The suggestion unit can suggest an appropriate action in consideration of the health data of the user at the time of suggestion. The suggestion unit, for example, suggests an optimal action in consideration of the health data of the user. The health data includes, for example, heart rate, number of steps, sleep data, etc., but is not limited to such examples. The suggestion unit, for example, suggests an action that allows the user to relax based on the heart rate data of the user. The suggestion unit can also suggest an action that encourages rest based on the sleep data of the user. The suggestion unit can also suggest moderate exercise based on the exercise data of the user. This makes it possible to suggest a more appropriate action by considering the health data. A part or all of the above-mentioned processing in the suggestion unit may be performed, for example, using AI, or may be performed without using AI. For example, the suggestion unit can input the health data of the user to the generation AI and cause the generation AI to execute the suggestion of the optimal action.

[0046] The suggestion unit can customize the proposed content by reflecting the user's past feedback at the time of suggestion. The suggestion unit customizes the proposed content by reflecting the user's past feedback, for example. The past feedback includes, but is not limited to, the user's evaluation, comments, and usage history. The suggestion unit customizes the proposed content based on, for example, the user's past feedback. The suggestion unit can also analyze the user's feedback and make an optimal suggestion. The suggestion unit can also adjust the proposed content by reflecting the user's past feedback. This makes it possible to make a more appropriate suggestion by reflecting the past feedback. A part or all of the above-mentioned processing in the suggestion unit may be performed, for example, using AI, or may be performed without using AI. For example, the suggestion unit can input the user's past feedback data to the generation AI and cause the generation AI to customize the proposed content.

[0047] The voice reception unit can select an optimal response by referring to the user's past voice command history when receiving the voice. The voice reception unit, for example, selects an optimal response by referring to the user's past voice command history. The voice command history includes, for example, previously used voice commands, frequency, success rate, etc., but is not limited to such examples. The voice reception unit selects an optimal response based on, for example, a voice command used by the user in the past. The voice reception unit can also analyze the user's voice command history and quickly respond to the most frequently used command. The voice reception unit can also provide an appropriate response by referring to the user's past voice command history. As a result, an optimal response can be provided by referring to the past voice command history. A part or all of the above-mentioned processing in the voice reception unit may be performed, for example, using AI, or may be performed without using AI. For example, the voice reception unit can input the user's voice command history data to the generation AI and cause the generation AI to select an optimal response.

[0048] The voice reception unit can select the optimal response method in consideration of the device information of the user when receiving the voice. The voice reception unit selects the optimal response method in consideration of, for example, the device information of the user. The device information includes, for example, the type of device, the OS, the usage status, etc., but is not limited to such examples. For example, when the user is using a smartphone, the voice reception unit provides a response method that matches the screen size. In addition, when the user is using a tablet, the voice reception unit can also provide a response method optimized for a large screen. In addition, when the user is using a smart watch, the voice reception unit can also provide a simple and highly visible response method. This makes it possible to provide an optimal response by considering the device information. Part or all of the above-mentioned processing in the voice reception unit may be performed, for example, using AI, or may be performed without using AI. For example, the voice reception unit can input the device information of the user to the generation AI and cause the generation AI to select the optimal response method.

[0049] The collection unit can select the optimal collection method by referring to the user's past visual information history at the time of collection. The collection unit, for example, selects the optimal collection method by referring to the user's past visual information history. The visual information history includes, for example, images and videos collected in the past, frequency, and purpose of use, but is not limited to such examples. The collection unit, for example, selects the optimal collection method based on visual information collected by the user in the past. The collection unit can also analyze the user's visual information history and quickly respond to the most frequently collected information. The collection unit can also refer to the user's past visual information history and provide an appropriate collection method. This makes it possible to optimally collect information by referring to the past visual information history. A part or all of the above-mentioned processing in the collection unit may be performed, for example, using AI, or may be performed without using AI. For example, the collection unit can input the user's visual information history data to the generation AI and cause the generation AI to select the optimal collection method.

[0050] The collection unit can collect optimal visual information in consideration of the geographical location information of the user at the time of collection. The collection unit, for example, collects optimal visual information in consideration of the geographical location information of the user. The geographical location information includes, for example, GPS data, Wi-Fi location information, and the like, but is not limited to such examples. For example, when the user is in a specific location, the collection unit collects visual information suitable for that location. In addition, when the user is traveling, the collection unit can also collect visual information of the travel destination. In addition, when the user is at work, the collection unit can also collect visual information related to work. This makes it possible to collect optimal visual information by considering the geographical location information. Part or all of the above-mentioned processing in the collection unit may be performed, for example, using AI, or may be performed without using AI. For example, the collection unit can input the geographical location information of the user to the generation AI and cause the generation AI to execute collection of optimal visual information.

[0051] The system according to the embodiment is not limited to the above-described example, and various modifications are possible, for example, as follows.

[0052] The generative AI system may further include an olfactory sensor unit that collects olfactory information of the user. The olfactory sensor unit, for example, detects odors around the user and collects the information. For example, when the user is cooking, the olfactory sensor unit detects the odor of ingredients and infers the next action. In addition, when the user is out, the olfactory sensor unit can also detect odors in the surrounding environment and infer the next action. Furthermore, the olfactory sensor unit can estimate the user's emotional state from the odor and suggest the next action based on that information. In this way, by collecting olfactory information, more accurate action inference is possible.

[0053] The generative AI system may further include a tactile sensor unit that collects tactile information of the user. The tactile sensor unit, for example, detects the texture and temperature of an object touched by the user and collects the information. For example, when the user touches a specific object, the tactile sensor unit detects the texture and temperature of the object and infers the next action. In addition, when the user is relaxed, the tactile sensor unit can collect information on the object being touched and infer the next action. Furthermore, the tactile sensor unit can estimate the user's emotional state from the sense of touch and suggest the next action based on the information. In this way, by collecting tactile information, more accurate action inference is possible.

[0054] The generative AI system may further include an olfactory sensor unit that collects olfactory information of the user. The olfactory sensor unit, for example, detects odors around the user and collects the information. For example, when the user is cooking, the olfactory sensor unit detects the odor of ingredients and infers the next action. In addition, when the user is out, the olfactory sensor unit can also detect odors in the surrounding environment and infer the next action. Furthermore, the olfactory sensor unit can estimate the user's emotional state from the odor and suggest the next action based on that information. In this way, by collecting olfactory information, more accurate action inference is possible.

[0055] The generative AI system may further include a tactile sensor unit that collects tactile information of the user. The tactile sensor unit, for example, detects the texture and temperature of an object touched by the user and collects the information. For example, when the user touches a specific object, the tactile sensor unit detects the texture and temperature of the object and infers the next action. In addition, when the user is relaxed, the tactile sensor unit can collect information on the object being touched and infer the next action. Furthermore, the tactile sensor unit can estimate the user's emotional state from the sense of touch and suggest the next action based on the information. In this way, by collecting tactile information, more accurate action inference is possible.

[0056] The generative AI system may further include an olfactory sensor unit that collects olfactory information of the user. The olfactory sensor unit, for example, detects odors around the user and collects the information. For example, when the user is cooking, the olfactory sensor unit detects the odor of ingredients and infers the next action. In addition, when the user is out, the olfactory sensor unit can also detect odors in the surrounding environment and infer the next action. Furthermore, the olfactory sensor unit can estimate the user's emotional state from the odor and suggest the next action based on that information. In this way, by collecting olfactory information, more accurate action inference is possible.

[0057] The generative AI system may further include a tactile sensor unit that collects tactile information of the user. The tactile sensor unit, for example, detects the texture and temperature of an object touched by the user and collects the information. For example, when the user touches a specific object, the tactile sensor unit detects the texture and temperature of the object and infers the next action. In addition, when the user is relaxed, the tactile sensor unit can collect information on the object being touched and infer the next action. Furthermore, the tactile sensor unit can estimate the user's emotional state from the sense of touch and suggest the next action based on the information. In this way, by collecting tactile information, more accurate action inference is possible.

[0058] The generative AI system may further include an olfactory sensor unit that collects olfactory information of the user. The olfactory sensor unit, for example, detects odors around the user and collects the information. For example, when the user is cooking, the olfactory sensor unit detects the odor of ingredients and infers the next action. In addition, when the user is out, the olfactory sensor unit can also detect odors in the surrounding environment and infer the next action. Furthermore, the olfactory sensor unit can estimate the user's emotional state from the odor and suggest the next action based on that information. In this way, by collecting olfactory information, more accurate action inference is possible.

[0059] The generative AI system may further include a tactile sensor unit that collects tactile information of the user. The tactile sensor unit, for example, detects the texture and temperature of an object touched by the user and collects the information. For example, when the user touches a specific object, the tactile sensor unit detects the texture and temperature of the object and infers the next action. In addition, when the user is relaxed, the tactile sensor unit can collect information on the object being touched and infer the next action. Furthermore, the tactile sensor unit can estimate the user's emotional state from the sense of touch and suggest the next action based on the information. In this way, by collecting tactile information, more accurate action inference is possible.

[0060] The generative AI system may further include an olfactory sensor unit that collects olfactory information of the user. The olfactory sensor unit, for example, detects odors around the user and collects the information. For example, when the user is cooking, the olfactory sensor unit detects the odor of ingredients and infers the next action. In addition, when the user is out, the olfactory sensor unit can also detect odors in the surrounding environment and infer the next action. Furthermore, the olfactory sensor unit can estimate the user's emotional state from the odor and suggest the next action based on that information. In this way, by collecting olfactory information, more accurate action inference is possible.

[0061] The generative AI system may further include a tactile sensor unit that collects tactile information of the user. The tactile sensor unit, for example, detects the texture and temperature of an object touched by the user and collects the information. For example, when the user touches a specific object, the tactile sensor unit detects the texture and temperature of the object and infers the next action. In addition, when the user is relaxed, the tactile sensor unit can collect information on the object being touched and infer the next action. Furthermore, the tactile sensor unit can estimate the user's emotional state from the sense of touch and suggest the next action based on the information. In this way, by collecting tactile information, more accurate action inference is possible.

[0062] The process flow of the first embodiment will be briefly described below.

[0063] Step 1: The learning unit learns the user's past information. The user's past information includes past behavioral history, purchasing history, browsing history, etc. The learning unit collects information such as the user's past actions, comments, schedules, etc., and the AI ​​learns from it. This makes it possible to understand the user's behavioral patterns. Step 2: The prediction unit analyzes the information before and after the user's action based on the information learned by the learning unit, and predicts the next action. Information before and after the action includes the situation immediately before the action and the results after the action. The prediction unit uses AI to analyze what information is related to the user before and after they take a specific action. This creates the foundation for predicting the next action. Step 3: The suggestion unit suggests to the user the next action predicted by the prediction unit. The next action includes the next action to be taken and predicted behavioral patterns. When the user asks, "What should I do next?", the suggestion unit uses AI to suggest the next action. This allows the user to move on to the next step smoothly without being confused about what to do.

[0064] (Example 2) The system according to the embodiment of the present invention is a generative AI system in which AI complements memory and supports the next action. This generative AI system learns the user's past information, analyzes information before and after the action, and predicts the next action. For example, information such as the user's past actions, remarks, and schedules is collected, and the AI ​​learns it. This makes it possible to grasp the user's behavioral patterns. Next, based on the learned information, the information before and after the user's action is analyzed. For example, the AI ​​analyzes what information is related before and after the user takes a specific action. This builds a foundation for predicting the next action. Furthermore, the predicted next action is suggested to the user. For example, when the user says, "What should I do next?", the AI ​​suggests the next action. This allows the user to move smoothly to the next step without being confused about what to do. It also has a function to collect visual information. For example, it grasps the situation around the user through a camera and predicts the next action based on that. This makes it possible to make more accurate suggestions. In this way, the generative AI system supports memory and functions as a partner to make life smoother. It is a reliable presence when the user is confused about what to do or forgets information. This allows the generative AI system to support the user's actions and make life smoother.

[0065] The generation AI system according to the embodiment includes a learning unit, an inference unit, and a suggestion unit. The learning unit learns the user's past information. The user's past information includes, for example, past behavior history, purchase history, browsing history, etc., but is not limited to such examples. The learning unit collects information such as the user's past actions, remarks, schedules, etc., and the AI ​​learns it. This makes it possible to grasp the user's behavioral pattern. The inference unit analyzes information before and after the user's action based on the information learned by the learning unit, and infers the next action. The information before and after the action includes, for example, the situation immediately before the action, the result after the action, etc., but is not limited to such examples. For example, the inference unit uses the AI ​​to analyze what information is related before and after the user takes a specific action. This lays the foundation for inferring the next action. The suggestion unit suggests the next action inferred by the inference unit to the user. The next action includes, for example, the next action to be taken, a predicted behavior pattern, etc., but is not limited to such examples. For example, when the user says, "What should I do next?", the AI ​​suggests the next action. This allows the user to smoothly proceed to the next step without being confused about what to do. As a result, the generative AI system according to the embodiment supports the user's actions and makes life smoother.

[0066] The learning unit learns the user's past information. The user's past information includes, but is not limited to, past behavioral history, purchase history, browsing history, etc. The learning unit collects information such as the user's past actions, remarks, and schedules, and the AI ​​learns it. Specifically, data is collected from the devices and applications used by the user and stored in a database on the cloud. For example, the user's location information and app usage history are collected from smartphone applications, browsing history and search queries are collected from web browsers, and communication content is collected from emails and messaging apps. These data are anonymized to protect privacy and are managed in a secure environment. The AI ​​uses these data to analyze the user's behavioral patterns and interests. For example, if a user tends to visit a specific place at a specific time of day, the AI ​​learns the pattern and predicts the next visit. In addition, the AI ​​uses the purchase history to understand what products the user is interested in and uses it to suggest related products. Furthermore, the learning unit updates the user's behavioral patterns over time and performs analysis based on the latest information. This makes it possible to respond appropriately even if the user's behavior or interests change. The learning department uses this data to create a profile of the user, laying the foundation for providing services tailored to individual needs and preferences.

[0067] The prediction unit analyzes information before and after the user's behavior based on the information learned by the learning unit, and predicts the next behavior. The information before and after the behavior includes, for example, the situation immediately before the behavior and the result after the behavior, but is not limited to such examples. In the prediction unit, for example, the AI ​​analyzes what information is related before and after the user takes a specific behavior. Specifically, the user's past behavior and its result are extracted from the database, and the AI ​​analyzes it. For example, information such as what behavior the user took after participating in a specific event, or what review the user left after purchasing a specific product is analyzed. The AI ​​uses these data to model the causal relationship of the behavior and predict the next action to be taken. Furthermore, the prediction unit grasps the user's current situation based on data collected in real time and predicts the next action. For example, the prediction unit predicts the next action to be taken taking into account the user's current location, time of day, surrounding environmental information, etc. In addition, the prediction unit can make more accurate predictions by referring to not only the user's past behavior patterns, but also the behavioral data of other users. This allows the prediction unit to predict the user's next action with high accuracy and lay the foundation for making appropriate suggestions.

[0068] The suggestion unit suggests the next action predicted by the prediction unit to the user. The next action includes, for example, the next action to be taken, a predicted behavior pattern, and the like, but is not limited to such examples. When the user says, for example, "What should I do next?", the suggestion unit uses the AI ​​to suggest the next action. Specifically, the AI ​​suggests the optimal action based on the user's current situation and past behavior patterns. For example, if the user wants to relax between work, the AI ​​suggests an appropriate relaxation method, taking into account past relaxation methods, the current time of day, and the surrounding environment. Also, if the user is shopping, the AI ​​suggests the optimal product based on the past purchase history and the current store inventory information. The suggestion unit collects user feedback and continuously improves the accuracy of the suggestions. For example, the AI ​​collects the satisfaction and results after the user performs the suggested action as feedback, and learns from this to improve the accuracy of the next suggestion. The suggestion unit can also customize the suggestions according to the user's preferences and needs. For example, if the user likes movies of a particular genre, the AI ​​preferentially suggests movies related to that genre. This allows the suggestion unit to suggest optimal actions to the user and smoothly support their life.

[0069] The voice reception unit receives the user's voice, and the estimation unit can estimate the user's next action when the voice reception unit receives the user's voice. The voice reception unit, for example, receives the user's voice with a microphone and converts it into text data using voice recognition technology. For example, the voice reception unit uses voice recognition software to automatically analyze the voice and save it as text. The voice reception unit can also build a system that recognizes the user's voice in real time and displays it as text data. For example, text is displayed on a screen at the same time as voice input. The voice reception unit also uses voice input to convert the contents dictated by the user into text and saves the text data. For example, voice recognition technology can also be used to perform highly accurate text conversion. This allows the voice reception unit to estimate the next action by receiving the user's voice. A part or all of the above-mentioned processing in the voice reception unit may be performed using AI, for example, or may be performed without using AI. For example, the voice reception unit can input voice data acquired by a microphone to a generation AI and have the generation AI execute conversion from voice data to text data.

[0070] The collection unit collects visual information, and the estimation unit can estimate the user's next behavior based on the information learned by the learning unit and the visual information collected by the collection unit. The visual information includes, for example, images, videos, real-time videos, etc., but is not limited to such examples. The collection unit, for example, uses a camera to capture the situation around the user and collects visual information. For example, the collection unit analyzes the images and videos captured by the camera to grasp the user's behavior pattern. The collection unit can also analyze the real-time video to grasp the user's current situation. For example, the collection unit analyzes the real-time video captured by the camera and monitors the user's behavior in real time. In this way, the collection unit can estimate the next behavior by collecting visual information. A part or all of the above-mentioned processing in the collection unit may be performed, for example, using AI, or may be performed without using AI. For example, the collection unit can input image data captured by a camera to the generation AI and cause the generation AI to execute analysis of visual information from the image data.

[0071] The learning unit can estimate the user's emotion and select learning data based on the estimated user's emotion. For example, the learning unit captures the user's facial expression with a camera and estimates the emotion using an emotion estimation algorithm. For example, the learning unit calculates an emotion score based on the change in facial expression. The learning unit can also record the user's voice and estimate the emotion using a voice analysis technique. For example, the learning unit analyzes the tone and speed of the voice and calculates an emotion score. The learning unit can also collect the user's biometric data (heart rate and electrodermal activity) with a sensor and estimate the emotion using an emotion estimation algorithm. For example, the learning unit calculates an emotion score based on the fluctuation of the heart rate. This enables more appropriate learning by selecting learning data based on the user's emotion. The emotion estimation is realized using an emotion estimation function using, for example, an emotion engine or a generation AI. The generation AI is, for example, a text generation AI (for example, LLM) or a multimodal generation AI, but is not limited to such examples. A part or all of the above-mentioned processing in the learning unit may be performed using, for example, an AI, or may be performed without using an AI. For example, the learning unit can input image data of a user captured by a camera into the generation AI and have the generation AI estimate the user's emotions.

[0072] The learning unit can classify the user's past behavior history by time period and learn behavior patterns in specific time periods. For example, the learning unit classifies the user's past behavior history by time period and learns behavior patterns in specific time periods. Time periods include, for example, morning, afternoon, night, and specific time ranges, but are not limited to such examples. For example, the learning unit learns the behavior patterns performed by the user in the morning time period and optimizes the morning routine. The learning unit can also learn the behavior patterns performed by the user in the lunch break time period and optimize how to spend the lunch break. The learning unit can also learn the behavior patterns performed by the user in the evening time period and optimize how to relax in the evening. As a result, by learning behavior patterns for each time period, it is possible to suggest optimal behavior for a specific time period. Part or all of the above-mentioned processing in the learning unit may be performed using, for example, AI, or may be performed without using AI. For example, the learning unit can input the user's behavior history data to the generation AI and cause the generation AI to execute learning of behavior patterns for each time period.

[0073] The learning unit can learn the user's health data in addition to the user's behavior history and improve the accuracy of the behavior pattern. The learning unit can learn the user's health data (e.g., heart rate, sleep pattern) in addition to the user's behavior history, for example, and improve the accuracy of the behavior pattern. The health data includes, for example, heart rate, number of steps, sleep data, etc., but is not limited to such examples. The learning unit can learn, for example, the user's heart rate data and optimize the behavior pattern during periods of high stress. The learning unit can also learn the user's sleep pattern and optimize the behavior pattern during lack of sleep. The learning unit can also learn the user's exercise data and optimize the behavior pattern after exercise. As a result, the accuracy of the behavior pattern is improved by learning the health data. Part or all of the above-mentioned processing in the learning unit may be performed, for example, using AI, or may be performed without using AI. For example, the learning unit can input the user's health data to the generation AI and cause the generation AI to execute the improvement of the accuracy of the behavior pattern.

[0074] The learning unit can estimate the user's emotion and adjust the frequency of learning based on the estimated user's emotion. For example, the learning unit captures the user's facial expression with a camera and estimates the emotion using an emotion estimation algorithm. For example, the learning unit calculates an emotion score based on the change in facial expression. The learning unit can also record the user's voice and estimate the emotion using a voice analysis technique. For example, the learning unit analyzes the tone and speed of the voice and calculates the emotion score. The learning unit can also collect the user's biometric data (heart rate and electrodermal activity) with a sensor and estimate the emotion using an emotion estimation algorithm. For example, the learning unit calculates the emotion score based on the fluctuation of the heart rate. This enables more appropriate learning by adjusting the frequency of learning based on the user's emotion. The emotion estimation is realized using an emotion estimation function using, for example, an emotion engine or a generation AI. The generation AI is, for example, a text generation AI (for example, LLM) or a multimodal generation AI, but is not limited to such examples. A part or all of the above-mentioned processing in the learning unit may be performed using, for example, an AI, or may be performed without using an AI. For example, the learning unit can input image data of a user captured by a camera into the generation AI and have the generation AI estimate the user's emotions.

[0075] The learning unit can analyze the user's social media activity and reflect it in the learning of the behavioral pattern. The learning unit, for example, analyzes the user's social media activity and reflects it in the learning of the behavioral pattern. The social media activity includes, for example, the content of the post, the number of likes, and comments, but is not limited to such examples. The learning unit, for example, learns the activity shared by the user on social media and reflects it in the behavioral pattern. The learning unit can also analyze the content of the user's social media post and learn the interests and concerns. The learning unit can also analyze the user's social media friendships and learn the factors that affect the behavioral pattern. In this way, the analysis of the social media activity can be reflected in the learning of the behavioral pattern. A part or all of the above-mentioned processing in the learning unit may be performed, for example, using AI, or may be performed without using AI. For example, the learning unit can input the user's social media data to the generation AI and cause the generation AI to execute the learning of the behavioral pattern.

[0076] The learning unit can learn a behavior pattern in a specific location by taking into account the geographical location information of the user. The learning unit, for example, learns a behavior pattern in a specific location by taking into account the geographical location information of the user. The geographical location information includes, for example, GPS data, Wi-Fi location information, and the like, but is not limited to such examples. The learning unit, for example, learns a behavior pattern when the user is in a specific location and proposes an optimal behavior in that location. The learning unit can also learn a behavior pattern when the user is traveling and propose an optimal behavior at the travel destination. The learning unit can also learn a behavior pattern when the user is at work and propose an behavior that improves work efficiency. In this way, the behavior pattern in a specific location can be learned by taking into account the geographical location information. A part or all of the above-mentioned processing in the learning unit may be performed, for example, using AI, or may be performed without using AI. For example, the learning unit can input the geographical location information of the user to the generation AI and cause the generation AI to execute learning of the behavior pattern.

[0077] The estimation unit can estimate the user's emotion and estimate the next action based on the estimated user's emotion. For example, the estimation unit captures the user's facial expression with a camera and estimates the emotion using an emotion estimation algorithm. For example, the estimation unit calculates an emotion score based on the change in facial expression. The estimation unit can also record the user's voice and estimate the emotion using a voice analysis technique. For example, the estimation unit analyzes the tone and speed of the voice and calculates an emotion score. The estimation unit can also collect the user's biometric data (heart rate and electrodermal activity) with a sensor and estimate the emotion using an emotion estimation algorithm. For example, the estimation unit calculates an emotion score based on the fluctuation of the heart rate. This makes it possible to suggest a more appropriate action by estimating the next action based on the user's emotion. The estimation of the emotion is realized using an emotion estimation function using, for example, an emotion engine or a generation AI. The generation AI is, for example, a text generation AI (for example, LLM) or a multimodal generation AI, but is not limited to such examples. A part or all of the above-mentioned processing in the estimation unit may be performed using, for example, an AI, or may be performed without using an AI. For example, the estimation unit can input image data of a user captured by a camera into the generation AI and have the generation AI estimate the user's emotions.

[0078] The estimation unit can compare the user's past behavior pattern with the current situation in real time and estimate the next behavior. The estimation unit, for example, compares the user's past behavior pattern with the current situation in real time and estimates the next behavior. The current situation includes, for example, a current location, a current activity, a surrounding environment, and the like, but is not limited to such examples. The estimation unit, for example, estimates the next behavior based on the behavior the user performed in the same situation in the past. The estimation unit can also analyze the user's current situation in real time and estimate the optimal behavior. The estimation unit can also compare the user's past behavior pattern with the current situation and estimate the next behavior. As a result, the next behavior can be estimated by comparing the past behavior pattern with the current situation. A part or all of the above-mentioned processing in the estimation unit may be performed, for example, using AI, or may be performed without using AI. For example, the estimation unit can input the user's past behavior pattern data and current situation data to the generation AI and cause the generation AI to execute estimation of the next behavior.

[0079] The estimation unit can estimate the next behavior based on the environmental information around the user in addition to the information before and after the user's behavior. The estimation unit estimates the next behavior by considering the environmental information around the user (e.g., weather, traffic conditions) in addition to the information before and after the user's behavior. The environmental information around the user includes, but is not limited to, weather information, surrounding sounds, temperature, and the like. The estimation unit estimates the next behavior based on, for example, weather information. The estimation unit can also estimate the next behavior based on traffic conditions. The estimation unit can also comprehensively analyze the environmental information around the user and estimate the next behavior. This allows the next behavior to be more accurately estimated by considering the environmental information around the user. A part or all of the above-mentioned processing in the estimation unit may be performed using, for example, an AI, or may be performed without using an AI. For example, the estimation unit can input weather information and traffic condition data to the generation AI and cause the generation AI to execute estimation of the next behavior.

[0080] The estimation unit can estimate the user's emotion and determine the priority of the estimation result based on the estimated user's emotion. For example, the estimation unit captures the user's facial expression with a camera and estimates the emotion using an emotion estimation algorithm. For example, the estimation unit calculates an emotion score based on the change in facial expression. The estimation unit can also record the user's voice and estimate the emotion using a voice analysis technique. For example, the estimation unit analyzes the tone and speed of the voice and calculates the emotion score. The estimation unit can also collect the user's biometric data (heart rate and electrodermal activity) with a sensor and estimate the emotion using an emotion estimation algorithm. For example, the estimation unit calculates the emotion score based on the fluctuation of the heart rate. As a result, the priority of the estimation result can be determined based on the user's emotion, so that a more appropriate action can be proposed. The emotion estimation is realized using an emotion estimation function using, for example, an emotion engine or a generation AI. The generation AI is, for example, a text generation AI (for example, LLM) or a multimodal generation AI, but is not limited to such examples. A part or all of the above-mentioned processing in the estimation unit may be performed using, for example, AI, or may be performed without using AI. For example, the estimation unit may input image data of a user taken by a camera to the generation AI and cause the generation AI to estimate the user's emotions.

[0081] The estimation unit can estimate the next action by taking into account the schedule information of the user. The estimation unit estimates the next action by taking into account the schedule information of the user, for example. The schedule information includes, but is not limited to, calendar events, reminders, task management information, and the like. The estimation unit estimates the next action based on the schedule of the user, for example. The estimation unit can also estimate the optimal action by taking into account the schedule of the user. The estimation unit can also estimate the next action based on the schedule information of the user. As a result, the next action can be more accurately estimated by taking into account the schedule information. A part or all of the above-mentioned processing in the estimation unit may be performed, for example, using AI, or may be performed without using AI. For example, the estimation unit can input the schedule information of the user to the generation AI and cause the generation AI to execute estimation of the next action.

[0082] The estimation unit can analyze the user's past purchase history and estimate the next behavior. The estimation unit, for example, analyzes the user's past purchase history and estimates the next behavior. The purchase history includes, for example, online shopping history, purchase history at a store, and the like, but is not limited to such examples. The estimation unit estimates, for example, the next purchase behavior based on the user's past purchase history. The estimation unit can also analyze the user's purchase pattern and estimate the next behavior. The estimation unit can also comprehensively analyze the user's purchase history and estimate the next behavior. In this way, the next behavior can be estimated by analyzing the purchase history. A part or all of the above-mentioned processing in the estimation unit may be performed, for example, using AI, or may be performed without using AI. For example, the estimation unit can input the user's purchase history data to the generation AI and cause the generation AI to execute estimation of the next behavior.

[0083] The suggestion unit can estimate the user's emotion and adjust the expression method of the proposal based on the estimated user's emotion. For example, the suggestion unit captures the user's facial expression with a camera and estimates the emotion using an emotion estimation algorithm. For example, the suggestion unit calculates an emotion score based on the change in facial expression. The suggestion unit can also record the user's voice and estimate the emotion using a voice analysis technique. For example, the suggestion unit analyzes the tone and speed of the voice and calculates an emotion score. The suggestion unit can also collect the user's biometric data (heart rate and electrodermal activity) with a sensor and estimate the emotion using an emotion estimation algorithm. For example, the suggestion unit calculates an emotion score based on the fluctuation of the heart rate. This enables a more appropriate proposal by adjusting the expression method of the proposal based on the user's emotion. The emotion estimation is realized using an emotion estimation function using, for example, an emotion engine or a generation AI. The generation AI is a text generation AI (for example, LLM) or a multimodal generation AI, but is not limited to such examples. A part or all of the above-mentioned processing in the suggestion unit may be performed using, for example, AI, or may be performed without using AI. For example, the suggestion unit may input image data of a user captured by a camera to the generation AI and cause the generation AI to estimate the user's emotions.

[0084] The suggestion unit can adjust the level of detail of the proposal based on the user's past behavior history at the time of proposal. The suggestion unit adjusts the level of detail of the proposal based on the user's past behavior history, for example. The past behavior history includes, but is not limited to, for example, a movement history, a history of used apps, and a web browsing history. The suggestion unit makes a detailed proposal based on, for example, a user's past behavior. The suggestion unit can also analyze the user's past behavior history and make an optimal proposal. The suggestion unit can also adjust the level of detail of the proposal based on the user's behavior pattern. As a result, a more appropriate proposal can be made by adjusting the level of detail of the proposal based on the past behavior history. A part or all of the above-mentioned processing in the suggestion unit may be performed, for example, using AI, or may be performed without using AI. For example, the suggestion unit can input the user's past behavior history data to the generation AI and cause the generation AI to adjust the level of detail of the proposal.

[0085] The suggestion unit can apply different proposal algorithms depending on the user's current situation at the time of proposal. The suggestion unit applies different proposal algorithms depending on the user's current situation (e.g., location, time), for example. The current situation includes, but is not limited to, the current location, current activity, and surrounding environment, for example. For example, when the user is in a specific location, the suggestion unit makes a proposal suitable for that location. In addition, when the user is in a specific time period, the suggestion unit can also make a proposal suitable for that time period. In addition, the suggestion unit can comprehensively analyze the user's current situation and make an optimal proposal. This makes it possible to make a more appropriate proposal by applying different proposal algorithms depending on the current situation. Part or all of the above-mentioned processing in the suggestion unit may be performed, for example, using AI, or may be performed without using AI. For example, the suggestion unit can input the user's current situation data to the generation AI and cause the generation AI to apply different proposal algorithms.

[0086] The suggestion unit can estimate the user's emotion and determine the priority of suggestions based on the estimated user's emotion. For example, the suggestion unit captures the user's facial expression with a camera and estimates the emotion using an emotion estimation algorithm. For example, the suggestion unit calculates an emotion score based on the change in facial expression. The suggestion unit can also record the user's voice and estimate the emotion using a voice analysis technique. For example, the suggestion unit analyzes the tone and speed of the voice and calculates an emotion score. The suggestion unit can also collect the user's biometric data (heart rate and electrodermal activity) with a sensor and estimate the emotion using an emotion estimation algorithm. For example, the suggestion unit calculates an emotion score based on the fluctuation of the heart rate. This enables more appropriate suggestions by determining the priority of suggestions based on the user's emotion. The emotion estimation is realized using an emotion estimation function using, for example, an emotion engine or a generation AI. The generation AI is, for example, a text generation AI (for example, LLM) or a multimodal generation AI, but is not limited to such examples. A part or all of the above-mentioned processing in the suggestion unit may be performed using, for example, an AI, or may be performed without using an AI. For example, the suggestion unit can input image data of a user captured by a camera into the generation AI and have the generation AI estimate the user's emotions.

[0087] The suggestion unit can suggest an appropriate action in consideration of the health data of the user at the time of suggestion. The suggestion unit, for example, suggests an optimal action in consideration of the health data of the user. The health data includes, for example, heart rate, number of steps, sleep data, etc., but is not limited to such examples. The suggestion unit, for example, suggests an action that allows the user to relax based on the heart rate data of the user. The suggestion unit can also suggest an action that encourages rest based on the sleep data of the user. The suggestion unit can also suggest moderate exercise based on the exercise data of the user. This makes it possible to suggest a more appropriate action by considering the health data. A part or all of the above-mentioned processing in the suggestion unit may be performed, for example, using AI, or may be performed without using AI. For example, the suggestion unit can input the health data of the user to the generation AI and cause the generation AI to execute the suggestion of the optimal action.

[0088] The suggestion unit can customize the proposed content by reflecting the user's past feedback at the time of suggestion. The suggestion unit customizes the proposed content by reflecting the user's past feedback, for example. The past feedback includes, but is not limited to, the user's evaluation, comments, and usage history. The suggestion unit customizes the proposed content based on, for example, the user's past feedback. The suggestion unit can also analyze the user's feedback and make an optimal suggestion. The suggestion unit can also adjust the proposed content by reflecting the user's past feedback. This makes it possible to make a more appropriate suggestion by reflecting the past feedback. A part or all of the above-mentioned processing in the suggestion unit may be performed, for example, using AI, or may be performed without using AI. For example, the suggestion unit can input the user's past feedback data to the generation AI and cause the generation AI to customize the proposed content.

[0089] The voice reception unit can estimate the user's emotion and adjust the response method of the voice reception based on the estimated user's emotion. For example, the voice reception unit captures the user's facial expression with a camera and estimates the emotion using an emotion estimation algorithm. For example, the voice reception unit calculates an emotion score based on the change in facial expression. The voice reception unit can also record the user's voice and estimate the emotion using a voice analysis technique. For example, the voice reception unit analyzes the tone and speed of the voice and calculates an emotion score. The voice reception unit can also collect the user's biometric data (heart rate and electrodermal activity) with a sensor and estimate the emotion using an emotion estimation algorithm. For example, the voice reception unit calculates an emotion score based on the fluctuation of the heart rate. This allows a more appropriate response by adjusting the response method of the voice reception based on the user's emotion. The emotion estimation is realized using an emotion estimation function using, for example, an emotion engine or a generation AI. The generation AI is a text generation AI (for example, LLM) or a multimodal generation AI, but is not limited to such examples. A part or all of the above-mentioned processing in the voice reception unit may be performed using, for example, AI, or may be performed without using AI. For example, the voice reception unit may input image data of a user captured by a camera to the generation AI, and cause the generation AI to estimate the user's emotions.

[0090] The voice reception unit can select an optimal response by referring to the user's past voice command history when receiving the voice. The voice reception unit, for example, selects an optimal response by referring to the user's past voice command history. The voice command history includes, for example, previously used voice commands, frequency, success rate, etc., but is not limited to such examples. The voice reception unit selects an optimal response based on, for example, a voice command used by the user in the past. The voice reception unit can also analyze the user's voice command history and quickly respond to the most frequently used command. The voice reception unit can also provide an appropriate response by referring to the user's past voice command history. As a result, an optimal response can be provided by referring to the past voice command history. A part or all of the above-mentioned processing in the voice reception unit may be performed, for example, using AI, or may be performed without using AI. For example, the voice reception unit can input the user's voice command history data to the generation AI and cause the generation AI to select an optimal response.

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

[0092] The voice reception unit can select the optimal response method in consideration of the device information of the user when receiving the voice. The voice reception unit selects the optimal response method in consideration of, for example, the device information of the user. The device information includes, for example, the type of device, the OS, the usage status, etc., but is not limited to such examples. For example, when the user is using a smartphone, the voice reception unit provides a response method that matches the screen size. In addition, when the user is using a tablet, the voice reception unit can also provide a response method optimized for a large screen. In addition, when the user is using a smart watch, the voice reception unit can also provide a simple and highly visible response method. This makes it possible to provide an optimal response by considering the device information. Part or all of the above-mentioned processing in the voice reception unit may be performed, for example, using AI, or may be performed without using AI. For example, the voice reception unit can input the device information of the user to the generation AI and cause the generation AI to select the optimal response method.

[0093] The collection unit can estimate the user's emotion and adjust the method of collecting visual information based on the estimated user's emotion. For example, the collection unit captures the user's facial expression with a camera and estimates the emotion using an emotion estimation algorithm. For example, the collection unit calculates an emotion score based on the change in facial expression. The collection unit can also record the user's voice and estimate the emotion using a voice analysis technique. For example, the collection unit analyzes the tone and speed of the voice and calculates the emotion score. The collection unit can also collect the user's biometric data (heart rate and electrodermal activity) with a sensor and estimate the emotion using an emotion estimation algorithm. For example, the collection unit calculates the emotion score based on the fluctuation of the heart rate. This enables more appropriate information collection by adjusting the method of collecting visual information based on the user's emotion. The emotion estimation is realized using an emotion estimation function using, for example, an emotion engine or a generation AI. The generation AI is, for example, a text generation AI (for example, LLM) or a multimodal generation AI, but is not limited to such examples. A part or all of the above-mentioned processing in the collection unit may be performed using, for example, AI, or may be performed without using AI. For example, the collection unit may input image data of a user taken by a camera to the generation AI and cause the generation AI to estimate the user's emotions.

[0094] The collection unit can select the optimal collection method by referring to the user's past visual information history at the time of collection. The collection unit, for example, selects the optimal collection method by referring to the user's past visual information history. The visual information history includes, for example, images and videos collected in the past, frequency, and purpose of use, but is not limited to such examples. The collection unit, for example, selects the optimal collection method based on visual information collected by the user in the past. The collection unit can also analyze the user's visual information history and quickly respond to the most frequently collected information. The collection unit can also refer to the user's past visual information history and provide an appropriate collection method. This makes it possible to optimally collect information by referring to the past visual information history. A part or all of the above-mentioned processing in the collection unit may be performed, for example, using AI, or may be performed without using AI. For example, the collection unit can input the user's visual information history data to the generation AI and cause the generation AI to select the optimal collection method.

[0095] The collection unit can estimate the user's emotion and determine the priority of the visual information to be collected based on the estimated user's emotion. For example, the collection unit captures the user's facial expression with a camera and estimates the emotion using an emotion estimation algorithm. For example, the collection unit calculates an emotion score based on the change in the facial expression. The collection unit can also record the user's voice and estimate the emotion using a voice analysis technique. For example, the collection unit analyzes the tone and speed of the voice and calculates the emotion score. The collection unit can also collect the user's biometric data (heart rate and electrodermal activity) with a sensor and estimate the emotion using an emotion estimation algorithm. For example, the collection unit calculates the emotion score based on the fluctuation of the heart rate. This enables more appropriate information collection by determining the priority of the visual information to be collected based on the user's emotion. The emotion estimation is realized using an emotion estimation function using, for example, an emotion engine or a generation AI. The generation AI is, for example, a text generation AI (for example, LLM) or a multimodal generation AI, but is not limited to such examples. A part or all of the above-mentioned processing in the collection unit may be performed using, for example, AI, or may be performed without using AI. For example, the collection unit may input image data of a user taken by a camera to the generation AI and cause the generation AI to estimate the user's emotions.

[0096] The collection unit can collect optimal visual information in consideration of the geographical location information of the user at the time of collection. The collection unit, for example, collects optimal visual information in consideration of the geographical location information of the user. The geographical location information includes, for example, GPS data, Wi-Fi location information, and the like, but is not limited to such examples. For example, when the user is in a specific location, the collection unit collects visual information suitable for that location. In addition, when the user is traveling, the collection unit can also collect visual information of the travel destination. In addition, when the user is at work, the collection unit can also collect visual information related to work. This makes it possible to collect optimal visual information by considering the geographical location information. Part or all of the above-mentioned processing in the collection unit may be performed, for example, using AI, or may be performed without using AI. For example, the collection unit can input the geographical location information of the user to the generation AI and cause the generation AI to execute collection of optimal visual information.

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

[0098] The generative AI system may further include an olfactory sensor unit that collects olfactory information of the user. The olfactory sensor unit, for example, detects odors around the user and collects the information. For example, when the user is cooking, the olfactory sensor unit detects the odor of ingredients and infers the next action. In addition, when the user is out, the olfactory sensor unit can also detect odors in the surrounding environment and infer the next action. Furthermore, the olfactory sensor unit can estimate the user's emotional state from the odor and suggest the next action based on that information. In this way, by collecting olfactory information, more accurate action inference is possible.

[0099] The generative AI system may further include a tactile sensor unit that collects tactile information of the user. The tactile sensor unit, for example, detects the texture and temperature of an object touched by the user and collects the information. For example, when the user touches a specific object, the tactile sensor unit detects the texture and temperature of the object and infers the next action. In addition, when the user is relaxed, the tactile sensor unit can collect information on the object being touched and infer the next action. Furthermore, the tactile sensor unit can estimate the user's emotional state from the sense of touch and suggest the next action based on the information. In this way, by collecting tactile information, more accurate action inference is possible.

[0100] The generative AI system may further include an olfactory sensor unit that collects olfactory information of the user. The olfactory sensor unit, for example, detects odors around the user and collects the information. For example, when the user is cooking, the olfactory sensor unit detects the odor of ingredients and infers the next action. In addition, when the user is out, the olfactory sensor unit can also detect odors in the surrounding environment and infer the next action. Furthermore, the olfactory sensor unit can estimate the user's emotional state from the odor and suggest the next action based on that information. In this way, by collecting olfactory information, more accurate action inference is possible.

[0101] The generative AI system may further include a tactile sensor unit that collects tactile information of the user. The tactile sensor unit, for example, detects the texture and temperature of an object touched by the user and collects the information. For example, when the user touches a specific object, the tactile sensor unit detects the texture and temperature of the object and infers the next action. In addition, when the user is relaxed, the tactile sensor unit can collect information on the object being touched and infer the next action. Furthermore, the tactile sensor unit can estimate the user's emotional state from the sense of touch and suggest the next action based on the information. In this way, by collecting tactile information, more accurate action inference is possible.

[0102] The generative AI system may further include an olfactory sensor unit that collects olfactory information of the user. The olfactory sensor unit, for example, detects odors around the user and collects the information. For example, when the user is cooking, the olfactory sensor unit detects the odor of ingredients and infers the next action. In addition, when the user is out, the olfactory sensor unit can also detect odors in the surrounding environment and infer the next action. Furthermore, the olfactory sensor unit can estimate the user's emotional state from the odor and suggest the next action based on that information. In this way, by collecting olfactory information, more accurate action inference is possible.

[0103] The generative AI system may further include a tactile sensor unit that collects tactile information of the user. The tactile sensor unit, for example, detects the texture and temperature of an object touched by the user and collects the information. For example, when the user touches a specific object, the tactile sensor unit detects the texture and temperature of the object and infers the next action. In addition, when the user is relaxed, the tactile sensor unit can collect information on the object being touched and infer the next action. Furthermore, the tactile sensor unit can estimate the user's emotional state from the sense of touch and suggest the next action based on the information. In this way, by collecting tactile information, more accurate action inference is possible.

[0104] The generative AI system may further include an olfactory sensor unit that collects olfactory information of the user. The olfactory sensor unit, for example, detects odors around the user and collects the information. For example, when the user is cooking, the olfactory sensor unit detects the odor of ingredients and infers the next action. In addition, when the user is out, the olfactory sensor unit can also detect odors in the surrounding environment and infer the next action. Furthermore, the olfactory sensor unit can estimate the user's emotional state from the odor and suggest the next action based on that information. In this way, by collecting olfactory information, more accurate action inference is possible.

[0105] The generative AI system may further include a tactile sensor unit that collects tactile information of the user. The tactile sensor unit, for example, detects the texture and temperature of an object touched by the user and collects the information. For example, when the user touches a specific object, the tactile sensor unit detects the texture and temperature of the object and infers the next action. In addition, when the user is relaxed, the tactile sensor unit can collect information on the object being touched and infer the next action. Furthermore, the tactile sensor unit can estimate the user's emotional state from the sense of touch and suggest the next action based on the information. In this way, by collecting tactile information, more accurate action inference is possible.

[0106] The generative AI system may further include an olfactory sensor unit that collects olfactory information of the user. The olfactory sensor unit, for example, detects odors around the user and collects the information. For example, when the user is cooking, the olfactory sensor unit detects the odor of ingredients and infers the next action. In addition, when the user is out, the olfactory sensor unit can also detect odors in the surrounding environment and infer the next action. Furthermore, the olfactory sensor unit can estimate the user's emotional state from the odor and suggest the next action based on that information. In this way, by collecting olfactory information, more accurate action inference is possible.

[0107] The generative AI system may further include a tactile sensor unit that collects tactile information of the user. The tactile sensor unit, for example, detects the texture and temperature of an object touched by the user and collects the information. For example, when the user touches a specific object, the tactile sensor unit detects the texture and temperature of the object and infers the next action. In addition, when the user is relaxed, the tactile sensor unit can collect information on the object being touched and infer the next action. Furthermore, the tactile sensor unit can estimate the user's emotional state from the sense of touch and suggest the next action based on the information. In this way, by collecting tactile information, more accurate action inference is possible.

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

[0109] Step 1: The learning unit learns the user's past information. The user's past information includes past behavioral history, purchasing history, browsing history, etc. The learning unit collects information such as the user's past actions, comments, schedules, etc., and the AI ​​learns from it. This makes it possible to understand the user's behavioral patterns. Step 2: The prediction unit analyzes the information before and after the user's action based on the information learned by the learning unit, and predicts the next action. Information before and after the action includes the situation immediately before the action and the results after the action. The prediction unit uses AI to analyze what information is related to the user before and after they take a specific action. This creates the foundation for predicting the next action. Step 3: The suggestion unit suggests to the user the next action predicted by the prediction unit. The next action includes the next action to be taken and predicted behavioral patterns. When the user asks, "What should I do next?", the suggestion unit uses AI to suggest the next action. This allows the user to move on to the next step smoothly without being confused about what to do.

[0110] The specific processing unit 290 transmits the result of the specific processing to the smart device 14. In the smart device 14, the control unit 46A causes the output device 40 to output the result of the specific processing. The microphone 38B acquires a voice indicating a user input for the result of the specific processing. The control unit 46A transmits the voice data indicating the user input acquired by the microphone 38B to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the voice data.

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

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

[0113] For example, the learning unit is realized by the control unit 46A of the smart device 14 or the specific processing unit 290 of the data processing device 12. For example, the learning unit collects the user's past actions and remarks using the camera 42 and microphone 38B of the smart device 14, and the control unit 46A learns them. The estimation unit is realized by, for example, the specific processing unit 290 of the data processing device 12, and analyzes information before and after the user's action based on the learned information, and estimates the next action. The suggestion unit is realized by, for example, the control unit 46A of the smart device 14 or the specific processing unit 290 of the data processing device 12, and suggests the estimated next action to the user. The correspondence between each unit and the device or control unit is not limited to the above-mentioned example, and various changes are possible.

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

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

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

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

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

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

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

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

[0122] The processor 28 reads the specific processing program 56 from the storage 32, and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

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

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

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

[0126] The specific processing unit 290 transmits the result of the specific processing to the smart glasses 214. In the smart glasses 214, the control unit 46A causes the speaker 240 to output the result of the specific processing. The microphone 238 acquires a voice indicating a user input for the result of the specific processing. The control unit 46A transmits the voice data indicating the user input acquired by the microphone 238 to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the voice data.

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

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

[0129] For example, the learning unit is realized by the control unit 46A of the smart glasses 214 or the specific processing unit 290 of the data processing device 12. For example, the learning unit collects the user's past actions and remarks using the camera 42 and microphone 238 of the smart glasses 214, and the control unit 46A learns them. The estimation unit is realized by, for example, the specific processing unit 290 of the data processing device 12, and analyzes information before and after the user's action based on the learned information, and estimates the next action. The suggestion unit is realized by, for example, the control unit 46A of the smart glasses 214 or the specific processing unit 290 of the data processing device 12, and suggests the estimated next action to the user. The correspondence between each unit and the device or control unit is not limited to the above-mentioned example, and various changes are possible.

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

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

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

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

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

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

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

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

[0138] The processor 28 reads the specific processing program 56 from the storage 32, and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

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

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

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

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

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

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

[0145] For example, the learning unit is realized by the control unit 46A of the headset type terminal 314 or the specific processing unit 290 of the data processing device 12. For example, the learning unit collects the user's past actions and remarks using the camera 42 and microphone 238 of the headset type terminal 314, and the control unit 46A learns them. The estimation unit is realized by, for example, the specific processing unit 290 of the data processing device 12, and analyzes information before and after the user's action based on the learned information, and estimates the next action. The suggestion unit is realized by, for example, the control unit 46A of the headset type terminal 314 or the specific processing unit 290 of the data processing device 12, and suggests the estimated next action to the user. The correspondence between each unit and the device or control unit is not limited to the above-mentioned example, and various changes are possible.

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

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

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

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

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

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

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

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

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

[0155] The processor 28 reads the specific processing program 56 from the storage 32, and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

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

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

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

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

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

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

[0162] For example, the learning unit is realized by the control unit 46A of the robot 414 or the specific processing unit 290 of the data processing device 12. For example, the learning unit collects the user's past actions and remarks using the camera 42 and microphone 238 of the robot 414, and the control unit 46A learns them. The estimation unit is realized by, for example, the specific processing unit 290 of the data processing device 12, and analyzes information before and after the user's action based on the learned information, and estimates the next action. The suggestion unit is realized by, for example, the control unit 46A of the robot 414 or the specific processing unit 290 of the data processing device 12, and suggests the estimated next action to the user. The correspondence between each unit and the device or control unit is not limited to the above-mentioned example, and various changes are possible.

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

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

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

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

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

[0168] The emotion map defines two emotions that promote learning. The first is the negative emotion around the middle of "repentance" or "remorse" on the situation side. In other words, this is when the robot experiences negative emotions such as "I never want to feel this way again" or "I don't want to be scolded again." The other is the positive emotion around "desire" on the response side. In other words, this is when the robot has positive feelings such as "I want more" or "I want to know more."

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

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

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

[0172] In addition, the specific processing program 56 may be stored in a storage device such as a server connected to the data processing device 12 via the network 54, and the specific processing program 56 may be downloaded and installed on the computer 22 upon request from the data processing device 12.

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

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

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

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

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

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

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

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

[0181] (Appendix 1) A learning unit that learns past information of a user; a prediction unit that analyzes information before and after the user's behavior based on the information learned by the learning unit and predicts the user's next behavior; A suggestion unit that suggests to the user the next action predicted by the prediction unit. A system characterized by: (Appendix 2) A voice receiving unit is provided for receiving a user's voice, The estimation unit is When the voice of the user is received by the voice receiving unit, the next action of the user is predicted. 2. The system of claim 1, (Appendix 3) A collection unit for collecting visual information, The estimation unit is Predicting a next action of the user based on the information learned by the learning unit and the visual information collected by the collecting unit. 2. The system of claim 1, (Appendix 4) The learning unit is Estimate the user's emotions and select learning data based on the estimated user emotions. 2. The system of claim 1, (Appendix 5) The learning unit is Classify users' past behavioral history by time period and learn behavioral patterns during specific time periods 2. The system of claim 1, (Appendix 6) The learning unit is In addition to the user's behavioral history, the system learns the user's health data to improve the accuracy of behavioral patterns. 2. The system of claim 1, (Appendix 7) The learning unit is Infer user emotions and adjust the frequency of learning based on the estimated user emotions. 2. The system of claim 1, (Appendix 8) The learning unit is Analyze users' social media activity and use it to learn behavioral patterns 2. The system of claim 1, (Appendix 9) The learning unit is Learn behavioral patterns in specific locations based on the user's geographic location 2. The system of claim 1, (Appendix 10) The estimation unit is Infer user emotions and predict next actions based on the inferred user emotions 2. The system of claim 1, (Appendix 11) The estimation unit is Compare the user's past behavior patterns with the current situation in real time to predict the next action 2. The system of claim 1, (Appendix 12) The estimation unit is In addition to information about the user's actions before and after the action, the system predicts the user's next action based on information about the user's surrounding environment. 2. The system of claim 1, (Appendix 13) The estimation unit is Inferring user emotions and prioritizing inference results based on the inferred user emotions 2. The system of claim 1, (Appendix 14) The estimation unit is Given the user's schedule information, infer what they'll do next 2. The system of claim 1, (Appendix 15) The estimation unit is Analyze users' past purchase history and predict their next actions 2. The system of claim 1, (Appendix 16) The suggestion unit, Infer user emotions and adjust the presentation of suggestions based on the inferred user emotions 2. The system of claim 1, (Appendix 17) The suggestion unit, When making suggestions, adjust the level of detail based on the user's past behavior 2. The system of claim 1, (Appendix 18) The suggestion unit, When making suggestions, apply different suggestion algorithms depending on the user's current situation 2. The system of claim 1, (Appendix 19) The suggestion unit, Estimate user sentiment and prioritize suggestions based on the estimated user sentiment 2. The system of claim 1, (Appendix 20) The suggestion unit, When making suggestions, the system takes into account the user's health data to suggest appropriate actions. 2. The system of claim 1, (Appendix 21) The suggestion unit, When making suggestions, customize the suggestions based on the user's past feedback 2. The system of claim 1, (Appendix 22) The voice receiving unit is To estimate a user's emotion and adjust a response method of a voice reception based on the estimated user's emotion. 3. The system of claim 2, (Appendix 23) The voice receiving unit is When receiving voice commands, the system selects the optimal response by referring to the user's past voice command history. 3. The system of claim 2, (Appendix 24) The voice receiving unit is Estimate user emotions and prioritize voice commands based on the estimated user emotions 3. The system of claim 2, (Appendix 25) The voice receiving unit is When accepting a voice call, the optimal response method is selected taking into account the user's device information. 3. The system of claim 2, (Appendix 26) The collecting unit includes: To estimate a user's emotion and adjust a method of collecting visual information based on the estimated user's emotion. 4. The system of claim 3. (Appendix 27) The collecting unit includes: When collecting data, the optimal collection method is selected by referring to the user's past visual information history. 4. The system of claim 3. (Appendix 28) The collecting unit includes: Estimate the user's emotions and prioritize the visual information to be collected based on the estimated user's emotions. 4. The system of claim 3. (Appendix 29) The collecting unit includes: At the time of collection, the optimal visual information is collected by taking into account the user's geographic location information. 4. The system of claim 3. [Explanation of symbols]

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

Claims

1. A learning unit that learns past information of a user; an estimation unit that analyzes information before and after the user's behavior based on the information learned by the learning unit and estimates the user's next behavior; A suggestion unit that suggests to the user the next action predicted by the prediction unit. A system characterized by:

2. a voice receiving unit for receiving a voice of the user, The estimation unit is When the voice of the user is received by the voice receiving unit, the next action of the user is predicted.

2. The system of claim 1 .

3. A collection unit for collecting visual information, The estimation unit is Predicting a next action of the user based on the information learned by the learning unit and the visual information collected by the collecting unit.

2. The system of claim 1 .

4. The learning unit is The user's emotion is estimated, and learning data is selected based on the estimated user's emotion.

2. The system of claim 1 .

5. The learning unit is Classifying the user's past behavioral history by time period and learning behavioral patterns during specific time periods 2. The system of claim 1 .

6. The learning unit is In addition to the user's behavioral history, the system learns the user's health data to improve the accuracy of the behavioral pattern.

2. The system of claim 1 .

7. The learning unit is Estimating the user's emotion and adjusting the frequency of learning based on the estimated user's emotion.

2. The system of claim 1 .

8. The learning unit is Analyzing the user's social media activity and incorporating it into learning behavioral patterns 2. The system of claim 1 .

9. The learning unit is Learning behavioral patterns in specific locations based on the geographic location information of the user.

2. The system of claim 1 .

10. The estimation unit is Estimating the user's emotion and predicting a next action based on the estimated user's emotion.

2. The system of claim 1 .

Images