system

Abstract

The system according to this embodiment aims to deeply understand the user's intentions and preferences and provide personalized services. [Solution] The system according to the embodiment comprises an intent understanding unit, a suggestion unit, a learning unit, and a provision unit. The intent understanding unit understands the user's intent. The suggestion unit makes suggestions based on the information understood by the intent understanding unit. The learning unit learns the user's preferences and habits. The provision unit provides personalized services based on the information learned by the learning 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, which is performed by at least one processor, including steps of receiving a user utterance, adding the user utterance to a prompt including an instruction sentence related to an explanation of a chatbot character, encoding the prompt, and inputting the encoded prompt into a language model to generate a chatbot utterance in response to the user utterance.

Prior Art Documents

Patent Documents

[0003]

Patent Document 1

Summary of the Invention

Problems to be Solved by the Invention

[0004] In the prior art, there is a problem that the user's intention and preference are not deeply understood and individualized services are not sufficiently provided.

[0005] The system according to the embodiment aims to deeply understand the user's intention and preference and provide individualized services.

Means for Solving the Problems

[0006] The system according to this embodiment comprises an intent understanding unit, a suggestion unit, a learning unit, and a service provision unit. The intent understanding unit understands the user's intent. The suggestion unit makes suggestions based on the information understood by the intent understanding unit. The learning unit learns the user's preferences and habits. The service provision unit provides personalized services based on the information learned by the learning unit. [Effects of the Invention]

[0007] The system according to this embodiment can deeply understand the user's intentions and preferences and provide personalized services. [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 numbered 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) An excellent AI secretary system according to an embodiment of the present invention is a system that understands the user's true needs and proactively provides appropriate support. The excellent AI secretary system has the ability to deeply understand the user's intentions and possesses the foresight to anticipate situations and make suggestions. Furthermore, it has the ability to respond accurately and quickly, learn the user's preferences and habits, and provide personalized services. For example, the excellent AI secretary system checks the weather forecast, schedule, and belongings before the user goes out and suggests the most appropriate attire. For example, if the user asks "What's the weather like today?" before going out, the AI ​​checks the weather forecast and, considering the user's schedule and belongings, suggests, "It's going to rain today, so you should take an umbrella. Also, you have an important meeting this afternoon, so I recommend wearing a suit." Next, the excellent AI secretary system recommends appropriate meals and restaurants based on the user's physical condition and location information. For example, if the user says "I'm hungry," the AI ​​checks the user's current location information and physical condition data and recommends, "There's a delicious Japanese restaurant nearby. They have a wide variety of healthy options, so I recommend it." This system evolves to meet user needs the more it is used, becoming more convenient and indispensable. For example, it learns the restaurants and dishes the user frequently visits and incorporates this into future recommendations. It also learns the user's schedule and habits, proactively providing necessary information and suggestions. In this way, a superior AI assistant system deeply understands the user's intentions, makes suggestions with foresight, and responds accurately and quickly, becoming an indispensable presence for the user. This allows a superior AI assistant system to evolve to meet user needs, becoming more convenient and indispensable.

[0029] The excellent AI assistant system according to this embodiment comprises an intent understanding unit, a suggestion unit, a learning unit, and a provision unit. The intent understanding unit understands the user's intent. For example, the intent understanding unit analyzes the user's statements using natural language processing technology to understand the intent. The intent understanding unit can also analyze the user's behavioral history to understand the intent. For example, the intent understanding unit infers the user's current intent based on past actions and statements. The suggestion unit makes suggestions based on the information understood by the intent understanding unit. For example, the suggestion unit checks the user's schedule and weather forecast and suggests the most appropriate attire. The suggestion unit can also recommend appropriate meals and restaurants based on the user's physical condition and location information. For example, if the user says "I'm hungry," the suggestion unit recommends a nearby restaurant based on the user's current location and physical condition data. The learning unit learns the user's preferences and habits. For example, the learning unit learns the restaurants the user frequently uses and their favorite dishes, and reflects this in future recommendations. Furthermore, the learning unit can learn the user's schedule and habits and proactively provide necessary information and suggestions. For example, the learning unit learns that the user has a habit of going to the gym every Monday and suggests what items the user needs to bring before going to the gym. The provision unit provides personalized services based on the information learned by the learning unit. For example, the provision unit provides customized services based on the user's preferences. The provision unit can also proactively provide necessary information and suggestions based on the user's schedule and habits. For example, the provision unit provides the gym's opening hours and congestion status before the user goes to the gym. As a result, the excellent secretary AI system according to the embodiment can provide optimal support to the user by understanding the user's intentions, making suggestions, learning, and providing. Some or all of the above-described processes in the intention understanding unit, suggestion unit, learning unit, and provision unit may be performed using, for example, a generation AI, or not using a generation AI. For example, the intention understanding unit can input the user's statements into the generation AI and have the generation AI perform the intention understanding. The suggestion department can input the user's schedule and weather forecast into a generating AI, which can then generate suggestions for the most suitable clothing.The learning unit inputs user preferences and habits into the generating AI and allows the AI ​​to perform the learning process. The service unit inputs the learned information into the generating AI and allows the AI ​​to provide personalized services.

[0030] The intent understanding unit understands the user's intentions. For example, it analyzes the user's utterances using natural language processing techniques to understand their intentions. Specifically, it uses a combination of natural language processing techniques such as morphological analysis, contextual analysis, and sentiment analysis. Morphological analysis breaks down the user's utterances into individual words and analyzes the meaning of each word. Contextual analysis considers the overall context of the utterance and analyzes the relationships between words. Sentiment analysis extracts emotions from the user's utterances to help understand their intentions. The intent understanding unit can also analyze the user's behavioral history to understand their intentions. For example, it can infer the user's current intentions based on their past actions and utterances. Machine learning algorithms can be used to analyze behavioral history. For example, it can detect patterns in which a user repeats certain actions during specific time periods and infer their current intentions based on those patterns. Furthermore, the intent understanding unit achieves more accurate intent understanding by also considering the user's profile information and past dialogue history. For example, if a user has frequently asked questions about a particular topic in the past, it prioritizes considering intentions related to that topic. This allows the intent understanding unit to analyze the user's intentions from multiple perspectives based on their statements and actions, thereby achieving accurate understanding.

[0031] The suggestion unit makes suggestions based on information understood by the intent understanding unit. For example, the suggestion unit checks the user's schedule and weather forecast to suggest the most appropriate clothing. Specifically, it retrieves data from the user's calendar app and weather forecast API, integrates this information, and generates suggestions. For example, if the user has an outdoor activity planned, it will suggest appropriate clothing and items to bring based on the weather forecast. The suggestion unit can also recommend appropriate meals and restaurants based on the user's physical condition and location information. For example, if the user says "I'm hungry," it will recommend a nearby restaurant based on the user's current location and physical condition data. Physical condition data can be obtained from wearable devices such as smartwatches and fitness trackers. This allows the suggestion unit to make optimal suggestions tailored to the user's health condition and current situation. Furthermore, the suggestion unit can make more personalized suggestions by taking into account the user's past preferences and feedback. For example, it can record restaurants and types of cuisine the user has previously enjoyed and make new suggestions based on that. This allows the suggestion unit to provide optimal suggestions tailored to the user's needs and preferences, improving user satisfaction.

[0032] The learning unit learns the user's preferences and habits. For example, it learns the restaurants the user frequently visits and their favorite dishes, and incorporates this into future recommendations. Specifically, it uses machine learning algorithms to analyze user behavior and preference data and extract patterns. For example, it uses collaborative filtering and content-based filtering to recommend restaurants and dishes that match the user's preferences. The learning unit can also learn the user's schedule and habits and proactively provide necessary information and suggestions. For example, it learns that the user has a habit of going to the gym every Monday and suggests items needed before going to the gym. This involves detecting regular patterns by analyzing the user's calendar app and past behavior history. Furthermore, the learning unit can improve the accuracy of its suggestions by continuously collecting user feedback and updating its learning model. For example, when the user rates a suggestion as "good" or "bad," this rating is reflected in the learning model, improving future suggestions. In this way, the learning unit can continuously learn the user's preferences and habits and provide a more personalized service.

[0033] The service provider provides personalized services based on information learned by the learning provider. For example, the service provider provides customized services based on user preferences. Specifically, it provides personalized recommendations based on the user's past preferences and behavioral history. For example, it recommends new content based on the genres of movies and dramas the user has enjoyed watching in the past. The service provider can also proactively provide necessary information and suggestions based on the user's schedule and habits. For example, the service provider provides the gym's opening hours and congestion status before the user goes to the gym. This includes using real-time updated data to provide the user with the latest information. Furthermore, the service provider can collect user feedback and continuously improve the quality of the service. For example, by having users evaluate the information and suggestions provided, the service content can be reviewed and improved based on that evaluation. In this way, the service provider can always provide the best possible service to the user and improve user satisfaction. Furthermore, the service provider can reliably transmit information using multiple communication methods. For example, it can reliably deliver important information by using not only smartphone notifications but also voice calls, SMS, and email in combination. This allows the service provider to deliver personalized services quickly and reliably to users, thereby improving user convenience.

[0034] The suggestion department can check the weather forecast, schedule, and belongings before a user leaves home and suggest the most appropriate attire. For example, if a user asks "What's the weather like today?" before leaving home, the suggestion department will check the weather forecast, consider the user's schedule and belongings, and suggest, "It's going to rain today, so you should take an umbrella. Also, you have an important meeting this afternoon, so I recommend wearing a suit." The suggestion department can also check the user's schedule and suggest clothing suitable for activities outside the home. For example, if a user asks "What should I wear today?", the suggestion department will check the schedule and suggest, "You have a casual meeting today, so I recommend casual attire." Furthermore, the suggestion department can check the user's belongings and suggest necessary items. For example, if a user asks "What should I bring today?", the suggestion department will check the packing list and suggest, "It's going to rain today, so you should take an umbrella. Also, you have an important meeting this afternoon, so I recommend bringing your laptop." In this way, the suggestion department can support the user's preparation by suggesting the most appropriate attire before they leave home. Some or all of the above-described processes in the proposal unit may be performed using, for example, a generative AI, or without using a generative AI. For example, the proposal unit can input weather forecasts, schedules, and information about what to bring into the generative AI, and have the generative AI make suggestions for the most suitable clothing.

[0035] The suggestion unit can recommend appropriate meals and restaurants based on the user's physical condition and location. For example, if a user says, "I'm hungry," the suggestion unit checks the user's current location and physical condition data and recommends, "There's a delicious Japanese restaurant nearby. They have a wide variety of healthy options, so I recommend it." The suggestion unit can also recommend appropriate meals considering the user's physical condition. For example, if a user says, "I'm tired today," the suggestion unit checks the user's physical condition data and recommends, "There's a restaurant that offers meals effective for fatigue recovery. They have a variety of vitamin-rich dishes, so I recommend it." Furthermore, the suggestion unit can recommend nearby restaurants based on the user's location. For example, if a user says, "I want to have lunch nearby," the suggestion unit checks the user's current location and recommends, "There's a delicious Italian restaurant nearby. They have a wide variety of lunch options, so I recommend it." By recommending appropriate meals and restaurants based on physical condition and location information, the system can improve the user's health and convenience. Some or all of the above processing in the suggestion unit may be performed using, for example, generative AI, or without generative AI. For example, the suggestion department can input health data and location information into a generating AI, which can then perform the task of recommending appropriate meals and restaurants.

[0036] The learning unit can learn which restaurants and dishes a user frequently visits and reflect this in future recommendations. For example, the learning unit can collect data on restaurants the user has visited in the past to identify frequently used restaurants. The learning unit can also learn the user's preferred dishes and reflect this in future recommendations. For example, the learning unit can collect data on dishes the user has ordered in the past to identify their preferred dishes. Furthermore, the learning unit can improve the accuracy of recommendations based on user feedback. For example, the learning unit can collect user ratings of restaurants and dishes and reflect this in future recommendations. This allows for a more personalized service by learning the user's preferences and reflecting them in future recommendations. Some or all of the above processing in the learning unit may be performed using, for example, generative AI, or not using generative AI. For example, the learning unit can input restaurant and dish data into a generative AI and have the generative AI perform the learning.

[0037] The learning unit can learn the user's schedule and habits and proactively provide necessary information and suggestions. For example, the learning unit can collect the user's schedule data and identify recurring appointments. It can also learn the user's habits and proactively provide necessary information and suggestions. For example, the learning unit can learn that the user has a habit of going to the gym every Monday and suggest items needed before going to the gym. Furthermore, the learning unit can improve the accuracy of its suggestions based on user feedback. For example, the learning unit can collect the user's evaluation of the suggestions and incorporate it into future suggestions. In this way, by learning the user's schedule and habits and proactively providing necessary information and suggestions, user convenience can be improved. Some or all of the above processing in the learning unit may be performed using, for example, a generative AI, or not using a generative AI. For example, the learning unit can input schedule data and habit information into a generative AI and have the generative AI perform the learning.

[0038] The intent understanding unit can improve the accuracy of intent understanding by analyzing the user's past utterance history. For example, the intent understanding unit predicts intent based on phrases the user has frequently used in the past. The intent understanding unit can also analyze the user's past utterance patterns and interpret intent. Furthermore, the intent understanding unit can understand intent by referring to questions and requests the user has made in the past. In this way, the accuracy of intent understanding can be improved by analyzing the user's past utterance history. Some or all of the above processing in the intent understanding unit may be performed using, for example, a generative AI, or without a generative AI. For example, the intent understanding unit can input past utterance history into a generative AI and have the generative AI perform intent understanding.

[0039] The intent understanding unit can interpret intentions by considering the user's current situation and environment. For example, if the user is out, the intent understanding unit will interpret intentions by considering their actions while out. It can also interpret intentions by considering activities at home if the user is at home. Furthermore, if the user is in a meeting, the intent understanding unit can interpret intentions by considering the content of the meeting. This allows for a more accurate interpretation of intentions by considering the user's current situation and environment. Some or all of the above processing in the intent understanding unit may be performed using, for example, a generative AI, or without a generative AI. For example, the intent understanding unit can input data on the current situation and environment into a generative AI and have the generative AI perform the interpretation of intentions.

[0040] The intent understanding unit can interpret intentions by taking into account the user's geographical location information. For example, if the user is in a specific location, the intent understanding unit can interpret intentions related to that location. Furthermore, if the user is on the move, the intent understanding unit can interpret intentions related to their destination. Additionally, if the user is at home, the intent understanding unit can interpret intentions related to activities at home. This makes the interpretation of intentions more accurate by considering the user's geographical location information. Some or all of the above processing in the intent understanding unit may be performed using, for example, a generative AI, or without a generative AI. For example, the intent understanding unit can input geographical location information into a generative AI and have the generative AI perform the interpretation of intentions.

[0041] The intent understanding unit can analyze a user's social media activity and interpret their intentions. For example, the intent understanding unit can interpret intentions based on a user's statements on social media. Furthermore, the intent understanding unit can analyze a user's social media activity patterns and predict their intentions. In addition, the intent understanding unit can understand intentions based on a user's social media interactions. This allows for a more accurate interpretation of intentions by analyzing the user's social media activity. Some or all of the above-described processes in the intent understanding unit may be performed using, for example, generative AI, or without generative AI. For example, the intent understanding unit can input social media activity data into a generative AI and have the generative AI perform the interpretation of intentions.

[0042] The suggestion unit can make optimal suggestions by referring to the user's past selection history. For example, the suggestion unit can make suggestions for the next visit based on the restaurant the user has previously selected. It can also suggest clothing preferences based on the user's past selection history. Furthermore, the suggestion unit can suggest a next travel destination based on the travel destination the user has previously selected. This allows for more appropriate suggestions by referring to the user's past selection history. Some or all of the above processing in the suggestion unit may be performed using, for example, a generative AI, or without a generative AI. For example, the suggestion unit can input the past selection history into a generative AI and have the generative AI execute the optimal suggestion.

[0043] The suggestion unit can customize its suggestions by considering the user's current situation and environment. For example, if the user is out, the suggestion unit can make suggestions related to activities at their current location. Similarly, if the user is at home, it can make suggestions related to activities at home. Furthermore, if the user is in a meeting, it can make suggestions related to the meeting's content. This allows for more appropriate suggestions by considering the user's current situation and environment. Some or all of the above processing in the suggestion unit may be performed using, for example, a generative AI, or without one. For example, the suggestion unit can input data on the current situation and environment into the generative AI and have the generative AI customize the suggestions.

[0044] The suggestion unit can make optimal suggestions by considering the user's geographical location information. For example, if the user is in a specific location, the suggestion unit can make suggestions related to that location. Furthermore, if the user is on the move, the suggestion unit can make suggestions related to their destination. Additionally, if the user is at home, the suggestion unit can make suggestions related to activities at home. This allows for more appropriate suggestions by considering the user's geographical location information. Some or all of the above processing in the suggestion unit may be performed using, for example, a generative AI, or without a generative AI. For example, the suggestion unit can input geographical location information into a generative AI and have the generative AI execute the optimal suggestion.

[0045] The suggestion unit can analyze the user's social media activity and make relevant suggestions when making suggestions. For example, the suggestion unit can make suggestions based on the user's social media posts. The suggestion unit can also analyze the user's social media activity patterns and make suggestions. Furthermore, the suggestion unit can make suggestions based on the user's social media interactions. This allows for more appropriate suggestions by analyzing the user's social media activity. Some or all of the above processing in the suggestion unit may be performed using, for example, a generative AI, or without a generative AI. For example, the suggestion unit can input social media activity data into a generative AI and have the generative AI execute relevant suggestions.

[0046] The learning unit can optimize the learning algorithm by referring to past learning data during the learning process. For example, the learning unit can select the optimal learning algorithm based on past learning data. The learning unit can also select an algorithm that improves learning efficiency from past learning data. Furthermore, the learning unit can analyze past learning data and optimize the learning algorithm. This makes it possible to optimize the learning algorithm by referring to past learning data. Some or all of the above processes in the learning unit may be performed using, for example, a generative AI, or without a generative AI. For example, the learning unit can input past learning data into a generative AI and have the generative AI perform the optimization of the learning algorithm.

[0047] The learning unit can weight the training data based on the user's schedule and habits during training. For example, the learning unit can weight important data based on the user's schedule. It can also weight relevant data based on the user's habits. Furthermore, the learning unit can weight the training data while considering the user's schedule and habits. This allows for more appropriate training by weighting the training data based on the user's schedule and habits. Some or all of the above processing in the learning unit may be performed using, for example, a generative AI, or without a generative AI. For example, the learning unit can input schedule and habit data into a generative AI and have the generative AI perform the weighting of the training data.

[0048] The service provider can provide the most suitable service by referring to the user's past usage history when providing the service. For example, the service provider can provide the next service based on the services the user has used in the past. The service provider can also provide the user's preferred service based on their past usage history. Furthermore, the service provider can analyze the services the user has used in the past and provide the most suitable service. In this way, more appropriate services can be provided by referring to the user's past usage history. Some or all of the above processing in the service provider may be performed using, for example, a generative AI, or without a generative AI. For example, the service provider can input past usage history into a generative AI and have the generative AI execute the provision of the most suitable service.

[0049] The service provider can customize the service content when providing the service, taking into account the user's current situation and environment. For example, if the user is out, the service provider can provide the service at their location. Alternatively, if the user is at home, the service provider can provide the service at their home. Furthermore, if the user is in a meeting, the service provider can provide services related to the meeting's content. This allows for the provision of more appropriate services by considering the user's current situation and environment. Some or all of the above-described processes in the service provider may be performed using, for example, a generative AI, or without one. For example, the service provider can input data on the current situation and environment into the generative AI and have the generative AI perform the customization of the service content.

[0050] The service provider can provide the most appropriate service by considering the user's geographical location information when providing the service. For example, if the user is in a specific location, the service provider can provide services related to that location. Furthermore, if the user is on the move, the service provider can provide services at the user's destination. In addition, if the user is at home, the service provider can provide services at home. This allows for the provision of more appropriate services by considering the user's geographical location information. Some or all of the above processing in the service provider may be performed using, for example, a generative AI, or without a generative AI. For example, the service provider can input geographical location information into a generative AI and have the generative AI perform the task of providing the most appropriate service.

[0051] The service provider can analyze the user's social media activity and provide relevant services when providing services. For example, the service provider can provide services based on the user's social media posts. The service provider can also analyze the user's social media activity patterns and provide services based on those patterns. Furthermore, the service provider can provide services based on the user's social media interactions. This allows for the provision of more appropriate services by analyzing the user's social media activity. Some or all of the above processing in the service provider may be performed using, for example, a generative AI, or without a generative AI. For example, the service provider can input social media activity data into a generative AI and have the generative AI perform the provision of relevant services.

[0052] The system according to the embodiment is not limited to the example described above, and various modifications are possible, for example, as follows.

[0053] A sophisticated AI assistant system can analyze a user's past behavior patterns and predict future actions. For example, if a user has a habit of having lunch at a specific restaurant every Friday, the system can automatically make a reservation at that restaurant. Similarly, if a user has a habit of exercising at a specific time, the system can send exercise reminders at that time. Furthermore, if a user tends to attend a particular event, the system can provide information about that event in advance. This allows the system to predict user behavior and provide more efficient support.

[0054] A sophisticated AI assistant system can monitor a user's health data and make suggestions based on their health status. For example, it can analyze the user's heart rate and sleep data to suggest appropriate exercise and rest. It can also analyze the user's dietary data and suggest nutritionally balanced meals. Furthermore, it can suggest regular health checkups and doctor appointments based on the user's health status. In this way, it can provide comprehensive support for the user's health.

[0055] A sophisticated AI assistant system can optimize a user's schedule and support efficient time management. For example, it can analyze the user's schedule and adjust overlapping appointments. It can also prioritize important tasks in the schedule based on the user's priorities. Furthermore, it can identify the user's free time and suggest times for relaxation and rest. This streamlines the user's time management and reduces stress.

[0056] A sophisticated AI assistant system can learn a user's hobbies and interests and suggest new activities based on that. For example, if a user enjoys outdoor activities, it can suggest new hiking trails or campsites. If a user enjoys cooking, it can suggest new recipes or cooking classes. Furthermore, if a user enjoys reading, it can suggest new books or reading clubs. This allows for the provision of new activities tailored to the user's hobbies and interests.

[0057] A sophisticated AI assistant system can leverage a user's geographical location to support travel planning. For example, if a user is traveling to a specific city, it can suggest tourist attractions and restaurants in that city. If the user is planning a trip focused on nature, it can suggest hiking trails and campsites. Furthermore, if the user is planning a business trip, it can provide information on meeting rooms and business lounges. This allows for comprehensive support of the user's travel planning.

[0058] The following briefly describes the processing flow for example form 1.

[0059] Step 1: The intent understanding unit understands the user's intent. The intent understanding unit analyzes the user's statements using natural language processing technology to understand their intent. It can also analyze the user's behavior history and infer their current intent based on past actions and statements. Step 2: The suggestion unit makes suggestions based on the information understood by the intent understanding unit. The suggestion unit checks the user's schedule and weather forecast and suggests appropriate clothing. It can also recommend suitable meals and restaurants based on the user's physical condition and location information. Step 3: The learning unit learns the user's preferences and habits. The learning unit learns the restaurants the user frequently visits and their favorite dishes, and reflects this in future recommendations. It can also learn the user's schedule and habits, and proactively provide necessary information and suggestions. Step 4: The service provider provides personalized services based on the information learned by the learning provider. The service provider provides customized services based on the user's preferences and proactively provides necessary information and suggestions based on the user's schedule and habits.

[0060] (Example of form 2) An excellent AI secretary system according to an embodiment of the present invention is a system that understands the user's true needs and proactively provides appropriate support. The excellent AI secretary system has the ability to deeply understand the user's intentions and possesses the foresight to anticipate situations and make suggestions. Furthermore, it has the ability to respond accurately and quickly, learn the user's preferences and habits, and provide personalized services. For example, the excellent AI secretary system checks the weather forecast, schedule, and belongings before the user goes out and suggests the most appropriate attire. For example, if the user asks "What's the weather like today?" before going out, the AI ​​checks the weather forecast and, considering the user's schedule and belongings, suggests, "It's going to rain today, so you should take an umbrella. Also, you have an important meeting this afternoon, so I recommend wearing a suit." Next, the excellent AI secretary system recommends appropriate meals and restaurants based on the user's physical condition and location information. For example, if the user says "I'm hungry," the AI ​​checks the user's current location information and physical condition data and recommends, "There's a delicious Japanese restaurant nearby. They have a wide variety of healthy options, so I recommend it." This system evolves to meet user needs the more it is used, becoming more convenient and indispensable. For example, it learns the restaurants and dishes the user frequently visits and incorporates this into future recommendations. It also learns the user's schedule and habits, proactively providing necessary information and suggestions. In this way, a superior AI assistant system deeply understands the user's intentions, makes suggestions with foresight, and responds accurately and quickly, becoming an indispensable presence for the user. This allows a superior AI assistant system to evolve to meet user needs, becoming more convenient and indispensable.

[0061] The excellent AI assistant system according to this embodiment comprises an intent understanding unit, a suggestion unit, a learning unit, and a provision unit. The intent understanding unit understands the user's intent. For example, the intent understanding unit analyzes the user's statements using natural language processing technology to understand the intent. The intent understanding unit can also analyze the user's behavioral history to understand the intent. For example, the intent understanding unit infers the user's current intent based on past actions and statements. The suggestion unit makes suggestions based on the information understood by the intent understanding unit. For example, the suggestion unit checks the user's schedule and weather forecast and suggests the most appropriate attire. The suggestion unit can also recommend appropriate meals and restaurants based on the user's physical condition and location information. For example, if the user says "I'm hungry," the suggestion unit recommends a nearby restaurant based on the user's current location and physical condition data. The learning unit learns the user's preferences and habits. For example, the learning unit learns the restaurants the user frequently uses and their favorite dishes, and reflects this in future recommendations. Furthermore, the learning unit can learn the user's schedule and habits and proactively provide necessary information and suggestions. For example, the learning unit learns that the user has a habit of going to the gym every Monday and suggests what items the user needs to bring before going to the gym. The provision unit provides personalized services based on the information learned by the learning unit. For example, the provision unit provides customized services based on the user's preferences. The provision unit can also proactively provide necessary information and suggestions based on the user's schedule and habits. For example, the provision unit provides the gym's opening hours and congestion status before the user goes to the gym. As a result, the excellent secretary AI system according to the embodiment can provide optimal support to the user by understanding the user's intentions, making suggestions, learning, and providing. Some or all of the above-described processes in the intention understanding unit, suggestion unit, learning unit, and provision unit may be performed using, for example, a generation AI, or not using a generation AI. For example, the intention understanding unit can input the user's statements into the generation AI and have the generation AI perform the intention understanding. The suggestion department can input the user's schedule and weather forecast into a generating AI, which can then generate suggestions for the most suitable clothing.The learning unit inputs user preferences and habits into the generating AI and allows the AI ​​to perform the learning process. The service unit inputs the learned information into the generating AI and allows the AI ​​to provide personalized services.

[0062] The intent understanding unit understands the user's intentions. For example, it analyzes the user's utterances using natural language processing techniques to understand their intentions. Specifically, it uses a combination of natural language processing techniques such as morphological analysis, contextual analysis, and sentiment analysis. Morphological analysis breaks down the user's utterances into individual words and analyzes the meaning of each word. Contextual analysis considers the overall context of the utterance and analyzes the relationships between words. Sentiment analysis extracts emotions from the user's utterances to help understand their intentions. The intent understanding unit can also analyze the user's behavioral history to understand their intentions. For example, it can infer the user's current intentions based on their past actions and utterances. Machine learning algorithms can be used to analyze behavioral history. For example, it can detect patterns in which a user repeats certain actions during specific time periods and infer their current intentions based on those patterns. Furthermore, the intent understanding unit achieves more accurate intent understanding by also considering the user's profile information and past dialogue history. For example, if a user has frequently asked questions about a particular topic in the past, it prioritizes considering intentions related to that topic. This allows the intent understanding unit to analyze the user's intentions from multiple perspectives based on their statements and actions, thereby achieving accurate understanding.

[0063] The suggestion unit makes suggestions based on information understood by the intent understanding unit. For example, the suggestion unit checks the user's schedule and weather forecast to suggest the most appropriate clothing. Specifically, it retrieves data from the user's calendar app and weather forecast API, integrates this information, and generates suggestions. For example, if the user has an outdoor activity planned, it will suggest appropriate clothing and items to bring based on the weather forecast. The suggestion unit can also recommend appropriate meals and restaurants based on the user's physical condition and location information. For example, if the user says "I'm hungry," it will recommend a nearby restaurant based on the user's current location and physical condition data. Physical condition data can be obtained from wearable devices such as smartwatches and fitness trackers. This allows the suggestion unit to make optimal suggestions tailored to the user's health condition and current situation. Furthermore, the suggestion unit can make more personalized suggestions by taking into account the user's past preferences and feedback. For example, it can record restaurants and types of cuisine the user has previously enjoyed and make new suggestions based on that. This allows the suggestion unit to provide optimal suggestions tailored to the user's needs and preferences, improving user satisfaction.

[0064] The learning unit learns the user's preferences and habits. For example, it learns the restaurants the user frequently visits and their favorite dishes, and incorporates this into future recommendations. Specifically, it uses machine learning algorithms to analyze user behavior and preference data and extract patterns. For example, it uses collaborative filtering and content-based filtering to recommend restaurants and dishes that match the user's preferences. The learning unit can also learn the user's schedule and habits and proactively provide necessary information and suggestions. For example, it learns that the user has a habit of going to the gym every Monday and suggests items needed before going to the gym. This involves detecting regular patterns by analyzing the user's calendar app and past behavior history. Furthermore, the learning unit can improve the accuracy of its suggestions by continuously collecting user feedback and updating its learning model. For example, when the user rates a suggestion as "good" or "bad," this rating is reflected in the learning model, improving future suggestions. In this way, the learning unit can continuously learn the user's preferences and habits and provide a more personalized service.

[0065] The service provider provides personalized services based on information learned by the learning provider. For example, the service provider provides customized services based on user preferences. Specifically, it provides personalized recommendations based on the user's past preferences and behavioral history. For example, it recommends new content based on the genres of movies and dramas the user has enjoyed watching in the past. The service provider can also proactively provide necessary information and suggestions based on the user's schedule and habits. For example, the service provider provides the gym's opening hours and congestion status before the user goes to the gym. This includes using real-time updated data to provide the user with the latest information. Furthermore, the service provider can collect user feedback and continuously improve the quality of the service. For example, by having users evaluate the information and suggestions provided, the service content can be reviewed and improved based on that evaluation. In this way, the service provider can always provide the best possible service to the user and improve user satisfaction. Furthermore, the service provider can reliably transmit information using multiple communication methods. For example, it can reliably deliver important information by using not only smartphone notifications but also voice calls, SMS, and email in combination. This allows the service provider to deliver personalized services quickly and reliably to users, thereby improving user convenience.

[0066] The suggestion department can check the weather forecast, schedule, and belongings before a user leaves home and suggest the most appropriate attire. For example, if a user asks "What's the weather like today?" before leaving home, the suggestion department will check the weather forecast, consider the user's schedule and belongings, and suggest, "It's going to rain today, so you should take an umbrella. Also, you have an important meeting this afternoon, so I recommend wearing a suit." The suggestion department can also check the user's schedule and suggest clothing suitable for activities outside the home. For example, if a user asks "What should I wear today?", the suggestion department will check the schedule and suggest, "You have a casual meeting today, so I recommend casual attire." Furthermore, the suggestion department can check the user's belongings and suggest necessary items. For example, if a user asks "What should I bring today?", the suggestion department will check the packing list and suggest, "It's going to rain today, so you should take an umbrella. Also, you have an important meeting this afternoon, so I recommend bringing your laptop." In this way, the suggestion department can support the user's preparation by suggesting the most appropriate attire before they leave home. Some or all of the above-described processes in the proposal unit may be performed using, for example, a generative AI, or without using a generative AI. For example, the proposal unit can input weather forecasts, schedules, and information about what to bring into the generative AI, and have the generative AI make suggestions for the most suitable clothing.

[0067] The suggestion unit can recommend appropriate meals and restaurants based on the user's physical condition and location. For example, if a user says, "I'm hungry," the suggestion unit checks the user's current location and physical condition data and recommends, "There's a delicious Japanese restaurant nearby. They have a wide variety of healthy options, so I recommend it." The suggestion unit can also recommend appropriate meals considering the user's physical condition. For example, if a user says, "I'm tired today," the suggestion unit checks the user's physical condition data and recommends, "There's a restaurant that offers meals effective for fatigue recovery. They have a variety of vitamin-rich dishes, so I recommend it." Furthermore, the suggestion unit can recommend nearby restaurants based on the user's location. For example, if a user says, "I want to have lunch nearby," the suggestion unit checks the user's current location and recommends, "There's a delicious Italian restaurant nearby. They have a wide variety of lunch options, so I recommend it." By recommending appropriate meals and restaurants based on physical condition and location information, the system can improve the user's health and convenience. Some or all of the above processing in the suggestion unit may be performed using, for example, generative AI, or without generative AI. For example, the suggestion department can input health data and location information into a generating AI, which can then perform the task of recommending appropriate meals and restaurants.

[0068] The learning unit can learn which restaurants and dishes a user frequently visits and reflect this in future recommendations. For example, the learning unit can collect data on restaurants the user has visited in the past to identify frequently used restaurants. The learning unit can also learn the user's preferred dishes and reflect this in future recommendations. For example, the learning unit can collect data on dishes the user has ordered in the past to identify their preferred dishes. Furthermore, the learning unit can improve the accuracy of recommendations based on user feedback. For example, the learning unit can collect user ratings of restaurants and dishes and reflect this in future recommendations. This allows for a more personalized service by learning the user's preferences and reflecting them in future recommendations. Some or all of the above processing in the learning unit may be performed using, for example, generative AI, or not using generative AI. For example, the learning unit can input restaurant and dish data into a generative AI and have the generative AI perform the learning.

[0069] The learning unit can learn the user's schedule and habits and proactively provide necessary information and suggestions. For example, the learning unit can collect the user's schedule data and identify recurring appointments. It can also learn the user's habits and proactively provide necessary information and suggestions. For example, the learning unit can learn that the user has a habit of going to the gym every Monday and suggest items needed before going to the gym. Furthermore, the learning unit can improve the accuracy of its suggestions based on user feedback. For example, the learning unit can collect the user's evaluation of the suggestions and incorporate it into future suggestions. In this way, by learning the user's schedule and habits and proactively providing necessary information and suggestions, user convenience can be improved. Some or all of the above processing in the learning unit may be performed using, for example, a generative AI, or not using a generative AI. For example, the learning unit can input schedule data and habit information into a generative AI and have the generative AI perform the learning.

[0070] The intent understanding unit can estimate the user's emotions and adjust the interpretation of intentions based on the estimated emotions. For example, if the user is stressed, the intent understanding unit will prioritize suggestions that promote relaxation. It can also offer suggestions to calm down if the user is agitated. Furthermore, if the user is tired, it can offer suggestions to encourage rest. This allows for more appropriate support by adjusting the interpretation of intentions based on the user's emotions. Emotion estimation is achieved using an emotion estimation function, such as an emotion engine or generative AI. Generative AI may include, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI. Some or all of the processing described above in the intent understanding unit may be performed using, for example, a generative AI, or not. For example, the intent understanding unit can input user emotion data into a generative AI and have the generative AI perform the interpretation of intentions.

[0071] The intent understanding unit can improve the accuracy of intent understanding by analyzing the user's past utterance history. For example, the intent understanding unit predicts intent based on phrases the user has frequently used in the past. The intent understanding unit can also analyze the user's past utterance patterns and interpret intent. Furthermore, the intent understanding unit can understand intent by referring to questions and requests the user has made in the past. In this way, the accuracy of intent understanding can be improved by analyzing the user's past utterance history. Some or all of the above processing in the intent understanding unit may be performed using, for example, a generative AI, or without a generative AI. For example, the intent understanding unit can input past utterance history into a generative AI and have the generative AI perform intent understanding.

[0072] The intent understanding unit can interpret intentions by considering the user's current situation and environment. For example, if the user is out, the intent understanding unit will interpret intentions by considering their actions while out. It can also interpret intentions by considering activities at home if the user is at home. Furthermore, if the user is in a meeting, the intent understanding unit can interpret intentions by considering the content of the meeting. This allows for a more accurate interpretation of intentions by considering the user's current situation and environment. Some or all of the above processing in the intent understanding unit may be performed using, for example, a generative AI, or without a generative AI. For example, the intent understanding unit can input data on the current situation and environment into a generative AI and have the generative AI perform the interpretation of intentions.

[0073] The intent understanding unit can estimate the user's emotions and determine the priority of intentions based on the estimated emotions. For example, if the user is showing an emotion of urgency, the intent understanding unit will prioritize responding to that. It can also respond to users who are relaxed with normal priority. Furthermore, if the user is agitated, the intent understanding unit can prioritize suggestions for calming down. This allows for more appropriate responses by determining the priority of intentions based on the user's emotions. Emotion estimation is achieved using an emotion estimation function, such as an emotion engine or generative AI. Generative AI may be, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI. Some or all of the processing described above in the intent understanding unit may be performed using, for example, a generative AI, or not. For example, the intent understanding unit can input user emotion data into a generative AI and have the generative AI determine the priority of intentions.

[0074] The intent understanding unit can interpret intentions by taking into account the user's geographical location information. For example, if the user is in a specific location, the intent understanding unit can interpret intentions related to that location. Furthermore, if the user is on the move, the intent understanding unit can interpret intentions related to their destination. Additionally, if the user is at home, the intent understanding unit can interpret intentions related to activities at home. This makes the interpretation of intentions more accurate by considering the user's geographical location information. Some or all of the above processing in the intent understanding unit may be performed using, for example, a generative AI, or without a generative AI. For example, the intent understanding unit can input geographical location information into a generative AI and have the generative AI perform the interpretation of intentions.

[0075] The intent understanding unit can analyze a user's social media activity and interpret their intentions. For example, the intent understanding unit can interpret intentions based on a user's statements on social media. Furthermore, the intent understanding unit can analyze a user's social media activity patterns and predict their intentions. In addition, the intent understanding unit can understand intentions based on a user's social media interactions. This allows for a more accurate interpretation of intentions by analyzing the user's social media activity. Some or all of the above-described processes in the intent understanding unit may be performed using, for example, generative AI, or without generative AI. For example, the intent understanding unit can input social media activity data into a generative AI and have the generative AI perform the interpretation of intentions.

[0076] The suggestion unit can estimate the user's emotions and adjust the way suggestions are presented based on those emotions. For example, if the user is stressed, the suggestion unit can offer suggestions to help them relax. If the user is excited, the suggestion unit can offer suggestions to help them calm down. Furthermore, if the user is tired, the suggestion unit can offer suggestions to encourage rest. By adjusting the way suggestions are presented based on the user's emotions, more appropriate suggestions can be made. Emotion estimation is achieved using an emotion estimation function, such as an emotion engine or generative AI. Generative AI may be, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI. Some or all of the above processing in the suggestion unit may be performed using a generative AI, or not. For example, the suggestion unit can input user emotion data into a generative AI and have the generative AI adjust the way suggestions are presented.

[0077] The suggestion unit can make optimal suggestions by referring to the user's past selection history. For example, the suggestion unit can make suggestions for the next visit based on the restaurant the user has previously selected. It can also suggest clothing preferences based on the user's past selection history. Furthermore, the suggestion unit can suggest a next travel destination based on the travel destination the user has previously selected. This allows for more appropriate suggestions by referring to the user's past selection history. Some or all of the above processing in the suggestion unit may be performed using, for example, a generative AI, or without a generative AI. For example, the suggestion unit can input the past selection history into a generative AI and have the generative AI execute the optimal suggestion.

[0078] The suggestion unit can customize its suggestions by considering the user's current situation and environment. For example, if the user is out, the suggestion unit can make suggestions related to activities at their current location. Similarly, if the user is at home, it can make suggestions related to activities at home. Furthermore, if the user is in a meeting, it can make suggestions related to the meeting's content. This allows for more appropriate suggestions by considering the user's current situation and environment. Some or all of the above processing in the suggestion unit may be performed using, for example, a generative AI, or without one. For example, the suggestion unit can input data on the current situation and environment into the generative AI and have the generative AI customize the suggestions.

[0079] The suggestion unit can estimate the user's emotions and determine the priority of suggestions based on those emotions. For example, if the user is showing an emotion of urgency, the suggestion unit will prioritize that. If the user is relaxed, the suggestion unit can also prioritize suggestions to help the user calm down. This allows for a more appropriate response by prioritizing suggestions based on the user's emotions. Emotion estimation is achieved using an emotion estimation function, such as an emotion engine or generative AI. Generative AI may be, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI. Some or all of the processing described above in the suggestion unit may be performed using a generative AI, or not. For example, the suggestion unit can input user emotion data into a generative AI and have the generative AI determine the priority of suggestions.

[0080] The suggestion unit can make optimal suggestions by considering the user's geographical location information. For example, if the user is in a specific location, the suggestion unit can make suggestions related to that location. Furthermore, if the user is on the move, the suggestion unit can make suggestions related to their destination. Additionally, if the user is at home, the suggestion unit can make suggestions related to activities at home. This allows for more appropriate suggestions by considering the user's geographical location information. Some or all of the above processing in the suggestion unit may be performed using, for example, a generative AI, or without a generative AI. For example, the suggestion unit can input geographical location information into a generative AI and have the generative AI execute the optimal suggestion.

[0081] The suggestion unit can analyze the user's social media activity and make relevant suggestions when making suggestions. For example, the suggestion unit can make suggestions based on the user's social media posts. The suggestion unit can also analyze the user's social media activity patterns and make suggestions. Furthermore, the suggestion unit can make suggestions based on the user's social media interactions. This allows for more appropriate suggestions by analyzing the user's social media activity. Some or all of the above processing in the suggestion unit may be performed using, for example, a generative AI, or without a generative AI. For example, the suggestion unit can input social media activity data into a generative AI and have the generative AI execute relevant suggestions.

[0082] The learning unit can estimate the user's emotions and select training data based on the estimated emotions. For example, if the user is relaxed, the learning unit will prioritize learning data related to relaxation. Similarly, if the user is stressed, the learning unit can prioritize learning data related to stress reduction. Furthermore, if the user is excited, the learning unit can prioritize learning data that helps the user calm down. This allows for more appropriate learning by selecting training data based on the user's emotions. Emotion estimation is achieved using an emotion estimation function, such as an emotion engine or generative AI. Generative AI may be, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI. Some or all of the above-described processes in the learning unit may be performed using, for example, a generative AI, or not. For example, the learning unit can input user emotion data into a generative AI and have the generative AI perform the selection of training data.

[0083] The learning unit can optimize the learning algorithm by referring to past learning data during the learning process. For example, the learning unit can select the optimal learning algorithm based on past learning data. The learning unit can also select an algorithm that improves learning efficiency from past learning data. Furthermore, the learning unit can analyze past learning data and optimize the learning algorithm. This makes it possible to optimize the learning algorithm by referring to past learning data. Some or all of the above processes in the learning unit may be performed using, for example, a generative AI, or without a generative AI. For example, the learning unit can input past learning data into a generative AI and have the generative AI perform the optimization of the learning algorithm.

[0084] The learning unit can estimate the user's emotions and adjust the learning frequency based on the estimated emotions. For example, the learning unit can increase the learning frequency if the user is relaxed. It can also decrease the learning frequency if the user is stressed. Furthermore, it can adjust the learning frequency if the user is excited. This allows for more appropriate learning by adjusting the learning frequency based on the user's emotions. Emotion estimation is achieved using an emotion estimation function, for example, using an emotion engine or generative AI. The generative AI is, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI. Some or all of the above processing in the learning unit may be performed using a generative AI, or not. For example, the learning unit can input user emotion data into a generative AI and have the generative AI adjust the learning frequency.

[0085] The learning unit can weight the training data based on the user's schedule and habits during training. For example, the learning unit can weight important data based on the user's schedule. It can also weight relevant data based on the user's habits. Furthermore, the learning unit can weight the training data while considering the user's schedule and habits. This allows for more appropriate training by weighting the training data based on the user's schedule and habits. Some or all of the above processing in the learning unit may be performed using, for example, a generative AI, or without a generative AI. For example, the learning unit can input schedule and habit data into a generative AI and have the generative AI perform the weighting of the training data.

[0086] The service provider can estimate the user's emotions and adjust the service delivery method based on the estimated emotions. For example, if the user is relaxed, the service provider can provide a relaxing service. If the user is stressed, the service provider can also provide a stress-reducing service. Furthermore, if the user is agitated, the service provider can provide a calming service. In this way, by adjusting the service delivery method based on the user's emotions, a more appropriate service can be provided. Emotion estimation is achieved using an emotion estimation function, for example, using an emotion engine or generative AI. The generative AI is, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI. Some or all of the above processing in the service provider may be performed using a generative AI, or not using a generative AI. For example, the service provider can input user emotion data into a generative AI and have the generative AI adjust the service delivery method.

[0087] The service provider can provide the most suitable service by referring to the user's past usage history when providing the service. For example, the service provider can provide the next service based on the services the user has used in the past. The service provider can also provide the user's preferred service based on their past usage history. Furthermore, the service provider can analyze the services the user has used in the past and provide the most suitable service. In this way, more appropriate services can be provided by referring to the user's past usage history. Some or all of the above processing in the service provider may be performed using, for example, a generative AI, or without a generative AI. For example, the service provider can input past usage history into a generative AI and have the generative AI execute the provision of the most suitable service.

[0088] The service provider can customize the service content when providing the service, taking into account the user's current situation and environment. For example, if the user is out, the service provider can provide the service at their location. Alternatively, if the user is at home, the service provider can provide the service at their home. Furthermore, if the user is in a meeting, the service provider can provide services related to the meeting's content. This allows for the provision of more appropriate services by considering the user's current situation and environment. Some or all of the above-described processes in the service provider may be performed using, for example, a generative AI, or without one. For example, the service provider can input data on the current situation and environment into the generative AI and have the generative AI perform the customization of the service content.

[0089] The service provider can estimate the user's emotions and determine service priorities based on those estimated emotions. For example, if the user is showing an emotion of urgency, the service provider will prioritize providing services. Alternatively, if the user is relaxed, the service provider can provide services with normal priority. Furthermore, if the user is agitated, the service provider can prioritize services to help them calm down. This allows for more appropriate responses by prioritizing services based on the user's emotions. Emotion estimation is achieved using an emotion estimation function, such as an emotion engine or generative AI. Generative AI may be, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI. Some or all of the above-described processes in the service provider may be performed using or without a generative AI. For example, the service provider can input user emotion data into a generative AI and have the generative AI determine service priorities.

[0090] The service provider can provide the most appropriate service by considering the user's geographical location information when providing the service. For example, if the user is in a specific location, the service provider can provide services related to that location. Furthermore, if the user is on the move, the service provider can provide services at the user's destination. In addition, if the user is at home, the service provider can provide services at home. This allows for the provision of more appropriate services by considering the user's geographical location information. Some or all of the above processing in the service provider may be performed using, for example, a generative AI, or without a generative AI. For example, the service provider can input geographical location information into a generative AI and have the generative AI perform the task of providing the most appropriate service.

[0091] The service provider can analyze the user's social media activity and provide relevant services when providing services. For example, the service provider can provide services based on the user's social media posts. The service provider can also analyze the user's social media activity patterns and provide services based on those patterns. Furthermore, the service provider can provide services based on the user's social media interactions. This allows for the provision of more appropriate services by analyzing the user's social media activity. Some or all of the above processing in the service provider may be performed using, for example, a generative AI, or without a generative AI. For example, the service provider can input social media activity data into a generative AI and have the generative AI perform the provision of relevant services.

[0092] The system according to the embodiment is not limited to the example described above, and various modifications are possible, for example, as follows.

[0093] A sophisticated AI assistant system can estimate a user's emotions and monitor their stress levels based on those estimates. For example, if a user is experiencing high stress levels, the system can suggest relaxing music or meditation apps. It can also adjust work schedules and encourage breaks when a user is stressed. Furthermore, if a user is stressed, the system can suggest stress-reducing activities. This helps manage the user's stress levels and supports a healthy lifestyle.

[0094] A sophisticated AI assistant system can analyze a user's past behavior patterns and predict future actions. For example, if a user has a habit of having lunch at a specific restaurant every Friday, the system can automatically make a reservation at that restaurant. Similarly, if a user has a habit of exercising at a specific time, the system can send exercise reminders at that time. Furthermore, if a user tends to attend a particular event, the system can provide information about that event in advance. This allows the system to predict user behavior and provide more efficient support.

[0095] A sophisticated AI assistant system can estimate the user's emotions and adjust its communication tone based on those emotions. For example, if the user is angry, the system will respond in a calm and composed tone. If the user is sad, the system can respond in a comforting tone. Furthermore, if the user is happy, the system can respond in an empathetic tone. This allows for appropriate communication tailored to the user's emotions.

[0096] A sophisticated AI assistant system can monitor a user's health data and make suggestions based on their health status. For example, it can analyze the user's heart rate and sleep data to suggest appropriate exercise and rest. It can also analyze the user's dietary data and suggest nutritionally balanced meals. Furthermore, it can suggest regular health checkups and doctor appointments based on the user's health status. In this way, it can provide comprehensive support for the user's health.

[0097] A sophisticated AI assistant system can estimate a user's emotions and suggest entertainment based on those emotions. For example, if the user is tired, it can suggest relaxing movies or music. If the user is excited, it can suggest action movies or energetic music. Furthermore, if the user is sad, it can suggest comedy movies or cheerful music to lift their spirits. This allows for entertainment tailored to the user's emotions.

[0098] A sophisticated AI assistant system can optimize a user's schedule and support efficient time management. For example, it can analyze the user's schedule and adjust overlapping appointments. It can also prioritize important tasks in the schedule based on the user's priorities. Furthermore, it can identify the user's free time and suggest times for relaxation and rest. This streamlines the user's time management and reduces stress.

[0099] A sophisticated AI assistant system can estimate the user's emotions and adjust its feedback based on those emotions. For example, if the user is stressed, it will prioritize positive feedback. If the user is relaxed, it can provide constructive feedback. Furthermore, if the user is agitated, it can provide feedback to help them calm down. This allows for appropriate feedback tailored to the user's emotions.

[0100] A sophisticated AI assistant system can learn a user's hobbies and interests and suggest new activities based on that. For example, if a user enjoys outdoor activities, it can suggest new hiking trails or campsites. If a user enjoys cooking, it can suggest new recipes or cooking classes. Furthermore, if a user enjoys reading, it can suggest new books or reading clubs. This allows for the provision of new activities tailored to the user's hobbies and interests.

[0101] A sophisticated AI assistant system can estimate the user's emotions and adjust the timing of reminders based on those emotions. For example, if the user is stressed, the reminder might be delayed slightly. If the user is relaxed, the reminder can be sent at the normal time. Furthermore, if the user is excited, the reminder can be sent earlier. This allows the system to provide reminders at the appropriate time according to the user's emotions.

[0102] A sophisticated AI assistant system can leverage a user's geographical location to support travel planning. For example, if a user is traveling to a specific city, it can suggest tourist attractions and restaurants in that city. If the user is planning a trip focused on nature, it can suggest hiking trails and campsites. Furthermore, if the user is planning a business trip, it can provide information on meeting rooms and business lounges. This allows for comprehensive support of the user's travel planning.

[0103] The following briefly describes the processing flow for example form 2.

[0104] Step 1: The intent understanding unit understands the user's intent. The intent understanding unit analyzes the user's statements using natural language processing technology to understand their intent. It can also analyze the user's behavior history and infer their current intent based on past actions and statements. Step 2: The suggestion unit makes suggestions based on the information understood by the intent understanding unit. The suggestion unit checks the user's schedule and weather forecast and suggests appropriate clothing. It can also recommend suitable meals and restaurants based on the user's physical condition and location information. Step 3: The learning unit learns the user's preferences and habits. The learning unit learns the restaurants the user frequently visits and their favorite dishes, and reflects this in future recommendations. It can also learn the user's schedule and habits, and proactively provide necessary information and suggestions. Step 4: The service provider provides personalized services based on the information learned by the learning provider. The service provider provides customized services based on the user's preferences and proactively provides necessary information and suggestions based on the user's schedule and habits.

[0105] 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.

[0106] 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.

[0107] 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.

[0108] Each of the multiple elements described above, including the intent understanding unit, suggestion unit, learning unit, and provision unit, is implemented in at least one of the smart device 14 and the data processing unit 12. For example, the intent understanding unit is implemented by the control unit 46A of the smart device 14, which analyzes the user's utterances and understands their intent. The suggestion unit is implemented by the specific processing unit 290 of the data processing unit 12, which checks the user's schedule and weather forecast and suggests the most appropriate clothing. The learning unit is implemented by the specific processing unit 290 of the data processing unit 12, which learns the user's preferences and habits. The provision unit is implemented by the control unit 46A of the smart device 14, which provides personalized services based on the learned information. The correspondence between each unit and the device or control unit is not limited to the examples described above, and various modifications are possible.

[0109] [Second Embodiment] Figure 3 shows an example of the configuration of the data processing system 210 according to the second embodiment.

[0110] 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.

[0111] 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.

[0112] 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.

[0113] The microphone 238 receives voice commands and other instructions from the user by receiving voice signals. 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.

[0114] 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).

[0115] 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.

[0116] 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.

[0117] 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.

[0118] 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.

[0119] 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.

[0120] 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.).

[0121] 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.

[0122] 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.

[0123] 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.

[0124] Each of the multiple elements described above, including the intent understanding unit, suggestion unit, learning unit, and provision unit, is implemented in at least one of the smart glasses 214 and the data processing unit 12. For example, the intent understanding unit is implemented by the control unit 46A of the smart glasses 214, which analyzes the user's speech and understands their intent. The suggestion unit is implemented by the specific processing unit 290 of the data processing unit 12, which checks the user's schedule and weather forecast and suggests the most appropriate clothing. The learning unit is implemented by the specific processing unit 290 of the data processing unit 12, which learns the user's preferences and habits. The provision unit is implemented by the control unit 46A of the smart glasses 214, which provides personalized services based on the learned information. The correspondence between each unit and the device or control unit is not limited to the examples described above, and various modifications are possible.

[0125] [Third Embodiment] Figure 5 shows an example of the configuration of the data processing system 310 according to the third embodiment.

[0126] 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.

[0127] 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.

[0128] 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.

[0129] The microphone 238 receives voice commands and other instructions from the user by receiving voice signals. 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.

[0130] 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).

[0131] 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.

[0132] 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.

[0133] 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.

[0134] 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.

[0135] 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.

[0136] 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.).

[0137] 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.

[0138] 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.

[0139] 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.

[0140] Each of the multiple elements described above, including the intent understanding unit, suggestion unit, learning unit, and provision unit, is implemented in at least one of the headset terminal 314 and the data processing unit 12. For example, the intent understanding unit is implemented by the control unit 46A of the headset terminal 314, which analyzes the user's speech and understands their intent. The suggestion unit is implemented by the specific processing unit 290 of the data processing unit 12, which checks the user's schedule and weather forecast and suggests the most appropriate clothing. The learning unit is implemented by the specific processing unit 290 of the data processing unit 12, which learns the user's preferences and habits. The provision unit is implemented by the control unit 46A of the headset terminal 314, which provides personalized services based on the learned information. The correspondence between each unit and the device or control unit is not limited to the example described above, and various modifications are possible.

[0141] [Fourth Embodiment] Figure 7 shows an example of the configuration of the data processing system 410 according to the fourth embodiment.

[0142] 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.

[0143] 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.

[0144] 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.

[0145] The microphone 238 receives voice commands and other instructions from the user by receiving voice signals. 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.

[0146] 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).

[0147] 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.

[0148] 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.

[0149] 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.

[0150] 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.

[0151] 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.

[0152] 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.

[0153] 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.).

[0154] 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.

[0155] 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.

[0156] 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.

[0157] Each of the multiple elements described above, including the intent understanding unit, suggestion unit, learning unit, and provision unit, is implemented in at least one of the robot 414 and the data processing unit 12. For example, the intent understanding unit is implemented by the control unit 46A of the robot 414, which analyzes the user's utterances and understands their intentions. The suggestion unit is implemented by the specific processing unit 290 of the data processing unit 12, which checks the user's schedule and weather forecast and suggests the most appropriate clothing. The learning unit is implemented by the specific processing unit 290 of the data processing unit 12, which learns the user's preferences and habits. The provision unit is implemented by the control unit 46A of the robot 414, which provides personalized services based on the learned information. The correspondence between each unit and the device or control unit is not limited to the examples described above, and various modifications are possible.

[0158] 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.

[0159] 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.

[0160] 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.

[0161] 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.

[0162] 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.

[0163] 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."

[0164] 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.

[0165] 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.

[0166] 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.

[0167] 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.

[0168] 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.

[0169] 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.

[0170] 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.

[0171] 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.

[0172] 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.

[0173] 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.

[0174] 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.

[0175] 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.

[0176] (Note 1) An intent understanding unit that understands the user's intentions, A proposal unit that makes a proposal based on the information understood by the intent understanding unit, A learning unit that learns user preferences and habits, The system comprises a provisioning unit that provides personalized services based on information learned by the learning unit. A system characterized by the following features. (Note 2) The aforementioned proposal section is, Before you go out, check the weather forecast, your schedule, and what to bring, and we'll suggest the most appropriate clothing. The system described in Appendix 1, characterized by the features described herein. (Note 3) The aforementioned proposal section is, Based on your health condition and location, we recommend appropriate meals and restaurants. The system described in Appendix 1, characterized by the features described herein. (Note 4) The aforementioned learning unit, The system learns which restaurants users frequently visit and their preferred cuisines, and uses this information to improve future recommendations. The system described in Appendix 1, characterized by the features described herein. (Note 5) The aforementioned learning unit, It learns the user's schedule and habits and proactively provides necessary information and suggestions. The system described in Appendix 1, characterized by the features described herein. (Note 6) The aforementioned intent understanding unit, It estimates the user's emotions and adjusts the interpretation of intent based on the estimated user emotions. The system described in Appendix 1, characterized by the features described herein. (Note 7) The aforementioned intent understanding unit, Analyzing the user's past statements improves the accuracy of understanding their intent. The system described in Appendix 1, characterized by the features described herein. (Note 8) The aforementioned intent understanding unit, Interpret the user's intent by considering their current situation and environment. The system described in Appendix 1, characterized by the features described herein. (Note 9) The aforementioned intent understanding unit, It estimates the user's emotions and prioritizes intentions based on those estimated emotions. The system described in Appendix 1, characterized by the features described herein. (Note 10) The aforementioned intent understanding unit, Interpret intent by considering the user's geographical location. The system described in Appendix 1, characterized by the features described herein. (Note 11) The aforementioned intent understanding unit, Analyze users' social media activity and interpret their intentions. The system described in Appendix 1, characterized by the features described herein. (Note 12) 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 13) The aforementioned proposal section is, When making suggestions, the system refers to the user's past selection history to provide the most suitable recommendations. The system described in Appendix 1, characterized by the features described herein. (Note 14) The aforementioned proposal section is, When making a proposal, customize the proposal content to take into account the user's current situation and environment. The system described in Appendix 1, characterized by the features described herein. (Note 15) The aforementioned proposal section is, It estimates the user's emotions and determines the priority of suggestions based on the estimated user emotions. The system described in Appendix 1, characterized by the features described herein. (Note 16) The aforementioned proposal section is, When making a proposal, we take the user's geographical location into consideration to provide the most suitable suggestion. The system described in Appendix 1, characterized by the features described herein. (Note 17) The aforementioned proposal section is, When making a proposal, we analyze the user's social media activity and make relevant suggestions. 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, 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 21) The aforementioned learning unit, During training, the training data is weighted based on the user's schedule and habits. The system described in Appendix 1, characterized by the features described herein. (Note 22) The aforementioned supply unit is, We estimate the user's emotions and adjust the way we deliver the service based on those estimated emotions. The system described in Appendix 1, characterized by the features described herein. (Note 23) The aforementioned supply unit is, When providing services, we refer to the user's past usage history to provide the most suitable service. The system described in Appendix 1, characterized by the features described herein. (Note 24) The aforementioned supply unit is, When providing the service, we customize the service content to take into account the user's current situation and environment. The system described in Appendix 1, characterized by the features described herein. (Note 25) The aforementioned supply unit is, It estimates user sentiment and prioritizes services based on the estimated user sentiment. The system described in Appendix 1, characterized by the features described herein. (Note 26) The aforementioned supply unit is, When providing services, we take into account the user's geographical location to provide the most suitable service. The system described in Appendix 1, characterized by the features described herein. (Note 27) The aforementioned supply unit is, When providing the service, we analyze the user's social media activity and provide relevant services. The system described in Appendix 1, characterized by the features described herein. [Explanation of symbols]

[0177] 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. An intent understanding unit that understands the user's intentions, A proposal unit that makes a proposal based on the information understood by the intent understanding unit, A learning unit that learns user preferences and habits, The system comprises a provisioning unit that provides personalized services based on information learned by the learning unit. A system characterized by the following features.

2. The aforementioned proposal section is, Before you go out, check the weather forecast, your schedule, and what to bring, and we'll suggest the most appropriate clothing. The system according to feature 1.

3. The aforementioned proposal section is, Based on your health condition and location, we recommend appropriate meals and restaurants. The system according to feature 1.

4. The aforementioned learning unit, The system learns which restaurants users frequently visit and their preferred cuisines, and uses this information to improve future recommendations. The system according to feature 1.

5. The aforementioned learning unit, It learns the user's schedule and habits and proactively provides necessary information and suggestions. The system according to feature 1.

6. The aforementioned intent understanding unit, It estimates the user's emotions and adjusts the interpretation of intent based on the estimated user emotions. The system according to feature 1.

7. The aforementioned intent understanding unit, Analyzing the user's past statements improves the accuracy of understanding their intent. The system according to feature 1.

8. The aforementioned intent understanding unit, Interpret the user's intent by considering their current situation and environment. The system according to feature 1.

9. The aforementioned intent understanding unit, It estimates the user's emotions and determines the priority of intentions based on the estimated user emotions. The system according to feature 1.

10. The aforementioned intent understanding unit, Interpret intent by considering the user's geographical location. The system according to feature 1.

Images