system

Abstract

The system according to this embodiment aims to learn the user's interests and behavior and provide suggestions and notifications at the optimal timing. [Solution] The system according to the embodiment comprises a reception unit, an analysis unit, a learning unit, a suggestion unit, and a support unit. The reception unit receives voice input from the user. The analysis unit analyzes the voice input received by the reception unit. The learning unit learns the user's interests and behavior based on the information analyzed by the analysis unit. The suggestion unit makes suggestions and notifications at the optimal timing based on the information learned by the learning unit. The support unit provides personalized support based on the information suggested by the suggestion unit.

Description

Technical Field

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

Background Art

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

Prior Art Documents

Patent Documents

[0003]

Patent Document 1

Summary of the Invention

Problems to be Solved by the Invention

[0004] In the conventional technology, learning the user's interests and behaviors and making proposals and notifications at the optimal timing have not been sufficiently carried out, and there is room for improvement.

[0005] The system according to the embodiment aims to learn the user's interests and behaviors and make proposals and notifications at the optimal timing.

Means for Solving the Problems

[0006] The system according to this embodiment comprises a reception unit, an analysis unit, a learning unit, a suggestion unit, and a support unit. The reception unit receives voice input from the user. The analysis unit analyzes the voice input received by the reception unit. The learning unit learns the user's interests and behaviors based on the information analyzed by the analysis unit. The suggestion unit makes suggestions and notifications at the optimal timing based on the information learned by the learning unit. The support unit provides personalized support based on the information suggested by the suggestion unit. [Effects of the Invention]

[0007] The system according to this embodiment can learn the user's interests and behavior and make suggestions and notifications at the optimal timing. [Brief explanation of the drawing]

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

[0028] (Example of form 1) The voice platform according to an embodiment of the present invention is a system that combines a generative AI and an AI agent. This voice platform aims to streamline information gathering and task management for users using voice. Users input questions and instructions by voice, and the generative AI analyzes the voice to process appropriate information and tasks. The generative AI learns the user's interests and behaviors and provides suggestions, notifications, reminders, and personalized support at the optimal time. This expands advertising revenue and service usage opportunities and provides sustainable value that improves the customer experience. For example, a user gives instructions by voice such as "What's the weather like today?" or "Remind me of tomorrow's meeting." This voice input is analyzed by the generative AI, and appropriate information and tasks are processed. The generative AI learns the user's interests and behaviors and automatically notifies the user when they need weather information. Also, if a user repeatedly performs a particular task, it makes suggestions to streamline that task. The generative AI provides personalized support to the user. For example, if a user is working on a particular project, it provides information and resources related to that project. It also manages the user's schedule and reminds them of important events and tasks. This platform also includes mechanisms to expand advertising revenue and service usage opportunities. For example, if a user shows interest in a particular product or service, it will provide relevant advertisements and promotions based on that information. This increases advertising revenue while also providing users with useful information. Furthermore, this platform offers various functions to enrich users' lives. For example, if a user is interested in health management, the generative AI will provide health-related information and advice. It will also provide information on areas of the user's hobbies and interests, supporting a more fulfilling daily life. In this way, the voice platform, which combines generative AI and AI agents, provides sustainable value that improves the customer experience by streamlining information gathering and task management according to user needs and providing personalized support.This allows the voice platform to efficiently analyze user voice input and provide optimal suggestions, notifications, and personalized support based on their interests and behaviors.

[0029] The voice platform according to this embodiment comprises a reception unit, an analysis unit, a learning unit, a suggestion unit, and a support unit. The reception unit receives voice input from the user. The reception unit allows the user to input questions or instructions by voice, for example. For example, the user may give instructions such as "What's the weather like today?" or "Remind me of tomorrow's meeting." The analysis unit analyzes the voice input received by the reception unit. The analysis unit analyzes the voice input using, for example, a generative AI and processes appropriate information or tasks. The generative AI converts the voice into text using, for example, speech recognition technology and analyzes the text. The learning unit learns the user's interests and behaviors based on the information analyzed by the analysis unit. The learning unit learns the user's interests and behavior patterns using, for example, a machine learning algorithm. The suggestion unit makes suggestions and notifications at the optimal timing based on the information learned by the learning unit. The suggestion unit automatically notifies the user when they need weather information, for example. The suggestion unit makes suggestions to make a particular task more efficient if the user repeatedly performs that task. The support unit provides personalized support based on the information suggested by the suggestion unit. For example, if the user is working on a specific project, the support unit provides information and resources related to that project. For example, the support unit manages the user's schedule and reminds them of important events and tasks. As a result, the voice platform according to the embodiment can efficiently analyze the user's voice input and provide optimal suggestions, notifications, and personalized support based on their interests and behaviors.

[0030] The reception unit accepts voice input from users. For example, users can input questions and instructions by voice. Specifically, when a user gives instructions such as "What's the weather like today?" or "Remind me of tomorrow's meeting," the reception unit uses a high-sensitivity microphone and noise-canceling technology to accurately capture the user's voice while eliminating ambient noise. Furthermore, the reception unit has a function to automatically detect the start and end of voice input, and switches to voice input mode when the user utters a specific trigger word (for example, "Hey, Assistant"). This allows users to input voice information in a natural conversational flow. The reception unit also has multilingual support, and can appropriately recognize and process voice input even if the user uses different languages. For example, it supports multiple languages ​​such as English, Japanese, and Spanish, and can automatically switch languages ​​based on the user's language settings. In this way, the reception unit can meet the diverse needs of users and improve the convenience of voice input.

[0031] The analysis unit analyzes the voice input received by the reception unit. The analysis unit analyzes the voice input using, for example, generative AI, and processes appropriate information and tasks. Specifically, the generative AI converts speech to text using speech recognition technology and then analyzes that text. The speech recognition technology uses a deep learning-based speech model, enabling high-accuracy conversion of speech to text. Furthermore, the generative AI uses natural language processing (NLP) technology to understand the meaning of the text and analyze the user's intent. For example, if the voice input is "What's the weather like today?", the generative AI understands the intent to "provide weather information" and retrieves appropriate weather information. Also, if the voice input is "Remind me of tomorrow's meeting," the generative AI recognizes the task to "set a meeting reminder" and sets a reminder based on the user's schedule. The analysis unit performs these processes in real time, enabling a rapid response to user voice input. Furthermore, the analysis unit can perform more accurate analysis by considering the user's past voice input history and behavioral patterns. This allows the analysis unit to accurately analyze the user's voice input and provide appropriate information and tasks.

[0032] The learning unit learns user interests and behaviors based on information analyzed by the analysis unit. For example, the learning unit learns user interests and behavioral patterns using machine learning algorithms. Specifically, the learning unit collects user voice input history and behavioral data, and models user interests and behavioral patterns based on this data. For example, if a user frequently inquires about weather information, the learning unit will determine that the user is interested in the weather and will prioritize providing weather information. Also, if a user tends to set reminders at a specific time, the learning unit will suggest reminders at that time. The learning unit can continuously learn from this data and respond to changes in user interests and behavioral patterns. Furthermore, the learning unit can use clustering technology to identify user groups with similar interests and behavioral patterns and make optimal suggestions for each group. As a result, the learning unit can accurately learn user interests and behaviors and provide personalized services.

[0033] The suggestion unit makes suggestions and notifications at the optimal time based on the information learned by the learning unit. For example, the suggestion unit automatically notifies users when they need weather information. Specifically, the suggestion unit makes suggestions at the optimal time, taking into account the user's schedule and past behavioral patterns. For example, if a user has a habit of checking the weather information every morning before going to work, the suggestion unit will notify them of the weather information during the time before they go to work. Also, if a user repeatedly performs a specific task, the suggestion unit will make suggestions to make that task more efficient. For example, if a user schedules a meeting at the same time every week, the suggestion unit will automatically set a meeting reminder and notify the user. The suggestion unit can customize these suggestions to the user's preferences and provide the information the user needs most at the optimal time. Furthermore, the suggestion unit can collect user feedback and continuously improve the accuracy and effectiveness of its suggestions. In this way, the suggestion unit can provide users with optimal suggestions and notifications, improving user convenience.

[0034] The support department provides personalized support based on information proposed by the proposal department. For example, if a user is working on a specific project, the support department will provide information and resources related to that project. Specifically, the support department will automatically collect and provide documents, tools, and reference materials related to the user's project. It will also manage the user's schedule and remind them of important events and tasks. For example, if a user is preparing for a meeting, the support department will provide meeting-related materials and past meeting minutes to support the meeting's progress. Furthermore, the support department can continuously improve its support based on user feedback and provide personalized support tailored to the user's needs. For example, if a user frequently requests specific information, the support department will adjust its support to prioritize providing that information. This allows the support department to provide optimal support to the user and improve the efficiency of the user's projects and tasks.

[0035] The proposal department includes an advertising department that provides advertisements based on user interests and behavior. For example, if a user shows interest in a particular product or service, the proposal department will provide relevant advertisements and promotions based on that information. For example, the proposal department will learn user interests and behavior patterns and provide advertisements at the optimal time. For example, if a user frequently visits a particular website, the proposal department will provide advertisements related to that website. In this way, the proposal department can increase advertising revenue by providing advertisements based on user interests and behavior.

[0036] The support department includes an information provision department that provides information to enrich users' lives. For example, if a user is interested in health management, the support department will provide health-related information and advice. For example, the support department will provide information related to the user's hobbies and areas of interest to help them enrich their daily lives. For example, if a user is participating in a specific event, the support department will provide information related to that event. In this way, the support department can improve the customer experience by providing information that enriches users' lives.

[0037] The support unit includes a health management unit that provides information related to the user's health management. For example, if a user is interested in health management, the support unit provides health-related information and advice. For example, the support unit provides advice on the user's diet and exercise. For example, the support unit monitors the user's health status and provides information related to health management. In this way, the support unit can support the user's health by providing information related to their health management.

[0038] The support unit includes a hobby information unit that provides information about the user's hobbies and interests. For example, the support unit provides information about areas in which the user has hobbies or interests. For example, if the user is interested in a particular hobby, the support unit provides information related to that hobby. For example, if the user is starting a new hobby, the support unit provides information about that hobby. In this way, the support unit can enrich the user's life by providing information about the user's hobbies and interests.

[0039] The reception desk analyzes the user's past voice input history and selects the optimal reception method. For example, the reception desk may prioritize suggesting voice input methods that the user has frequently used in the past. For example, the reception desk may select the optimal reception method for a specific time period based on the user's past voice input history. For example, the reception desk may analyze the user's past voice input history and suggest the most efficient reception method. In this way, the reception desk can select the optimal reception method by analyzing the user's past voice input history.

[0040] The reception unit filters voice input based on the user's current situation and areas of interest. For example, the reception unit accepts only relevant voice input based on the user's current situation. For example, the reception unit prioritizes accepting relevant voice input based on the user's areas of interest. For example, the reception unit filters out unnecessary voice input by considering the user's current situation and areas of interest. In this way, the reception unit can prioritize accepting highly relevant voice input by filtering voice input based on the user's current situation and areas of interest.

[0041] The reception unit, when receiving voice input, prioritizes receiving input that is highly relevant, taking into account the user's geographical location. For example, if the user is in a specific location, the reception unit prioritizes receiving voice input related to that location. For example, the reception unit prioritizes receiving voice input that is highly relevant based on the user's current location. For example, the reception unit prioritizes receiving the most relevant voice input by taking into account the user's geographical location. As a result, the reception unit can prioritize receiving voice input that is highly relevant by taking into account the user's geographical location.

[0042] The reception unit analyzes the user's social media activity when receiving voice input and accepts relevant input. For example, the reception unit prioritizes receiving relevant voice input based on the user's social media activity. For example, the reception unit analyzes the user's social media activity and accepts the most suitable voice input. For example, the reception unit accepts relevant voice input based on the user's social media activity. This allows the reception unit to prioritize receiving relevant voice input by analyzing the user's social media activity.

[0043] The analysis unit adjusts the level of detail of the analysis based on the importance of the voice input during analysis. For example, the analysis unit performs a detailed analysis for important voice inputs. For example, the analysis unit performs a standard analysis for normal voice inputs. For example, the analysis unit performs a rapid analysis for urgent voice inputs. In this way, the analysis unit can perform a detailed analysis for important voice inputs by adjusting the level of detail of the analysis based on the importance of the voice input.

[0044] The analysis unit applies different analysis algorithms depending on the category of the voice input during analysis. For example, the analysis unit applies a weather forecast-specific analysis algorithm to weather information. For example, the analysis unit applies a task management-specific analysis algorithm to task management information. For example, the analysis unit applies a health management-specific analysis algorithm to health information. By applying different analysis algorithms depending on the category of the voice input, the analysis unit can provide more appropriate analysis results.

[0045] The analysis unit determines the priority of analysis based on the submission date of the voice input. For example, the analysis unit prioritizes analysis of urgent voice inputs. For example, the analysis unit analyzes normal voice inputs with a standard priority. For example, the analysis unit postpones analysis of older voice inputs. In this way, the analysis unit can prioritize analysis of urgent voice inputs by determining the priority of analysis based on the submission date of the voice inputs.

[0046] The analysis unit adjusts the order of analysis based on the relevance of the voice inputs during analysis. For example, the analysis unit prioritizes analyzing voice inputs that are highly relevant. For example, the analysis unit postpones analyzing voice inputs that are less relevant. For example, the analysis unit analyzes the relevance of the voice inputs and performs the analysis in the optimal order. In this way, the analysis unit can prioritize analyzing voice inputs that are highly relevant by adjusting the order of analysis based on the relevance of the voice inputs.

[0047] The learning unit optimizes the learning algorithm by referring to past learning data during the learning process. For example, the learning unit selects the optimal learning algorithm based on past learning data. For example, the learning unit analyzes past learning data and improves the learning algorithm. For example, the learning unit optimizes the learning algorithm by referring to past learning data. In this way, the learning unit can optimize the learning algorithm and improve the accuracy of learning by referring to past learning data.

[0048] The learning unit analyzes user behavior patterns during learning to improve learning accuracy. For example, the learning unit analyzes user behavior patterns to improve learning accuracy. For example, the learning unit selects the optimal learning method based on user behavior patterns. For example, the learning unit analyzes user behavior patterns to improve learning accuracy. Thus, the learning unit can improve learning accuracy by analyzing user behavior patterns.

[0049] The learning unit weights the training data based on the timing of voice input submissions during training. For example, the learning unit gives higher weight to urgent voice inputs. For example, the learning unit gives standard weight to normal voice inputs. For example, the learning unit gives lower weight to past voice inputs. In this way, the learning unit can give higher weight to urgent voice inputs by weighting the training data based on the timing of voice input submissions.

[0050] The learning unit supplements the learning data by analyzing the user's social media activity during training. For example, the learning unit supplements the learning data from the user's social media activity. The learning unit supplements the learning data by analyzing the user's social media activity. The learning unit supplements the learning data based on the user's social media activity. This allows the learning unit to improve the accuracy of learning by supplementing the learning data through analysis of the user's social media activity.

[0051] The proposal department adjusts the level of detail in its proposals based on the user's level of interest. For example, if the user's level of interest is high, the proposal department will provide a detailed proposal. For example, if the user's level of interest is low, the proposal department will provide a concise proposal. The proposal department adjusts the level of detail in its proposals according to the user's level of interest. In this way, the proposal department can provide more appropriate proposals by adjusting the level of detail in its proposals based on the user's level of interest.

[0052] The proposal unit applies different proposal algorithms depending on the user's behavior patterns when making a proposal. For example, the proposal unit applies the optimal proposal algorithm based on the user's frequently performed actions. For example, the proposal unit analyzes the user's behavior patterns and selects the optimal proposal algorithm. For example, the proposal unit adjusts the proposal algorithm according to the user's behavior patterns. In this way, the proposal unit can make more appropriate proposals by applying different proposal algorithms according to the user's behavior patterns.

[0053] The proposal department determines the priority of proposals based on the user's behavior history when making proposals. For example, the proposal department prioritizes important proposals based on the user's behavior history. For example, the proposal department analyzes the user's behavior history to determine the optimal priority of proposals. For example, the proposal department adjusts the priority of proposals based on the user's behavior history. In this way, the proposal department can prioritize important proposals by determining the priority of proposals based on the user's behavior history.

[0054] The proposal department adjusts the order of proposals based on user relevance. For example, the proposal department prioritizes highly relevant proposals. For example, the proposal department postpones less relevant proposals. For example, the proposal department analyzes user relevance and determines the optimal order of proposals. This allows the proposal department to prioritize highly relevant proposals by adjusting the order of proposals based on user relevance.

[0055] The support department analyzes the user's past behavior during support to select the optimal support method. For example, the support department selects the optimal support method based on the user's past behavior. For example, the support department analyzes the user's past behavior and provides the optimal support method. For example, the support department selects the optimal support method by referring to the user's past behavior. This allows the support department to select the optimal support method by analyzing the user's past behavior.

[0056] The support unit customizes the support methods based on the user's current situation during support. For example, the support unit provides the optimal support method according to the user's current situation. For example, the support unit analyzes the user's current situation and customizes the support methods. For example, the support unit adjusts the support methods based on the user's current situation. This allows the support unit to provide more appropriate support by customizing the support methods based on the user's current situation.

[0057] The support department selects the optimal support method when providing support, taking into account the user's geographical location. For example, the support department provides the optimal support method based on the user's current location. The support department selects the optimal support method, taking into account the user's geographical location. For example, the support department provides the optimal support method according to the user's current location. This allows the support department to provide the optimal support method by considering the user's geographical location.

[0058] The support department analyzes the user's social media activity and proposes support measures during support. For example, the support department proposes the optimal support measures based on the user's social media activity. The support department analyzes the user's social media activity and proposes support measures. The support department proposes support measures based on the user's social media activity. This allows the support department to propose the optimal support measures by analyzing the user's social media activity.

[0059] The advertising department, when providing ads, analyzes the user's past ad click history to select the most suitable ad. For example, the advertising department selects the most suitable ad based on the user's past ad click history. For example, the advertising department analyzes the user's past ad click history and provides the most suitable ad. For example, the advertising department selects the most suitable ad by referring to the user's past ad click history. This allows the advertising department to select the most suitable ad by analyzing the user's past ad click history.

[0060] The advertising department filters ads based on the user's current situation and areas of interest when delivering ads. For example, the advertising department displays only relevant ads according to the user's current situation. For example, the advertising department prioritizes displaying relevant ads based on the user's areas of interest. For example, the advertising department filters out irrelevant ads by considering the user's current situation and areas of interest. As a result, the advertising department can provide more relevant ads by filtering ads based on the user's current situation and areas of interest.

[0061] The advertising department provides highly relevant advertisements by considering the user's geographical location information when delivering advertisements. For example, the advertising department provides highly relevant advertisements based on the user's current location. For example, the advertising department provides optimal advertisements by considering the user's geographical location information. For example, the advertising department provides highly relevant advertisements according to the user's current location. In this way, the advertising department can provide highly relevant advertisements by considering the user's geographical location information.

[0062] The advertising department analyzes users' social media activity and provides relevant advertisements when delivering them. For example, the advertising department provides relevant advertisements based on users' social media activity. For example, the advertising department analyzes users' social media activity and provides optimal advertisements. For example, the advertising department provides relevant advertisements based on users' social media activity. This allows the advertising department to provide relevant advertisements by analyzing users' social media activity.

[0063] The information provision department analyzes the user's past information browsing history to select the most suitable information when providing information. For example, the information provision department selects the most suitable information from the user's past information browsing history. For example, the information provision department analyzes the user's past information browsing history and provides the most suitable information. For example, the information provision department selects the most suitable information by referring to the user's past information browsing history. In this way, the information provision department can select the most suitable information by analyzing the user's past information browsing history.

[0064] The information provider filters information based on the user's current situation and areas of interest when providing information. For example, the information provider displays only relevant information according to the user's current situation. For example, the information provider prioritizes displaying relevant information based on the user's areas of interest. For example, the information provider filters out unnecessary information considering the user's current situation and areas of interest. As a result, the information provider can provide more relevant information by filtering information based on the user's current situation and areas of interest.

[0065] The information provider will provide highly relevant information by considering the user's geographical location when providing information. For example, the information provider will provide highly relevant information based on the user's current location. For example, the information provider will provide optimal information by considering the user's geographical location. For example, the information provider will provide highly relevant information according to the user's current location. In this way, the information provider can provide highly relevant information by considering the user's geographical location.

[0066] The information provision department analyzes the user's social media activity and provides relevant information when providing information. For example, the information provision department provides relevant information based on the user's social media activity. For example, the information provision department analyzes the user's social media activity and provides optimal information. For example, the information provision department provides relevant information based on the user's social media activity. In this way, the information provision department can provide relevant information by analyzing the user's social media activity.

[0067] The Health Management Department provides optimal health management advice by referring to the user's past health data. For example, the Health Management Department provides optimal health management advice based on the user's past health data. For example, the Health Management Department analyzes the user's past health data to provide optimal health management advice. For example, the Health Management Department provides optimal health management advice by referring to the user's past health data. This allows the Health Management Department to provide optimal health management advice by referring to the user's past health data.

[0068] The Health Management Department customizes health management advice by considering the user's current health condition. For example, the Health Management Department provides optimal health management advice based on the user's current health condition. For example, the Health Management Department analyzes the user's current health condition and customizes the health management advice. For example, the Health Management Department adjusts the health management advice based on the user's current health condition. This allows the Health Management Department to provide more appropriate health management advice by considering the user's current health condition.

[0069] The Health Management Department provides optimal health management advice by considering the user's device information. For example, if the user is using a smartphone, the Health Management Department provides health management advice tailored to the screen size. If the user is using a tablet, the Health Management Department provides health management advice optimized for a larger screen. If the user is using a smartwatch, the Health Management Department provides concise and highly visible health management advice. In this way, the Health Management Department can provide optimal health management advice by considering the user's device information.

[0070] The Health Management Department analyzes users' social media activity when providing health management advice and offers relevant advice. For example, the Health Management Department provides relevant health management advice based on users' social media activity. For example, the Health Management Department analyzes users' social media activity and provides optimal health management advice. For example, the Health Management Department provides relevant health management advice based on users' social media activity. This allows the Health Management Department to provide relevant health management advice by analyzing users' social media activity.

[0071] The Hobby Information Department provides optimal suggestions by referring to the user's past hobby history when suggesting hobbies. For example, the Hobby Information Department provides optimal hobby suggestions based on the user's past hobby history. For example, the Hobby Information Department analyzes the user's past hobby history and provides optimal hobby suggestions. For example, the Hobby Information Department provides optimal hobby suggestions by referring to the user's past hobby history. In this way, the Hobby Information Department can provide optimal hobby suggestions by referring to the user's past hobby history.

[0072] The Hobby Information Department filters hobby suggestions based on the user's current situation and areas of interest. For example, it may suggest only relevant hobbies based on the user's current situation. For example, it may prioritize suggesting relevant hobbies based on the user's areas of interest. For example, it may filter out unnecessary hobby suggestions by considering the user's current situation and areas of interest. In this way, the Hobby Information Department can provide more relevant hobby suggestions by filtering suggestions based on the user's current situation and areas of interest.

[0073] The Hobby Information Department provides optimal hobby suggestions by considering the user's geographical location. For example, the Hobby Information Department provides highly relevant hobby suggestions based on the user's current location. The Hobby Information Department provides optimal hobby suggestions by considering the user's geographical location. The Hobby Information Department provides highly relevant hobby suggestions based on the user's current location. In this way, the Hobby Information Department can provide optimal hobby suggestions by considering the user's geographical location.

[0074] The Hobby Information Department analyzes users' social media activity when suggesting hobbies and provides relevant suggestions. For example, the Hobby Information Department provides relevant hobby suggestions based on users' social media activity. For example, the Hobby Information Department analyzes users' social media activity and provides optimal hobby suggestions. For example, the Hobby Information Department provides relevant hobby suggestions based on users' social media activity. In this way, the Hobby Information Department can provide relevant hobby suggestions by analyzing users' social media activity.

[0075] The system according to the embodiment is not limited to the example described above, and various modifications are possible, for example, as follows.

[0076] The reception desk can refer to the user's past voice input history when receiving a user's voice input and suggest the most suitable reception method. For example, it can prioritize suggesting voice input methods that the user has frequently used in the past. It can also select the most suitable reception method for a specific time period based on the user's past voice input history. Furthermore, it can analyze the user's past voice input history and suggest the most efficient reception method. In this way, the reception desk can select the most suitable reception method by analyzing the user's past voice input history.

[0077] The suggestion function can analyze user behavior patterns and provide optimal suggestions. For example, it can provide optimal suggestions based on actions that users frequently perform. It can also analyze user behavior patterns and select the optimal suggestion algorithm. Furthermore, it can adjust the suggestion algorithm according to the user's behavior patterns. As a result, the suggestion function can provide more appropriate suggestions by applying different suggestion algorithms according to the user's behavior patterns.

[0078] The advertising department can analyze a user's past ad click history and select the most suitable ad. For example, it can select the most suitable ad based on a user's past ad click history. It can also analyze a user's past ad click history and provide the most suitable ad. Furthermore, it can select the most suitable ad by referring to a user's past ad click history. In this way, the advertising department can select the most suitable ad by analyzing a user's past ad click history.

[0079] The Health Management Department can refer to users' past health data and provide optimal health management advice. For example, it can provide optimal health management advice based on users' past health data. It can also analyze users' past health data and provide optimal health management advice. Furthermore, it can refer to users' past health data and provide optimal health management advice. In this way, the Health Management Department can provide optimal health management advice by referring to users' past health data.

[0080] The reception unit can prioritize receiving voice input that is highly relevant, taking into account the user's geographical location. For example, if the user is in a specific location, it can prioritize receiving voice input related to that location. It can also prioritize receiving voice input that is highly relevant based on the user's current location. Furthermore, it can prioritize receiving the most appropriate voice input by considering the user's geographical location. In this way, the reception unit can prioritize receiving voice input that is highly relevant by taking the user's geographical location into account.

[0081] The analysis unit can determine the priority of analysis based on the submission date of the voice input. For example, it can prioritize analysis of urgent voice inputs. It can also analyze regular voice inputs with a standard priority. Furthermore, it can postpone the analysis of older voice inputs. As a result, the analysis unit can prioritize analysis of urgent voice inputs by determining the priority of analysis based on the submission date of the voice inputs.

[0082] The following briefly describes the processing flow for example form 1.

[0083] Step 1: The reception desk accepts voice input from the user. For example, the user can input questions or instructions by voice. Specifically, the user can give instructions such as "What's the weather like today?" or "Remind me of tomorrow's meeting." Step 2: The analysis unit analyzes the voice input received by the reception unit. For example, it uses a generation AI to analyze the voice input and process appropriate information and tasks. The generation AI uses speech recognition technology to convert the voice into text and then analyzes that text. Step 3: The learning unit learns user interests and behaviors based on the information analyzed by the analysis unit. For example, it learns user interests and behavioral patterns using machine learning algorithms. Step 4: The suggestion unit makes suggestions and notifications at the optimal time based on the information learned by the learning unit. For example, it automatically sends a notification when the user needs weather information. Also, if the user repeatedly performs a specific task, it makes suggestions to make that task more efficient. Step 5: The support team provides personalized support based on the information proposed by the proposal team. For example, if a user is working on a specific project, they will provide information and resources related to that project. They will also manage the user's schedule and remind them of important events and tasks.

[0084] (Example of form 2) The voice platform according to an embodiment of the present invention is a system that combines a generative AI and an AI agent. This voice platform aims to streamline information gathering and task management for users using voice. Users input questions and instructions by voice, and the generative AI analyzes the voice to process appropriate information and tasks. The generative AI learns the user's interests and behaviors and provides suggestions, notifications, reminders, and personalized support at the optimal time. This expands advertising revenue and service usage opportunities and provides sustainable value that improves the customer experience. For example, a user gives instructions by voice such as "What's the weather like today?" or "Remind me of tomorrow's meeting." This voice input is analyzed by the generative AI, and appropriate information and tasks are processed. The generative AI learns the user's interests and behaviors and automatically notifies the user when they need weather information. Also, if a user repeatedly performs a particular task, it makes suggestions to streamline that task. The generative AI provides personalized support to the user. For example, if a user is working on a particular project, it provides information and resources related to that project. It also manages the user's schedule and reminds them of important events and tasks. This platform also includes mechanisms to expand advertising revenue and service usage opportunities. For example, if a user shows interest in a particular product or service, it will provide relevant advertisements and promotions based on that information. This increases advertising revenue while also providing users with useful information. Furthermore, this platform offers various functions to enrich users' lives. For example, if a user is interested in health management, the generative AI will provide health-related information and advice. It will also provide information on areas of the user's hobbies and interests, supporting a more fulfilling daily life. In this way, the voice platform, which combines generative AI and AI agents, provides sustainable value that improves the customer experience by streamlining information gathering and task management according to user needs and providing personalized support.This allows the voice platform to efficiently analyze user voice input and provide optimal suggestions, notifications, and personalized support based on their interests and behaviors.

[0085] The voice platform according to this embodiment comprises a reception unit, an analysis unit, a learning unit, a suggestion unit, and a support unit. The reception unit receives voice input from the user. The reception unit allows the user to input questions or instructions by voice, for example. For example, the user may give instructions such as "What's the weather like today?" or "Remind me of tomorrow's meeting." The analysis unit analyzes the voice input received by the reception unit. The analysis unit analyzes the voice input using, for example, a generative AI and processes appropriate information or tasks. The generative AI converts the voice into text using, for example, speech recognition technology and analyzes the text. The learning unit learns the user's interests and behaviors based on the information analyzed by the analysis unit. The learning unit learns the user's interests and behavior patterns using, for example, a machine learning algorithm. The suggestion unit makes suggestions and notifications at the optimal timing based on the information learned by the learning unit. The suggestion unit automatically notifies the user when they need weather information, for example. The suggestion unit makes suggestions to make a particular task more efficient if the user repeatedly performs that task. The support unit provides personalized support based on the information suggested by the suggestion unit. For example, if the user is working on a specific project, the support unit provides information and resources related to that project. For example, the support unit manages the user's schedule and reminds them of important events and tasks. As a result, the voice platform according to the embodiment can efficiently analyze the user's voice input and provide optimal suggestions, notifications, and personalized support based on their interests and behaviors.

[0086] The reception unit accepts voice input from users. For example, users can input questions and instructions by voice. Specifically, when a user gives instructions such as "What's the weather like today?" or "Remind me of tomorrow's meeting," the reception unit uses a high-sensitivity microphone and noise-canceling technology to accurately capture the user's voice while eliminating ambient noise. Furthermore, the reception unit has a function to automatically detect the start and end of voice input, and switches to voice input mode when the user utters a specific trigger word (for example, "Hey, Assistant"). This allows users to input voice information in a natural conversational flow. The reception unit also has multilingual support, and can appropriately recognize and process voice input even if the user uses different languages. For example, it supports multiple languages ​​such as English, Japanese, and Spanish, and can automatically switch languages ​​based on the user's language settings. In this way, the reception unit can meet the diverse needs of users and improve the convenience of voice input.

[0087] The analysis unit analyzes the voice input received by the reception unit. The analysis unit analyzes the voice input using, for example, generative AI, and processes appropriate information and tasks. Specifically, the generative AI converts speech to text using speech recognition technology and then analyzes that text. The speech recognition technology uses a deep learning-based speech model, enabling high-accuracy conversion of speech to text. Furthermore, the generative AI uses natural language processing (NLP) technology to understand the meaning of the text and analyze the user's intent. For example, if the voice input is "What's the weather like today?", the generative AI understands the intent to "provide weather information" and retrieves appropriate weather information. Also, if the voice input is "Remind me of tomorrow's meeting," the generative AI recognizes the task to "set a meeting reminder" and sets a reminder based on the user's schedule. The analysis unit performs these processes in real time, enabling a rapid response to user voice input. Furthermore, the analysis unit can perform more accurate analysis by considering the user's past voice input history and behavioral patterns. This allows the analysis unit to accurately analyze the user's voice input and provide appropriate information and tasks.

[0088] The learning unit learns user interests and behaviors based on information analyzed by the analysis unit. For example, the learning unit learns user interests and behavioral patterns using machine learning algorithms. Specifically, the learning unit collects user voice input history and behavioral data, and models user interests and behavioral patterns based on this data. For example, if a user frequently inquires about weather information, the learning unit will determine that the user is interested in the weather and will prioritize providing weather information. Also, if a user tends to set reminders at a specific time, the learning unit will suggest reminders at that time. The learning unit can continuously learn from this data and respond to changes in user interests and behavioral patterns. Furthermore, the learning unit can use clustering technology to identify user groups with similar interests and behavioral patterns and make optimal suggestions for each group. As a result, the learning unit can accurately learn user interests and behaviors and provide personalized services.

[0089] The suggestion unit makes suggestions and notifications at the optimal time based on the information learned by the learning unit. For example, the suggestion unit automatically notifies users when they need weather information. Specifically, the suggestion unit makes suggestions at the optimal time, taking into account the user's schedule and past behavioral patterns. For example, if a user has a habit of checking the weather information every morning before going to work, the suggestion unit will notify them of the weather information during the time before they go to work. Also, if a user repeatedly performs a specific task, the suggestion unit will make suggestions to make that task more efficient. For example, if a user schedules a meeting at the same time every week, the suggestion unit will automatically set a meeting reminder and notify the user. The suggestion unit can customize these suggestions to the user's preferences and provide the information the user needs most at the optimal time. Furthermore, the suggestion unit can collect user feedback and continuously improve the accuracy and effectiveness of its suggestions. In this way, the suggestion unit can provide users with optimal suggestions and notifications, improving user convenience.

[0090] The support department provides personalized support based on information proposed by the proposal department. For example, if a user is working on a specific project, the support department will provide information and resources related to that project. Specifically, the support department will automatically collect and provide documents, tools, and reference materials related to the user's project. It will also manage the user's schedule and remind them of important events and tasks. For example, if a user is preparing for a meeting, the support department will provide meeting-related materials and past meeting minutes to support the meeting's progress. Furthermore, the support department can continuously improve its support based on user feedback and provide personalized support tailored to the user's needs. For example, if a user frequently requests specific information, the support department will adjust its support to prioritize providing that information. This allows the support department to provide optimal support to the user and improve the efficiency of the user's projects and tasks.

[0091] The proposal department includes an advertising department that provides advertisements based on user interests and behavior. For example, if a user shows interest in a particular product or service, the proposal department will provide relevant advertisements and promotions based on that information. For example, the proposal department will learn user interests and behavior patterns and provide advertisements at the optimal time. For example, if a user frequently visits a particular website, the proposal department will provide advertisements related to that website. In this way, the proposal department can increase advertising revenue by providing advertisements based on user interests and behavior.

[0092] The support department includes an information provision department that provides information to enrich users' lives. For example, if a user is interested in health management, the support department will provide health-related information and advice. For example, the support department will provide information related to the user's hobbies and areas of interest to help them enrich their daily lives. For example, if a user is participating in a specific event, the support department will provide information related to that event. In this way, the support department can improve the customer experience by providing information that enriches users' lives.

[0093] The support unit includes a health management unit that provides information related to the user's health management. For example, if a user is interested in health management, the support unit provides health-related information and advice. For example, the support unit provides advice on the user's diet and exercise. For example, the support unit monitors the user's health status and provides information related to health management. In this way, the support unit can support the user's health by providing information related to their health management.

[0094] The support unit includes a hobby information unit that provides information about the user's hobbies and interests. For example, the support unit provides information about areas in which the user has hobbies or interests. For example, if the user is interested in a particular hobby, the support unit provides information related to that hobby. For example, if the user is starting a new hobby, the support unit provides information about that hobby. In this way, the support unit can enrich the user's life by providing information about the user's hobbies and interests.

[0095] The reception system estimates the user's emotions and adjusts the timing of voice input acceptance based on the estimated emotions. For example, if the user is stressed, the reception system delays the timing of voice input acceptance to allow the user to input in a relaxed state. For example, if the user is in a hurry, the reception system speeds up the timing of voice input acceptance to allow for a quick response. For example, if the user is concentrating, the reception system adjusts the timing of voice input acceptance to avoid interrupting their concentration. In this way, the reception system can accept voice input at a more appropriate time by adjusting the timing of voice input acceptance according to the user's emotions. Emotion estimation is achieved using an emotion estimation function, for example, using an emotion engine or generative AI. Generative AI is, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI.

[0096] The reception desk analyzes the user's past voice input history and selects the optimal reception method. For example, the reception desk may prioritize suggesting voice input methods that the user has frequently used in the past. For example, the reception desk may select the optimal reception method for a specific time period based on the user's past voice input history. For example, the reception desk may analyze the user's past voice input history and suggest the most efficient reception method. In this way, the reception desk can select the optimal reception method by analyzing the user's past voice input history.

[0097] The reception unit filters voice input based on the user's current situation and areas of interest. For example, the reception unit accepts only relevant voice input based on the user's current situation. For example, the reception unit prioritizes accepting relevant voice input based on the user's areas of interest. For example, the reception unit filters out unnecessary voice input by considering the user's current situation and areas of interest. In this way, the reception unit can prioritize accepting highly relevant voice input by filtering voice input based on the user's current situation and areas of interest.

[0098] The reception unit estimates the user's emotions and determines the priority of voice input to be received based on the estimated emotions. For example, if the user is stressed, the reception unit will prioritize important voice input. For example, if the user is relaxed, the reception unit will prioritize normal voice input. For example, if the user is in a hurry, the reception unit will prioritize urgent voice input. In this way, the reception unit can prioritize important voice input by determining the priority of voice input according to the user's emotions. Emotion estimation is achieved using an emotion estimation function, for example, using an emotion engine or generative AI. Generative AI is, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI.

[0099] The reception unit, when receiving voice input, prioritizes receiving input that is highly relevant, taking into account the user's geographical location. For example, if the user is in a specific location, the reception unit prioritizes receiving voice input related to that location. For example, the reception unit prioritizes receiving voice input that is highly relevant based on the user's current location. For example, the reception unit prioritizes receiving the most relevant voice input by taking into account the user's geographical location. As a result, the reception unit can prioritize receiving voice input that is highly relevant by taking into account the user's geographical location.

[0100] The reception unit analyzes the user's social media activity when receiving voice input and accepts relevant input. For example, the reception unit prioritizes receiving relevant voice input based on the user's social media activity. For example, the reception unit analyzes the user's social media activity and accepts the most suitable voice input. For example, the reception unit accepts relevant voice input based on the user's social media activity. This allows the reception unit to prioritize receiving relevant voice input by analyzing the user's social media activity.

[0101] The analysis unit estimates the user's emotions and adjusts the presentation of the analysis based on the estimated emotions. For example, if the user is relaxed, the analysis unit provides detailed analysis results. If the user is in a hurry, the analysis unit provides concise analysis results. If the user is excited, the analysis unit provides visually stimulating analysis results. In this way, the analysis unit can provide more appropriate analysis results by adjusting the presentation of the analysis according to the user's emotions. Emotion estimation is achieved using an emotion estimation function, for example, using an emotion engine or generative AI. Generative AI is, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI.

[0102] The analysis unit adjusts the level of detail of the analysis based on the importance of the voice input during analysis. For example, the analysis unit performs a detailed analysis for important voice inputs. For example, the analysis unit performs a standard analysis for normal voice inputs. For example, the analysis unit performs a rapid analysis for urgent voice inputs. In this way, the analysis unit can perform a detailed analysis for important voice inputs by adjusting the level of detail of the analysis based on the importance of the voice input.

[0103] The analysis unit applies different analysis algorithms depending on the category of the voice input during analysis. For example, the analysis unit applies a weather forecast-specific analysis algorithm to weather information. For example, the analysis unit applies a task management-specific analysis algorithm to task management information. For example, the analysis unit applies a health management-specific analysis algorithm to health information. By applying different analysis algorithms depending on the category of the voice input, the analysis unit can provide more appropriate analysis results.

[0104] The analysis unit estimates the user's emotions and adjusts the length of the analysis based on the estimated emotions. For example, if the user is in a hurry, the analysis unit performs a short, concise analysis. If the user is relaxed, the analysis unit performs a detailed analysis. If the user is excited, the analysis unit performs a visually stimulating analysis. In this way, the analysis unit can provide more appropriate analysis results by adjusting the length of the analysis according to the user's emotions. Emotion estimation is achieved using an emotion estimation function, for example, using an emotion engine or generative AI. Generative AI is, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI.

[0105] The analysis unit determines the priority of analysis based on the submission date of the voice input. For example, the analysis unit prioritizes analysis of urgent voice inputs. For example, the analysis unit analyzes normal voice inputs with a standard priority. For example, the analysis unit postpones analysis of older voice inputs. In this way, the analysis unit can prioritize analysis of urgent voice inputs by determining the priority of analysis based on the submission date of the voice inputs.

[0106] The analysis unit adjusts the order of analysis based on the relevance of the voice inputs during analysis. For example, the analysis unit prioritizes analyzing voice inputs that are highly relevant. For example, the analysis unit postpones analyzing voice inputs that are less relevant. For example, the analysis unit analyzes the relevance of the voice inputs and performs the analysis in the optimal order. In this way, the analysis unit can prioritize analyzing voice inputs that are highly relevant by adjusting the order of analysis based on the relevance of the voice inputs.

[0107] The learning unit estimates the user's emotions and selects training data based on the estimated emotions. For example, if the user is relaxed, the learning unit selects detailed training data. For example, if the user is in a hurry, the learning unit selects concise training data. For example, if the user is excited, the learning unit selects visually stimulating training data. In this way, the learning unit can select more appropriate training data according to the user's emotions. Emotion estimation is achieved using an emotion estimation function, for example, using an emotion engine or generative AI. Generative AI is, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI.

[0108] The learning unit optimizes the learning algorithm by referring to past learning data during the learning process. For example, the learning unit selects the optimal learning algorithm based on past learning data. For example, the learning unit analyzes past learning data and improves the learning algorithm. For example, the learning unit optimizes the learning algorithm by referring to past learning data. In this way, the learning unit can optimize the learning algorithm and improve the accuracy of learning by referring to past learning data.

[0109] The learning unit analyzes user behavior patterns during learning to improve learning accuracy. For example, the learning unit analyzes user behavior patterns to improve learning accuracy. For example, the learning unit selects the optimal learning method based on user behavior patterns. For example, the learning unit analyzes user behavior patterns to improve learning accuracy. Thus, the learning unit can improve learning accuracy by analyzing user behavior patterns.

[0110] The learning unit estimates the user's emotions and adjusts the learning frequency based on the estimated emotions. For example, if the user is relaxed, the learning unit learns more frequently. If the user is in a hurry, the learning unit reduces the learning frequency. If the user is excited, the learning unit adjusts the learning frequency. In this way, the learning unit can learn at a more appropriate frequency by adjusting the learning frequency according to the user's emotions. Emotion estimation is achieved using an emotion estimation function, for example, using an emotion engine or generative AI. Generative AI is, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI.

[0111] The learning unit weights the training data based on the timing of voice input submissions during training. For example, the learning unit gives higher weight to urgent voice inputs. For example, the learning unit gives standard weight to normal voice inputs. For example, the learning unit gives lower weight to past voice inputs. In this way, the learning unit can give higher weight to urgent voice inputs by weighting the training data based on the timing of voice input submissions.

[0112] The learning unit supplements the learning data by analyzing the user's social media activity during training. For example, the learning unit supplements the learning data from the user's social media activity. The learning unit supplements the learning data by analyzing the user's social media activity. The learning unit supplements the learning data based on the user's social media activity. This allows the learning unit to improve the accuracy of learning by supplementing the learning data through analysis of the user's social media activity.

[0113] The suggestion unit estimates the user's emotions and adjusts the way it presents its suggestions based on those emotions. For example, if the user is relaxed, the suggestion unit will provide detailed suggestions. If the user is in a hurry, the suggestion unit will provide concise suggestions. If the user is excited, the suggestion unit will provide visually stimulating suggestions. In this way, the suggestion unit can provide more appropriate suggestions by adjusting the way it presents its suggestions according to the user's emotions. Emotion estimation is achieved using an emotion estimation function, such as an emotion engine or generative AI. Generative AI includes, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI.

[0114] The proposal department adjusts the level of detail in its proposals based on the user's level of interest. For example, if the user's level of interest is high, the proposal department will provide a detailed proposal. For example, if the user's level of interest is low, the proposal department will provide a concise proposal. The proposal department adjusts the level of detail in its proposals according to the user's level of interest. In this way, the proposal department can provide more appropriate proposals by adjusting the level of detail in its proposals based on the user's level of interest.

[0115] The proposal unit applies different proposal algorithms depending on the user's behavior patterns when making a proposal. For example, the proposal unit applies the optimal proposal algorithm based on the user's frequently performed actions. For example, the proposal unit analyzes the user's behavior patterns and selects the optimal proposal algorithm. For example, the proposal unit adjusts the proposal algorithm according to the user's behavior patterns. In this way, the proposal unit can make more appropriate proposals by applying different proposal algorithms according to the user's behavior patterns.

[0116] The suggestion unit estimates the user's emotions and adjusts the length of the suggestions based on the estimated emotions. For example, if the user is in a hurry, the suggestion unit will provide short, concise suggestions. If the user is relaxed, the suggestion unit will provide detailed suggestions. If the user is excited, the suggestion unit will provide visually stimulating suggestions. In this way, the suggestion unit can provide more appropriate suggestions by adjusting the length of the suggestions according to the user's emotions. Emotion estimation is achieved using emotion estimation functions, such as emotion engines or generative AI. Generative AI includes, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI.

[0117] The proposal department determines the priority of proposals based on the user's behavior history when making proposals. For example, the proposal department prioritizes important proposals based on the user's behavior history. For example, the proposal department analyzes the user's behavior history to determine the optimal priority of proposals. For example, the proposal department adjusts the priority of proposals based on the user's behavior history. In this way, the proposal department can prioritize important proposals by determining the priority of proposals based on the user's behavior history.

[0118] The proposal department adjusts the order of proposals based on user relevance. For example, the proposal department prioritizes highly relevant proposals. For example, the proposal department postpones less relevant proposals. For example, the proposal department analyzes user relevance and determines the optimal order of proposals. This allows the proposal department to prioritize highly relevant proposals by adjusting the order of proposals based on user relevance.

[0119] The support unit estimates the user's emotions and adjusts its support methods based on the estimated emotions. For example, if the user is stressed, the support unit provides a relaxing support method. For example, if the user is relaxed, the support unit provides detailed support. For example, if the user is in a hurry, the support unit provides quick support. In this way, the support unit can provide more appropriate support by adjusting its support methods according to the user's emotions. Emotion estimation is achieved using an emotion estimation function, for example, using an emotion engine or generative AI. Generative AI is, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI.

[0120] The support department analyzes the user's past behavior during support to select the optimal support method. For example, the support department selects the optimal support method based on the user's past behavior. For example, the support department analyzes the user's past behavior and provides the optimal support method. For example, the support department selects the optimal support method by referring to the user's past behavior. This allows the support department to select the optimal support method by analyzing the user's past behavior.

[0121] The support unit customizes the support methods based on the user's current situation during support. For example, the support unit provides the optimal support method according to the user's current situation. For example, the support unit analyzes the user's current situation and customizes the support methods. For example, the support unit adjusts the support methods based on the user's current situation. This allows the support unit to provide more appropriate support by customizing the support methods based on the user's current situation.

[0122] The support unit estimates the user's emotions and prioritizes support based on the estimated emotions. For example, if the user is stressed, the support unit will prioritize important support. For example, if the user is relaxed, the support unit will prioritize normal support. For example, if the user is in a hurry, the support unit will prioritize urgent support. In this way, the support unit can prioritize important support by prioritizing support according to the user's emotions. Emotion estimation is achieved using emotion estimation functions, such as emotion engines or generative AI. Generative AI includes, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI.

[0123] The support department selects the optimal support method when providing support, taking into account the user's geographical location. For example, the support department provides the optimal support method based on the user's current location. The support department selects the optimal support method, taking into account the user's geographical location. For example, the support department provides the optimal support method according to the user's current location. This allows the support department to provide the optimal support method by considering the user's geographical location.

[0124] The support department analyzes the user's social media activity and proposes support measures during support. For example, the support department proposes the optimal support measures based on the user's social media activity. The support department analyzes the user's social media activity and proposes support measures. The support department proposes support measures based on the user's social media activity. This allows the support department to propose the optimal support measures by analyzing the user's social media activity.

[0125] The advertising department estimates the user's emotions and adjusts how ads are displayed based on those emotions. For example, if the user is relaxed, the advertising department displays detailed ads. If the user is in a hurry, the advertising department displays concise ads. If the user is excited, the advertising department displays visually stimulating ads. In this way, the advertising department can provide more effective ads by adjusting how ads are displayed according to the user's emotions. Emotion estimation is achieved using emotion estimation functions, such as emotion engines or generative AI. Generative AI includes, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI.

[0126] The advertising department, when providing ads, analyzes the user's past ad click history to select the most suitable ad. For example, the advertising department selects the most suitable ad based on the user's past ad click history. For example, the advertising department analyzes the user's past ad click history and provides the most suitable ad. For example, the advertising department selects the most suitable ad by referring to the user's past ad click history. This allows the advertising department to select the most suitable ad by analyzing the user's past ad click history.

[0127] The advertising department filters ads based on the user's current situation and areas of interest when delivering ads. For example, the advertising department displays only relevant ads according to the user's current situation. For example, the advertising department prioritizes displaying relevant ads based on the user's areas of interest. For example, the advertising department filters out irrelevant ads by considering the user's current situation and areas of interest. As a result, the advertising department can provide more relevant ads by filtering ads based on the user's current situation and areas of interest.

[0128] The advertising department estimates the user's emotions and prioritizes ads based on those emotions. For example, if the user is stressed, the advertising department will prioritize displaying important ads. For example, if the user is relaxed, the advertising department will prioritize displaying normal ads. For example, if the user is in a hurry, the advertising department will prioritize displaying urgent ads. In this way, the advertising department can prioritize important ads by prioritizing them according to the user's emotions. Emotion estimation is achieved using emotion estimation functions, such as emotion engines or generative AI. Generative AI includes, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI.

[0129] The advertising department provides highly relevant advertisements by considering the user's geographical location information when delivering advertisements. For example, the advertising department provides highly relevant advertisements based on the user's current location. For example, the advertising department provides optimal advertisements by considering the user's geographical location information. For example, the advertising department provides highly relevant advertisements according to the user's current location. In this way, the advertising department can provide highly relevant advertisements by considering the user's geographical location information.

[0130] The advertising department analyzes users' social media activity and provides relevant advertisements when delivering them. For example, the advertising department provides relevant advertisements based on users' social media activity. For example, the advertising department analyzes users' social media activity and provides optimal advertisements. For example, the advertising department provides relevant advertisements based on users' social media activity. This allows the advertising department to provide relevant advertisements by analyzing users' social media activity.

[0131] The information provider estimates the user's emotions and adjusts how information is displayed based on the estimated emotions. For example, if the user is relaxed, the information provider displays detailed information. If the user is in a hurry, the information provider displays concise information. If the user is excited, the information provider displays visually stimulating information. In this way, the information provider can provide more appropriate information by adjusting how information is displayed according to the user's emotions. Emotion estimation is achieved using an emotion estimation function, for example, using an emotion engine or generative AI. Generative AI is, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI.

[0132] The information provision department analyzes the user's past information browsing history to select the most suitable information when providing information. For example, the information provision department selects the most suitable information from the user's past information browsing history. For example, the information provision department analyzes the user's past information browsing history and provides the most suitable information. For example, the information provision department selects the most suitable information by referring to the user's past information browsing history. In this way, the information provision department can select the most suitable information by analyzing the user's past information browsing history.

[0133] The information provider filters information based on the user's current situation and areas of interest when providing information. For example, the information provider displays only relevant information according to the user's current situation. For example, the information provider prioritizes displaying relevant information based on the user's areas of interest. For example, the information provider filters out unnecessary information considering the user's current situation and areas of interest. As a result, the information provider can provide more relevant information by filtering information based on the user's current situation and areas of interest.

[0134] The information provider estimates the user's emotions and prioritizes information based on those emotions. For example, if the user is stressed, the information provider will prioritize displaying important information. For example, if the user is relaxed, the information provider will prioritize displaying normal information. For example, if the user is in a hurry, the information provider will prioritize displaying urgent information. In this way, the information provider can prioritize providing important information by prioritizing information according to the user's emotions. Emotion estimation is achieved using an emotion estimation function, for example, using an emotion engine or generative AI. Generative AI is, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI.

[0135] The information provider will provide highly relevant information by considering the user's geographical location when providing information. For example, the information provider will provide highly relevant information based on the user's current location. For example, the information provider will provide optimal information by considering the user's geographical location. For example, the information provider will provide highly relevant information according to the user's current location. In this way, the information provider can provide highly relevant information by considering the user's geographical location.

[0136] The information provision department analyzes the user's social media activity and provides relevant information when providing information. For example, the information provision department provides relevant information based on the user's social media activity. For example, the information provision department analyzes the user's social media activity and provides optimal information. For example, the information provision department provides relevant information based on the user's social media activity. In this way, the information provision department can provide relevant information by analyzing the user's social media activity.

[0137] The Health Management Department estimates the user's emotions and adjusts health management advice based on the estimated emotions. For example, if the user is stressed, the Health Management Department provides relaxing health management advice. For example, if the user is relaxed, the Health Management Department provides detailed health management advice. For example, if the user is in a hurry, the Health Management Department provides concise health management advice. In this way, the Health Management Department can provide more appropriate health management advice by adjusting it according to the user's emotions. Emotion estimation is achieved using an emotion estimation function, for example, using an emotion engine or generative AI. Generative AI is, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI.

[0138] The Health Management Department provides optimal health management advice by referring to the user's past health data. For example, the Health Management Department provides optimal health management advice based on the user's past health data. For example, the Health Management Department analyzes the user's past health data to provide optimal health management advice. For example, the Health Management Department provides optimal health management advice by referring to the user's past health data. This allows the Health Management Department to provide optimal health management advice by referring to the user's past health data.

[0139] The Health Management Department customizes health management advice by considering the user's current health condition. For example, the Health Management Department provides optimal health management advice based on the user's current health condition. For example, the Health Management Department analyzes the user's current health condition and customizes the health management advice. For example, the Health Management Department adjusts the health management advice based on the user's current health condition. This allows the Health Management Department to provide more appropriate health management advice by considering the user's current health condition.

[0140] The Health Management Department estimates the user's emotions and determines the priority of health management based on the estimated emotions. For example, if the user is stressed, the Health Management Department will prioritize providing important health management advice. For example, if the user is relaxed, the Health Management Department will prioritize providing regular health management advice. For example, if the user is in a hurry, the Health Management Department will prioritize providing urgent health management advice. In this way, the Health Management Department can prioritize providing important health management advice by determining the priority of health management according to the user's emotions. Emotion estimation is achieved using an emotion estimation function, for example, using an emotion engine or generative AI. Generative AI is, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI.

[0141] The Health Management Department provides optimal health management advice by considering the user's device information. For example, if the user is using a smartphone, the Health Management Department provides health management advice tailored to the screen size. If the user is using a tablet, the Health Management Department provides health management advice optimized for a larger screen. If the user is using a smartwatch, the Health Management Department provides concise and highly visible health management advice. In this way, the Health Management Department can provide optimal health management advice by considering the user's device information.

[0142] The Health Management Department analyzes users' social media activity when providing health management advice and offers relevant advice. For example, the Health Management Department provides relevant health management advice based on users' social media activity. For example, the Health Management Department analyzes users' social media activity and provides optimal health management advice. For example, the Health Management Department provides relevant health management advice based on users' social media activity. This allows the Health Management Department to provide relevant health management advice by analyzing users' social media activity.

[0143] The Hobby Information Department estimates the user's emotions and adjusts its hobby suggestion method based on the estimated emotions. For example, if the user is relaxed, the Hobby Information Department will suggest detailed hobbies. If the user is in a hurry, the Hobby Information Department will suggest concise hobbies. If the user is excited, the Hobby Information Department will suggest visually stimulating hobbies. In this way, the Hobby Information Department can provide more appropriate hobby suggestions by adjusting its hobby suggestion method according to the user's emotions. Emotion estimation is achieved using an emotion estimation function, for example, using an emotion engine or generative AI. Generative AI is, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI.

[0144] The Hobby Information Department provides optimal suggestions by referring to the user's past hobby history when suggesting hobbies. For example, the Hobby Information Department provides optimal hobby suggestions based on the user's past hobby history. For example, the Hobby Information Department analyzes the user's past hobby history and provides optimal hobby suggestions. For example, the Hobby Information Department provides optimal hobby suggestions by referring to the user's past hobby history. In this way, the Hobby Information Department can provide optimal hobby suggestions by referring to the user's past hobby history.

[0145] The Hobby Information Department filters hobby suggestions based on the user's current situation and areas of interest. For example, it may suggest only relevant hobbies based on the user's current situation. For example, it may prioritize suggesting relevant hobbies based on the user's areas of interest. For example, it may filter out unnecessary hobby suggestions by considering the user's current situation and areas of interest. In this way, the Hobby Information Department can provide more relevant hobby suggestions by filtering suggestions based on the user's current situation and areas of interest.

[0146] The Hobby Information Department estimates the user's emotions and prioritizes hobbies based on those emotions. For example, if the user is stressed, the Hobby Information Department prioritizes important hobby suggestions. For example, if the user is relaxed, the Hobby Information Department prioritizes normal hobby suggestions. For example, if the user is in a hurry, the Hobby Information Department prioritizes urgent hobby suggestions. In this way, the Hobby Information Department can prioritize important hobby suggestions by determining hobby priorities according to the user's emotions. Emotion estimation is achieved using an emotion estimation function, for example, using an emotion engine or generative AI. Generative AI is, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI.

[0147] The Hobby Information Department provides optimal hobby suggestions by considering the user's geographical location. For example, the Hobby Information Department provides highly relevant hobby suggestions based on the user's current location. The Hobby Information Department provides optimal hobby suggestions by considering the user's geographical location. The Hobby Information Department provides highly relevant hobby suggestions based on the user's current location. In this way, the Hobby Information Department can provide optimal hobby suggestions by considering the user's geographical location.

[0148] The Hobby Information Department analyzes users' social media activity when suggesting hobbies and provides relevant suggestions. For example, the Hobby Information Department provides relevant hobby suggestions based on users' social media activity. For example, the Hobby Information Department analyzes users' social media activity and provides optimal hobby suggestions. For example, the Hobby Information Department provides relevant hobby suggestions based on users' social media activity. In this way, the Hobby Information Department can provide relevant hobby suggestions by analyzing users' social media activity.

[0149] The system according to the embodiment is not limited to the example described above, and various modifications are possible, for example, as follows.

[0150] The reception desk can refer to the user's past voice input history when receiving a user's voice input and suggest the most suitable reception method. For example, it can prioritize suggesting voice input methods that the user has frequently used in the past. It can also select the most suitable reception method for a specific time period based on the user's past voice input history. Furthermore, it can analyze the user's past voice input history and suggest the most efficient reception method. In this way, the reception desk can select the most suitable reception method by analyzing the user's past voice input history.

[0151] The analysis unit can estimate the user's emotions when analyzing voice input and adjust the presentation of the analysis based on the estimated emotions. For example, if the user is relaxed, it can provide detailed analysis results. If the user is in a hurry, it can provide concise analysis results. Furthermore, if the user is excited, it can provide visually stimulating analysis results. In this way, the analysis unit can provide more appropriate analysis results by adjusting the presentation of the analysis according to the user's emotions.

[0152] The suggestion function can analyze user behavior patterns and provide optimal suggestions. For example, it can provide optimal suggestions based on actions that users frequently perform. It can also analyze user behavior patterns and select the optimal suggestion algorithm. Furthermore, it can adjust the suggestion algorithm according to the user's behavior patterns. As a result, the suggestion function can provide more appropriate suggestions by applying different suggestion algorithms according to the user's behavior patterns.

[0153] The support department can estimate the user's emotions and adjust its support methods based on those estimates. For example, if the user is stressed, it can provide a relaxing support method. If the user is relaxed, it can provide more detailed support. Furthermore, if the user is in a hurry, it can provide quick support. In this way, the support department can provide more appropriate support by adjusting its support methods according to the user's emotions.

[0154] The advertising department can analyze a user's past ad click history and select the most suitable ad. For example, it can select the most suitable ad based on a user's past ad click history. It can also analyze a user's past ad click history and provide the most suitable ad. Furthermore, it can select the most suitable ad by referring to a user's past ad click history. In this way, the advertising department can select the most suitable ad by analyzing a user's past ad click history.

[0155] The information provider can estimate the user's emotions and adjust how information is displayed based on those emotions. For example, if the user is relaxed, detailed information can be displayed. If the user is in a hurry, concise information can be displayed. Furthermore, if the user is excited, visually stimulating information can be displayed. In this way, the information provider can provide more appropriate information by adjusting how information is displayed according to the user's emotions.

[0156] The Health Management Department can refer to users' past health data and provide optimal health management advice. For example, it can provide optimal health management advice based on users' past health data. It can also analyze users' past health data and provide optimal health management advice. Furthermore, it can refer to users' past health data and provide optimal health management advice. In this way, the Health Management Department can provide optimal health management advice by referring to users' past health data.

[0157] The hobby information department can estimate the user's emotions and adjust its hobby suggestion method based on those emotions. For example, if the user is relaxed, it can provide detailed hobby suggestions. If the user is in a hurry, it can provide concise suggestions. Furthermore, if the user is excited, it can provide visually stimulating hobby suggestions. In this way, the hobby information department can provide more appropriate hobby suggestions by adjusting its method of suggestion according to the user's emotions.

[0158] The reception unit can prioritize receiving voice input that is highly relevant, taking into account the user's geographical location. For example, if the user is in a specific location, it can prioritize receiving voice input related to that location. It can also prioritize receiving voice input that is highly relevant based on the user's current location. Furthermore, it can prioritize receiving the most appropriate voice input by considering the user's geographical location. In this way, the reception unit can prioritize receiving voice input that is highly relevant by taking the user's geographical location into account.

[0159] The analysis unit can determine the priority of analysis based on the submission date of the voice input. For example, it can prioritize analysis of urgent voice inputs. It can also analyze regular voice inputs with a standard priority. Furthermore, it can postpone the analysis of older voice inputs. As a result, the analysis unit can prioritize analysis of urgent voice inputs by determining the priority of analysis based on the submission date of the voice inputs.

[0160] The following briefly describes the processing flow for example form 2.

[0161] Step 1: The reception desk accepts voice input from the user. For example, the user can input questions or instructions by voice. Specifically, the user can give instructions such as "What's the weather like today?" or "Remind me of tomorrow's meeting." Step 2: The analysis unit analyzes the voice input received by the reception unit. For example, it uses a generation AI to analyze the voice input and process appropriate information and tasks. The generation AI uses speech recognition technology to convert the voice into text and then analyzes that text. Step 3: The learning unit learns user interests and behaviors based on the information analyzed by the analysis unit. For example, it learns user interests and behavioral patterns using machine learning algorithms. Step 4: The suggestion unit makes suggestions and notifications at the optimal time based on the information learned by the learning unit. For example, it automatically sends a notification when the user needs weather information. Also, if the user repeatedly performs a specific task, it makes suggestions to make that task more efficient. Step 5: The support team provides personalized support based on the information proposed by the proposal team. For example, if a user is working on a specific project, they will provide information and resources related to that project. They will also manage the user's schedule and remind them of important events and tasks.

[0162] The specific processing unit 290 transmits the result of the specific processing to the smart device 14. In the smart device 14, the control unit 46A causes the output device 40 to output the result of the specific processing. The microphone 38B acquires audio indicating user input for the result of the specific processing. The control unit 46A transmits the audio data indicating user input acquired by the microphone 38B to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the audio data.

[0163] Data generation model 58 is a form of so-called generative AI (Artificial Intelligence). An example of data generation model 58 is ChatGPT (registered trademark) (Internet search).<URL: https: / / openai.com / blog / chatgpt> Examples of generative AI include text generation AI, image generation AI, and multimodal generation AI. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 is input with prompts containing instructions, and with inference data such as audio data representing speech, text data representing text, and image data representing images (e.g., still image data or video data). The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference result in one or more data formats from audio data, text data, and image data. The data generation model 58 includes, for example, text generation AI, image generation AI, and multimodal generation AI. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The specific processing unit 290 performs the specific processing described above using the data generation model 58. The data generation model 58 may be a fine-tuned model that outputs inference results from prompts that do not contain instructions, in which case the data generation model 58 can output inference results from prompts that do not contain instructions. In the data processing device 12, etc., there are multiple types of data generation models 58, and the data generation model 58 includes AI other than generative AI. AI other than generative AI includes, for example, linear regression, logistic regression, decision trees, random forests, support vector machines (SVMs), k-means clustering, convolutional neural networks (CNNs), recurrent neural networks (RNNs), generative adversarial networks (GANs), or naive Bayes, and can perform various processes, but is not limited to these examples. Also, the AI ​​may be an AI agent. Furthermore, when the processing of each of the above parts is performed by the AI, the processing may be performed by the AI ​​in part or in whole, but is not limited to this example.Furthermore, processing performed by AI, including generative AI, may be replaced with rule-based processing, and rule-based processing may be replaced with processing performed by AI, including generative AI.

[0164] Furthermore, the processing performed by the data processing system 10 described above is carried out by the specific processing unit 290 of the data processing device 12 or the control unit 46A of the smart device 14, but it may also be carried out by the specific processing unit 290 of the data processing device 12 and the control unit 46A of the smart device 14. In addition, the specific processing unit 290 of the data processing device 12 acquires or collects information necessary for processing from the smart device 14 or an external device, and the smart device 14 acquires or collects information necessary for processing from the data processing device 12 or an external device.

[0165] Each of the multiple elements described above, including the reception unit, analysis unit, learning unit, proposal unit, and support unit, is implemented in at least one of the smart device 14 and the data processing unit 12. For example, the reception unit receives the user's voice input using the microphone 38B of the smart device 14 and transmits the voice data to the data processing unit 12 via the control unit 46A. The analysis unit is implemented by the specific processing unit 290 of the data processing unit 12 and analyzes the voice input using a generation AI. The learning unit is implemented by the specific processing unit 290 of the data processing unit 12 and learns the user's interests and behavior using a machine learning algorithm. The proposal unit is implemented by the specific processing unit 290 of the data processing unit 12 and makes proposals and notifications at the optimal timing based on the learned information. The support unit is implemented by the specific processing unit 290 of the data processing unit 12 and provides personalized support based on the proposed information. The correspondence between each unit and the device or control unit is not limited to the example described above and can be changed in various ways.

[0166] [Second Embodiment] Figure 3 shows an example of the configuration of the data processing system 210 according to the second embodiment.

[0167] As shown in Figure 3, the data processing system 210 includes a data processing device 12 and smart glasses 214. An example of the data processing device 12 is a server.

[0168] The data processing device 12 comprises a computer 22, a database 24, and a communication interface 26. The computer 22 comprises a processor 28, RAM 30, and storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication interface 26 are also connected to the bus 34. The communication interface 26 is connected to a network 54. An example of the network 54 is a WAN and / or LAN.

[0169] The smart glasses 214 include a computer 36, a microphone 238, a speaker 240, a camera 42, and a communication interface 44. The computer 36 includes a processor 46, RAM 48, and storage 50. The processor 46, RAM 48, and storage 50 are connected to a bus 52. The microphone 238, speaker 240, and camera 42 are also connected to the bus 52.

[0170] The microphone 238 receives voice signals from the user and accepts instructions from the user. The microphone 238 captures the voice signals from the user, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to the instructions from the processor 46.

[0171] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an image sensor such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, which captures images of the area around the user (for example, an imaging range defined by a field of view equivalent to the field of vision of a typical healthy person).

[0172] Communication interface 44 is connected to network 54. Communication interfaces 44 and 26 are responsible for the exchange of various information between processor 46 and processor 28 via network 54. The exchange of various information between processor 46 and processor 28 using communication interfaces 44 and 26 is performed in a secure manner.

[0173] Figure 4 shows an example of the main functions of the data processing device 12 and the smart glasses 214. As shown in Figure 4, the data processing device 12 performs specific processing by the processor 28. The storage 32 stores the specific processing program 56.

[0174] The processor 28 reads a specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 acting as a specific processing unit 290 according to the specific processing program 56 executed on the RAM 30.

[0175] Storage 32 stores the data generation model 58 and the emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290. The identification processing unit 290 can estimate the user's emotions using the emotion identification model 59 and perform identification processing using the user's emotions. The emotion estimation function (emotion identification function) using the emotion identification model 59 performs various estimations and predictions regarding the user's emotions, including but not limited to these examples. Furthermore, emotion estimation and prediction also include, for example, emotion analysis.

[0176] In the smart glasses 214, specific processing is performed by the processor 46. The storage 50 stores a specific processing program 60. The processor 46 reads the specific processing program 60 from the storage 50 and executes the read specific processing program 60 on the RAM 48. The specific processing is realized by the processor 46 acting as a control unit 46A according to the specific processing program 60 executed on the RAM 48. The smart glasses 214 also have a data generation model 58 and an emotion identification model 59, similar to the data generation model and emotion identification model 59, and can perform processing similar to that of the specific processing unit 290 using these models.

[0177] Furthermore, other devices besides the data processing device 12 may also have the data generation model 58. For example, a server device may have the data generation model 58. In this case, the data processing device 12 obtains processing results (such as prediction results) using the data generation model 58 by communicating with the server device that has the data generation model 58. Also, the data processing device 12 may be a server device or a terminal device owned by the user (for example, a mobile phone, robot, home appliance, etc.).

[0178] The specific processing unit 290 transmits the result of the specific processing to the smart glasses 214. In the smart glasses 214, the control unit 46A causes the speaker 240 to output the result of the specific processing. The microphone 238 acquires audio indicating user input for the result of the specific processing. The control unit 46A transmits the audio data indicating user input acquired by the microphone 238 to the data processing unit 12. In the data processing unit 12, the specific processing unit 290 acquires the audio data.

[0179] The data generation model 58 is a so-called generative AI. An example of a data generation model 58 is a generative AI such as ChatGPT. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 is input with prompts containing instructions, and inference data such as audio data representing speech, text data representing text, and image data representing images (e.g., still image data or video data). The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference result in one or more data formats such as audio data, text data, and image data. The data generation model 58 includes, for example, text generation AI, image generation AI, and multimodal generation AI. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The specific processing unit 290 performs the specific processing described above using the data generation model 58. The data generation model 58 may be a fine-tuned model that outputs inference results from prompts that do not contain instructions, in which case the data generation model 58 can output inference results from prompts that do not contain instructions. In the data processing device 12, etc., there are multiple types of data generation models 58, and the data generation model 58 includes AI other than generative AI. AI other than generative AI includes, for example, linear regression, logistic regression, decision trees, random forests, support vector machines (SVM), k-means clustering, convolutional neural networks (CNN), recurrent neural networks (RNN), generative adversarial networks (GAN), or naive Bayes, and can perform various processes, but is not limited to these examples. Also, the AI ​​may be an AI agent. Furthermore, when the processing of each part described above is performed by the AI, the processing may be performed by the AI ​​in part or in whole, but is not limited to this example. Also, processing performed by an AI including a generative AI may be replaced by rule-based processing, and rule-based processing may be replaced by processing performed by an AI including a generative AI.

[0180] The data processing system 210 according to the second embodiment performs the same processing as the data processing system 10 according to the first embodiment. The processing by the data processing system 210 is performed by the specific processing unit 290 of the data processing device 12 or the control unit 46A of the smart glasses 214, but it may also be performed by the specific processing unit 290 of the data processing device 12 and the control unit 46A of the smart glasses 214. In addition, the specific processing unit 290 of the data processing device 12 acquires or collects information necessary for processing from the smart glasses 214 or an external device, and the smart glasses 214 acquires or collects information necessary for processing from the data processing device 12 or an external device.

[0181] Each of the multiple elements described above, including the reception unit, analysis unit, learning unit, proposal unit, and support unit, is implemented in at least one of the smart glasses 214 and the data processing unit 12. For example, the reception unit receives the user's voice input using the microphone 238 of the smart glasses 214 and transmits the voice data to the data processing unit 12 via the control unit 46A. The analysis unit is implemented by the specific processing unit 290 of the data processing unit 12 and analyzes the voice input using a generation AI. The learning unit is implemented by the specific processing unit 290 of the data processing unit 12 and learns the user's interests and behavior using a machine learning algorithm. The proposal unit is implemented by the specific processing unit 290 of the data processing unit 12 and makes proposals and notifications at the optimal timing based on the learned information. The support unit is implemented by the specific processing unit 290 of the data processing unit 12 and provides personalized support based on the proposed information. The correspondence between each unit and the device or control unit is not limited to the example described above and can be changed in various ways.

[0182] [Third Embodiment] Figure 5 shows an example of the configuration of the data processing system 310 according to the third embodiment.

[0183] As shown in Figure 5, the data processing system 310 includes a data processing device 12 and a headset terminal 314. An example of the data processing device 12 is a server.

[0184] The data processing device 12 comprises a computer 22, a database 24, and a communication interface 26. The computer 22 comprises a processor 28, RAM 30, and storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication interface 26 are also connected to the bus 34. The communication interface 26 is connected to a network 54. An example of the network 54 is a WAN and / or LAN.

[0185] The headset terminal 314 includes a computer 36, a microphone 238, a speaker 240, a camera 42, a communication interface 44, and a display 343. The computer 36 includes a processor 46, RAM 48, and storage 50. The processor 46, RAM 48, and storage 50 are connected to a bus 52. The microphone 238, speaker 240, camera 42, and display 343 are also connected to the bus 52.

[0186] The microphone 238 receives voice signals from the user and accepts instructions from the user. The microphone 238 captures the voice signals from the user, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to the instructions from the processor 46.

[0187] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an image sensor such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, which captures images of the area around the user (for example, an imaging range defined by a field of view equivalent to the field of vision of a typical healthy person).

[0188] Communication interface 44 is connected to network 54. Communication interfaces 44 and 26 are responsible for the exchange of various information between processor 46 and processor 28 via network 54. The exchange of various information between processor 46 and processor 28 using communication interfaces 44 and 26 is performed in a secure manner.

[0189] Figure 6 shows an example of the main functions of the data processing device 12 and the headset terminal 314. As shown in Figure 6, the data processing device 12 performs specific processing using the processor 28. The storage 32 stores the specific processing program 56.

[0190] The processor 28 reads a specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 acting as a specific processing unit 290 according to the specific processing program 56 executed on the RAM 30.

[0191] Storage 32 stores the data generation model 58 and the emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290. The identification processing unit 290 can estimate the user's emotions using the emotion identification model 59 and perform identification processing using the user's emotions. The emotion estimation function (emotion identification function) using the emotion identification model 59 performs various estimations and predictions regarding the user's emotions, including but not limited to these examples. Furthermore, emotion estimation and prediction also include, for example, emotion analysis.

[0192] In the headset terminal 314, specific processing is performed by the processor 46. The storage 50 stores a specific program 60. The processor 46 reads the specific program 60 from the storage 50 and executes the read specific program 60 on the RAM 48. The specific processing is realized by the processor 46 acting as a control unit 46A according to the specific program 60 executed on the RAM 48. The headset terminal 314 also has a data generation model 58 and an emotion identification model 59, similar to the data generation model and emotion identification model 59, and can perform processing similar to that of the specific processing unit 290 using these models.

[0193] Furthermore, other devices besides the data processing device 12 may also have the data generation model 58. For example, a server device may have the data generation model 58. In this case, the data processing device 12 obtains processing results (such as prediction results) using the data generation model 58 by communicating with the server device that has the data generation model 58. Also, the data processing device 12 may be a server device or a terminal device owned by the user (for example, a mobile phone, robot, home appliance, etc.).

[0194] The specific processing unit 290 transmits the result of the specific processing to the headset terminal 314. In the headset terminal 314, the control unit 46A causes the speaker 240 and display 343 to output the result of the specific processing. The microphone 238 acquires audio indicating user input for the result of the specific processing. The control unit 46A transmits the audio data indicating user input acquired by the microphone 238 to the data processing unit 12. In the data processing unit 12, the specific processing unit 290 acquires the audio data.

[0195] The data generation model 58 is a so-called generative AI. An example of a data generation model 58 is a generative AI such as ChatGPT. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 is input with prompts containing instructions, and inference data such as audio data representing speech, text data representing text, and image data representing images (e.g., still image data or video data). The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference result in one or more data formats such as audio data, text data, and image data. The data generation model 58 includes, for example, text generation AI, image generation AI, and multimodal generation AI. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The specific processing unit 290 performs the specific processing described above using the data generation model 58. The data generation model 58 may be a fine-tuned model that outputs inference results from prompts that do not contain instructions, in which case the data generation model 58 can output inference results from prompts that do not contain instructions. In the data processing device 12, etc., there are multiple types of data generation models 58, and the data generation model 58 includes AI other than generative AI. AI other than generative AI includes, for example, linear regression, logistic regression, decision trees, random forests, support vector machines (SVM), k-means clustering, convolutional neural networks (CNN), recurrent neural networks (RNN), generative adversarial networks (GAN), or naive Bayes, and can perform various processes, but is not limited to these examples. Also, the AI ​​may be an AI agent. Furthermore, when the processing of each part described above is performed by the AI, the processing may be performed by the AI ​​in part or in whole, but is not limited to this example. Also, processing performed by an AI including a generative AI may be replaced by rule-based processing, and rule-based processing may be replaced by processing performed by an AI including a generative AI.

[0196] The data processing system 310 according to the third embodiment performs the same processing as the data processing system 10 according to the first embodiment. The processing by the data processing system 310 is performed by the specific processing unit 290 of the data processing device 12 or the control unit 46A of the headset terminal 314, but may also be performed by the specific processing unit 290 of the data processing device 12 and the control unit 46A of the headset terminal 314. In addition, the specific processing unit 290 of the data processing device 12 acquires or collects information necessary for processing from the headset terminal 314 or an external device, and the headset terminal 314 acquires or collects information necessary for processing from the data processing device 12 or an external device.

[0197] Each of the multiple elements described above, including the reception unit, analysis unit, learning unit, proposal unit, and support unit, is implemented in at least one of the headset terminal 314 and the data processing unit 12. For example, the reception unit receives the user's voice input using the microphone 238 of the headset terminal 314 and transmits the voice data to the data processing unit 12 via the control unit 46A. The analysis unit is implemented by the specific processing unit 290 of the data processing unit 12 and analyzes the voice input using a generation AI. The learning unit is implemented by the specific processing unit 290 of the data processing unit 12 and learns the user's interests and behavior using a machine learning algorithm. The proposal unit is implemented by the specific processing unit 290 of the data processing unit 12 and makes proposals and notifications at the optimal timing based on the learned information. The support unit is implemented by the specific processing unit 290 of the data processing unit 12 and provides personalized support based on the proposed information. The correspondence between each unit and the device or control unit is not limited to the example described above and can be changed in various ways.

[0198] [Fourth Embodiment] Figure 7 shows an example of the configuration of the data processing system 410 according to the fourth embodiment.

[0199] As shown in Figure 7, the data processing system 410 includes a data processing device 12 and a robot 414. An example of the data processing device 12 is a server.

[0200] The data processing device 12 comprises a computer 22, a database 24, and a communication interface 26. The computer 22 comprises a processor 28, RAM 30, and storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication interface 26 are also connected to the bus 34. The communication interface 26 is connected to a network 54. An example of the network 54 is a WAN and / or LAN.

[0201] The robot 414 includes a computer 36, a microphone 238, a speaker 240, a camera 42, a communication interface 44, and a controlled object 443. The computer 36 includes a processor 46, RAM 48, and storage 50. The processor 46, RAM 48, and storage 50 are connected to a bus 52. The microphone 238, speaker 240, camera 42, and controlled object 443 are also connected to the bus 52.

[0202] The microphone 238 receives voice signals from the user and accepts instructions from the user. The microphone 238 captures the voice signals from the user, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to the instructions from the processor 46.

[0203] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an image sensor such as a CMOS image sensor or CCD image sensor, which captures images of the area around the user (for example, an imaging range defined by a field of view equivalent to the field of vision of a typical healthy person).

[0204] Communication interface 44 is connected to network 54. Communication interfaces 44 and 26 are responsible for the exchange of various information between processor 46 and processor 28 via network 54. The exchange of various information between processor 46 and processor 28 using communication interfaces 44 and 26 is performed in a secure manner.

[0205] The controlled object 443 includes a display device, LEDs in the eyes, and motors that drive the arms, hands, and feet. The posture and gestures of the robot 414 are controlled by controlling the motors of the arms, hands, and feet. Some of the robot 414's emotions can be expressed by controlling these motors. The robot 414's facial expressions can also be expressed by controlling the illumination state of the LEDs in its eyes.

[0206] Figure 8 shows an example of the main functions of the data processing device 12 and the robot 414. As shown in Figure 8, the data processing device 12 performs specific processing using the processor 28. The storage 32 stores the specific processing program 56.

[0207] The processor 28 reads a specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 acting as a specific processing unit 290 according to the specific processing program 56 executed on the RAM 30.

[0208] Storage 32 stores the data generation model 58 and the emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290. The identification processing unit 290 can estimate the user's emotions using the emotion identification model 59 and perform identification processing using the user's emotions. The emotion estimation function (emotion identification function) using the emotion identification model 59 performs various estimations and predictions regarding the user's emotions, including but not limited to these examples. Furthermore, emotion estimation and prediction also include, for example, emotion analysis.

[0209] In robot 414, specific processing is performed by processor 46. A specific program 60 is stored in storage 50. Processor 46 reads the specific program 60 from storage 50 and executes it on RAM 48. The specific processing is achieved by processor 46 acting as a control unit 46A according to the specific program 60 executed on RAM 48. Robot 414 also has data generation model 58 and emotion identification model 59, similar to those of the robot, and can perform processing similar to that of the specific processing unit 290 using these models.

[0210] Furthermore, other devices besides the data processing device 12 may also have the data generation model 58. For example, a server device may have the data generation model 58. In this case, the data processing device 12 obtains processing results (such as prediction results) using the data generation model 58 by communicating with the server device that has the data generation model 58. Also, the data processing device 12 may be a server device or a terminal device owned by the user (for example, a mobile phone, robot, home appliance, etc.).

[0211] The specific processing unit 290 transmits the result of the specific processing to the robot 414. In the robot 414, the control unit 46A causes the speaker 240 and the controlled object 443 to output the result of the specific processing. The microphone 238 acquires audio indicating user input for the result of the specific processing. The control unit 46A transmits the audio data indicating user input acquired by the microphone 238 to the data processing unit 12. In the data processing unit 12, the specific processing unit 290 acquires the audio data.

[0212] The data generation model 58 is a so-called generative AI. An example of a data generation model 58 is a generative AI such as ChatGPT. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 is input with prompts containing instructions, and inference data such as audio data representing speech, text data representing text, and image data representing images (e.g., still image data or video data). The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference result in one or more data formats such as audio data, text data, and image data. The data generation model 58 includes, for example, text generation AI, image generation AI, and multimodal generation AI. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The specific processing unit 290 performs the specific processing described above using the data generation model 58. The data generation model 58 may be a fine-tuned model that outputs inference results from prompts that do not contain instructions, in which case the data generation model 58 can output inference results from prompts that do not contain instructions. In the data processing device 12, etc., there are multiple types of data generation models 58, and the data generation model 58 includes AI other than generative AI. AI other than generative AI includes, for example, linear regression, logistic regression, decision trees, random forests, support vector machines (SVM), k-means clustering, convolutional neural networks (CNN), recurrent neural networks (RNN), generative adversarial networks (GAN), or naive Bayes, and can perform various processes, but is not limited to these examples. Also, the AI ​​may be an AI agent. Furthermore, when the processing of each part described above is performed by the AI, the processing may be performed by the AI ​​in part or in whole, but is not limited to this example. Also, processing performed by an AI including a generative AI may be replaced by rule-based processing, and rule-based processing may be replaced by processing performed by an AI including a generative AI.

[0213] The data processing system 410 according to the fourth embodiment performs the same processing as the data processing system 10 according to the first embodiment. The processing by the data processing system 410 is performed by the specific processing unit 290 of the data processing device 12 or the control unit 46A of the robot 414, but it may also be performed by the specific processing unit 290 of the data processing device 12 and the control unit 46A of the robot 414. In addition, the specific processing unit 290 of the data processing device 12 acquires or collects information necessary for processing from the robot 414 or an external device, and the robot 414 acquires or collects information necessary for processing from the data processing device 12 or an external device.

[0214] Each of the multiple elements described above, including the reception unit, analysis unit, learning unit, proposal unit, and support unit, is implemented in at least one of the robot 414 and the data processing unit 12. For example, the reception unit receives the user's voice input using the microphone 238 of the robot 414 and transmits the voice data to the data processing unit 12 via the control unit 46A. The analysis unit is implemented by the specific processing unit 290 of the data processing unit 12 and analyzes the voice input using a generation AI. The learning unit is implemented by the specific processing unit 290 of the data processing unit 12 and learns the user's interests and behavior using a machine learning algorithm. The proposal unit is implemented by the specific processing unit 290 of the data processing unit 12 and makes proposals and notifications at the optimal timing based on the learned information. The support unit is implemented by the specific processing unit 290 of the data processing unit 12 and provides personalized support based on the proposed information. The correspondence between each unit and the device or control unit is not limited to the example described above and can be changed in various ways.

[0215] Furthermore, the emotion identification model 59, acting as an emotion engine, may determine the user's emotion according to a specific mapping. Specifically, the emotion identification model 59 may determine the user's emotion according to a specific mapping, which is an emotion map (see Figure 9). Similarly, the emotion identification model 59 may also determine the robot's emotion, and the identification processing unit 290 may perform identification processing using the robot's emotion.

[0216] Figure 9 shows the emotion map 400, in which multiple emotions are mapped. In the emotion map 400, emotions are arranged in concentric circles radiating from the center. The closer to the center of the concentric circles, the more primitive the emotions are located. Further out of the concentric circles, emotions representing states and actions arising from mental states are located. Emotion is a concept that includes feelings and mental states. On the left side of the concentric circles, emotions that are generally generated from reactions occurring in the brain are located. On the right side of the concentric circles, emotions that are generally induced by situational judgment are located. Above and below the concentric circles, emotions that are generally generated from reactions occurring in the brain and induced by situational judgment are located. In addition, the emotion of "pleasure" is located on the upper side of the concentric circles, and the emotion of "displeasure" is located on the lower side. Thus, in the emotion map 400, multiple emotions are mapped based on the structure in which emotions arise, and emotions that are likely to occur simultaneously are mapped close together.

[0217] These emotions are distributed at the 3 o'clock position on the Emotion Map 400, and usually fluctuate between feelings of security and anxiety. In the right half of the Emotion Map 400, situational awareness takes precedence over internal feelings, resulting in a calm impression.

[0218] The inside of the Emotion Map 400 represents inner thoughts, while the outside represents actions. Therefore, the further you go from the outside of the Emotion Map 400, the more visible (expressed in actions) your emotions become.

[0219] Here, human emotions are based on various balances, such as posture and blood sugar levels. When these balances deviate from the ideal, it results in discomfort, and when they approach the ideal, it results in pleasure. Similarly, in robots, cars, and motorcycles, emotions can be created based on various balances, such as posture and battery level. When these balances deviate from the ideal, it results in discomfort, and when they approach the ideal, it results in pleasure. The emotion map can be generated based, for example, on Dr. Mitsuyoshi's emotion map (Research on a system for analyzing brain physiological signals of speech emotion recognition and emotion, Tokushima University, doctoral dissertation: https: / / ci.nii.ac.jp / naid / 500000375379). The left half of the emotion map contains emotions belonging to a region called "response," where sensation is dominant. The right half of the emotion map contains emotions belonging to a region called "situation," where situational awareness is dominant.

[0220] The emotion map defines two emotions that promote learning. One is the emotion around the middle of the negative "repentance" and "reflection" on the situation side. In other words, it is when the robot experiences negative emotions such as "I never want to feel this way again" or "I don't want to be scolded again." The other is the emotion around the positive "desire" on the reaction side. In other words, it is when the robot has positive feelings such as "I want more" or "I want to know more."

[0221] The emotion identification model 59 inputs user input into a pre-trained neural network, obtains emotion values ​​representing each emotion shown in the emotion map 400, and determines the user's emotion. This neural network is pre-trained based on multiple training data sets, which are combinations of user input and emotion values ​​representing each emotion shown in the emotion map 400. Furthermore, this neural network is trained so that emotions located close together have similar values, as shown in the emotion map 900 in Figure 10. Figure 10 shows an example where multiple emotions such as "reassured," "calm," and "confident" have similar emotion values.

[0222] In the above embodiment, an example was given in which a specific process is performed by a single computer 22. However, the technology of this disclosure is not limited thereto, and a distributed processing method for the specific process may be used, which includes computer 22 and multiple other computers.

[0223] In the above embodiment, an example was given in which the specific processing program 56 is stored in the storage 32, but the technology of this disclosure is not limited thereto. For example, the specific processing program 56 may be stored in a portable, computer-readable, non-temporary storage medium such as a USB (Universal Serial Bus) memory. The specific processing program 56 stored in the non-temporary storage medium is installed in the computer 22 of the data processing device 12. The processor 28 executes specific processing according to the specific processing program 56.

[0224] Alternatively, the specific processing program 56 may be stored in a storage device such as a server connected to the data processing device 12 via the network 54, and the specific processing program 56 may be downloaded and installed on the computer 22 in response to a request from the data processing device 12.

[0225] Furthermore, it is not necessary to store the entirety of the specific processing program 56 in a storage device such as a server connected to the data processing device 12 via the network 54, or to store the entirety of the specific processing program 56 in the storage 32; it is acceptable to store only a portion of the specific processing program 56.

[0226] The following types of processors can be used as hardware resources to perform specific processing. Examples of processors include a CPU, a general-purpose processor that functions as a hardware resource to perform specific processing by executing software, i.e., a program. Other examples of processors include dedicated electrical circuits, such as FPGAs (Field-Programmable Gate Arrays), PLDs (Programmable Logic Devices), or ASICs (Application Specific Integrated Circuits), which have circuit configurations specifically designed to perform specific processing. All of these processors have built-in or connected memory, and all of them perform specific processing by using memory.

[0227] The hardware resource that performs a specific process may consist of one of these various processors, or it may consist of a combination of two or more processors of the same or different types (for example, a combination of multiple FPGAs, or a combination of a CPU and an FPGA). Alternatively, the hardware resource that performs a specific process may consist of a single processor.

[0228] Examples of configurations using a single processor include, firstly, a configuration in which one or more CPUs and software are combined to form a single processor, and this processor functions as a hardware resource that performs a specific process. Secondly, there is a configuration using a processor that realizes the functions of the entire system, including multiple hardware resources that perform a specific process, on a single IC chip, as exemplified by SoCs (System-on-a-chip). In this way, a specific process is realized using one or more of the above types of processors as hardware resources.

[0229] Furthermore, the hardware structure of these various processors can more specifically utilize electrical circuits that combine circuit elements such as semiconductor devices. Also, the specific processing described above is merely an example. Therefore, it goes without saying that unnecessary steps can be deleted, new steps added, or the processing order rearranged, as long as it does not deviate from the main purpose.

[0230] Furthermore, although the above-described examples were divided into four embodiments, some or all of these embodiments may be combined. Also, the smart device 14, smart glasses 214, headset terminal 314, and robot 414 are just examples, and they may be combined, or other devices may be used. Also, although the above-described examples were divided into two embodiments, Embodiment 1 and Embodiment 2, these may be combined.

[0231] The descriptions and illustrations presented above are detailed explanations of the technical aspects of this disclosure and are merely examples of the technical aspects. For example, the above descriptions of the structure, function, operation, and effect are examples of the structure, function, operation, and effect of the technical aspects of this disclosure. Therefore, it goes without saying that you may delete unnecessary parts, add new elements, or replace elements in the descriptions and illustrations presented above, as long as you do not deviate from the essence of the technical aspects of this disclosure. Furthermore, in order to avoid confusion and facilitate understanding of the technical aspects of this disclosure, explanations of common technical knowledge and other things that do not require special explanation to enable the implementation of the technical aspects of this disclosure have been omitted from the descriptions and illustrations presented above.

[0232] All documents, patent applications, and technical standards described herein are incorporated by reference to the same extent as if each individual document, patent application, and technical standard were specifically and individually noted to be incorporated by reference.

[0233] (Note 1) A reception area that accepts voice input from users, An analysis unit analyzes the voice input received by the reception unit, A learning unit learns the user's interests and behavior based on the information analyzed by the aforementioned analysis unit, A proposal unit makes suggestions and notifications at the optimal timing based on the information learned by the aforementioned learning unit, The system includes a support unit that provides personalized support based on the information proposed by the proposal unit. A system characterized by the following features. (Note 2) The aforementioned proposal section is, It includes an advertising department that provides advertisements based on user interests and behavior. The system described in Appendix 1, characterized by the features described herein. (Note 3) The aforementioned support unit is It includes an information provision department that provides information to enrich users' lives. The system described in Appendix 1, characterized by the features described herein. (Note 4) The aforementioned support unit is It has a health management department that provides information on users' health management. The system described in Appendix 1, characterized by the features described herein. (Note 5) The aforementioned support unit is It includes a hobby information section that provides information about users' hobbies and interests. The system described in Appendix 1, characterized by the features described herein. (Note 6) The aforementioned reception unit is The system estimates the user's emotions and adjusts the timing of voice input acceptance based on the estimated emotions. The system described in Appendix 1, characterized by the features described herein. (Note 7) The aforementioned reception unit is The system analyzes the user's past voice input history and selects the optimal reception method. The system described in Appendix 1, characterized by the features described herein. (Note 8) The aforementioned reception unit is When receiving voice input, filtering is performed based on the user's current situation and areas of interest. The system described in Appendix 1, characterized by the features described herein. (Note 9) The aforementioned reception unit is It estimates the user's emotions and determines the priority of voice input to accept based on the estimated emotions. The system described in Appendix 1, characterized by the features described herein. (Note 10) The aforementioned reception unit is When receiving voice input, the system prioritizes accepting input that is highly relevant, taking into account the user's geographical location. The system described in Appendix 1, characterized by the features described herein. (Note 11) The aforementioned reception unit is When receiving voice input, the system analyzes the user's social media activity and accepts relevant input. The system described in Appendix 1, characterized by the features described herein. (Note 12) The aforementioned analysis unit, The system estimates the user's emotions and adjusts the representation of the analysis based on the estimated emotions. The system described in Appendix 1, characterized by the features described herein. (Note 13) The aforementioned analysis unit, During analysis, the level of detail of the analysis is adjusted based on the importance of the voice input. The system described in Appendix 1, characterized by the features described herein. (Note 14) The aforementioned analysis unit, During analysis, different analysis algorithms are applied depending on the category of the audio input. The system described in Appendix 1, characterized by the features described herein. (Note 15) The aforementioned analysis unit, It estimates the user's emotions and adjusts the length of the analysis based on the estimated user emotions. The system described in Appendix 1, characterized by the features described herein. (Note 16) The aforementioned analysis unit, During analysis, the priority of analysis is determined based on when the voice input was submitted. The system described in Appendix 1, characterized by the features described herein. (Note 17) The aforementioned analysis unit, During analysis, the order of analysis is adjusted based on the relevance of the audio input. The system described in Appendix 1, characterized by the features described herein. (Note 18) The aforementioned learning unit, The system estimates the user's emotions and selects training data based on those estimated emotions. The system described in Appendix 1, characterized by the features described herein. (Note 19) The aforementioned learning unit, During training, the learning algorithm is optimized by referring to past training data. The system described in Appendix 1, characterized by the features described herein. (Note 20) The aforementioned learning unit, During training, user behavior patterns are analyzed to improve the accuracy of the learning process. The system described in Appendix 1, characterized by the features described herein. (Note 21) The aforementioned learning unit, It estimates the user's emotions and adjusts the learning frequency based on the estimated user emotions. The system described in Appendix 1, characterized by the features described herein. (Note 22) The aforementioned learning unit, During training, the training data is weighted based on when the voice input was submitted. The system described in Appendix 1, characterized by the features described herein. (Note 23) The aforementioned learning unit, During training, the system analyzes users' social media activity to supplement the training data. The system described in Appendix 1, characterized by the features described herein. (Note 24) The aforementioned proposal section is, It estimates the user's emotions and adjusts the way suggestions are presented based on those estimated emotions. The system described in Appendix 1, characterized by the features described herein. (Note 25) The aforementioned proposal section is, When making a proposal, adjust the level of detail based on the user's level of interest. The system described in Appendix 1, characterized by the features described herein. (Note 26) The aforementioned proposal section is, When making suggestions, different suggestion algorithms are applied depending on the user's behavior patterns. The system described in Appendix 1, characterized by the features described herein. (Note 27) The aforementioned proposal section is, It estimates the user's emotions and adjusts the length of the suggestion based on the estimated emotions. The system described in Appendix 1, characterized by the features described herein. (Note 28) The aforementioned proposal section is, When making suggestions, the priority of suggestions is determined based on the user's behavior history. The system described in Appendix 1, characterized by the features described herein. (Note 29) The aforementioned proposal section is, When making suggestions, adjust the order of suggestions based on user relevance. The system described in Appendix 1, characterized by the features described herein. (Note 30) The aforementioned support unit is It estimates the user's emotions and adjusts the support method based on the estimated user emotions. The system described in Appendix 1, characterized by the features described herein. (Note 31) The aforementioned support unit is During support, we analyze the user's past behavior to select the most appropriate support method. The system described in Appendix 1, characterized by the features described herein. (Note 32) The aforementioned support unit is During support, customize the support methods based on the user's current situation. The system described in Appendix 1, characterized by the features described herein. (Note 33) The support unit estimates the user's emotion and determines the priority of support based on the estimated user emotion The system according to Appendix 1, characterized by the above. (Appendix 34) The support unit selects an optimal support method considering the user's geographical location information during support The system according to Appendix 1, characterized by the above. (Appendix 35) The support unit analyzes the user's social media activities and proposes support means during support The system according to Appendix 1, characterized by the above. (Appendix 36) The advertisement providing unit estimates the user's emotion and adjusts the advertisement display method based on the estimated user emotion The system according to Appendix 2, characterized by the above. (Appendix 37) The advertisement providing unit selects an optimal advertisement by analyzing the user's past advertisement click history during advertisement provision The system according to Appendix 2, characterized by the above. (Appendix 38) The advertisement providing unit filters advertisements based on the user's current situation and areas of interest during advertisement provision The system according to Appendix 2, characterized by the above. (Appendix 39) The advertisement providing unit estimates the user's emotion and determines the priority of advertisements based on the estimated user emotion The system according to Appendix 2, characterized by the above. (Appendix 40) The advertisement providing unit provides highly relevant advertisements considering the user's geographical location information during advertisement provision The system according to Appendix 2, characterized by the above. (Appendix 41) The aforementioned advertising department, When providing advertisements, we analyze users' social media activity to deliver relevant ads. The system described in Appendix 2, characterized by the features described herein. (Note 42) The aforementioned information provision unit, It estimates the user's emotions and adjusts how information is displayed based on those estimated emotions. The system described in Appendix 3, characterized by the features described herein. (Note 43) The aforementioned information provision unit, When providing information, the system analyzes the user's past information browsing history to select the most relevant information. The system described in Appendix 3, characterized by the features described herein. (Note 44) The aforementioned information provision unit, When providing information, filter the information based on the user's current situation and areas of interest. The system described in Appendix 3, characterized by the features described herein. (Note 45) The aforementioned information provision unit, It estimates the user's emotions and prioritizes information based on those estimated emotions. The system described in Appendix 3, characterized by the features described herein. (Note 46) The aforementioned information provision unit, When providing information, we will consider the user's geographical location to provide highly relevant information. The system described in Appendix 3, characterized by the features described herein. (Note 47) The aforementioned information provision unit, When providing information, we analyze the user's social media activity and provide relevant information. The system described in Appendix 3, characterized by the features described herein. (Note 48) The aforementioned health management department, It estimates the user's emotions and adjusts health management advice based on those estimated emotions. The system described in Appendix 4, characterized by the features described herein. (Note 49) The health management department refers to the user's past health data to provide optimal advice when giving health management advice The system according to appendix 4, characterized by the above. (Appendix 50) The health management department customizes the advice considering the user's current health condition when giving health management advice The system according to appendix 4, characterized by the above. (Appendix 51) The health management department estimates the user's emotion and determines the priority of health management based on the estimated user's emotion The system according to appendix 4, characterized by the above. (Appendix 52) The health management department refers to the user's device information to provide optimal advice when giving health management advice The system according to appendix 4, characterized by the above. (Appendix 53) The health management department analyzes the user's social media activities to provide relevant advice when giving health management advice The system according to appendix 4, characterized by the above. (Appendix 54) The hobby information department estimates the user's emotion and adjusts the method of hobby recommendation based on the estimated user's emotion The system according to appendix 5, characterized by the above. (Appendix 55) The hobby information department refers to the user's past hobby history to provide optimal recommendations when making hobby recommendations The system according to appendix 5, characterized by the above. (Appendix 56) The hobby information department filters the recommendations based on the user's current situation and areas of interest when making hobby recommendations The system according to appendix 5, characterized by the above. (Note 57) The aforementioned hobby information department, It estimates the user's emotions and determines the priority of hobbies based on those estimated emotions. The system described in Appendix 5, characterized by the features described herein. (Note 58) The aforementioned hobby information department, When suggesting hobbies, we provide optimal suggestions by taking into account the user's geographical location. The system described in Appendix 5, characterized by the features described herein. (Note 59) The aforementioned hobby information department, When suggesting hobbies, the system analyzes the user's social media activity to provide relevant suggestions. The system described in Appendix 5, characterized by the features described herein. [Explanation of Symbols]

[0234] 10, 210, 310, 410 Data Processing Systems 12 Data Processing Devices 14 Smart Devices 214 Smart Glasses 314 Headset-type terminal 414 Robots

Claims

1. A reception area that accepts voice input from users, An analysis unit analyzes the voice input received by the reception unit, A learning unit learns the user's interests and behavior based on the information analyzed by the aforementioned analysis unit, A proposal unit makes suggestions and notifications at the optimal timing based on the information learned by the aforementioned learning unit, The system includes a support unit that provides personalized support based on the information proposed by the proposal unit. A system characterized by the following features.

2. The aforementioned proposal section is, It includes an advertising department that provides advertisements based on user interests and behavior. The system according to feature 1.

3. The aforementioned support unit is It includes an information provision department that provides information to enrich users' lives. The system according to feature 1.

4. The aforementioned support unit is It has a health management department that provides information on users' health management. The system according to feature 1.

5. The aforementioned support unit is It includes a hobby information section that provides information about users' hobbies and interests. The system according to feature 1.

6. The aforementioned reception unit is The system estimates the user's emotions and adjusts the timing of voice input acceptance based on the estimated emotions. The system according to feature 1.

7. The aforementioned reception unit is The system analyzes the user's past voice input history and selects the optimal reception method. The system according to feature 1.

8. The aforementioned reception unit is When receiving voice input, filtering is performed based on the user's current situation and areas of interest. The system according to feature 1.

9. The aforementioned reception unit is It estimates the user's emotions and determines the priority of voice input to accept based on the estimated emotions. The system according to feature 1.

10. The aforementioned reception unit is When receiving voice input, the system prioritizes accepting input that is highly relevant, taking into account the user's geographical location. The system according to feature 1.

Images