System

Abstract

To provide a system that suggests optimal actions based on a user's daily conversations, open data, and weather information, and reflects them in a calendar.SOLUTION: A system according to an embodiment includes a reception unit, an analysis unit, a writing unit, a feedback reception unit, and a learning unit. The reception unit receives a user's conversation contents. The analysis unit analyzes the conversation contents received by the reception unit or open data or weather information, and suggests actions. The writing unit writes the actions suggested by the analysis unit in a calendar. The feedback reception unit receives feedback from the user. The learning unit analyzes the feedback received by the feedback reception unit and reflects it in a next suggestion.SELECTED DRAWING: Figure 1

Description

[Technical field]

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

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

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

[0004] Conventional technology does not adequately suggest optimal actions based on a user's daily conversations, open data, and weather information, and does not reflect these in the calendar, so there is room for improvement.

[0005] The system according to the embodiment aims to suggest optimal actions based on the user's daily conversations, open data, and weather information, and to reflect these in the calendar. [Means for solving the problem]

[0006] The system according to the embodiment includes a reception unit, an analysis unit, a writing unit, a feedback reception unit, and a learning unit. The reception unit receives the content of the user's conversation. The analysis unit analyzes the content of the conversation, open data, or weather information received by the reception unit, and suggests an action. The writing unit writes the action suggested by the analysis unit in a calendar. The feedback reception unit receives feedback from the user. The learning unit analyzes the feedback received by the feedback reception unit and reflects it in the next suggestion. Effect of the Invention

[0007] The system according to the embodiment can suggest optimal actions to take based on a user's daily conversations, open data, and weather information, and reflect these in the calendar. [Brief description of the drawings]

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

[0028] (Example 1) The behavior support system according to the embodiment of the present invention is a system in which a user has a daily conversation with an AI the night before, and derives what to do the next day. In this behavior support system, a user has a daily conversation with an AI the night before, and in the conversation, the user's plans, hopes, mood, etc. are discussed. Next, the AI ​​analyzes open data, weather information, and the contents of the conversation to derive the optimal behavior for the user. For example, it can suggest going out on a sunny day, and indoor activities on a rainy day. The AI ​​automatically writes the derived behavior into the user's calendar. Furthermore, after the user acts according to the itinerary, feedback is provided to the AI. For example, the user conveys impressions such as "the proposed outing was fun" or "the indoor activities were meaningful." The AI ​​learns this feedback and reflects it in the next proposal. This allows the AI ​​to learn the user's preferences and behavioral patterns and make more optimal proposals. For example, a busy businessman can make a schedule to efficiently complete his work, or a plan to cherish time with his family. It is also possible for a student to make a schedule to balance study and play. This allows the behavior support system to efficiently plan the user's daily actions and spend fulfilling days.

[0029] The action support system according to the embodiment includes a reception unit, an analysis unit, a writing unit, a feedback reception unit, and a learning unit. The reception unit receives the content of the user's conversation. The content of the user's conversation includes, for example, voice data, text data, a specific topic, and the like, but is not limited to such examples. The reception unit converts the user's voice into text data, for example, using a voice recognition technology. The reception unit can also directly receive the user's text message. The analysis unit analyzes the content of the conversation, open data, and weather information received by the reception unit, and proposes an action. The analysis unit analyzes the content of the conversation, for example, using a natural language processing technology, and understands the user's intention and desire. The analysis unit also acquires open data and weather information, and proposes an action based on the information. For example, the analysis unit acquires weather forecast data and proposes an action based on the weather. The writing unit writes the action proposed by the analysis unit into a calendar. The writing unit automatically writes the action into a calendar service, for example, Google (registered trademark) Calendar or Outlook (registered trademark) Calendar, using an API. The feedback reception unit accepts the user's feedback. The feedback receiving unit receives, for example, user ratings, comments, survey results, etc. The learning unit analyzes the feedback received by the feedback receiving unit and reflects the feedback in the next proposal. The learning unit analyzes the feedback using, for example, a machine learning algorithm and improves the accuracy of the proposal. As a result, the action support system according to the embodiment can improve the accuracy of the next proposal by suggesting optimal actions based on the content of the user's conversation, writing them in a calendar, and learning the feedback.

[0030] The reception unit receives the contents of the user's conversation. The contents of the user's conversation include, but are not limited to, voice data, text data, and specific topics. The reception unit converts the user's voice into text data, for example, using a voice recognition technology. Specifically, a voice recognition model using deep learning is used as the voice recognition technology. This model is trained using a large amount of voice data and corresponding text data, and can convert voice into text with high accuracy. In order to accommodate the language, accent, and speaking speed of the user, the voice recognition model supports multiple languages ​​and also incorporates noise canceling technology. Furthermore, the reception unit can directly receive the user's text message. For example, the reception unit receives a text message input by the user through a chatbot or messaging app in real time and transmits it to the analysis unit. This allows the user to interact with the system not only through voice input but also through text input. The reception unit plays a role of centrally managing the contents of the user's input and smoothly transferring them to the analysis unit.

[0031] The analysis unit analyzes the conversation content, open data, and weather information received by the reception unit, and proposes an action. The analysis unit analyzes the conversation content using, for example, natural language processing technology to understand the user's intention and desire. Specifically, a transformer model or a recurrent neural network (RNN) is used as a natural language processing technology. These models can extract keywords and context from the user's utterance and understand the user's intention with high accuracy. The analysis unit also acquires open data and weather information, and proposes an action based on the information. For example, the analysis unit acquires weather forecast data and proposes an action based on the weather. Specifically, the analysis unit analyzes the weather forecast data and proposes indoor activities when rain is expected, and proposes outdoor activities when sunny weather is expected. The analysis unit also utilizes open data such as traffic information and event information to propose the optimal action for the user. For example, when traffic congestion is expected, it can propose a detour route or suggest avoiding the time of an event when congestion is expected. As a result, the analysis unit can comprehensively analyze the user's intention and external information and propose the optimal action.

[0032] The writing unit writes the action proposed by the analysis unit in the calendar. The writing unit automatically writes the action to a calendar service such as Google (registered trademark) Calendar or Outlook (registered trademark) Calendar using an API. Specifically, the writing unit adds a new event to the user's calendar using the calendar service's API. For example, if the user accepts the proposed action, the writing unit can write the proposed date and time and content in the calendar and set a reminder. This allows the user to smoothly execute the proposed action without forgetting it. The writing unit can also check the free time on the user's calendar and suggest an action in the optimal time slot. For example, if the user already has an event scheduled on the user's calendar, the writing unit takes that event into consideration and suggests a new action in a time slot that does not overlap with the event. This makes it possible to efficiently manage the user's schedule and reduce wasted time. Furthermore, the writing unit respects the privacy settings of the user's calendar and checks the access rights as necessary. This makes it possible to make appropriate action suggestions while protecting the user's privacy.

[0033] The feedback receiving unit receives user feedback. The feedback receiving unit receives, for example, user evaluations, comments, survey results, and the like. Specifically, the feedback receiving unit provides an interface for evaluating how the user felt about the proposed action and how satisfied he or she is. For example, after the user performs the action, an evaluation form may be displayed on the application, allowing the user to input star ratings and comments. In addition, a survey may be periodically conducted to collect the user's opinions and requests. The feedback receiving unit plays a role in centrally managing these feedbacks and handing them over to the learning unit. Furthermore, the feedback receiving unit can receive user feedback in real time. For example, if a problem occurs while the user is performing the action, feedback can be sent immediately and the system can be notified. This allows the system to respond quickly and improve the user's experience. The feedback receiving unit not only collects user feedback, but also analyzes the content of the feedback and provides data to be reflected in the next proposal. This allows the feedback receiving unit to play an important role in realizing better proposals that reflect the user's opinions.

[0034] The learning unit analyzes the feedback received by the feedback receiving unit and reflects it in the next proposal. The learning unit, for example, uses a machine learning algorithm to analyze the feedback and improve the accuracy of the proposal. Specifically, the learning unit trains a model using the user's feedback data and continuously improves the accuracy of the proposal. For example, the learning unit learns the characteristics of proposals that the user has given a high rating, and prioritizes proposals with similar characteristics. In addition, the learning unit analyzes the cause of a proposal that has received a low rating, and adjusts the model so that a similar problem does not occur. The learning unit can analyze the pattern of the proposal using the feedback data and grasp the user's preferences and behavioral patterns. This makes it possible to make proposals customized for each user, and improve the user's satisfaction. Furthermore, the learning unit can improve the model by utilizing not only the feedback data but also other data sources. For example, it is possible to make more accurate proposals using past proposal history and user behavior data. The learning unit analyzes these data in an integrated manner and builds an optimal model for improving the accuracy of the proposal. This makes it possible for the learning unit to realize highly accurate proposals that reflect the user's feedback, and improve the performance of the entire system.

[0035] The analysis unit may include a weather acquisition unit that acquires weather information. The weather acquisition unit acquires weather information, for example, from data of the Japan Meteorological Agency or a private weather forecast service. The weather acquisition unit may acquire weather information in real time, for example, using an API. In addition, the weather acquisition unit may periodically update the weather information and hold the latest information. This allows the acquisition of weather information to suggest actions based on the weather. For example, the weather acquisition unit may suggest going outside on a sunny day and suggest indoor activities on a rainy day. Some or all of the above-mentioned processing in the weather acquisition unit may be performed, for example, using AI or may be performed without using AI. For example, the weather acquisition unit may optimize a method of acquiring weather information using an AI model for acquiring weather information.

[0036] The analysis unit may include a data acquisition unit that acquires open data. The data acquisition unit acquires open data from, for example, government data, public APIs, databases, etc. The data acquisition unit may acquire open data in real time, for example, using an API. In addition, the data acquisition unit may periodically update the open data and hold the latest information. This allows for action suggestions based on more diverse information by acquiring open data. For example, the data acquisition unit may acquire open data such as traffic information and event information, and suggest actions based on the information. A part or all of the above-mentioned processing in the data acquisition unit may be performed, for example, using AI, or may be performed without using AI. For example, the data acquisition unit may optimize the data acquisition method using an AI model for acquiring open data.

[0037] The feedback receiving unit may include an impression analysis unit that analyzes the user's impressions. The impression analysis unit may analyze impressions such as user ratings, comments, and survey results. The impression analysis unit may analyze impressions using, for example, natural language processing technology to understand the user's intentions and emotions. The impression analysis unit may classify the contents of impressions using, for example, text analysis technology to distinguish positive impressions and negative impressions. In this way, by analyzing the user's impressions, the contents of the feedback can be understood in more detail and reflected in the next proposal. The estimation of emotions is realized using an emotion estimation function using, for example, an emotion engine or a generation AI. The generation AI may be a text generation AI (for example, LLM) or a multimodal generation AI, but is not limited to such examples. A part or all of the above-mentioned processing in the impression analysis unit may be performed using, for example, an AI, or may be performed without using an AI. For example, the impression analysis unit may input the user's impression data to the generation AI and cause the generation AI to execute the analysis of the impressions.

[0038] The learning unit may include a proposal reflection unit that reflects the opinions analyzed by the opinion analysis unit in the next proposal. The proposal reflection unit updates the next proposal content based on the opinions analyzed by the opinion analysis unit, for example. The proposal reflection unit can learn the opinion data using, for example, a machine learning algorithm, and improve the accuracy of the proposal. As a result, the next proposal is improved based on the analyzed opinions, thereby improving the accuracy of the proposal. For example, the proposal reflection unit can propose a similar action based on positive opinions, and propose a different action based on negative opinions. A part or all of the above-mentioned processing in the proposal reflection unit may be performed using, for example, AI, or may be performed without using AI. For example, the proposal reflection unit can input the opinion data analyzed by the opinion analysis unit to the generation AI and cause the generation AI to update the next proposal content.

[0039] The reception unit can analyze the user's past conversation history and select the optimal conversation topic. The reception unit, for example, stores the user's past conversation history in a database and analyzes it. The reception unit can analyze the contents of the past conversations and identify the user's interests and preferences, for example, using natural language processing technology. This enables a conversation that is interesting to the user by selecting the optimal topic based on the past conversation history. For example, the reception unit preferentially selects topics in which the user has shown interest in the past. In addition, the reception unit can provide a comfortable conversation by excluding topics that the user has avoided in the past. Furthermore, the reception unit can select a topic suitable for a specific time period from the user's past conversation history. A part or all of the above-mentioned processing in the reception unit may be performed, for example, using AI, or may be performed without using AI. For example, the reception unit can input the user's past conversation data to the generation AI and cause the generation AI to execute a process of selecting the optimal conversation topic.

[0040] The reception unit can perform filtering based on the user's current living situation and field of interest when receiving a conversation. The reception unit, for example, stores information on the user's current living situation and field of interest in a database and analyzes it. The reception unit can obtain information such as the user's schedule, health condition, and home environment, and filter conversation topics based on the information. This enables a more relevant conversation by filtering based on the user's living situation and field of interest. For example, the reception unit preferentially selects topics related to a project that the user is currently working on. In addition, the reception unit can select appropriate topics based on the user's current living situation (e.g., work, family, hobbies). Furthermore, the reception unit can also select conversation topics based on the user's field of interest (e.g., sports, music, travel). Part or all of the above-mentioned processing in the reception unit may be performed using, for example, AI, or may be performed without using AI. For example, the reception unit can input data on the user's living situation and field of interest to the generation AI and cause the generation AI to execute the filtering process.

[0041] The reception unit can preferentially receive a topic with high relevance based on the geographical location information of the user when receiving a conversation. The reception unit, for example, acquires the geographical location information of the user using GPS data or a location information service. The reception unit can preferentially select a topic related to the user's current location, for example. This allows for a more appropriate conversation by selecting a topic with high relevance based on the user's geographical location information. For example, the reception unit preferentially selects a topic related to the user's current location. In addition, the reception unit can talk about local events and news based on the user's geographical location information. Furthermore, the reception unit can talk about local tourist spots and restaurants based on the user's geographical location information. A part or all of the above-mentioned processing in the reception unit may be performed, for example, using AI, or may be performed without using AI. For example, the reception unit can input the user's geographical location information to the generation AI and cause the generation AI to execute a process of selecting a topic with high relevance.

[0042] The reception unit can analyze the user's social media activity and receive related topics when receiving a conversation. The reception unit, for example, stores and analyzes the user's social media activity in a database. The reception unit can, for example, use natural language processing technology to analyze the content of social media posts and identify the user's interests and preferences. This enables a more appropriate conversation by selecting related topics based on the user's social media activity. For example, the reception unit preferentially selects topics that the user frequently posts on social media. In addition, the reception unit can identify current interests from the user's social media activity and select related topics. Furthermore, the reception unit can select topics in which the user's followers and friends on social media are interested. A part or all of the above-mentioned processing in the reception unit may be performed, for example, using AI, or may be performed without using AI. For example, the reception unit can input the user's social media data to the generation AI and cause the generation AI to execute a process of selecting related topics.

[0043] During the analysis, the analysis unit can suggest an action by referring to the user's past action history. The analysis unit, for example, stores the user's past action history in a database and analyzes it. The analysis unit can, for example, use natural language processing technology to analyze the content of past actions and identify the user's action pattern. This makes it possible to make effective suggestions for the user by suggesting optimal actions based on the past action history. For example, the analysis unit suggests optimal actions based on the user's past successful action patterns. In addition, the analysis unit can suggest actions to avoid failure from the user's past action history. Furthermore, the analysis unit can analyze the user's past action history and suggest the most efficient action. Part or all of the above-mentioned processing in the analysis unit may be performed, for example, using AI, or may be performed without using AI. For example, the analysis unit can input the user's past action data to the generation AI and cause the generation AI to execute a process of suggesting optimal actions.

[0044] The analysis unit can customize the action proposal based on the user's current living situation during the analysis. The analysis unit, for example, stores information on the user's current living situation in a database and analyzes it. The analysis unit can obtain information such as the user's schedule, health condition, and home environment, and customize the action proposal based on the information. This enables more appropriate proposals by customizing the action proposal based on the user's living situation. For example, the analysis unit proposes an action related to a project that the user is currently working on. In addition, the analysis unit can propose appropriate actions based on the user's current living situation (e.g., work, home, hobbies). Furthermore, the analysis unit can also propose actions based on the user's areas of interest (e.g., sports, music, travel). Part or all of the above-mentioned processing in the analysis unit may be performed, for example, using AI, or may be performed without using AI. For example, the analysis unit can input data on the user's living situation to the generation AI and cause the generation AI to customize the action proposal.

[0045] The analysis unit can suggest optimal actions in consideration of the user's geographical location information during analysis. The analysis unit, for example, acquires the user's geographical location information using GPS data or a location information service. The analysis unit can, for example, preferentially suggest actions related to the user's current location. This allows for more appropriate suggestions by suggesting optimal actions based on the user's geographical location information. For example, the analysis unit preferentially suggests actions related to the user's current location. In addition, the analysis unit can suggest local events and activities based on the user's geographical location information. Furthermore, the analysis unit can suggest local tourist spots and restaurants based on the user's geographical location information. Some or all of the above-mentioned processing in the analysis unit may be performed, for example, using AI, or may be performed without using AI. For example, the analysis unit can input the user's geographical location information to the generation AI and cause the generation AI to execute a process of suggesting optimal actions.

[0046] The analysis unit can analyze the user's social media activities and make action suggestions during the analysis. The analysis unit, for example, stores the user's social media activities in a database and analyzes them. The analysis unit can, for example, use natural language processing technology to analyze the content of social media posts and identify the user's interests and preferences. This enables more appropriate suggestions by making action suggestions based on the user's social media activities. For example, the analysis unit preferentially suggests activities that the user frequently posts on social media. In addition, the analysis unit can identify current interests from the user's social media activities and suggest related actions. Furthermore, the analysis unit can suggest activities in which the user's followers and friends on social media are interested. A part or all of the above-mentioned processing in the analysis unit may be performed, for example, using AI, or may be performed without using AI. For example, the analysis unit can input the user's social media data to the generation AI and cause the generation AI to execute a process of making action suggestions.

[0047] The writing unit can select a writing method by referring to the user's past schedule history when writing. The writing unit, for example, stores the user's past schedule history in a database and analyzes it. The writing unit can, for example, use natural language processing technology to analyze past schedule contents and identify the user's schedule pattern. This enables effective schedule management for the user by selecting an optimal writing method based on the past schedule history. For example, the writing unit selects an optimal writing method based on a schedule pattern that the user has been successful in the past. In addition, the writing unit can select a writing method to avoid failure from the user's past schedule history. Furthermore, the writing unit can analyze the user's past schedule history and select the most efficient writing method. Part or all of the above-mentioned processing in the writing unit may be performed, for example, using AI, or may be performed without using AI. For example, the writing unit can input the user's past schedule data to the generation AI and cause the generation AI to execute a process of selecting an optimal writing method.

[0048] The writing unit can customize the contents of the calendar based on the user's current living situation at the time of writing. The writing unit, for example, stores information on the user's current living situation in a database and analyzes it. The writing unit can obtain information such as the user's schedule, health condition, and home environment, and customize the contents of the calendar based on the information. This enables more appropriate schedule management by customizing the contents of the calendar based on the user's living situation. For example, the writing unit writes an event related to a project that the user is currently working on into the calendar. In addition, the writing unit can write an appropriate event into the calendar based on the user's current living situation (e.g., work, home, hobbies). Furthermore, the writing unit can customize the contents of the calendar based on the user's areas of interest (e.g., sports, music, travel). Part or all of the above-mentioned processing in the writing unit may be performed, for example, using AI, or may be performed without using AI. For example, the writing unit can input data on the user's living situation into the generation AI and cause the generation AI to execute a process of customizing the contents of the calendar.

[0049] The writing unit can select calendar contents based on the geographical location information of the user at the time of writing. The writing unit, for example, acquires the geographical location information of the user using GPS data or a location information service. The writing unit can, for example, preferentially write plans related to the user's current location. This allows more appropriate schedule management by selecting optimal calendar contents based on the user's geographical location information. For example, the writing unit preferentially writes plans related to the user's current location. In addition, the writing unit can write local events and activities in the calendar based on the user's geographical location information. Furthermore, the writing unit can write local tourist spots and restaurant plans in the calendar based on the user's geographical location information. A part or all of the above-mentioned processing in the writing unit may be performed, for example, using AI or may be performed without using AI. For example, the writing unit can input the user's geographical location information to the generation AI and cause the generation AI to execute a process of selecting optimal calendar contents.

[0050] The writing unit can adjust the calendar contents by analyzing the user's social media activity at the time of writing. The writing unit, for example, stores and analyzes the user's social media activity in a database. The writing unit can, for example, use natural language processing technology to analyze the content of social media posts and identify the user's interests and preferences. This enables more appropriate schedule management by adjusting the calendar contents based on the user's social media activity. For example, the writing unit writes in the calendar the activities that the user frequently posts on social media. In addition, the writing unit can identify current interests from the user's social media activity and write related plans in the calendar. Furthermore, the writing unit can also write in the calendar the activities in which the user's followers and friends on social media are interested. Part or all of the above-mentioned processing in the writing unit may be performed, for example, using AI, or may be performed without using AI. For example, the writing unit can input the user's social media data into the generation AI and cause the generation AI to execute a process of adjusting the calendar contents.

[0051] The feedback receiving unit can select the receiving method by referring to the user's past feedback history when receiving feedback. The feedback receiving unit, for example, stores the user's past feedback history in a database and analyzes it. The feedback receiving unit can, for example, use natural language processing technology to analyze the past feedback content and identify the user's feedback pattern. This enables effective feedback for the user by selecting the optimal receiving method based on the past feedback history. For example, if the user provided detailed feedback in the past, the feedback receiving unit requests similar detailed feedback. In addition, if the user provided brief feedback in the past, the feedback receiving unit can request brief feedback. Furthermore, the feedback receiving unit can preferentially request feedback in a specific format from the user's past feedback history. Part or all of the above-mentioned processing in the feedback receiving unit may be performed, for example, using AI, or may be performed without using AI. For example, the feedback receiving unit can input the user's past feedback data to the generation AI and cause the generation AI to execute a process of selecting the optimal receiving method.

[0052] The feedback receiving unit can receive feedback based on the geographical location information of the user when receiving the feedback. The feedback receiving unit acquires the geographical location information of the user using, for example, GPS data or a location information service. The feedback receiving unit can preferentially receive, for example, feedback related to the user's current location. This allows for more appropriate feedback by receiving optimal feedback based on the user's geographical location information. For example, the feedback receiving unit preferentially receives feedback related to the user's current location. In addition, the feedback receiving unit can receive feedback regarding local events and activities based on the user's geographical location information. Furthermore, the feedback receiving unit can also receive feedback regarding local tourist spots and restaurants based on the user's geographical location information. A part or all of the above-mentioned processing in the feedback receiving unit may be performed using, for example, an AI, or may be performed without using an AI. For example, the feedback receiving unit can input the user's geographical location information to the generation AI and cause the generation AI to execute a process of receiving optimal feedback.

[0053] The learning unit can improve the learning algorithm by referring to past learning data during learning. The learning unit, for example, stores and analyzes past learning data in a database. The learning unit can, for example, use a machine learning algorithm to analyze past learning data and adjust parameters of the algorithm. This enables more effective learning by optimizing the learning algorithm based on the past learning data. For example, the learning unit selects the most effective algorithm from the past learning data and optimizes learning. In addition, the learning unit can analyze past learning data and adjust parameters of the algorithm. Furthermore, the learning unit can introduce a new algorithm based on the past learning data and optimize learning. A part or all of the above-mentioned processing in the learning unit may be performed, for example, using AI, or may be performed without using AI. For example, the learning unit can input past learning data to the generation AI and cause the generation AI to execute improvement of the learning algorithm.

[0054] The learning unit can weight the learning data by referring to the time of feedback submission during learning. The learning unit, for example, stores the time of feedback submission in a database and analyzes it. The learning unit can weight the learning data based on the time of feedback submission using, for example, a machine learning algorithm. This allows for more effective learning by weighting the learning data based on the time of feedback submission. For example, the learning unit performs learning by placing emphasis on data immediately after feedback is submitted. In addition, the learning unit can weight data based on the time period in which feedback is submitted. Furthermore, the learning unit can weight data based on the frequency at which feedback is submitted. A part or all of the above-mentioned processing in the learning unit may be performed using, for example, an AI, or may be performed without using an AI. For example, the learning unit can input feedback submission time data to a generation AI and cause the generation AI to perform weighting of the learning data.

[0055] When acquiring weather information, the weather acquisition unit can select an acquisition method by referring to the user's past weather history. The weather acquisition unit, for example, stores the user's past weather history in a database and analyzes it. The weather acquisition unit can, for example, use a machine learning algorithm to analyze the past weather history and select a method for acquiring optimal weather information. As a result, it is possible to acquire weather information that is effective for the user by acquiring optimal weather information based on the past weather history. For example, the weather acquisition unit acquires optimal weather information based on weather conditions that the user has preferred in the past. In addition, the weather acquisition unit can acquire information from the user's past weather history, taking into account weather conditions that the user wants to avoid. Furthermore, the weather acquisition unit can analyze the user's past weather history and acquire the most suitable weather information. Part or all of the above-mentioned processing in the weather acquisition unit may be performed, for example, using AI, or may be performed without using AI. For example, the weather acquisition unit can input past weather history data to the generation AI and cause the generation AI to execute a process of selecting a method for acquiring optimal weather information.

[0056] The weather acquisition unit can acquire weather information based on the geographical location information of the user when acquiring weather information. The weather acquisition unit acquires the geographical location information of the user using, for example, GPS data or a location information service. The weather acquisition unit can, for example, preferentially acquire weather information related to the user's current location. This makes it possible to acquire more appropriate weather information by acquiring optimal weather information based on the user's geographical location information. For example, the weather acquisition unit preferentially acquires weather information for the user's current location. In addition, the weather acquisition unit can acquire local weather information based on the user's geographical location information. Furthermore, the weather acquisition unit can also acquire weather information for a travel destination based on the user's geographical location information. A part or all of the above-mentioned processing in the weather acquisition unit may be performed using, for example, an AI, or may be performed without using an AI. For example, the weather acquisition unit can input the user's geographical location information to the generation AI and cause the generation AI to execute a process of acquiring optimal weather information.

[0057] When acquiring open data, the data acquisition unit can select an acquisition method by referring to the user's past data history. The data acquisition unit, for example, stores the user's past data history in a database and analyzes it. The data acquisition unit can, for example, use a machine learning algorithm to analyze the past data history and select a method for acquiring the optimal open data. As a result, by acquiring optimal open data based on the past data history, it becomes possible to acquire data that is effective for the user. For example, the data acquisition unit acquires optimal open data based on data that the user liked in the past. In addition, the data acquisition unit can acquire information from the user's past data history, taking into account data that the user wants to avoid. Furthermore, the data acquisition unit can analyze the user's past data history and acquire the most suitable open data. Part or all of the above-mentioned processing in the data acquisition unit may be performed, for example, using AI, or may be performed without using AI. For example, the data acquisition unit can input the past data history to the generation AI and cause the generation AI to execute a process of selecting a method for acquiring the optimal open data.

[0058] The data acquisition unit can acquire data based on the geographical location information of the user when acquiring open data. The data acquisition unit acquires the geographical location information of the user using, for example, GPS data or a location information service. The data acquisition unit can, for example, preferentially acquire data related to the user's current location. This makes it possible to acquire more appropriate data by acquiring optimal data based on the user's geographical location information. For example, the data acquisition unit preferentially acquires data related to the user's current location. In addition, the data acquisition unit can acquire regional open data based on the user's geographical location information. Furthermore, the data acquisition unit can also acquire open data of travel destinations based on the user's geographical location information. A part or all of the above-mentioned processing in the data acquisition unit may be performed using, for example, AI, or may be performed without using AI. For example, the data acquisition unit can input the user's geographical location information to the generation AI and cause the generation AI to execute a process of acquiring optimal data.

[0059] The impression analysis unit can select an analysis method by referring to the user's past impression history when analyzing impressions. The impression analysis unit, for example, stores the user's past impression history in a database and analyzes it. The impression analysis unit can analyze the contents of past impressions and identify the user's impression pattern, for example, using natural language processing technology. This enables effective analysis for the user by selecting an optimal analysis method based on the past impression history. For example, the impression analysis unit selects an optimal analysis method based on detailed impressions provided by the user in the past. In addition, the impression analysis unit can preferentially analyze concise impressions from the user's past impression history. Furthermore, the impression analysis unit can analyze the user's past impression history and select the most effective analysis method. A part or all of the above-mentioned processing in the impression analysis unit may be performed, for example, using AI, or may be performed without using AI. For example, the impression analysis unit can input the past impression history to the generation AI and cause the generation AI to execute a process of selecting an optimal analysis method.

[0060] The impression analysis unit can analyze impressions taking into consideration the geographical location information of the user when analyzing impressions. The impression analysis unit, for example, acquires the geographical location information of the user using GPS data or a location information service. The impression analysis unit can, for example, preferentially analyze impressions related to the user's current location. This allows for more appropriate analysis by analyzing optimal impressions based on the user's geographical location information. For example, the impression analysis unit preferentially analyzes impressions related to the user's current location. In addition, the impression analysis unit can analyze impressions related to local events and activities based on the user's geographical location information. Furthermore, the impression analysis unit can analyze impressions related to local tourist spots and restaurants based on the user's geographical location information. A part or all of the above-mentioned processing in the impression analysis unit may be performed, for example, using AI or may be performed without using AI. For example, the impression analysis unit can input the user's geographical location information to the generation AI and cause the generation AI to execute a process of analyzing optimal impressions.

[0061] The proposal reflection unit can select a reflection method by referring to the user's past proposal history when reflecting a proposal. The proposal reflection unit, for example, stores the user's past proposal history in a database and analyzes it. The proposal reflection unit can analyze the past proposal history using, for example, a machine learning algorithm and select an optimal reflection method. This allows for an effective proposal for the user by selecting an optimal reflection method based on the past proposal history. For example, the proposal reflection unit selects an optimal reflection method based on a proposal pattern that the user has been successful in the past. In addition, the proposal reflection unit can select a reflection method to avoid failure from the user's past proposal history. Furthermore, the proposal reflection unit can analyze the user's past proposal history and select the most efficient reflection method. A part or all of the above-mentioned processing in the proposal reflection unit may be performed using, for example, AI, or may be performed without using AI. For example, the proposal reflection unit can input the past proposal history to the generation AI and cause the generation AI to execute a process of selecting an optimal reflection method.

[0062] The proposal reflecting unit can reflect the proposal based on the geographical location information of the user when reflecting the proposal. The proposal reflecting unit acquires the geographical location information of the user using, for example, GPS data or a location information service. The proposal reflecting unit can, for example, preferentially reflect a proposal related to the user's current location. This allows for more appropriate proposals by reflecting optimal proposals based on the user's geographical location information. For example, the proposal reflecting unit preferentially reflects a proposal related to the user's current location. In addition, the proposal reflecting unit can reflect proposals regarding local events and activities based on the user's geographical location information. Furthermore, the proposal reflecting unit can also reflect proposals regarding local tourist spots and restaurants based on the user's geographical location information. A part or all of the above-mentioned processing in the proposal reflecting unit may be performed using, for example, AI, or may be performed without using AI. For example, the proposal reflecting unit can input the user's geographical location information to the generating AI and cause the generating AI to execute a process of reflecting the optimal proposal.

[0063] The system according to the embodiment is not limited to the above-described example, and various modifications are possible, for example, as follows.

[0064] The behavior support system may further include a health data acquisition unit that acquires health data of the user. The health data acquisition unit acquires, for example, heart rate, step count, sleep data, and the like from the user's wearable device. This allows behavior suggestions to be customized based on the user's health condition. For example, if the user is tired, the analysis unit may suggest a relaxing activity. Also, if the user is not getting enough exercise, the analysis unit may suggest an activity that includes exercise. Furthermore, a schedule for ensuring an appropriate amount of sleep may be proposed based on the user's sleep data.

[0065] The action support system may further include a hobby data acquisition unit that customizes action suggestions based on the user's hobbies and interests. The hobby data acquisition unit identifies the user's hobbies and interests from, for example, the user's social media accounts and past action history. This allows action suggestions to be made based on the user's hobbies and interests. For example, if the user is interested in music, the analysis unit may suggest participation in a music event. Also, if the user is interested in sports, sporting events and activities may be suggested. Furthermore, if the user is interested in cooking, cooking classes and recipes may be suggested.

[0066] The action support system may further include a location information acquisition unit that acquires the geographical location information of the user. The location information acquisition unit acquires the user's current location using, for example, GPS data or a location information service. This allows action suggestions to be customized based on the user's current location. For example, if the user is in a tourist spot, the analysis unit may suggest tourist spots and restaurants. Also, if the user is at home, indoor activities may be suggested. Furthermore, if the user is on a business trip, activities at the business trip destination may be suggested.

[0067] The action support system may further include a social media analysis unit that analyzes the user's social media activity. The social media analysis unit may, for example, analyze the contents of posts and interests from the user's social media accounts. This may allow action suggestions to be made based on the user's social media activity. For example, activities related to topics about which the user frequently posts on social media may be suggested. Activities related to topics in which the user's followers and friends are interested may also be suggested. Furthermore, activities related to topics in which the user has shown interest in the past may also be suggested based on the user's social media activity history.

[0068] The behavior support system may further include a behavior history analysis unit that analyzes the user's past behavior history. The behavior history analysis unit, for example, stores the user's past behavior data in a database and analyzes it. This makes it possible to make behavior suggestions based on the user's past behavior history. For example, based on a behavior pattern that the user has been successful in the past, a similar behavior may be suggested. Also, suggestions may be made to help the user avoid behavior patterns that have failed in the past. Furthermore, the user's past behavior history may be analyzed to suggest the most efficient behavior.

[0069] The action support system may further include a life situation acquisition unit that acquires the user's current life situation. The life situation acquisition unit acquires information such as the user's schedule, health condition, and home environment. This allows action suggestions to be customized based on the user's current life situation. For example, an action related to a project the user is currently working on may be suggested. Also, appropriate rest and exercise may be suggested based on the user's health condition. Furthermore, an action for valuing time with family may be suggested based on the user's home environment.

[0070] The process flow of the first embodiment will be briefly described below.

[0071] Step 1: The reception unit receives the user's conversation content. The user's conversation content includes voice data, text data, specific topics, etc. The reception unit can convert the user's voice into text data using voice recognition technology, and can also directly receive the user's text message. Step 2: The analysis unit analyzes the conversation content, open data, and weather information received by the reception unit, and suggests actions. The analysis unit uses natural language processing technology to analyze the conversation content and understand the user's intentions and wishes. It also acquires open data and weather information, and suggests actions based on that information. For example, it acquires weather forecast data and suggests actions based on the weather. Step 3: The writing unit writes the actions suggested by the analysis unit into the calendar. The writing unit automatically writes the actions into a calendar service such as Google Calendar or Outlook Calendar using an API. Step 4: The feedback receiving unit receives user feedback The feedback receiving unit receives user ratings, comments, survey results, and the like. Step 5: The learning unit analyzes the feedback received by the feedback receiving unit and reflects the feedback in the next proposal. The learning unit analyzes the feedback using a machine learning algorithm to improve the accuracy of the proposal.

[0072] (Example 2) The behavior support system according to the embodiment of the present invention is a system in which a user has a daily conversation with an AI the night before, and derives what to do the next day. In this behavior support system, a user has a daily conversation with an AI the night before, and in the conversation, the user's plans, hopes, mood, etc. are discussed. Next, the AI ​​analyzes open data, weather information, and the contents of the conversation to derive the optimal behavior for the user. For example, it can suggest going out on a sunny day, and indoor activities on a rainy day. The AI ​​automatically writes the derived behavior into the user's calendar. Furthermore, after the user acts according to the itinerary, feedback is provided to the AI. For example, the user conveys impressions such as "the proposed outing was fun" or "the indoor activities were meaningful." The AI ​​learns this feedback and reflects it in the next proposal. This allows the AI ​​to learn the user's preferences and behavioral patterns and make more optimal proposals. For example, a busy businessman can make a schedule to efficiently complete his work, or a plan to cherish time with his family. It is also possible for a student to make a schedule to balance study and play. This allows the behavior support system to efficiently plan the user's daily actions and spend fulfilling days.

[0073] The action support system according to the embodiment includes a reception unit, an analysis unit, a writing unit, a feedback reception unit, and a learning unit. The reception unit receives the content of the user's conversation. The content of the user's conversation includes, for example, voice data, text data, a specific topic, and the like, but is not limited to such examples. The reception unit converts the user's voice into text data, for example, using a voice recognition technology. The reception unit can also directly receive the user's text message. The analysis unit analyzes the content of the conversation, open data, and weather information received by the reception unit, and proposes an action. The analysis unit analyzes the content of the conversation, for example, using a natural language processing technology, and understands the user's intention and desire. The analysis unit also acquires open data and weather information, and proposes an action based on the information. For example, the analysis unit acquires weather forecast data and proposes an action based on the weather. The writing unit writes the action proposed by the analysis unit into a calendar. The writing unit automatically writes the action into a calendar service, for example, Google Calendar or Outlook Calendar, using an API. The feedback reception unit accepts the user's feedback. The feedback receiving unit receives, for example, user ratings, comments, survey results, etc. The learning unit analyzes the feedback received by the feedback receiving unit and reflects the feedback in the next proposal. The learning unit analyzes the feedback using, for example, a machine learning algorithm and improves the accuracy of the proposal. As a result, the action support system according to the embodiment can improve the accuracy of the next proposal by suggesting optimal actions based on the content of the user's conversation, writing them in a calendar, and learning the feedback.

[0074] The reception unit receives the contents of the user's conversation. The contents of the user's conversation include, but are not limited to, voice data, text data, and specific topics. The reception unit converts the user's voice into text data, for example, using a voice recognition technology. Specifically, a voice recognition model using deep learning is used as the voice recognition technology. This model is trained using a large amount of voice data and corresponding text data, and can convert voice into text with high accuracy. In order to accommodate the language, accent, and speaking speed of the user, the voice recognition model supports multiple languages ​​and also incorporates noise canceling technology. Furthermore, the reception unit can directly receive the user's text message. For example, the reception unit receives a text message input by the user through a chatbot or messaging app in real time and transmits it to the analysis unit. This allows the user to interact with the system not only through voice input but also through text input. The reception unit plays a role of centrally managing the contents of the user's input and smoothly transferring them to the analysis unit.

[0075] The analysis unit analyzes the conversation content, open data, and weather information received by the reception unit, and proposes an action. The analysis unit analyzes the conversation content using, for example, natural language processing technology to understand the user's intention and desire. Specifically, a transformer model or a recurrent neural network (RNN) is used as a natural language processing technology. These models can extract keywords and context from the user's utterance and understand the user's intention with high accuracy. The analysis unit also acquires open data and weather information, and proposes an action based on the information. For example, the analysis unit acquires weather forecast data and proposes an action based on the weather. Specifically, the analysis unit analyzes the weather forecast data and proposes indoor activities when rain is expected, and proposes outdoor activities when sunny weather is expected. The analysis unit also utilizes open data such as traffic information and event information to propose the optimal action for the user. For example, when traffic congestion is expected, it can propose a detour route or suggest avoiding the time of an event when congestion is expected. As a result, the analysis unit can comprehensively analyze the user's intention and external information and propose the optimal action.

[0076] The writing unit writes the action proposed by the analysis unit in the calendar. The writing unit automatically writes the action to a calendar service such as Google Calendar or Outlook Calendar using an API. Specifically, the writing unit adds a new event to the user's calendar using the calendar service's API. For example, if the user accepts the proposed action, the writing unit can write the proposed date, time, and content in the calendar and set a reminder. This allows the user to smoothly execute the proposed action without forgetting it. The writing unit can also check the free time on the user's calendar and suggest an action in the optimal time slot. For example, if the user already has an event on his or her calendar, the writing unit takes that event into consideration and suggests a new action in a time slot that does not overlap with the event. This makes it possible to efficiently manage the user's schedule and reduce wasted time. Furthermore, the writing unit respects the privacy settings of the user's calendar and checks access permissions as necessary. This makes it possible to make appropriate action suggestions while protecting the user's privacy.

[0077] The feedback receiving unit receives user feedback. The feedback receiving unit receives, for example, user evaluations, comments, survey results, and the like. Specifically, the feedback receiving unit provides an interface for evaluating how the user felt about the proposed action and how satisfied he or she is. For example, after the user performs the action, an evaluation form may be displayed on the application, allowing the user to input star ratings and comments. In addition, a survey may be periodically conducted to collect the user's opinions and requests. The feedback receiving unit plays a role in centrally managing these feedbacks and handing them over to the learning unit. Furthermore, the feedback receiving unit can receive user feedback in real time. For example, if a problem occurs while the user is performing the action, feedback can be sent immediately and the system can be notified. This allows the system to respond quickly and improve the user's experience. The feedback receiving unit not only collects user feedback, but also analyzes the content of the feedback and provides data to be reflected in the next proposal. This allows the feedback receiving unit to play an important role in realizing better proposals that reflect the user's opinions.

[0078] The learning unit analyzes the feedback received by the feedback receiving unit and reflects it in the next proposal. The learning unit, for example, uses a machine learning algorithm to analyze the feedback and improve the accuracy of the proposal. Specifically, the learning unit trains a model using the user's feedback data and continuously improves the accuracy of the proposal. For example, the learning unit learns the characteristics of proposals that the user has given a high rating, and prioritizes proposals with similar characteristics. In addition, the learning unit analyzes the cause of a proposal that has received a low rating, and adjusts the model so that a similar problem does not occur. The learning unit can analyze the pattern of the proposal using the feedback data and grasp the user's preferences and behavioral patterns. This makes it possible to make proposals customized for each user, and improve the user's satisfaction. Furthermore, the learning unit can improve the model by utilizing not only the feedback data but also other data sources. For example, it is possible to make more accurate proposals using past proposal history and user behavior data. The learning unit analyzes these data in an integrated manner and builds an optimal model for improving the accuracy of the proposal. This makes it possible for the learning unit to realize highly accurate proposals that reflect the user's feedback, and improve the performance of the entire system.

[0079] The analysis unit may include a weather acquisition unit that acquires weather information. The weather acquisition unit acquires weather information, for example, from data of the Japan Meteorological Agency or a private weather forecast service. The weather acquisition unit may acquire weather information in real time, for example, using an API. In addition, the weather acquisition unit may periodically update the weather information and hold the latest information. This allows the acquisition of weather information to suggest actions based on the weather. For example, the weather acquisition unit may suggest going outside on a sunny day and suggest indoor activities on a rainy day. Some or all of the above-mentioned processing in the weather acquisition unit may be performed, for example, using AI or may be performed without using AI. For example, the weather acquisition unit may optimize a method of acquiring weather information using an AI model for acquiring weather information.

[0080] The analysis unit may include a data acquisition unit that acquires open data. The data acquisition unit acquires open data from, for example, government data, public APIs, databases, etc. The data acquisition unit may acquire open data in real time, for example, using an API. In addition, the data acquisition unit may periodically update the open data and hold the latest information. This allows for action suggestions based on more diverse information by acquiring open data. For example, the data acquisition unit may acquire open data such as traffic information and event information, and suggest actions based on the information. A part or all of the above-mentioned processing in the data acquisition unit may be performed, for example, using AI, or may be performed without using AI. For example, the data acquisition unit may optimize the data acquisition method using an AI model for acquiring open data.

[0081] The feedback receiving unit may include an impression analysis unit that analyzes the user's impressions. The impression analysis unit may analyze impressions such as user ratings, comments, and survey results. The impression analysis unit may analyze impressions using, for example, natural language processing technology to understand the user's intentions and emotions. The impression analysis unit may classify the contents of impressions using, for example, text analysis technology to distinguish positive impressions and negative impressions. In this way, by analyzing the user's impressions, the contents of the feedback can be understood in more detail and reflected in the next proposal. The estimation of emotions is realized using an emotion estimation function using, for example, an emotion engine or a generation AI. The generation AI may be a text generation AI (for example, LLM) or a multimodal generation AI, but is not limited to such examples. A part or all of the above-mentioned processing in the impression analysis unit may be performed using, for example, an AI, or may be performed without using an AI. For example, the impression analysis unit may input the user's impression data to the generation AI and cause the generation AI to execute the analysis of the impressions.

[0082] The learning unit may include a proposal reflection unit that reflects the opinions analyzed by the opinion analysis unit in the next proposal. The proposal reflection unit updates the next proposal content based on the opinions analyzed by the opinion analysis unit, for example. The proposal reflection unit can learn the opinion data using, for example, a machine learning algorithm, and improve the accuracy of the proposal. As a result, the next proposal is improved based on the analyzed opinions, thereby improving the accuracy of the proposal. For example, the proposal reflection unit can propose a similar action based on positive opinions, and propose a different action based on negative opinions. A part or all of the above-mentioned processing in the proposal reflection unit may be performed using, for example, AI, or may be performed without using AI. For example, the proposal reflection unit can input the opinion data analyzed by the opinion analysis unit to the generation AI and cause the generation AI to update the next proposal content.

[0083] The reception unit can estimate the user's emotion and adjust the way the conversation proceeds based on the estimated user's emotion. The reception unit estimates the user's emotion using, for example, voice analysis technology or facial expression recognition technology. For example, the reception unit analyzes the tone and speed of the user's voice and changes in facial expression to calculate an emotion score. This makes it possible to adjust the way the conversation proceeds according to the user's emotion. For example, if the user is stressed, the reception unit selects a relaxing topic and proceeds with the conversation in a gentle tone. Also, if the user is excited, the reception unit can select an energetic topic and proceed with the conversation in an active tone. Furthermore, if the user is tired, the reception unit can proceed with a short and concise conversation to reduce the burden on the user. The emotion estimation is realized using an emotion estimation function using, for example, an emotion engine or a generation AI. The generation AI is, for example, a text generation AI (for example, LLM) or a multimodal generation AI, but is not limited to such examples. A part or all of the above-mentioned processing in the reception unit may be performed using, for example, an AI, or may be performed without using an AI. For example, the reception unit can input the user's voice data and facial expression data to the generation AI and have the generation AI estimate emotions.

[0084] The reception unit can analyze the user's past conversation history and select the optimal conversation topic. The reception unit, for example, stores the user's past conversation history in a database and analyzes it. The reception unit can analyze the contents of the past conversations and identify the user's interests and preferences, for example, using natural language processing technology. This enables a conversation that is interesting to the user by selecting the optimal topic based on the past conversation history. For example, the reception unit preferentially selects topics in which the user has shown interest in the past. In addition, the reception unit can provide a comfortable conversation by excluding topics that the user has avoided in the past. Furthermore, the reception unit can select a topic suitable for a specific time period from the user's past conversation history. A part or all of the above-mentioned processing in the reception unit may be performed, for example, using AI, or may be performed without using AI. For example, the reception unit can input the user's past conversation data to the generation AI and cause the generation AI to execute a process of selecting the optimal conversation topic.

[0085] The reception unit can perform filtering based on the user's current living situation and field of interest when receiving a conversation. The reception unit, for example, stores information on the user's current living situation and field of interest in a database and analyzes it. The reception unit can obtain information such as the user's schedule, health condition, and home environment, and filter conversation topics based on the information. This enables a more relevant conversation by filtering based on the user's living situation and field of interest. For example, the reception unit preferentially selects topics related to a project that the user is currently working on. In addition, the reception unit can select appropriate topics based on the user's current living situation (e.g., work, family, hobbies). Furthermore, the reception unit can also select conversation topics based on the user's field of interest (e.g., sports, music, travel). Part or all of the above-mentioned processing in the reception unit may be performed using, for example, AI, or may be performed without using AI. For example, the reception unit can input data on the user's living situation and field of interest to the generation AI and cause the generation AI to execute the filtering process.

[0086] The reception unit can estimate the user's emotion and determine the priority of the conversation based on the estimated user's emotion. The reception unit estimates the user's emotion using, for example, a voice analysis technology or a facial expression recognition technology. For example, the reception unit analyzes the tone and speed of the user's voice and changes in facial expression to calculate an emotion score. This allows the priority of the conversation to be determined according to the user's emotion. For example, if the user is nervous, the reception unit preferentially selects a topic that can relax the user. Also, if the user is having fun, the reception unit can preferentially select an interesting topic. Furthermore, if the user is in a hurry, the reception unit can preferentially select an important topic. The emotion estimation is realized using an emotion estimation function using, for example, an emotion engine or a generation AI. The generation AI is, for example, a text generation AI (for example, LLM) or a multimodal generation AI, but is not limited to such examples. A part or all of the above-mentioned processing in the reception unit may be performed using, for example, an AI, or may be performed without using an AI. For example, the reception unit can input the user's voice data and facial expression data to the generation AI and cause the generation AI to execute emotion estimation.

[0087] The reception unit can preferentially receive a topic with high relevance based on the geographical location information of the user when receiving a conversation. The reception unit, for example, acquires the geographical location information of the user using GPS data or a location information service. The reception unit can preferentially select a topic related to the user's current location, for example. This allows for a more appropriate conversation by selecting a topic with high relevance based on the user's geographical location information. For example, the reception unit preferentially selects a topic related to the user's current location. In addition, the reception unit can talk about local events and news based on the user's geographical location information. Furthermore, the reception unit can talk about local tourist spots and restaurants based on the user's geographical location information. A part or all of the above-mentioned processing in the reception unit may be performed, for example, using AI, or may be performed without using AI. For example, the reception unit can input the user's geographical location information to the generation AI and cause the generation AI to execute a process of selecting a topic with high relevance.

[0088] The reception unit can analyze the user's social media activity and receive related topics when receiving a conversation. The reception unit, for example, stores and analyzes the user's social media activity in a database. The reception unit can, for example, use natural language processing technology to analyze the content of social media posts and identify the user's interests and preferences. This enables a more appropriate conversation by selecting related topics based on the user's social media activity. For example, the reception unit preferentially selects topics that the user frequently posts on social media. In addition, the reception unit can identify current interests from the user's social media activity and select related topics. Furthermore, the reception unit can select topics in which the user's followers and friends on social media are interested. A part or all of the above-mentioned processing in the reception unit may be performed, for example, using AI, or may be performed without using AI. For example, the reception unit can input the user's social media data to the generation AI and cause the generation AI to execute a process of selecting related topics.

[0089] The analysis unit can estimate the user's emotion and adjust the expression method of the action proposal based on the estimated user's emotion. The analysis unit estimates the user's emotion using, for example, voice analysis technology or facial expression recognition technology. For example, the analysis unit analyzes the tone and speed of the user's voice and changes in facial expression to calculate an emotion score. This allows the expression method of the action proposal to be adjusted according to the user's emotion. For example, if the user is relaxed, the analysis unit makes an action proposal in a gentle tone. Also, if the user is in a hurry, the analysis unit can make a concise and quick action proposal. Furthermore, if the user is excited, the analysis unit can make an action proposal in an energetic tone. The emotion estimation is realized using an emotion estimation function using, for example, an emotion engine or a generation AI. The generation AI is, for example, a text generation AI (for example, LLM) or a multimodal generation AI, but is not limited to such examples. A part or all of the above-mentioned processing in the analysis unit may be performed using, for example, an AI, or may be performed without using an AI. For example, the analysis unit can input the user's voice data and facial expression data to the generation AI and cause the generation AI to execute emotion estimation.

[0090] During the analysis, the analysis unit can suggest an action by referring to the user's past action history. The analysis unit, for example, stores the user's past action history in a database and analyzes it. The analysis unit can, for example, use natural language processing technology to analyze the content of past actions and identify the user's action pattern. This makes it possible to make effective suggestions for the user by suggesting optimal actions based on the past action history. For example, the analysis unit suggests optimal actions based on the user's past successful action patterns. In addition, the analysis unit can suggest actions to avoid failure from the user's past action history. Furthermore, the analysis unit can analyze the user's past action history and suggest the most efficient action. Part or all of the above-mentioned processing in the analysis unit may be performed, for example, using AI, or may be performed without using AI. For example, the analysis unit can input the user's past action data to the generation AI and cause the generation AI to execute a process of suggesting optimal actions.

[0091] The analysis unit can customize the action proposal based on the user's current living situation during the analysis. The analysis unit, for example, stores information on the user's current living situation in a database and analyzes it. The analysis unit can obtain information such as the user's schedule, health condition, and home environment, and customize the action proposal based on the information. This enables more appropriate proposals by customizing the action proposal based on the user's living situation. For example, the analysis unit proposes an action related to a project that the user is currently working on. In addition, the analysis unit can propose appropriate actions based on the user's current living situation (e.g., work, home, hobbies). Furthermore, the analysis unit can also propose actions based on the user's areas of interest (e.g., sports, music, travel). Part or all of the above-mentioned processing in the analysis unit may be performed, for example, using AI, or may be performed without using AI. For example, the analysis unit can input data on the user's living situation to the generation AI and cause the generation AI to customize the action proposal.

[0092] The analysis unit can estimate the user's emotions and determine the priority of action suggestions based on the estimated user's emotions. The analysis unit estimates the user's emotions using, for example, voice analysis technology or facial expression recognition technology. For example, the analysis unit analyzes the tone and speed of the user's voice and changes in facial expressions to calculate an emotion score. This allows the priority of action suggestions to be determined according to the user's emotions. For example, if the user is nervous, the analysis unit preferentially suggests actions that can relax. Also, if the user is having fun, the analysis unit can preferentially suggest interesting actions. Furthermore, if the user is in a hurry, the analysis unit can preferentially suggest important actions. The emotion estimation is realized using an emotion estimation function using, for example, an emotion engine or a generation AI. The generation AI is, for example, a text generation AI (for example, LLM) or a multimodal generation AI, but is not limited to such examples. A part or all of the above-mentioned processing in the analysis unit may be performed using, for example, an AI, or may be performed without using an AI. For example, the analysis unit can input the user's voice data and facial expression data to the generation AI and cause the generation AI to execute emotion estimation.

[0093] The analysis unit can suggest optimal actions in consideration of the user's geographical location information during analysis. The analysis unit, for example, acquires the user's geographical location information using GPS data or a location information service. The analysis unit can, for example, preferentially suggest actions related to the user's current location. This allows for more appropriate suggestions by suggesting optimal actions based on the user's geographical location information. For example, the analysis unit preferentially suggests actions related to the user's current location. In addition, the analysis unit can suggest local events and activities based on the user's geographical location information. Furthermore, the analysis unit can suggest local tourist spots and restaurants based on the user's geographical location information. Some or all of the above-mentioned processing in the analysis unit may be performed, for example, using AI, or may be performed without using AI. For example, the analysis unit can input the user's geographical location information to the generation AI and cause the generation AI to execute a process of suggesting optimal actions.

[0094] The analysis unit can analyze the user's social media activities and make action suggestions during the analysis. The analysis unit, for example, stores the user's social media activities in a database and analyzes them. The analysis unit can, for example, use natural language processing technology to analyze the content of social media posts and identify the user's interests and preferences. This enables more appropriate suggestions by making action suggestions based on the user's social media activities. For example, the analysis unit preferentially suggests activities that the user frequently posts on social media. In addition, the analysis unit can identify current interests from the user's social media activities and suggest related actions. Furthermore, the analysis unit can suggest activities in which the user's followers and friends on social media are interested. A part or all of the above-mentioned processing in the analysis unit may be performed, for example, using AI, or may be performed without using AI. For example, the analysis unit can input the user's social media data to the generation AI and cause the generation AI to execute a process of making action suggestions.

[0095] The writing unit can estimate the user's emotion and adjust the display method of the calendar based on the estimated user's emotion. The writing unit estimates the user's emotion using, for example, voice analysis technology or facial expression recognition technology. For example, the writing unit analyzes the tone and speed of the user's voice and changes in facial expression to calculate an emotion score. This allows the display method of the calendar to be adjusted according to the user's emotion. For example, when the user is relaxed, the writing unit displays the calendar in gentle colors. Also, when the user is in a hurry, the writing unit can highlight and display important appointments. Furthermore, when the user is excited, the writing unit can display the calendar in a visually stimulating design. The estimation of emotion is realized using an emotion estimation function using, for example, an emotion engine or a generation AI. The generation AI is, for example, a text generation AI (for example, LLM) or a multimodal generation AI, but is not limited to such examples. A part or all of the above-mentioned processing in the writing unit may be performed using, for example, an AI, or may be performed without using an AI. For example, the writing unit can input the user's voice data and facial expression data to the generation AI and cause the generation AI to execute a process of adjusting the display method of the calendar.

[0096] The writing unit can select a writing method by referring to the user's past schedule history when writing. The writing unit, for example, stores the user's past schedule history in a database and analyzes it. The writing unit can, for example, use natural language processing technology to analyze past schedule contents and identify the user's schedule pattern. This enables effective schedule management for the user by selecting an optimal writing method based on the past schedule history. For example, the writing unit selects an optimal writing method based on a schedule pattern that the user has been successful in the past. In addition, the writing unit can select a writing method to avoid failure from the user's past schedule history. Furthermore, the writing unit can analyze the user's past schedule history and select the most efficient writing method. Part or all of the above-mentioned processing in the writing unit may be performed, for example, using AI, or may be performed without using AI. For example, the writing unit can input the user's past schedule data to the generation AI and cause the generation AI to execute a process of selecting an optimal writing method.

[0097] The writing unit can customize the contents of the calendar based on the user's current living situation at the time of writing. The writing unit, for example, stores information on the user's current living situation in a database and analyzes it. The writing unit can obtain information such as the user's schedule, health condition, and home environment, and customize the contents of the calendar based on the information. This enables more appropriate schedule management by customizing the contents of the calendar based on the user's living situation. For example, the writing unit writes an event related to a project that the user is currently working on into the calendar. In addition, the writing unit can write an appropriate event into the calendar based on the user's current living situation (e.g., work, home, hobbies). Furthermore, the writing unit can customize the contents of the calendar based on the user's areas of interest (e.g., sports, music, travel). Part or all of the above-mentioned processing in the writing unit may be performed, for example, using AI, or may be performed without using AI. For example, the writing unit can input data on the user's living situation into the generation AI and cause the generation AI to execute a process of customizing the contents of the calendar.

[0098] The writing unit can estimate the user's emotion and determine the priority of the calendar based on the estimated user's emotion. The writing unit estimates the user's emotion using, for example, voice analysis technology or facial expression recognition technology. For example, the writing unit analyzes the tone and speed of the user's voice and changes in facial expression to calculate an emotion score. This allows the priority of the calendar to be determined according to the user's emotion. For example, if the user is nervous, the writing unit can preferentially write plans that allow them to relax. Also, if the user is having fun, the writing unit can preferentially write plans that are interesting. Furthermore, if the user is in a hurry, the writing unit can preferentially write plans that are important. The estimation of emotion is realized using an emotion estimation function using, for example, an emotion engine or a generation AI. The generation AI is, for example, a text generation AI (for example, LLM) or a multimodal generation AI, but is not limited to such examples. A part or all of the above-mentioned processing in the writing unit may be performed using, for example, an AI, or may be performed without using an AI. For example, the writing unit can input the user's voice data and facial expression data to the generation AI and cause the generation AI to execute a process of determining the priority of the calendar.

[0099] The writing unit can select calendar contents based on the geographical location information of the user at the time of writing. The writing unit, for example, acquires the geographical location information of the user using GPS data or a location information service. The writing unit can, for example, preferentially write plans related to the user's current location. This allows more appropriate schedule management by selecting optimal calendar contents based on the user's geographical location information. For example, the writing unit preferentially writes plans related to the user's current location. In addition, the writing unit can write local events and activities in the calendar based on the user's geographical location information. Furthermore, the writing unit can write local tourist spots and restaurant plans in the calendar based on the user's geographical location information. A part or all of the above-mentioned processing in the writing unit may be performed, for example, using AI or may be performed without using AI. For example, the writing unit can input the user's geographical location information to the generation AI and cause the generation AI to execute a process of selecting optimal calendar contents.

[0100] The writing unit can adjust the calendar contents by analyzing the user's social media activity at the time of writing. The writing unit, for example, stores and analyzes the user's social media activity in a database. The writing unit can, for example, use natural language processing technology to analyze the content of social media posts and identify the user's interests and preferences. This enables more appropriate schedule management by adjusting the calendar contents based on the user's social media activity. For example, the writing unit writes in the calendar the activities that the user frequently posts on social media. In addition, the writing unit can identify current interests from the user's social media activity and write related plans in the calendar. Furthermore, the writing unit can also write in the calendar the activities in which the user's followers and friends on social media are interested. Part or all of the above-mentioned processing in the writing unit may be performed, for example, using AI, or may be performed without using AI. For example, the writing unit can input the user's social media data into the generation AI and cause the generation AI to execute a process of adjusting the calendar contents.

[0101] The feedback receiving unit can estimate the user's emotion and adjust the feedback receiving method based on the estimated user's emotion. The feedback receiving unit estimates the user's emotion using, for example, a voice analysis technology or a facial expression recognition technology. For example, the feedback receiving unit analyzes the tone and speed of the user's voice and changes in facial expression to calculate an emotion score. This makes it possible to adjust the feedback receiving method according to the user's emotion. For example, when the user is relaxed, the feedback receiving unit provides an interface that requests detailed feedback. Also, when the user is in a hurry, the feedback receiving unit can provide an interface that requests brief feedback. Furthermore, when the user is excited, the feedback receiving unit can provide a feedback format that makes it easy to express emotions. The emotion estimation is realized using an emotion estimation function using, for example, an emotion engine or a generation AI. The generation AI is, for example, a text generation AI (for example, LLM) or a multimodal generation AI, but is not limited to such examples. A part or all of the above-mentioned processing in the feedback receiving unit may be performed using, for example, an AI, or may be performed without using an AI. For example, the feedback receiving unit can input the user's voice data and facial expression data to the generation AI and cause the generation AI to execute a process of adjusting the method of receiving feedback.

[0102] The feedback receiving unit can select the receiving method by referring to the user's past feedback history when receiving feedback. The feedback receiving unit, for example, stores the user's past feedback history in a database and analyzes it. The feedback receiving unit can, for example, use natural language processing technology to analyze the past feedback content and identify the user's feedback pattern. This enables effective feedback for the user by selecting the optimal receiving method based on the past feedback history. For example, if the user provided detailed feedback in the past, the feedback receiving unit requests similar detailed feedback. In addition, if the user provided brief feedback in the past, the feedback receiving unit can request brief feedback. Furthermore, the feedback receiving unit can preferentially request feedback in a specific format from the user's past feedback history. Part or all of the above-mentioned processing in the feedback receiving unit may be performed, for example, using AI, or may be performed without using AI. For example, the feedback receiving unit can input the user's past feedback data to the generation AI and cause the generation AI to execute a process of selecting the optimal receiving method.

[0103] The feedback receiving unit can estimate the user's emotion and determine the priority of feedback based on the estimated user's emotion. The feedback receiving unit estimates the user's emotion using, for example, a voice analysis technology or a facial expression recognition technology. For example, the feedback receiving unit analyzes the tone and speed of the user's voice and changes in facial expression to calculate an emotion score. This allows the priority of feedback to be determined according to the user's emotion. For example, if the user is nervous, the feedback receiving unit preferentially accepts feedback that allows the user to relax. Also, if the user is having fun, the feedback receiving unit can preferentially accept interesting feedback. Furthermore, if the user is in a hurry, the feedback receiving unit can preferentially accept important feedback. The emotion estimation is realized using an emotion estimation function using, for example, an emotion engine or a generation AI. The generation AI is, for example, a text generation AI (for example, LLM) or a multimodal generation AI, but is not limited to such examples. A part or all of the above-mentioned processing in the feedback receiving unit may be performed using, for example, an AI, or may be performed without using an AI. For example, the feedback receiving unit can input the user's voice data and facial expression data to the generation AI and cause the generation AI to execute a process of determining the priority of the feedback.

[0104] The feedback receiving unit can receive feedback based on the geographical location information of the user when receiving the feedback. The feedback receiving unit acquires the geographical location information of the user using, for example, GPS data or a location information service. The feedback receiving unit can preferentially receive, for example, feedback related to the user's current location. This allows for more appropriate feedback by receiving optimal feedback based on the user's geographical location information. For example, the feedback receiving unit preferentially receives feedback related to the user's current location. In addition, the feedback receiving unit can receive feedback regarding local events and activities based on the user's geographical location information. Furthermore, the feedback receiving unit can also receive feedback regarding local tourist spots and restaurants based on the user's geographical location information. A part or all of the above-mentioned processing in the feedback receiving unit may be performed using, for example, an AI, or may be performed without using an AI. For example, the feedback receiving unit can input the user's geographical location information to the generation AI and cause the generation AI to execute a process of receiving optimal feedback.

[0105] The learning unit can estimate the user's emotion and select learning data based on the estimated user's emotion. The learning unit estimates the user's emotion using, for example, voice analysis technology or facial expression recognition technology. For example, the learning unit analyzes the tone and speed of the user's voice and changes in facial expression to calculate an emotion score. This allows the learning data to be selected according to the user's emotion. For example, if the user is relaxed, the learning unit selects feedback with a gentle tone as the learning data. Also, if the user is in a hurry, the learning unit can select brief feedback as the learning data. Furthermore, if the user is excited, the learning unit can select energetic feedback as the learning data. The emotion estimation is realized using an emotion estimation function using, for example, an emotion engine or a generation AI. The generation AI is, for example, a text generation AI (for example, LLM) or a multimodal generation AI, but is not limited to such examples. A part or all of the above-mentioned processing in the learning unit may be performed using, for example, an AI, or may be performed without using an AI. For example, the learning unit can input the user's voice data and facial expression data to the generation AI and cause the generation AI to select the learning data.

[0106] The learning unit can improve the learning algorithm by referring to past learning data during learning. The learning unit, for example, stores and analyzes past learning data in a database. The learning unit can, for example, use a machine learning algorithm to analyze past learning data and adjust parameters of the algorithm. This enables more effective learning by optimizing the learning algorithm based on the past learning data. For example, the learning unit selects the most effective algorithm from the past learning data and optimizes learning. In addition, the learning unit can analyze past learning data and adjust parameters of the algorithm. Furthermore, the learning unit can introduce a new algorithm based on the past learning data and optimize learning. A part or all of the above-mentioned processing in the learning unit may be performed, for example, using AI, or may be performed without using AI. For example, the learning unit can input past learning data to the generation AI and cause the generation AI to execute improvement of the learning algorithm.

[0107] The learning unit can estimate the user's emotion and adjust the frequency of learning based on the estimated user's emotion. The learning unit estimates the user's emotion using, for example, voice analysis technology or facial expression recognition technology. For example, the learning unit analyzes the tone and speed of the user's voice and changes in facial expression to calculate an emotion score. This allows the frequency of learning to be adjusted according to the user's emotion. For example, when the user is relaxed, the learning unit performs learning frequently. Also, when the user is in a hurry, the learning unit can reduce the frequency of learning. Furthermore, when the user is excited, the learning unit can perform learning at an appropriate frequency. The estimation of emotion is realized using an emotion estimation function using, for example, an emotion engine or a generation AI. The generation AI is, for example, a text generation AI (for example, LLM) or a multimodal generation AI, but is not limited to such examples. A part or all of the above-mentioned processing in the learning unit may be performed using, for example, an AI, or may be performed without using an AI. For example, the learning unit can input the user's voice data and facial expression data to the generation AI and cause the generation AI to execute a process of adjusting the frequency of learning.

[0108] The learning unit can weight the learning data by referring to the time of feedback submission during learning. The learning unit, for example, stores the time of feedback submission in a database and analyzes it. The learning unit can weight the learning data based on the time of feedback submission using, for example, a machine learning algorithm. This allows for more effective learning by weighting the learning data based on the time of feedback submission. For example, the learning unit performs learning by placing emphasis on data immediately after feedback is submitted. In addition, the learning unit can weight data based on the time period in which feedback is submitted. Furthermore, the learning unit can weight data based on the frequency at which feedback is submitted. A part or all of the above-mentioned processing in the learning unit may be performed using, for example, an AI, or may be performed without using an AI. For example, the learning unit can input feedback submission time data to a generation AI and cause the generation AI to perform weighting of the learning data.

[0109] The weather acquisition unit can estimate the user's emotion and adjust the weather information acquisition method based on the estimated user's emotion. The weather acquisition unit estimates the user's emotion using, for example, voice analysis technology or facial expression recognition technology. For example, the weather acquisition unit analyzes the user's tone and speed of voice and changes in facial expression to calculate an emotion score. This allows the weather information acquisition method to be adjusted according to the user's emotion. For example, when the user is relaxed, the weather acquisition unit acquires detailed weather information. Also, when the user is in a hurry, the weather acquisition unit can acquire concise weather information. Furthermore, when the user is excited, the weather acquisition unit can acquire weather information that is visually easy to understand. The emotion estimation is realized using an emotion estimation function using, for example, an emotion engine or a generation AI. The generation AI is, for example, a text generation AI (for example, LLM) or a multimodal generation AI, but is not limited to such examples. A part or all of the above-mentioned processing in the weather acquisition unit may be performed using, for example, an AI, or may be performed without using an AI. For example, the weather acquisition unit can input the user's voice data and facial expression data into the generation AI and cause the generation AI to execute a process to adjust the method of acquiring weather information.

[0110] When acquiring weather information, the weather acquisition unit can select an acquisition method by referring to the user's past weather history. The weather acquisition unit, for example, stores the user's past weather history in a database and analyzes it. The weather acquisition unit can, for example, use a machine learning algorithm to analyze the past weather history and select a method for acquiring optimal weather information. As a result, it is possible to acquire weather information that is effective for the user by acquiring optimal weather information based on the past weather history. For example, the weather acquisition unit acquires optimal weather information based on weather conditions that the user has preferred in the past. In addition, the weather acquisition unit can acquire information from the user's past weather history, taking into account weather conditions that the user wants to avoid. Furthermore, the weather acquisition unit can analyze the user's past weather history and acquire the most suitable weather information. Part or all of the above-mentioned processing in the weather acquisition unit may be performed, for example, using AI, or may be performed without using AI. For example, the weather acquisition unit can input past weather history data to the generation AI and cause the generation AI to execute a process of selecting a method for acquiring optimal weather information.

[0111] The weather acquisition unit can estimate the user's emotion and determine the priority of the weather information based on the estimated user's emotion. The weather acquisition unit estimates the user's emotion using, for example, voice analysis technology or facial expression recognition technology. For example, the weather acquisition unit analyzes the tone and speed of the user's voice and changes in facial expression to calculate an emotion score. This allows the priority of the weather information to be determined according to the user's emotion. For example, if the user is nervous, the weather acquisition unit preferentially acquires weather information that can relax. Also, if the user is having fun, the weather acquisition unit can preferentially acquire interesting weather information. Furthermore, if the user is in a hurry, the weather acquisition unit can preferentially acquire important weather information. The emotion estimation is realized using an emotion estimation function using, for example, an emotion engine or a generation AI. The generation AI is, for example, a text generation AI (for example, LLM) or a multimodal generation AI, but is not limited to such examples. A part or all of the above-mentioned processing in the weather acquisition unit may be performed using, for example, an AI, or may be performed without using an AI. For example, the weather acquisition unit can input the user's voice data and facial expression data into the generation AI and cause the generation AI to execute a process of determining the priority of weather information.

[0112] The weather acquisition unit can acquire weather information based on the geographical location information of the user when acquiring weather information. The weather acquisition unit acquires the geographical location information of the user using, for example, GPS data or a location information service. The weather acquisition unit can, for example, preferentially acquire weather information related to the user's current location. This makes it possible to acquire more appropriate weather information by acquiring optimal weather information based on the user's geographical location information. For example, the weather acquisition unit preferentially acquires weather information for the user's current location. In addition, the weather acquisition unit can acquire local weather information based on the user's geographical location information. Furthermore, the weather acquisition unit can also acquire weather information for a travel destination based on the user's geographical location information. A part or all of the above-mentioned processing in the weather acquisition unit may be performed using, for example, an AI, or may be performed without using an AI. For example, the weather acquisition unit can input the user's geographical location information to the generation AI and cause the generation AI to execute a process of acquiring optimal weather information.

[0113] The data acquisition unit can estimate the user's emotion and adjust the method of acquiring open data based on the estimated user's emotion. The data acquisition unit estimates the user's emotion using, for example, voice analysis technology or facial expression recognition technology. For example, the data acquisition unit analyzes the tone and speed of the user's voice and changes in facial expression to calculate an emotion score. This allows the method of acquiring open data to be adjusted according to the user's emotion. For example, when the user is relaxed, the data acquisition unit acquires detailed open data. Also, when the user is in a hurry, the data acquisition unit can acquire concise open data. Furthermore, when the user is excited, the data acquisition unit can acquire visually easy-to-understand open data. The estimation of emotion is realized using an emotion estimation function using, for example, an emotion engine or a generation AI. The generation AI is, for example, a text generation AI (for example, LLM) or a multimodal generation AI, but is not limited to such examples. A part or all of the above-mentioned processing in the data acquisition unit may be performed using, for example, an AI, or may be performed without using an AI. For example, the data acquisition unit can input the user's voice data and facial expression data to the generation AI and cause the generation AI to execute a process of adjusting the method of acquiring open data.

[0114] When acquiring open data, the data acquisition unit can select an acquisition method by referring to the user's past data history. The data acquisition unit, for example, stores the user's past data history in a database and analyzes it. The data acquisition unit can, for example, use a machine learning algorithm to analyze the past data history and select a method for acquiring the optimal open data. As a result, by acquiring optimal open data based on the past data history, it becomes possible to acquire data that is effective for the user. For example, the data acquisition unit acquires optimal open data based on data that the user liked in the past. In addition, the data acquisition unit can acquire information from the user's past data history, taking into account data that the user wants to avoid. Furthermore, the data acquisition unit can analyze the user's past data history and acquire the most suitable open data. Part or all of the above-mentioned processing in the data acquisition unit may be performed, for example, using AI, or may be performed without using AI. For example, the data acquisition unit can input the past data history to the generation AI and cause the generation AI to execute a process of selecting a method for acquiring the optimal open data.

[0115] The data acquisition unit can estimate the user's emotions and determine the priority of open data based on the estimated user's emotions. The data acquisition unit estimates the user's emotions using, for example, voice analysis technology or facial expression recognition technology. For example, the data acquisition unit analyzes the tone and speed of the user's voice and changes in facial expressions to calculate an emotion score. This allows the priority of open data to be determined according to the user's emotions. For example, if the user is nervous, the data acquisition unit preferentially acquires data that can relax the user. Also, if the user is having fun, the data acquisition unit can preferentially acquire interesting data. Furthermore, if the user is in a hurry, the data acquisition unit can preferentially acquire important data. The emotion estimation is realized using an emotion estimation function using, for example, an emotion engine or a generation AI. The generation AI is, for example, a text generation AI (for example, LLM) or a multimodal generation AI, but is not limited to such examples. A part or all of the above-mentioned processing in the data acquisition unit may be performed using, for example, an AI, or may be performed without using an AI. For example, the data acquisition unit can input the user's voice data and facial expression data to the generation AI and cause the generation AI to execute a process of determining the priority of open data.

[0116] The data acquisition unit can acquire data based on the geographical location information of the user when acquiring open data. The data acquisition unit acquires the geographical location information of the user using, for example, GPS data or a location information service. The data acquisition unit can, for example, preferentially acquire data related to the user's current location. This makes it possible to acquire more appropriate data by acquiring optimal data based on the user's geographical location information. For example, the data acquisition unit preferentially acquires data related to the user's current location. In addition, the data acquisition unit can acquire regional open data based on the user's geographical location information. Furthermore, the data acquisition unit can also acquire open data of travel destinations based on the user's geographical location information. A part or all of the above-mentioned processing in the data acquisition unit may be performed using, for example, AI, or may be performed without using AI. For example, the data acquisition unit can input the user's geographical location information to the generation AI and cause the generation AI to execute a process of acquiring optimal data.

[0117] The impression analysis unit can estimate the user's emotion and adjust the impression analysis method based on the estimated user's emotion. The impression analysis unit estimates the user's emotion using, for example, voice analysis technology or facial expression recognition technology. For example, the impression analysis unit analyzes the tone and speed of the user's voice and changes in facial expression to calculate an emotion score. This makes it possible to adjust the impression analysis method according to the user's emotion. For example, if the user is relaxed, the impression analysis unit analyzes detailed impressions. Also, if the user is in a hurry, the impression analysis unit can analyze concise impressions. Furthermore, if the user is excited, the impression analysis unit can analyze impressions in a format that makes it easy to express emotions. The emotion estimation is realized using an emotion estimation function using, for example, an emotion engine or a generation AI. The generation AI is, for example, a text generation AI (for example, LLM) or a multimodal generation AI, but is not limited to such examples. A part or all of the above-mentioned processing in the impression analysis unit may be performed using, for example, an AI, or may be performed without using an AI. For example, the impression analysis unit can input the user's voice data and facial expression data into the generation AI and cause the generation AI to execute a process of adjusting the method of analyzing the impressions.

[0118] The impression analysis unit can select an analysis method by referring to the user's past impression history when analyzing impressions. The impression analysis unit, for example, stores the user's past impression history in a database and analyzes it. The impression analysis unit can analyze the contents of past impressions and identify the user's impression pattern, for example, using natural language processing technology. This enables effective analysis for the user by selecting an optimal analysis method based on the past impression history. For example, the impression analysis unit selects an optimal analysis method based on detailed impressions provided by the user in the past. In addition, the impression analysis unit can preferentially analyze concise impressions from the user's past impression history. Furthermore, the impression analysis unit can analyze the user's past impression history and select the most effective analysis method. A part or all of the above-mentioned processing in the impression analysis unit may be performed, for example, using AI, or may be performed without using AI. For example, the impression analysis unit can input the past impression history to the generation AI and cause the generation AI to execute a process of selecting an optimal analysis method.

[0119] The impression analysis unit can estimate the user's emotion and determine the priority of the impressions based on the estimated user's emotion. The impression analysis unit estimates the user's emotion using, for example, voice analysis technology or facial expression recognition technology. For example, the impression analysis unit analyzes the tone and speed of the user's voice and changes in facial expression to calculate an emotion score. This allows the priority of impressions to be determined according to the user's emotion. For example, if the user is nervous, the impression analysis unit preferentially analyzes relaxing impressions. Also, if the user is enjoying themselves, the impression analysis unit can preferentially analyze interesting impressions. Furthermore, if the user is in a hurry, the impression analysis unit can preferentially analyze important impressions. The emotion estimation is realized using an emotion estimation function using, for example, an emotion engine or a generation AI. The generation AI is, for example, a text generation AI (for example, LLM) or a multimodal generation AI, but is not limited to such examples. A part or all of the above-mentioned processing in the impression analysis unit may be performed using, for example, an AI, or may be performed without using an AI. For example, the impression analysis unit can input the user's voice data and facial expression data into the generation AI and have the generation AI execute a process to determine the priority of impressions.

[0120] The impression analysis unit can analyze impressions taking into consideration the geographical location information of the user when analyzing impressions. The impression analysis unit, for example, acquires the geographical location information of the user using GPS data or a location information service. The impression analysis unit can, for example, preferentially analyze impressions related to the user's current location. This allows for more appropriate analysis by analyzing optimal impressions based on the user's geographical location information. For example, the impression analysis unit preferentially analyzes impressions related to the user's current location. In addition, the impression analysis unit can analyze impressions related to local events and activities based on the user's geographical location information. Furthermore, the impression analysis unit can analyze impressions related to local tourist spots and restaurants based on the user's geographical location information. A part or all of the above-mentioned processing in the impression analysis unit may be performed, for example, using AI or may be performed without using AI. For example, the impression analysis unit can input the user's geographical location information to the generation AI and cause the generation AI to execute a process of analyzing optimal impressions.

[0121] The proposal reflection unit can estimate the user's emotion and adjust the proposal reflection method based on the estimated user's emotion. The proposal reflection unit estimates the user's emotion using, for example, voice analysis technology or facial expression recognition technology. For example, the proposal reflection unit analyzes the tone and speed of the user's voice and changes in facial expression to calculate an emotion score. This allows the proposal reflection method to be adjusted according to the user's emotion. For example, if the user is relaxed, the proposal reflection unit reflects the proposal in a gentle tone. Also, if the user is in a hurry, the proposal reflection unit can reflect a concise and quick proposal. Furthermore, if the user is excited, the proposal reflection unit can reflect the proposal in an energetic tone. The emotion estimation is realized using an emotion estimation function using, for example, an emotion engine or a generation AI. The generation AI is, for example, a text generation AI (for example, LLM) or a multimodal generation AI, but is not limited to such examples. A part or all of the above-mentioned processing in the proposal reflection unit may be performed using, for example, an AI, or may be performed without using an AI. For example, the suggestion reflection unit can input the user's voice data and facial expression data into the generation AI and cause the generation AI to execute a process of adjusting the method of reflecting suggestions.

[0122] The proposal reflection unit can select a reflection method by referring to the user's past proposal history when reflecting a proposal. The proposal reflection unit, for example, stores the user's past proposal history in a database and analyzes it. The proposal reflection unit can analyze the past proposal history using, for example, a machine learning algorithm and select an optimal reflection method. This allows for an effective proposal for the user by selecting an optimal reflection method based on the past proposal history. For example, the proposal reflection unit selects an optimal reflection method based on a proposal pattern that the user has been successful in the past. In addition, the proposal reflection unit can select a reflection method to avoid failure from the user's past proposal history. Furthermore, the proposal reflection unit can analyze the user's past proposal history and select the most efficient reflection method. A part or all of the above-mentioned processing in the proposal reflection unit may be performed using, for example, AI, or may be performed without using AI. For example, the proposal reflection unit can input the past proposal history to the generation AI and cause the generation AI to execute a process of selecting an optimal reflection method.

[0123] The proposal reflecting unit can estimate the user's emotion and determine the priority of proposals based on the estimated user's emotion. The proposal reflecting unit estimates the user's emotion using, for example, voice analysis technology or facial expression recognition technology. For example, the proposal reflecting unit analyzes the tone and speed of the user's voice and changes in facial expression to calculate an emotion score. This allows the priority of proposals to be determined according to the user's emotion. For example, if the user is nervous, the proposal reflecting unit preferentially reflects relaxing suggestions. Also, if the user is having fun, the proposal reflecting unit can preferentially reflect interesting suggestions. Furthermore, if the user is in a hurry, the proposal reflecting unit can preferentially reflect important suggestions. The emotion estimation is realized using an emotion estimation function using, for example, an emotion engine or a generation AI. The generation AI is, for example, a text generation AI (for example, LLM) or a multimodal generation AI, but is not limited to such examples. A part or all of the above-mentioned processing in the proposal reflecting unit may be performed using, for example, an AI, or may be performed without using an AI. For example, the suggestion reflection unit can input the user's voice data and facial expression data into the generation AI and cause the generation AI to execute a process of determining the priority of suggestions.

[0124] The proposal reflecting unit can reflect the proposal based on the geographical location information of the user when reflecting the proposal. The proposal reflecting unit acquires the geographical location information of the user using, for example, GPS data or a location information service. The proposal reflecting unit can, for example, preferentially reflect a proposal related to the user's current location. This allows for more appropriate proposals by reflecting optimal proposals based on the user's geographical location information. For example, the proposal reflecting unit preferentially reflects a proposal related to the user's current location. In addition, the proposal reflecting unit can reflect proposals regarding local events and activities based on the user's geographical location information. Furthermore, the proposal reflecting unit can also reflect proposals regarding local tourist spots and restaurants based on the user's geographical location information. A part or all of the above-mentioned processing in the proposal reflecting unit may be performed using, for example, AI, or may be performed without using AI. For example, the proposal reflecting unit can input the user's geographical location information to the generating AI and cause the generating AI to execute a process of reflecting the optimal proposal.

[0125] The system according to the embodiment is not limited to the above-described example, and various modifications are possible, for example, as follows.

[0126] The behavior support system may further include a health data acquisition unit that acquires health data of the user. The health data acquisition unit acquires, for example, heart rate, step count, sleep data, and the like from the user's wearable device. This allows behavior suggestions to be customized based on the user's health condition. For example, if the user is tired, the analysis unit may suggest a relaxing activity. Also, if the user is not getting enough exercise, the analysis unit may suggest an activity that includes exercise. Furthermore, a schedule for ensuring an appropriate amount of sleep may be proposed based on the user's sleep data.

[0127] The analysis unit can estimate the user's emotion and adjust the content of the action suggestions based on the estimated user's emotion. For example, if the user is stressed, the analysis unit can suggest relaxing activities. If the user is excited, the analysis unit can suggest energetic activities. Furthermore, if the user is sad, the analysis unit can suggest activities to lift the user's mood. Emotion estimation may be performed using voice analysis technology or facial expression recognition technology.

[0128] The action support system may further include a hobby data acquisition unit that customizes action suggestions based on the user's hobbies and interests. The hobby data acquisition unit identifies the user's hobbies and interests from, for example, the user's social media accounts and past action history. This allows action suggestions to be made based on the user's hobbies and interests. For example, if the user is interested in music, the analysis unit may suggest participation in a music event. Also, if the user is interested in sports, sporting events and activities may be suggested. Furthermore, if the user is interested in cooking, cooking classes and recipes may be suggested.

[0129] The feedback receiving unit can estimate the user's emotion and adjust the feedback receiving method based on the estimated user's emotion. For example, if the user is relaxed, the feedback receiving unit can provide an interface for requesting detailed feedback. If the user is in a hurry, the feedback receiving unit can provide an interface for requesting brief feedback. Furthermore, if the user is excited, the feedback receiving unit can provide a feedback format that makes it easy to express emotions. Emotion estimation may be performed using voice analysis technology or facial expression recognition technology.

[0130] The learning unit can estimate the user's emotion and select learning data based on the estimated user's emotion. For example, if the user is relaxed, the learning unit can select feedback with a gentle tone as the learning data. If the user is in a hurry, the learning unit can select brief feedback as the learning data. Furthermore, if the user is excited, the learning unit can select energetic feedback as the learning data. Emotion estimation may be performed using voice analysis technology or facial expression recognition technology.

[0131] The action support system may further include a location information acquisition unit that acquires the geographical location information of the user. The location information acquisition unit acquires the user's current location using, for example, GPS data or a location information service. This allows action suggestions to be customized based on the user's current location. For example, if the user is in a tourist spot, the analysis unit may suggest tourist spots and restaurants. Also, if the user is at home, indoor activities may be suggested. Furthermore, if the user is on a business trip, activities at the business trip destination may be suggested.

[0132] The action support system may further include a social media analysis unit that analyzes the user's social media activity. The social media analysis unit may, for example, analyze the contents of posts and interests from the user's social media accounts. This may allow action suggestions to be made based on the user's social media activity. For example, activities related to topics about which the user frequently posts on social media may be suggested. Activities related to topics in which the user's followers and friends are interested may also be suggested. Furthermore, activities related to topics in which the user has shown interest in the past may also be suggested based on the user's social media activity history.

[0133] The behavior support system may further include a behavior history analysis unit that analyzes the user's past behavior history. The behavior history analysis unit, for example, stores the user's past behavior data in a database and analyzes it. This makes it possible to make behavior suggestions based on the user's past behavior history. For example, based on a behavior pattern that the user has been successful in the past, a similar behavior may be suggested. Also, suggestions may be made to help the user avoid behavior patterns that have failed in the past. Furthermore, the user's past behavior history may be analyzed to suggest the most efficient behavior.

[0134] The action support system may further include a life situation acquisition unit that acquires the user's current life situation. The life situation acquisition unit acquires information such as the user's schedule, health condition, and home environment. This allows action suggestions to be customized based on the user's current life situation. For example, an action related to a project the user is currently working on may be suggested. Also, appropriate rest and exercise may be suggested based on the user's health condition. Furthermore, an action for valuing time with family may be suggested based on the user's home environment.

[0135] The action support system can further estimate the user's emotions and prioritize action suggestions based on the estimated user's emotions. For example, if the user is nervous, the analysis unit can prioritize suggesting actions that will relax the user. If the user is having fun, the analysis unit can prioritize suggesting interesting actions. If the user is in a hurry, the analysis unit can prioritize suggesting important actions. Emotion estimation may be performed using voice analysis technology or facial expression recognition technology.

[0136] The process flow of the second embodiment will be briefly described below.

[0137] Step 1: The reception unit receives the user's conversation content. The user's conversation content includes voice data, text data, specific topics, etc. The reception unit can convert the user's voice into text data using voice recognition technology, and can also directly receive the user's text message. Step 2: The analysis unit analyzes the conversation content, open data, and weather information received by the reception unit, and suggests actions. The analysis unit uses natural language processing technology to analyze the conversation content and understand the user's intentions and wishes. It also acquires open data and weather information, and suggests actions based on that information. For example, it acquires weather forecast data and suggests actions based on the weather. Step 3: The writing unit writes the actions suggested by the analysis unit into the calendar. The writing unit automatically writes the actions into a calendar service such as Google Calendar or Outlook Calendar using an API. Step 4: The feedback receiving unit receives user feedback The feedback receiving unit receives user ratings, comments, survey results, and the like. Step 5: The learning unit analyzes the feedback received by the feedback receiving unit and reflects the feedback in the next proposal. The learning unit analyzes the feedback using a machine learning algorithm to improve the accuracy of the proposal.

[0138] The specific processing unit 290 transmits the result of the specific processing to the smart device 14. In the smart device 14, the control unit 46A causes the output device 40 to output the result of the specific processing. The microphone 38B acquires a voice indicating a user input for the result of the specific processing. The control unit 46A transmits the voice data indicating the user input acquired by the microphone 38B to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the voice data.

[0139] The data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of the data generation model 58 is ChatGPT (registered trademark) (Internet search<URL: https: / / openai.com / blog / chatgpt> ) and other generation AIs. The data generation model 58 is obtained by performing deep learning on a neural network. A prompt including an instruction is input to the data generation model 58, and inference data such as voice data indicating a voice, text data indicating a text, and image data indicating an image (e.g., still image data or video data) are input. The data generation model 58 infers the input inference data according to the instruction indicated by the prompt, and outputs the inference result in one or more data formats of voice data, text data, and image data. The data generation model 58 includes, for example, a text generation AI, an image generation AI, and a multimodal generation AI. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The specification processing unit 290 performs the above-mentioned specification processing while using the data generation model 58. The data generation model 58 may be a fine-tuned model so as to output an inference result from a prompt that does not include an instruction, and in this case, the data generation model 58 can output an inference result from a prompt that does not include an instruction. In the data processing device 12 and the like, the data generation model 58 includes a plurality of types, and the data generation model 58 includes an AI other than the generation AI. The AI ​​other than the generation AI is, for example, a linear regression, a logistic regression, a decision tree, a random forest, a support vector machine (SVM), a k-means clustering, a convolutional neural network (CNN), a recurrent neural network (RNN), a generative adversarial network (GAN), or a naive Bayes, and can perform various processes, but is not limited to such examples. The AI ​​may also be an AI agent. In addition, when the processes of each of the above-mentioned parts are performed by an AI, the processes are performed in part or in whole by the AI, but are not limited to such examples.In addition, processing performed by AI including the generation AI may be replaced with rule-based processing, and rule-based processing may be replaced with processing performed by AI including the generation AI.

[0140] Furthermore, the above-described processing by the data processing system 10 is executed by the specific processing unit 290 of the data processing device 12 or the control unit 46A of the smart device 14, but may also be executed by the specific processing unit 290 of the data processing device 12 and the control unit 46A of the smart device 14. Furthermore, the specific processing unit 290 of the data processing device 12 acquires or collects information required for processing from the smart device 14 or an external device, and the smart device 14 acquires or collects information required for processing from the data processing device 12 or an external device.

[0141] Each of the multiple elements including the above-mentioned reception unit, analysis unit, writing unit, feedback reception unit, and learning unit is realized, for example, by at least one of the smart device 14 and the data processing device 12. For example, the reception unit receives the contents of the user's conversation using the microphone 38B or touch panel 38A of the smart device 14. The analysis unit is realized, for example, by the specific processing unit 290 of the data processing device 12, and analyzes the contents of the conversation, open data, and weather information. The writing unit is realized, for example, by the specific processing unit 290 of the data processing device 12, and writes the proposed action in a calendar. The feedback reception unit receives the user's feedback using, for example, the touch panel 38A or microphone 38B of the smart device 14. The learning unit is realized, for example, by the specific processing unit 290 of the data processing device 12, and analyzes the feedback and reflects it in the next proposal. The correspondence between each unit and the device or control unit is not limited to the above-mentioned example, and various changes are possible.

[0142] [Second embodiment] FIG. 3 shows an example of the configuration of a data processing system 210 according to the second embodiment.

[0143] 3, the data processing system 210 includes the data processing device 12 and smart glasses 214. An example of the data processing device 12 is a server.

[0144] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, the RAM 30, and the storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN and / or a LAN.

[0145] The smart glasses 214 include a computer 36, a microphone 238, a speaker 240, a camera 42, and a communication I / F 44. The computer 36 includes a processor 46, a RAM 48, and a storage 50. The processor 46, the RAM 48, and the storage 50 are connected to a bus 52. The microphone 238, the speaker 240, and the camera 42 are also connected to the bus 52.

[0146] The microphone 238 receives instructions and the like from the user by receiving voice uttered by the user. The microphone 238 captures the voice uttered by the user, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs the voice according to instructions from the processor 46.

[0147] Camera 42 is a small digital camera equipped with an optical system including a lens, an aperture, and a shutter, and an imaging element such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the user's surroundings (e.g., an imaging range defined by an angle of view equivalent to the width of the field of vision of an average healthy person).

[0148] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 are responsible for the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is performed in a secure state.

[0149] Fig. 4 shows an example of main functions of the data processing device 12 and the smart glasses 214. As shown in Fig. 4, in the data processing device 12, a specific process is performed by the processor 28. A specific process program 56 is stored in the storage 32.

[0150] The processor 28 reads the specific processing program 56 from the storage 32, and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[0151] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290. The identification processing unit 290 can estimate the emotion of the user using the emotion identification model 59 and perform identification processing using the user's emotion. In the emotion estimation function (emotion identification function) using the emotion identification model 59, various estimations and predictions regarding the user's emotion, including estimation and prediction of the user's emotion, are performed, but are not limited to such examples. In addition, the estimation and prediction of the emotion also include, for example, analysis of the emotion.

[0152] In the smart glasses 214, the specific processing is performed by the processor 46. The storage 50 stores a specific processing program 60. The processor 46 reads the specific processing program 60 from the storage 50 and executes the read specific processing program 60 on the RAM 48. The specific processing is realized by the processor 46 operating as the control unit 46A in accordance with the specific processing program 60 executed on the RAM 48. Note that the smart glasses 214 have a data generation model and an emotion identification model similar to the data generation model 58 and the emotion identification model 59, and can also perform processing similar to that of the specific processing unit 290 using these models.

[0153] Note that a device other than the data processing device 12 may have the data generation model 58. For example, a server device may have the data generation model 58. In this case, the data processing device 12 obtains a processing result (such as a prediction result) using the data generation model 58 by communicating with the server device having the data generation model 58. In addition, the data processing device 12 may be a server device, or may be a terminal device (such as a mobile phone, a robot, or a home appliance) owned by a user.

[0154] The specific processing unit 290 transmits the result of the specific processing to the smart glasses 214. In the smart glasses 214, the control unit 46A causes the speaker 240 to output the result of the specific processing. The microphone 238 acquires a voice indicating a user input for the result of the specific processing. The control unit 46A transmits the voice data indicating the user input acquired by the microphone 238 to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the voice data.

[0155] The data generation model 58 is a so-called generative AI. An example of the data generation model 58 is a generative AI such as ChatGPT. The data generation model 58 is obtained by performing deep learning on a neural network. A prompt including an instruction is input to the data generation model 58, and inference data such as voice data indicating a voice, text data indicating a text, and image data indicating an image (e.g., still image data or video data) is input. The data generation model 58 infers the input inference data according to the instruction indicated by the prompt, and outputs the inference result in one or more data formats of voice data, text data, and image data. The data generation model 58 includes, for example, a text generation AI, an image generation AI, and a multimodal generation AI. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The specification processing unit 290 performs the above-mentioned specification processing while using the data generation model 58. The data generation model 58 may be a fine-tuned model so as to output an inference result from a prompt that does not include an instruction, and in this case, the data generation model 58 can output an inference result from a prompt that does not include an instruction. In the data processing device 12 and the like, the data generation model 58 includes a plurality of types, and the data generation model 58 includes an AI other than the generation AI. The AI ​​other than the generation AI is, for example, a linear regression, a logistic regression, a decision tree, a random forest, a support vector machine (SVM), a k-means clustering, a convolutional neural network (CNN), a recurrent neural network (RNN), a generative adversarial network (GAN), or a naive Bayes, and can perform various processes, but is not limited to such examples. The AI ​​may be an AI agent. In addition, when the processes of each part described above are performed by an AI, the processes are performed in part or in whole by the AI, but are not limited to such examples. In addition, the processes performed by the AI ​​including the generation AI may be replaced with rule-based processes, and the rule-based processes may be replaced with processes performed by the AI ​​including the generation AI.

[0156] The data processing system 210 according to the second embodiment performs the same processing as the data processing system 10 according to the first embodiment. The processing by the data processing system 210 is executed by the specific processing unit 290 of the data processing device 12 or the control unit 46A of the smart glasses 214, but may be executed by the specific processing unit 290 of the data processing device 12 and the control unit 46A of the smart glasses 214. In addition, the specific processing unit 290 of the data processing device 12 acquires or collects information required for processing from the smart glasses 214 or an external device, and the smart glasses 214 acquires or collects information required for processing from the data processing device 12 or an external device.

[0157] Each of the multiple elements including the above-mentioned reception unit, analysis unit, writing unit, feedback reception unit, and learning unit is realized, for example, by at least one of the smart glasses 214 and the data processing device 12. For example, the reception unit receives the user's conversation content using the microphone 238 of the smart glasses 214. The analysis unit is realized, for example, by the specific processing unit 290 of the data processing device 12, and analyzes the conversation content, open data, and weather information. The writing unit is realized, for example, by the specific processing unit 290 of the data processing device 12, and writes the proposed action in the calendar. The feedback reception unit receives the user's feedback using, for example, the microphone 238 of the smart glasses 214. The learning unit is realized, for example, by the specific processing unit 290 of the data processing device 12, and analyzes the feedback and reflects it in the next proposal. The correspondence between each unit and the device or control unit is not limited to the above-mentioned example, and various changes are possible.

[0158] [Third embodiment] FIG. 5 shows an example of the configuration of a data processing system 310 according to the third embodiment.

[0159] 5, the data processing system 310 includes the data processing device 12 and a headset type terminal 314. An example of the data processing device 12 is a server.

[0160] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, the RAM 30, and the storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN and / or a LAN.

[0161] The headset type terminal 314 includes a computer 36, a microphone 238, a speaker 240, a camera 42, a communication I / F 44, and a display 343. The computer 36 includes a processor 46, a RAM 48, and a storage 50. The processor 46, the RAM 48, and the storage 50 are connected to a bus 52. The microphone 238, the speaker 240, the camera 42, and the display 343 are also connected to the bus 52.

[0162] The microphone 238 receives instructions and the like from the user by receiving voice uttered by the user. The microphone 238 captures the voice uttered by the user, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs the voice according to instructions from the processor 46.

[0163] Camera 42 is a small digital camera equipped with an optical system including a lens, an aperture, and a shutter, and an imaging element such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the user's surroundings (e.g., an imaging range defined by an angle of view equivalent to the width of the field of vision of an average healthy person).

[0164] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 are responsible for the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is performed in a secure state.

[0165] Fig. 6 shows an example of the main functions of the data processing device 12 and the headset type terminal 314. As shown in Fig. 6, in the data processing device 12, a specific process is performed by the processor 28. A specific process program 56 is stored in the storage 32.

[0166] The processor 28 reads the specific processing program 56 from the storage 32, and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[0167] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290. The identification processing unit 290 can estimate the emotion of the user using the emotion identification model 59 and perform identification processing using the user's emotion. In the emotion estimation function (emotion identification function) using the emotion identification model 59, various estimations and predictions regarding the user's emotion, including estimation and prediction of the user's emotion, are performed, but are not limited to such examples. In addition, the estimation and prediction of the emotion also include, for example, analysis of the emotion.

[0168] In the headset type terminal 314, the specific processing is performed by the processor 46. The storage 50 stores a specific program 60. The processor 46 reads the specific program 60 from the storage 50, and executes the read specific program 60 on the RAM 48. The specific processing is realized by the processor 46 operating as the control unit 46A in accordance with the specific program 60 executed on the RAM 48. Note that the headset type terminal 314 has a data generation model and an emotion identification model similar to the data generation model 58 and the emotion identification model 59, and can also perform processing similar to that of the identification processing unit 290 using these models.

[0169] Note that a device other than the data processing device 12 may have the data generation model 58. For example, a server device may have the data generation model 58. In this case, the data processing device 12 obtains a processing result (such as a prediction result) using the data generation model 58 by communicating with the server device having the data generation model 58. In addition, the data processing device 12 may be a server device, or may be a terminal device (such as a mobile phone, a robot, or a home appliance) owned by a user.

[0170] The specific processing unit 290 transmits the result of the specific processing to the headset type terminal 314. In the headset type terminal 314, the control unit 46A causes the speaker 240 and the display 343 to output the result of the specific processing. The microphone 238 acquires voice indicating a user input for the result of the specific processing. The control unit 46A transmits voice data indicating the user input acquired by the microphone 238 to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the voice data.

[0171] The data generation model 58 is a so-called generative AI. An example of the data generation model 58 is a generative AI such as ChatGPT. The data generation model 58 is obtained by performing deep learning on a neural network. A prompt including an instruction is input to the data generation model 58, and inference data such as voice data indicating a voice, text data indicating a text, and image data indicating an image (e.g., still image data or video data) is input. The data generation model 58 infers the input inference data according to the instruction indicated by the prompt, and outputs the inference result in one or more data formats of voice data, text data, and image data. The data generation model 58 includes, for example, a text generation AI, an image generation AI, and a multimodal generation AI. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The specification processing unit 290 performs the above-mentioned specification processing while using the data generation model 58. The data generation model 58 may be a fine-tuned model so as to output an inference result from a prompt that does not include an instruction, and in this case, the data generation model 58 can output an inference result from a prompt that does not include an instruction. In the data processing device 12 and the like, the data generation model 58 includes a plurality of types, and the data generation model 58 includes an AI other than the generation AI. The AI ​​other than the generation AI is, for example, a linear regression, a logistic regression, a decision tree, a random forest, a support vector machine (SVM), a k-means clustering, a convolutional neural network (CNN), a recurrent neural network (RNN), a generative adversarial network (GAN), or a naive Bayes, and can perform various processes, but is not limited to such examples. The AI ​​may be an AI agent. In addition, when the processes of each part described above are performed by an AI, the processes are performed in part or in whole by the AI, but are not limited to such examples. In addition, the processes performed by the AI ​​including the generation AI may be replaced with rule-based processes, and the rule-based processes may be replaced with processes performed by the AI ​​including the generation AI.

[0172] The data processing system 310 according to the third embodiment performs the same processing as the data processing system 10 according to the first embodiment. The processing by the data processing system 310 is executed by the specific processing unit 290 of the data processing device 12 or the control unit 46A of the headset type terminal 314, but may be executed by the specific processing unit 290 of the data processing device 12 and the control unit 46A of the headset type terminal 314. In addition, the specific processing unit 290 of the data processing device 12 acquires or collects information required for processing from the headset type terminal 314 or an external device, and the headset type terminal 314 acquires or collects information required for processing from the data processing device 12 or an external device.

[0173] Each of the multiple elements including the above-mentioned reception unit, analysis unit, writing unit, feedback reception unit, and learning unit is realized, for example, by at least one of the headset type terminal 314 and the data processing device 12. For example, the reception unit receives the contents of the user's conversation using the microphone 238 of the headset type terminal 314. The analysis unit is realized, for example, by the specific processing unit 290 of the data processing device 12, and analyzes the contents of the conversation, open data, and weather information. The writing unit is realized, for example, by the specific processing unit 290 of the data processing device 12, and writes the proposed action in the calendar. The feedback reception unit receives the user's feedback using, for example, the microphone 238 of the headset type terminal 314. The learning unit is realized, for example, by the specific processing unit 290 of the data processing device 12, and analyzes the feedback and reflects it in the next proposal. The correspondence between each unit and the device or control unit is not limited to the above-mentioned example, and various changes are possible.

[0174] [Fourth embodiment] FIG. 7 shows an example of the configuration of a data processing system 410 according to the fourth embodiment.

[0175] 7, a data processing system 410 includes a data processing device 12 and a robot 414. An example of the data processing device 12 is a server.

[0176] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, the RAM 30, and the storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN and / or a LAN.

[0177] The robot 414 includes a computer 36, a microphone 238, a speaker 240, a camera 42, a communication I / F 44, and a control target 443. The computer 36 includes a processor 46, a RAM 48, and a storage 50. The processor 46, the RAM 48, and the storage 50 are connected to a bus 52. The microphone 238, the speaker 240, the camera 42, and the control target 443 are also connected to the bus 52.

[0178] The microphone 238 receives instructions and the like from the user by receiving voice uttered by the user. The microphone 238 captures the voice uttered by the user, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs the voice according to instructions from the processor 46.

[0179] Camera 42 is a small digital camera equipped with an optical system including a lens, an aperture, and a shutter, and an imaging element such as a CMOS image sensor or a CCD image sensor, and captures images of the user's surroundings (e.g., an imaging range defined by an angle of view equivalent to the width of the field of vision of a typical healthy person).

[0180] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 are responsible for the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is performed in a secure state.

[0181] The control object 443 includes a display device, LEDs in the eyes, and motors for driving the arms, hands, and legs. The posture and behavior of the robot 414 are controlled by controlling the motors of the arms, hands, and legs. Some of the emotions of the robot 414 can be expressed by controlling these motors. In addition, the facial expressions of the robot 414 can also be expressed by controlling the light emission state of the LEDs in the eyes of the robot 414.

[0182] Fig. 8 shows an example of the main functions of the data processing device 12 and the robot 414. As shown in Fig. 8, in the data processing device 12, a specific process is performed by the processor 28. A specific process program 56 is stored in the storage 32.

[0183] The processor 28 reads the specific processing program 56 from the storage 32, and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[0184] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290. The identification processing unit 290 can estimate the emotion of the user using the emotion identification model 59 and perform identification processing using the user's emotion. In the emotion estimation function (emotion identification function) using the emotion identification model 59, various estimations and predictions regarding the user's emotion, including estimation and prediction of the user's emotion, are performed, but are not limited to such examples. In addition, the estimation and prediction of the emotion also include, for example, analysis of the emotion.

[0185] In the robot 414, the specific processing is performed by the processor 46. The storage 50 stores a specific program 60. The processor 46 reads out the specific program 60 from the storage 50, and executes the specific program 60 on the RAM 48. The specific processing is realized by the processor 46 operating as the control unit 46A in accordance with the specific program 60 executed on the RAM 48. The robot 414 has a data generation model and an emotion identification model similar to the data generation model 58 and the emotion identification model 59, and can also perform processing similar to that of the specific processing unit 290 using these models.

[0186] Note that a device other than the data processing device 12 may have the data generation model 58. For example, a server device may have the data generation model 58. In this case, the data processing device 12 obtains a processing result (such as a prediction result) using the data generation model 58 by communicating with the server device having the data generation model 58. In addition, the data processing device 12 may be a server device, or may be a terminal device (such as a mobile phone, a robot, or a home appliance) owned by a user.

[0187] The specific processing unit 290 transmits the result of the specific processing to the robot 414. In the robot 414, the control unit 46A causes the speaker 240 and the control target 443 to output the result of the specific processing. The microphone 238 acquires a voice indicating a user input for the result of the specific processing. The control unit 46A transmits voice data indicating the user input acquired by the microphone 238 to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the voice data.

[0188] The data generation model 58 is a so-called generative AI. An example of the data generation model 58 is a generative AI such as ChatGPT. The data generation model 58 is obtained by performing deep learning on a neural network. A prompt including an instruction is input to the data generation model 58, and inference data such as voice data indicating a voice, text data indicating a text, and image data indicating an image (e.g., still image data or video data) is input. The data generation model 58 infers the input inference data according to the instruction indicated by the prompt, and outputs the inference result in one or more data formats of voice data, text data, and image data. The data generation model 58 includes, for example, a text generation AI, an image generation AI, and a multimodal generation AI. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The specification processing unit 290 performs the above-mentioned specification processing while using the data generation model 58. The data generation model 58 may be a fine-tuned model so as to output an inference result from a prompt that does not include an instruction, and in this case, the data generation model 58 can output an inference result from a prompt that does not include an instruction. In the data processing device 12 and the like, the data generation model 58 includes a plurality of types, and the data generation model 58 includes an AI other than the generation AI. The AI ​​other than the generation AI is, for example, a linear regression, a logistic regression, a decision tree, a random forest, a support vector machine (SVM), a k-means clustering, a convolutional neural network (CNN), a recurrent neural network (RNN), a generative adversarial network (GAN), or a naive Bayes, and can perform various processes, but is not limited to such examples. The AI ​​may be an AI agent. In addition, when the processes of each part described above are performed by an AI, the processes are performed in part or in whole by the AI, but are not limited to such examples. In addition, the processes performed by the AI ​​including the generation AI may be replaced with rule-based processes, and the rule-based processes may be replaced with processes performed by the AI ​​including the generation AI.

[0189] The data processing system 410 according to the fourth embodiment performs the same processing as the data processing system 10 according to the first embodiment. The processing by the data processing system 410 is executed by the specific processing unit 290 of the data processing device 12 or the control unit 46A of the robot 414, but may be executed by the specific processing unit 290 of the data processing device 12 and the control unit 46A of the robot 414. In addition, the specific processing unit 290 of the data processing device 12 acquires or collects information required for processing from the robot 414 or an external device, etc., and the robot 414 acquires or collects information required for processing from the data processing device 12 or an external device, etc.

[0190] Each of the multiple elements including the above-mentioned reception unit, analysis unit, writing unit, feedback reception unit, and learning unit is realized, for example, by at least one of the robot 414 and the data processing device 12. For example, the reception unit receives the contents of the user's conversation using the microphone 238 of the robot 414. The analysis unit is realized, for example, by the specific processing unit 290 of the data processing device 12, and analyzes the contents of the conversation, open data, and weather information. The writing unit is realized, for example, by the specific processing unit 290 of the data processing device 12, and writes the proposed action in a calendar. The feedback reception unit receives the user's feedback using, for example, the microphone 238 of the robot 414. The learning unit is realized, for example, by the specific processing unit 290 of the data processing device 12, and analyzes the feedback and reflects it in the next proposal. The correspondence between each unit and the device or control unit is not limited to the above-mentioned example, and various changes are possible.

[0191] The emotion identification model 59 as an emotion engine may determine the emotion of the user according to a specific mapping. Specifically, the emotion identification model 59 may determine the emotion of the user according to an emotion map (see FIG. 9), which is a specific mapping. Similarly, the emotion identification model 59 may determine the emotion of the robot, and the identification processing unit 290 may perform identification processing using the emotion of the robot.

[0192] FIG. 9 is a diagram showing an emotion map 400 on which multiple emotions are mapped. In the emotion map 400, emotions are arranged in concentric circles radiating from the center. The closer to the center of the concentric circles, the more primitive emotions are arranged. The more outside the concentric circles, the more emotions that represent states and actions that arise from a state of mind are arranged. Emotions are a concept that includes emotions and mental states. On the left side of the concentric circles, emotions that are generally generated from reactions that occur in the brain are arranged. On the right side of the concentric circles, emotions that are generally induced by situational judgment are arranged. On the upper and lower sides of the concentric circles, emotions that are generally generated from reactions that occur in the brain and are induced by situational judgment are arranged. In addition, on the upper side of the concentric circles, emotions of "pleasure" are arranged, and on the lower side, emotions of "discomfort" are arranged. In this way, in the emotion map 400, multiple emotions are mapped based on the structure in which emotions are generated, and emotions that tend to occur simultaneously are mapped close to each other.

[0193] These emotions are distributed in the 3 o'clock direction of emotion map 400 and usually fluctuate between relief and anxiety. In the right half of emotion map 400, situational awareness dominates over internal sensations, resulting in a sense of calm.

[0194] The inside of emotion map 400 represents what is going on inside one's mind, and the outside of emotion map 400 represents behavior, so the further out you go on emotion map 400, the more visible the emotions become (the more they are expressed in behavior).

[0195] Here, human emotions are based on various balances such as posture and blood sugar level, and when these balances are far from the ideal, it indicates an unpleasant state, and when they are close to the ideal, it indicates a pleasant state. Emotions can also be created for robots, cars, motorcycles, etc., based on various balances such as posture and battery level, so that when these balances are far from the ideal, it indicates an unpleasant state, and when they are close to the ideal, it indicates a pleasant state. The emotion map may be generated, for example, based on the emotion map of Dr. Mitsuyoshi (Research on speech emotion recognition and emotion brain physiological signal analysis system, Tokushima University, doctoral dissertation: https: / / ci.nii.ac.jp / naid / 500000375379). On the left half of the emotion map, emotions belonging to an area called "reaction" where sensation is dominant are lined up. On the right half of the emotion map, emotions belonging to an area called "situation" where situation recognition is dominant are lined up.

[0196] The emotion map defines two emotions that promote learning. The first is the negative emotion around the middle of "repentance" or "remorse" on the situation side. In other words, this is when the robot experiences negative emotions such as "I never want to feel this way again" or "I don't want to be scolded again." The other is the positive emotion around "desire" on the response side. In other words, this is when the robot has positive feelings such as "I want more" or "I want to know more."

[0197] The emotion identification model 59 inputs the user input to a pre-trained neural network, obtains emotion values ​​indicating each emotion shown in the emotion map 400, and determines the emotion of the user. This neural network is pre-trained based on multiple learning data that are combinations of the user input and emotion values ​​indicating each emotion shown in the emotion map 400. Furthermore, this neural network is trained so that emotions that are located close to each other have similar values, as in the emotion map 900 shown in Fig. 10. Fig. 10 shows an example in which multiple emotions, "relief," "calm," and "encouraging," have similar emotion values.

[0198] In the above embodiment, an example was given in which a specific process is performed by one computer 22, but the technology disclosed herein is not limited to this, and distributed processing of the specific process may be performed by multiple computers, including computer 22.

[0199] In the above embodiment, an example in which the specific processing program 56 is stored in the storage 32 has been described, but the technology of the present disclosure is not limited to this. For example, the specific processing program 56 may be stored in a portable computer-readable non-transitory storage medium such as a Universal Serial Bus (USB) memory. The specific processing program 56 stored in the non-transitory storage medium is installed in the computer 22 of the data processing device 12. The processor 28 executes the specific processing in accordance with the specific processing program 56.

[0200] In addition, the specific processing program 56 may be stored in a storage device such as a server connected to the data processing device 12 via the network 54, and the specific processing program 56 may be downloaded and installed on the computer 22 upon request from the data processing device 12.

[0201] It is not necessary to store all of the specific processing program 56 in a storage device such as a server connected to the data processing device 12 via the network 54, or to store all of the specific processing program 56 in the storage 32; only a portion of the specific processing program 56 may be stored.

[0202] As the hardware resource for executing the specific process, various processors as shown below can be used. An example of the processor is a CPU, which is a general-purpose processor that functions as a hardware resource for executing the specific process by executing software, i.e., a program. Another example of the processor is a dedicated electric circuit, which is a processor having a circuit configuration designed exclusively for executing a specific process, such as a Field-Programmable Gate Array (FPGA), a Programmable Logic Device (PLD), or an Application Specific Integrated Circuit (ASIC). Each processor has a built-in or connected memory, and each processor executes the specific process by using the memory.

[0203] The hardware resource that executes the specific process may be one of these various processors, or may be a combination of two or more processors of the same or different types (for example, a combination of multiple FPGAs, or a combination of a CPU and an FPGA). Also, the hardware resource that executes the specific process may be a single processor.

[0204] As an example of a configuration using one processor, first, one processor is configured by combining one or more CPUs and software, and this processor functions as a hardware resource that executes a specific process. Second, there is a configuration using a processor that realizes the functions of the entire system including multiple hardware resources that execute a specific process on a single IC chip, as typified by SoC (System-on-a-chip). In this way, a specific process is realized using one or more of the above-mentioned various processors as hardware resources.

[0205] Furthermore, more specifically, the hardware structure of these various processors can be an electric circuit that combines circuit elements such as semiconductor elements. The specific processes described above are merely examples. It goes without saying that unnecessary steps may be deleted, new steps may be added, or the order of processes may be changed without departing from the spirit of the invention.

[0206] In the above example, the first to fourth embodiments are described separately, but some or all of these embodiments may be combined. The smart device 14, the smart glasses 214, the headset terminal 314, and the robot 414 are only examples, and they may be combined with each other, or may be other devices. In the above example, the first and second embodiments are described separately, but they may be combined.

[0207] The above description and illustrations are detailed descriptions of the parts related to the technology of the present disclosure, and are merely an example of the technology of the present disclosure. For example, the above description of the configuration, function, action, and effect is an example of the configuration, function, action, and effect of the parts related to the technology of the present disclosure. Therefore, it goes without saying that unnecessary parts may be deleted, new elements may be added, or replaced with respect to the description and illustrations shown above, within the scope of the gist of the technology of the present disclosure. In addition, in order to avoid confusion and to facilitate understanding of the parts related to the technology of the present disclosure, the description and illustrations shown above omit explanations of technical common sense that do not require particular explanation in enabling the implementation of the technology of the present disclosure.

[0208] All publications, patent applications, and standards mentioned in this specification are herein incorporated by reference to the same extent as if each individual publication, patent application, and standard was specifically and individually indicated to be incorporated by reference.

[0209] (Appendix 1) A reception unit that receives the contents of a user's conversation; An analysis unit that analyzes the conversation content, open data, and weather information received by the reception unit and proposes an action; a writing unit that writes the action suggested by the analysis unit into a calendar; a feedback receiving unit for receiving feedback from a user; A learning unit that analyzes the feedback received by the feedback receiving unit and reflects the feedback in the next proposal. A system characterized by: (Appendix 2) The analysis unit is Equipped with a weather acquisition unit that acquires weather information 2. The system of claim 1, (Appendix 3) The analysis unit is Equipped with a data acquisition unit that acquires open data 2. The system of claim 1, (Appendix 4) The feedback receiving unit, Equipped with an opinion analysis unit that analyzes user opinions 2. The system of claim 1, (Appendix 5) The learning unit is Equipped with a proposal reflection section that reflects the opinions analyzed by the opinion analysis section in the next proposal 2. The system of claim 1, (Appendix 6) The reception unit is Infer the user's emotions and adjust the way the conversation proceeds based on the estimated user emotions 2. The system of claim 1, (Appendix 7) The reception unit is Analyze the user's past conversation history and select conversation topics 2. The system of claim 1, (Appendix 8) The reception unit is When accepting a conversation, filter it based on the user's current life situation and interests 2. The system of claim 1, (Appendix 9) The reception unit is Estimate user emotions and prioritize conversations based on the estimated user emotions 2. The system of claim 1, (Appendix 10) The reception unit is When accepting conversations, prioritize topics that are more relevant to the user based on their geographic location. 2. The system of claim 1, (Appendix 11) The reception unit is When accepting a conversation, analyze the user's social media activity and accept related topics. 2. The system of claim 1, (Appendix 12) The analysis unit is Estimate the user's emotions and adjust the way action suggestions are presented based on the estimated user's emotions. 2. The system of claim 1, (Appendix 13) The analysis unit is During analysis, actions are suggested based on the user's past behavior history. 2. The system of claim 1, (Appendix 14) The analysis unit is During analysis, customize action suggestions based on the user's current life situation 2. The system of claim 1, (Appendix 15) The analysis unit is Estimate user emotions and prioritize action suggestions based on the estimated user emotions 2. The system of claim 1, (Appendix 16) The analysis unit is During analytics, suggest actions based on the user's geographic location 2. The system of claim 1, (Appendix 17) The analysis unit is During analytics, the social media activity of the user is analyzed to provide actionable suggestions. 2. The system of claim 1, (Appendix 18) The writing unit is Infer user emotions and adjust the way the calendar is displayed based on the inferred user emotions 2. The system of claim 1, (Appendix 19) The writing unit is When writing, select the writing method by referring to the user's past schedule history. 2. The system of claim 1, (Appendix 20) The writing unit is Customize your calendar content based on your current life situation as you post 2. The system of claim 1, (Appendix 21) The writing unit is Infer user emotions and prioritize calendars based on the inferred user emotions 2. The system of claim 1, (Appendix 22) The writing unit is Select calendar content based on user's geographic location when posting 2. The system of claim 1, (Appendix 23) The writing unit is Analyze your social media activity to adjust your calendar content as you post 2. The system of claim 1, (Appendix 24) The feedback receiving unit, Infer user emotions and adjust the way feedback is received based on the estimated user emotions 2. The system of claim 1, (Appendix 25) The feedback receiving unit, When receiving feedback, select the reception method by referring to the user's past feedback history 2. The system of claim 1, (Appendix 26) The feedback receiving unit, Estimate user emotions and prioritize feedback based on the estimated user emotions 2. The system of claim 1, (Appendix 27) The feedback receiving unit, When receiving feedback, feedback is accepted based on the user's geographic location information. 2. The system of claim 1, (Appendix 28) The learning unit is Estimate the user's emotions and select learning data based on the estimated user emotions. 2. The system of claim 1, (Appendix 29) The learning unit is During training, past training data is referenced to improve the learning algorithm 2. The system of claim 1, (Appendix 30) The learning unit is Infer user emotions and adjust the frequency of learning based on the estimated user emotions. 2. The system of claim 1, (Appendix 31) The learning unit is During training, the training data is weighted based on the time of feedback submission. 2. The system of claim 1, (Appendix 32) The weather acquisition unit is To estimate a user's emotion and adjust a method of obtaining weather information based on the estimated user's emotion. 3. The system of claim 2, (Appendix 33) The weather acquisition unit is When obtaining weather information, the method of obtaining the information is selected by referring to the user's past weather history. 3. The system of claim 2, (Appendix 34) The weather acquisition unit is Estimate user's emotions and prioritize weather information based on the estimated user's emotions 3. The system of claim 2, (Appendix 35) The weather acquisition unit is When obtaining weather information, obtain weather information based on the user's geographic location information. 3. The system of claim 2, (Appendix 36) The data acquisition unit is Estimate user sentiment and adjust the method of acquiring open data based on the estimated user sentiment 4. The system of claim 3. (Appendix 37) The data acquisition unit is When acquiring open data, the acquisition method is selected by referring to the user's past data history. 4. The system of claim 3. (Appendix 38) The data acquisition unit is Estimate user sentiment and prioritize open data based on the estimated user sentiment 4. The system of claim 3. (Appendix 39) The data acquisition unit is When acquiring open data, data is acquired based on the user's geographic location information. 4. The system of claim 3. (Appendix 40) The impression analysis unit is Inferring a user's emotions and adjusting the analysis method of the impressions based on the estimated user's emotions 5. The system of claim 4. (Appendix 41) The impression analysis unit is When analyzing impressions, the analysis method is selected by referring to the user's past impression history. 5. The system of claim 4. (Appendix 42) The impression analysis unit is Estimate user's emotions and prioritize comments based on the estimated user's emotions 5. The system of claim 4. (Appendix 43) The impression analysis unit is When analyzing opinions, analyze opinions based on the user's geographic location information 5. The system of claim 4. (Appendix 44) The proposal reflection unit, Infer user emotions and adjust how suggestions are reflected based on the estimated user emotions 6. The system of claim 5, (Appendix 45) The proposal reflection unit, When reflecting a suggestion, the method of reflection is selected by referring to the user's past suggestion history. 6. The system of claim 5, (Appendix 46) The proposal reflection unit, Estimate user sentiment and prioritize suggestions based on the estimated user sentiment 6. The system of claim 5, (Appendix 47) The proposal reflection unit, When applying suggestions, suggestions are applied based on the user's geographic location. 6. The system of claim 5, [Explanation of symbols]

[0210] 10, 210, 310, 410 Data Processing Systems 12 Data Processing Device 14 Smart Devices 214 Smart Glasses 314 Headset-type terminal 414 Robot

Claims

1. A reception unit that receives the contents of a user's conversation; An analysis unit that analyzes the conversation content, open data, and weather information received by the reception unit and proposes an action; a writing unit that writes the action suggested by the analysis unit into a calendar; a feedback receiving unit for receiving feedback from a user; A learning unit that analyzes the feedback received by the feedback receiving unit and reflects the feedback in the next proposal. A system characterized by:

2. The analysis unit is Equipped with a weather acquisition unit that acquires weather information 2. The system of claim 1 .

3. The analysis unit is a data acquisition unit for acquiring the open data 2. The system of claim 1 .

4. The feedback receiving unit, Equipped with an opinion analysis unit that analyzes user opinions 2. The system of claim 1 .

5. The learning unit is A proposal reflection unit is provided for reflecting the opinions analyzed by the opinion analysis unit in the next proposal.

5. The system of claim 4.

6. The reception unit is Infer the user's emotions and adjust the way the conversation proceeds based on the estimated user emotions 2. The system of claim 1 .

7. The reception unit is Analyze the user's past conversation history and select conversation topics 2. The system of claim 1 .

8. The reception unit is When accepting a conversation, filter it based on the user's current life situation and interests 2. The system of claim 1 .

9. The reception unit is Estimate user emotions and prioritize conversations based on the estimated user emotions 2. The system of claim 1 .

10. The reception unit is When accepting conversations, prioritize topics that are more relevant to the user based on their geographic location.

2. The system of claim 1 .

11. The reception unit is When accepting a conversation, analyze the user's social media activity and accept related topics.

2. The system of claim 1 .

12. The analysis unit is Estimate the user's emotions and adjust the way action suggestions are presented based on the estimated user's emotions.

2. The system of claim 1 .

Images