system

Abstract

The system according to the embodiment aims to accurately analyze the user's ambiguous instructions and context and execute appropriate actions. [Solution] A system according to an embodiment includes an analysis unit, a determination unit, and a control unit. The analysis unit analyzes ambiguous instructions. The determination unit determines an action based on the results of the analysis by the analysis unit. The control unit executes the action determined by the determination unit.

Description

[Technical Field]

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

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

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

[0004] Conventional technologies have had the problem of making it difficult to accurately understand ambiguous user instructions and context in smart homes and respond appropriately.

[0005] The system according to the embodiment aims to accurately analyze the user's ambiguous instructions and context and execute appropriate actions. [Means for solving the problem]

[0006] A system according to an embodiment includes an analysis unit, a determination unit, and a control unit. The analysis unit analyzes an ambiguous instruction. The determination unit determines an action based on the result of the analysis by the analysis unit. The control unit executes the action determined by the determination unit. [Effects of the Invention]

[0007] The system according to the embodiment can accurately analyze the user's ambiguous instructions and context and execute appropriate actions. [Brief explanation of the drawings]

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

[0026] In the smart device 14, the specific processing is performed by the processor 46. The storage 50 stores a specific processing program 60. The specific processing program 60 is used together with the specific processing program 56 by the data processing system 10. The processor 46 reads the specific processing program 60 from the storage 50 and executes the read specific processing program 60 on the RAM 48. The specific processing is realized by the processor 46 operating as the control unit 46A in accordance with the specific processing program 60 executed on the RAM 48. Note that the smart device 14 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. Furthermore, the data processing device 12 may be a server device, or may be a terminal device owned by a user (e.g., a mobile phone, a robot, a home appliance, etc.). Next, an example of processing by the data processing system 10 according to the first embodiment will be described.

[0028] (Example 1) A smart home system according to an embodiment of the present invention uses mechanisms such as generation AI and FunctionCall to control smart devices based on the user's situation and ambiguous instructions, improving user comfort. When a user issues a ambiguous instruction to a smart device, the generation AI analyzes the instruction and determines the appropriate smart device behavior. For example, if a user issues a ambiguous instruction such as "Make the room comfortable," the generation AI adjusts the air conditioner temperature and light brightness based on the user's current situation and past data. Furthermore, by using a butler agent as an interface, the user can operate the smart device in a natural, interactive manner. For example, in response to an instruction such as "Tell me tomorrow's schedule," the butler agent connects with a calendar app and provides the user's schedule via voice. The system also supports health management, monitoring the user's health status and providing necessary advice. For example, if a user issues an instruction such as "I've been feeling tired lately," the butler agent analyzes sleep and exercise data and provides appropriate advice. In this way, the use of generation AI and FunctionCall enables smart device control based on the user's ambiguous instructions and situation, improving user comfort. Furthermore, by using a butler agent, users can operate smart devices in a natural, interactive manner, enabling a wide range of applications, including schedule management and health management. This allows smart home systems to control smart devices in accordance with the user's ambiguous instructions and the situation, improving comfort. For example, if a user issues an ambiguous instruction to a smart device, the generation AI analyzes the instruction and determines the appropriate smart device behavior. Furthermore, by using a butler agent as an interface, users can operate smart devices in a natural, interactive manner, enabling a wide range of applications, including schedule management and health management.

[0029] A smart home system according to an embodiment includes an analysis unit, a determination unit, and a control unit. The analysis unit analyzes ambiguous instructions issued by a user. For example, the analysis unit uses a generation AI to analyze the user's ambiguous instructions using natural language processing technology. The analysis unit can also estimate the intent of the ambiguous instructions using a machine learning algorithm. The analysis unit can also use voice recognition technology to analyze voice instructions. For example, the analysis unit converts voice instructions into text and analyzes the text. The determination unit determines an action based on the analysis result by the analysis unit. For example, the determination unit uses a generation AI to determine an appropriate action, such as adjusting the temperature of an air conditioner or adjusting the brightness of lights. The determination unit can also determine an action based on past data of the user. The determination unit can also determine an action taking into account the user's current situation. For example, the determination unit determines an action based on information about the user's current environment (such as temperature, humidity, and illuminance). The control unit executes the action determined by the determination unit. For example, the control unit uses a generation AI to adjust the temperature of an air conditioner or the brightness of lights. The control unit may also provide an interface for controlling the smart device. The control unit may also adjust the control method based on user feedback. For example, the control unit may customize the control method by reflecting the user feedback. In this way, the smart home system according to the embodiment may analyze an ambiguous user instruction, determine an appropriate operation, and execute the operation, thereby improving the user's comfort.

[0030] The smart home system includes a health management unit that monitors the user's health condition and provides advice. The health management unit monitors the user's health condition. For example, the health management unit uses sensors to collect health data such as heart rate, blood pressure, and body temperature. The health management unit can also analyze the collected health data and evaluate the user's health condition. The health management unit also provides advice based on the user's health condition. For example, the health management unit uses generative AI to provide dietary and exercise advice for health management. The health management unit can also provide advice on relaxation based on the user's health condition. In this way, the system can support health management by monitoring the user's health condition and providing appropriate advice.

[0031] The smart home system includes a schedule management unit that manages the user's schedule and provides necessary information. The schedule management unit manages the user's schedule. For example, the schedule management unit works with a calendar app to manage the user's plans. The schedule management unit can also provide a reminder function and notify the user of plans. The schedule management unit also provides necessary information based on the user's schedule. For example, the schedule management unit provides information such as the location, time, and participants of meetings. The schedule management unit can also suggest an optimal schedule based on the user's schedule. In this way, the system can support schedule management by managing the user's schedule and providing necessary information.

[0032] The analysis unit can analyze the user's past instruction history and improve the accuracy of analyzing ambiguous instructions. For example, the analysis unit analyzes ambiguous instructions given by the user in the past and the results thereof, and the generation AI learns the patterns. The analysis unit can also identify frequently used phrases and expressions from the user's past instruction history and improve the analysis accuracy. The analysis unit can also allow the generation AI to select the optimal analysis method for ambiguous instructions based on the user's past instruction history. In this way, by analyzing the past instruction history, the analysis accuracy of ambiguous instructions can be improved.

[0033] The analysis unit can base its analysis of ambiguous instructions on information about the user's current environment. For example, the analysis unit acquires information about the user's current environment in real time, and the generation AI reflects this information in its analysis. The analysis unit can also perform analysis to more accurately understand the intention of ambiguous instructions based on the user's environmental information. The analysis unit can also allow the generation AI to select the optimal analysis method, taking into account the user's environmental information. This allows the intention of ambiguous instructions to be more accurately understood by taking into account the current environmental information.

[0034] When analyzing an ambiguous instruction, the analysis unit analyzes the user's voice tone and speed, thereby being able to more accurately grasp the intention of the instruction. For example, the analysis unit analyzes the user's voice tone to infer emotions and intentions. The analysis unit can also analyze the user's voice speed to determine whether the user is in a hurry. The analysis unit can also combine the user's voice tone and speed to more accurately grasp the intention of an ambiguous instruction. In this way, by analyzing the voice tone and speed, the intention of the instruction can be more accurately grasped.

[0035] When analyzing ambiguous instructions, the analysis unit can prioritize highly relevant analysis results by taking into account the user's geographical location information. For example, the analysis unit allows the generation AI to prioritize highly relevant analysis results based on the user's current location. The analysis unit can also select the optimal analysis result by taking into account the user's geographical location information. The analysis unit can also perform analysis to more accurately understand the intention of ambiguous instructions based on the user's location information. In this way, by taking into account the geographical location information, it is possible to provide highly relevant analysis results.

[0036] When analyzing ambiguous instructions, the analysis unit can analyze the user's social media activities and provide relevant analysis results. For example, the analysis unit analyzes the content of the user's social media posts and provides the relevant analysis results using AI. The analysis unit can also provide relevant analysis results by referring to the activities of the user's friends on social media. The analysis unit can also provide relevant analysis results based on the user's social media check-in information. In this way, it is possible to provide relevant analysis results by analyzing social media activities.

[0037] When analyzing ambiguous instructions, the analysis unit can customize the analysis method by reflecting the user's past feedback. For example, the analysis unit allows the generation AI to adjust the analysis method based on the user's past feedback. The analysis unit can also improve the accuracy of analyzing ambiguous instructions by reflecting the user's feedback. The analysis unit can also allow the generation AI to select the optimal analysis method by taking the user's past feedback into consideration. In this way, the analysis method can be customized and accuracy can be improved by reflecting the past feedback.

[0038] When determining an action, the determination unit can refer to the user's past action history to determine the action. For example, the determination unit allows the generation AI to determine the optimal action based on the user's past action history. The determination unit can also identify frequently used actions from the user's past action history, and the generation AI can prioritize those. The determination unit can also analyze the user's past action history, and the generation AI can determine the most efficient action. This allows the optimal action to be determined by referring to the past action history.

[0039] The determination unit can base the action on the user's current activity status. For example, the determination unit acquires the user's current activity status in real time, and the generation AI determines the action. The determination unit can also have the generation AI select the optimal action based on the user's activity status. The determination unit can also have the generation AI adjust the priority of actions, taking the user's activity status into consideration. This makes it possible to determine the optimal action by taking the current activity status into consideration.

[0040] When determining an action, the determination unit can take the user's health data into consideration when determining the action. For example, the determination unit allows the generation AI to determine the optimal action based on the user's heart rate. The determination unit can also allow the generation AI to determine the action based on the user's sleep data. The determination unit can also allow the generation AI to select the optimal action based on the user's health data. In this way, the optimal action can be determined by taking the health data into consideration.

[0041] When determining an action, the determination unit can determine the action by taking into consideration the user's geographical location information. For example, the determination unit allows the generation AI to determine the optimal action based on the user's current location. The determination unit can also allow the generation AI to select an action by taking into consideration the user's geographical location information. The determination unit can also allow the generation AI to determine the optimal action based on the user's location information. In this way, the optimal action can be determined by taking into consideration the geographical location information.

[0042] When determining an action, the determination unit can analyze the user's social media activity and determine the relevant action. For example, the determination unit analyzes the content posted by the user on social media, and the generation AI determines the relevant action. The determination unit can also cause the generation AI to determine an action by referring to the activity of the user's friends on social media. The determination unit can also cause the generation AI to determine an action based on the user's check-in information on social media. In this way, it is possible to determine the relevant action by analyzing social media activity.

[0043] When determining an action, the determination unit can customize the action determination method by reflecting the user's past feedback. In the determination unit, for example, the generation AI adjusts the action determination method based on the user's past feedback. The determination unit can also improve the accuracy of action determination by reflecting the user's feedback. The determination unit can also select the optimal action determination method by taking the user's past feedback into consideration. In this way, the action determination method can be customized and accuracy can be improved by reflecting the past feedback.

[0044] When controlling, the control unit can select a control method by referring to the user's past control history. For example, the control unit allows the generation AI to select the optimal control method based on the user's past control history. The control unit can also identify frequently used control methods from the user's past control history, and the generation AI can prioritize them. The control unit can also analyze the user's past control history, and the generation AI can select the most efficient control method. In this way, the optimal control method can be selected by referring to the past control history.

[0045] The control unit can base control on the user's current environmental information. For example, the control unit obtains the user's current environmental information in real time, and the generation AI reflects this information in the control. The control unit can also have the generation AI select the optimal control method based on the user's environmental information. The control unit can also have the generation AI adjust the control method by taking the user's environmental information into account. This makes it possible to provide the optimal control method by taking the current environmental information into account.

[0046] During control, the control unit can select a control method taking into account the user's health data. The control unit allows the generation AI to select the optimal control method based on the user's heart rate, for example. The control unit can also allow the generation AI to select a control method taking into account the user's sleep data. The control unit can also allow the generation AI to select the optimal control method based on the user's health data. This makes it possible to provide the optimal control method by taking into account the health data.

[0047] During control, the control unit can select a control method taking into account the user's geographical location information. In the control unit, for example, the generation AI selects the optimal control method based on the user's current location. The control unit can also select a control method taking into account the user's geographical location information. The control unit can also select a control method taking into account the user's location information. In this way, the optimal control method can be provided by taking into account the geographical location information.

[0048] During control, the control unit can analyze the user's social media activity and select a relevant control method. For example, the control unit analyzes the content of the user's social media posts, and the generation AI selects a relevant control method. The control unit can also have the generation AI select a control method based on the activity of the user's friends on social media. The control unit can also have the generation AI select a control method based on the user's check-in information on social media. In this way, a relevant control method can be provided by analyzing social media activity.

[0049] The control unit can customize the control method by reflecting the user's past feedback during control. For example, the control unit has the generation AI adjust the control method based on the user's past feedback. The control unit can also improve control accuracy by reflecting the user's feedback. The control unit can also have the generation AI select the optimal control method by taking the user's past feedback into consideration. In this way, the control method can be customized and accuracy can be improved by reflecting past feedback.

[0050] The health management unit can provide advice by referring to the user's past health data during health management. For example, the health management unit allows the generation AI to provide optimal advice based on the user's past health data. The health management unit can also identify common health problems from the user's past health data, and the generation AI can provide advice for those problems. The health management unit can also analyze the user's past health data, and the generation AI can provide the most effective advice. This makes it possible to provide optimal advice by referring to past health data.

[0051] The health management unit can take into account the user's current living situation when managing health. For example, the health management unit obtains the user's current living situation in real time, and the generation AI reflects this in the advice. The health management unit can also have the generation AI select the most appropriate advice based on the user's living situation. The health management unit can also have the generation AI adjust the priority of advice by taking the user's living situation into consideration. This makes it possible to provide the most appropriate advice by taking the user's current living situation into consideration.

[0052] The health management unit can provide advice taking into account the user's dietary data during health management. For example, the health management unit allows the generation AI to provide optimal advice based on the user's dietary data. The health management unit can also allow the generation AI to provide advice for maintaining health taking into account the user's dietary data. The health management unit can also allow the generation AI to suggest nutritionally balanced meals based on the user's dietary data. This makes it possible to provide optimal advice by taking into account dietary data.

[0053] The health management unit can provide advice taking into account the user's geographical location information during health management. For example, the health management unit allows the generation AI to provide optimal advice based on the user's current location. The health management unit can also allow the generation AI to select advice taking into account the user's geographical location information. The health management unit can also allow the generation AI to provide optimal advice based on the user's location information. In this way, optimal advice can be provided by taking into account the geographical location information.

[0054] The health management unit can analyze the user's social media activity during health management and provide relevant advice. For example, the health management unit analyzes the content posted by the user on social media, and the generation AI provides relevant advice. The health management unit can also provide advice by referring to the activities of the user's friends on social media. The health management unit can also provide advice by referring to the check-in information of the user on social media. In this way, relevant advice can be provided by analyzing social media activity.

[0055] The health management unit can customize the advice method by reflecting the user's past feedback during health management. In the health management unit, for example, the generation AI adjusts the advice method based on the user's past feedback. The health management unit can also improve the accuracy of the advice by reflecting the user's feedback. The health management unit can also have the generation AI select the optimal advice method by taking the user's past feedback into consideration. In this way, the advice method can be customized and accuracy can be improved by reflecting past feedback.

[0056] When managing a schedule, the schedule management unit can provide advice by referring to the user's past schedule history. For example, the schedule management unit allows the generation AI to provide optimal advice based on the user's past schedule history. The schedule management unit can also identify frequently used schedule patterns from the user's past schedule history, and the generation AI can prioritize them. The schedule management unit can also analyze the user's past schedule history and allow the generation AI to provide the most efficient advice. This makes it possible to provide optimal advice by referring to the past schedule history.

[0057] The schedule management unit can take into account the user's current activity status when managing the schedule. For example, the schedule management unit obtains the user's current activity status in real time, and the generation AI reflects this in the advice. The schedule management unit can also have the generation AI select the most appropriate advice based on the user's activity status. The schedule management unit can also have the generation AI adjust the priority of advice by taking the user's activity status into consideration. This makes it possible to provide the most appropriate advice by taking the current activity status into consideration.

[0058] The schedule management unit can provide advice taking into account the user's health data when managing the schedule. For example, the schedule management unit allows the generation AI to provide optimal advice based on the user's heart rate. The schedule management unit can also allow the generation AI to provide advice taking into account the user's sleep data. The schedule management unit can also allow the generation AI to provide optimal advice based on the user's health data. This makes it possible to provide optimal advice by taking into account the health data.

[0059] The schedule management unit can provide advice taking into account the user's geographical location information when managing the schedule. For example, the schedule management unit allows the generation AI to provide optimal advice based on the user's current location. The schedule management unit can also allow the generation AI to select advice taking into account the user's geographical location information. The schedule management unit can also allow the generation AI to provide optimal advice based on the user's location information. In this way, optimal advice can be provided by taking into account the geographical location information.

[0060] The schedule management unit can analyze the user's social media activity and provide relevant advice when managing the schedule. For example, the schedule management unit analyzes the content posted by the user on social media, and the generation AI provides relevant advice. The schedule management unit can also have the generation AI provide advice by referring to the activity of the user's friends on social media. The schedule management unit can also have the generation AI provide advice based on the user's check-in information on social media. In this way, relevant advice can be provided by analyzing social media activity.

[0061] The schedule management unit can customize the advice method by reflecting the user's past feedback when managing the schedule. In the schedule management unit, for example, the generation AI adjusts the advice method based on the user's past feedback. The schedule management unit can also improve the accuracy of the advice by reflecting the user's feedback. The schedule management unit can also have the generation AI select the optimal advice method by taking the user's past feedback into consideration. In this way, the advice method can be customized and accuracy can be improved by reflecting past feedback.

[0062] The system according to the embodiment is not limited to the above-described example, and various modifications are possible, for example, as follows.

[0063] The analysis unit can take into account the user's past purchase history when analyzing the user's ambiguous instruction. For example, the analysis unit infers the intention of the ambiguous instruction based on data on products and services purchased by the user in the past. The analysis unit can also identify frequently purchased products and services from the user's purchase history to improve the accuracy of the analysis. Furthermore, the analysis unit can select the optimal analysis method for the ambiguous instruction based on the user's purchase history. In this way, by taking into account the past purchase history, the accuracy of the analysis of the ambiguous instruction can be improved.

[0064] The analysis unit can base its analysis of ambiguous instructions on the user's current activity status. For example, the analysis unit acquires the user's current activity status in real time, and the generation AI reflects this in the analysis. The analysis unit can also perform analysis to more accurately understand the intention of ambiguous instructions based on the user's activity status. Furthermore, the analysis unit can select the optimal analysis method taking the user's activity status into consideration. This makes it possible to more accurately understand the intention of ambiguous instructions by taking the current activity status into consideration.

[0065] When analyzing ambiguous instructions, the analysis unit can prioritize highly relevant analysis results by taking into account the user's geographical location information. For example, the analysis unit uses a generation AI to prioritize highly relevant analysis results based on the user's current location. The analysis unit can also select the optimal analysis result by taking into account the user's geographical location information. Furthermore, the analysis unit can perform analysis to more accurately understand the intention of ambiguous instructions based on the user's location information. This makes it possible to provide highly relevant analysis results by taking into account the geographical location information.

[0066] The health management unit can provide advice by referring to the user's past health data when managing their health. For example, the health management unit allows the generation AI to provide optimal advice based on the user's past health data. The health management unit can also identify common health problems from the user's past health data, and the generation AI can provide advice for those problems. Furthermore, the health management unit can analyze the user's past health data and allow the generation AI to provide the most effective advice. This allows the optimal advice to be provided by referring to past health data.

[0067] The schedule management unit can analyze the user's social media activity and provide relevant advice when managing the schedule. For example, the schedule management unit analyzes the content of the user's posts on social media, and the generation AI provides relevant advice. The schedule management unit can also have the generation AI provide advice based on the activity of the user's friends on social media. Furthermore, the schedule management unit can have the generation AI provide advice based on the user's check-in information on social media. This makes it possible to provide relevant advice by analyzing social media activity.

[0068] When controlling, the control unit can select a control method by referring to the user's past control history. For example, the control unit allows the generation AI to select the optimal control method based on the user's past control history. The control unit can also identify frequently used control methods from the user's past control history, and the generation AI can prioritize them. Furthermore, the control unit can analyze the user's past control history, and the generation AI can select the most efficient control method. In this way, the optimal control method can be selected by referring to the past control history.

[0069] The processing flow of the first embodiment will be briefly explained below.

[0070] Step 1: The analysis unit analyzes the ambiguous instruction given by the user. For example, the analysis unit uses generative AI to analyze the ambiguous instruction by natural language processing technology. The analysis unit can also use a machine learning algorithm to infer the intention of the ambiguous instruction. The analysis unit can also use voice recognition technology to analyze the voice instruction. For example, the analysis unit converts the voice instruction into text and analyzes the text. Step 2: The decision unit determines an action based on the results of the analysis by the analysis unit. For example, the decision unit uses a generation AI to determine an appropriate action, such as adjusting the temperature of the air conditioner or the brightness of the lights. The decision unit can also determine an action based on the user's past data. The decision unit can also determine an action taking into account the user's current situation. For example, the decision unit determines an action based on the user's current environmental information (temperature, humidity, illuminance, etc.). Step 3: The control unit executes the operation determined by the determination unit. For example, the control unit uses the generation AI to adjust the temperature of the air conditioner or the brightness of the lights. The control unit can also provide an interface for controlling the smart device. The control unit can also adjust the control method based on user feedback. For example, the control unit customizes the control method by reflecting the user feedback.

[0071] (Example 2) A smart home system according to an embodiment of the present invention uses mechanisms such as generation AI and FunctionCall to control smart devices based on the user's situation and ambiguous instructions, improving user comfort. When a user issues a ambiguous instruction to a smart device, the generation AI analyzes the instruction and determines the appropriate smart device behavior. For example, if a user issues a ambiguous instruction such as "Make the room comfortable," the generation AI adjusts the air conditioner temperature and light brightness based on the user's current situation and past data. Furthermore, by using a butler agent as an interface, the user can operate the smart device in a natural, interactive manner. For example, in response to an instruction such as "Tell me tomorrow's schedule," the butler agent connects with a calendar app and provides the user's schedule via voice. The system also supports health management, monitoring the user's health status and providing necessary advice. For example, if a user issues an instruction such as "I've been feeling tired lately," the butler agent analyzes sleep and exercise data and provides appropriate advice. In this way, the use of generation AI and FunctionCall enables smart device control based on the user's ambiguous instructions and situation, improving user comfort. Furthermore, by using a butler agent, users can operate smart devices in a natural, interactive manner, enabling a wide range of applications, including schedule management and health management. This allows smart home systems to control smart devices in accordance with the user's ambiguous instructions and the situation, improving comfort. For example, if a user issues an ambiguous instruction to a smart device, the generation AI analyzes the instruction and determines the appropriate smart device behavior. Furthermore, by using a butler agent as an interface, users can operate smart devices in a natural, interactive manner, enabling a wide range of applications, including schedule management and health management.

[0072] A smart home system according to an embodiment includes an analysis unit, a determination unit, and a control unit. The analysis unit analyzes ambiguous instructions issued by a user. For example, the analysis unit uses a generation AI to analyze the user's ambiguous instructions using natural language processing technology. The analysis unit can also estimate the intent of the ambiguous instructions using a machine learning algorithm. The analysis unit can also use voice recognition technology to analyze voice instructions. For example, the analysis unit converts voice instructions into text and analyzes the text. The determination unit determines an action based on the analysis result by the analysis unit. For example, the determination unit uses a generation AI to determine an appropriate action, such as adjusting the temperature of an air conditioner or adjusting the brightness of lights. The determination unit can also determine an action based on past data of the user. The determination unit can also determine an action taking into account the user's current situation. For example, the determination unit determines an action based on information about the user's current environment (such as temperature, humidity, and illuminance). The control unit executes the action determined by the determination unit. For example, the control unit uses a generation AI to adjust the temperature of an air conditioner or the brightness of lights. The control unit may also provide an interface for controlling the smart device. The control unit may also adjust the control method based on user feedback. For example, the control unit may customize the control method by reflecting the user feedback. In this way, the smart home system according to the embodiment may analyze an ambiguous user instruction, determine an appropriate operation, and execute the operation, thereby improving the user's comfort.

[0073] The smart home system includes a health management unit that monitors the user's health condition and provides advice. The health management unit monitors the user's health condition. For example, the health management unit uses sensors to collect health data such as heart rate, blood pressure, and body temperature. The health management unit can also analyze the collected health data and evaluate the user's health condition. The health management unit also provides advice based on the user's health condition. For example, the health management unit uses generative AI to provide dietary and exercise advice for health management. The health management unit can also provide advice on relaxation based on the user's health condition. In this way, the system can support health management by monitoring the user's health condition and providing appropriate advice.

[0074] The smart home system includes a schedule management unit that manages the user's schedule and provides necessary information. The schedule management unit manages the user's schedule. For example, the schedule management unit works with a calendar app to manage the user's plans. The schedule management unit can also provide a reminder function and notify the user of plans. The schedule management unit also provides necessary information based on the user's schedule. For example, the schedule management unit provides information such as the location, time, and participants of meetings. The schedule management unit can also suggest an optimal schedule based on the user's schedule. In this way, the system can support schedule management by managing the user's schedule and providing necessary information.

[0075] The analysis unit can estimate the user's emotions and adjust the analysis method for ambiguous instructions based on the estimated user emotions. For example, if the user is feeling stressed, the analysis unit allows the generation AI to select a simple analysis method and provide quick results. Alternatively, if the user is relaxed, the analysis unit can allow the generation AI to perform a detailed analysis and provide more options. Alternatively, if the user is in a hurry, the analysis unit can allow the generation AI to select the quickest analysis method and provide immediate results. This allows for more appropriate analysis results to be provided by adjusting the analysis method according to the user's emotions. Emotion estimation is achieved using an emotion estimation function, for example, using an emotion engine or generation AI. The generation AI can be, but is not limited to, a text generation AI (e.g., LLM) or a multimodal generation AI.

[0076] The analysis unit can analyze the user's past instruction history and improve the accuracy of analyzing ambiguous instructions. For example, the analysis unit analyzes ambiguous instructions given by the user in the past and the results thereof, and the generation AI learns the patterns. The analysis unit can also identify frequently used phrases and expressions from the user's past instruction history and improve the analysis accuracy. The analysis unit can also allow the generation AI to select the optimal analysis method for ambiguous instructions based on the user's past instruction history. In this way, by analyzing the past instruction history, the analysis accuracy of ambiguous instructions can be improved.

[0077] The analysis unit can base its analysis of ambiguous instructions on information about the user's current environment. For example, the analysis unit acquires information about the user's current environment in real time, and the generation AI reflects this information in its analysis. The analysis unit can also perform analysis to more accurately understand the intention of ambiguous instructions based on the user's environmental information. The analysis unit can also allow the generation AI to select the optimal analysis method, taking into account the user's environmental information. This allows the intention of ambiguous instructions to be more accurately understood by taking into account the current environmental information.

[0078] When analyzing an ambiguous instruction, the analysis unit analyzes the user's voice tone and speed, thereby being able to more accurately grasp the intention of the instruction. For example, the analysis unit analyzes the user's voice tone to infer emotions and intentions. The analysis unit can also analyze the user's voice speed to determine whether the user is in a hurry. The analysis unit can also combine the user's voice tone and speed to more accurately grasp the intention of an ambiguous instruction. In this way, by analyzing the voice tone and speed, the intention of the instruction can be more accurately grasped.

[0079] The analysis unit can estimate the user's emotions and prioritize the analysis results based on the estimated user emotions. For example, if the user is feeling stressed, the analysis unit can cause the generation AI to prioritize and provide the most important analysis results. Furthermore, if the user is relaxed, the analysis unit can also cause the generation AI to provide detailed analysis results. Furthermore, if the user is in a hurry, the analysis unit can also adjust the priority so that the generation AI can provide results quickly. This allows the generation AI to prioritize the analysis results according to the user's emotions, thereby providing more appropriate results. Emotion estimation is achieved using an emotion estimation function, for example, using an emotion engine or generation AI. The generation AI can be, but is not limited to, a text generation AI (e.g., LLM) or a multimodal generation AI.

[0080] When analyzing ambiguous instructions, the analysis unit can prioritize highly relevant analysis results by taking into account the user's geographical location information. For example, the analysis unit allows the generation AI to prioritize highly relevant analysis results based on the user's current location. The analysis unit can also select the optimal analysis result by taking into account the user's geographical location information. The analysis unit can also perform analysis to more accurately understand the intention of ambiguous instructions based on the user's location information. In this way, by taking into account the geographical location information, it is possible to provide highly relevant analysis results.

[0081] When analyzing ambiguous instructions, the analysis unit can analyze the user's social media activities and provide relevant analysis results. For example, the analysis unit analyzes the content of the user's social media posts and provides the relevant analysis results using AI. The analysis unit can also provide relevant analysis results by referring to the activities of the user's friends on social media. The analysis unit can also provide relevant analysis results based on the user's social media check-in information. In this way, it is possible to provide relevant analysis results by analyzing social media activities.

[0082] When analyzing ambiguous instructions, the analysis unit can customize the analysis method by reflecting the user's past feedback. For example, the analysis unit allows the generation AI to adjust the analysis method based on the user's past feedback. The analysis unit can also improve the accuracy of analyzing ambiguous instructions by reflecting the user's feedback. The analysis unit can also allow the generation AI to select the optimal analysis method by taking the user's past feedback into consideration. In this way, the analysis method can be customized and accuracy can be improved by reflecting the past feedback.

[0083] The determination unit can estimate the user's emotions and adjust the action determination method based on the estimated user's emotions. For example, if the user is feeling stressed, the determination unit can cause the generation AI to determine a simple and quick action. Also, if the user is relaxed, the determination unit can cause the generation AI to determine a detailed action. Also, if the user is in a hurry, the determination unit can cause the generation AI to determine the quickest action. This makes it possible to provide more appropriate actions by adjusting the action determination method according to the user's emotions. Emotion estimation is realized using an emotion estimation function, for example, using an emotion engine or generation AI. The generation AI can be a text generation AI (e.g., LLM) or a multimodal generation AI, but is not limited to these examples.

[0084] When determining an action, the determination unit can refer to the user's past action history to determine the action. For example, the determination unit allows the generation AI to determine the optimal action based on the user's past action history. The determination unit can also identify frequently used actions from the user's past action history, and the generation AI can prioritize those. The determination unit can also analyze the user's past action history, and the generation AI can determine the most efficient action. This allows the optimal action to be determined by referring to the past action history.

[0085] The determination unit can base the action on the user's current activity status. For example, the determination unit acquires the user's current activity status in real time, and the generation AI determines the action. The determination unit can also have the generation AI select the optimal action based on the user's activity status. The determination unit can also have the generation AI adjust the priority of actions, taking the user's activity status into consideration. This makes it possible to determine the optimal action by taking the current activity status into consideration.

[0086] When determining an action, the determination unit can take the user's health data into consideration when determining the action. For example, the determination unit allows the generation AI to determine the optimal action based on the user's heart rate. The determination unit can also allow the generation AI to determine the action based on the user's sleep data. The determination unit can also allow the generation AI to select the optimal action based on the user's health data. In this way, the optimal action can be determined by taking the health data into consideration.

[0087] The determination unit can estimate the user's emotions and determine the priority of actions based on the estimated user emotions. For example, if the user is feeling stressed, the determination unit can cause the generation AI to prioritize the most important actions. Furthermore, if the user is relaxed, the determination unit can cause the generation AI to prioritize detailed actions. Furthermore, if the user is in a hurry, the determination unit can cause the generation AI to prioritize actions that can be performed quickly. In this way, by determining the priority of actions according to the user's emotions, more appropriate actions can be provided. Emotion estimation is realized using an emotion estimation function, for example, using an emotion engine or generation AI. The generation AI can be, but is not limited to, a text generation AI (e.g., LLM) or a multimodal generation AI.

[0088] When determining an action, the determination unit can determine the action by taking into consideration the user's geographical location information. For example, the determination unit allows the generation AI to determine the optimal action based on the user's current location. The determination unit can also allow the generation AI to select an action by taking into consideration the user's geographical location information. The determination unit can also allow the generation AI to determine the optimal action based on the user's location information. In this way, the optimal action can be determined by taking into consideration the geographical location information.

[0089] When determining an action, the determination unit can analyze the user's social media activity and determine the relevant action. For example, the determination unit analyzes the content posted by the user on social media, and the generation AI determines the relevant action. The determination unit can also cause the generation AI to determine an action by referring to the activity of the user's friends on social media. The determination unit can also cause the generation AI to determine an action based on the user's check-in information on social media. In this way, it is possible to determine the relevant action by analyzing social media activity.

[0090] When determining an action, the determination unit can customize the action determination method by reflecting the user's past feedback. In the determination unit, for example, the generation AI adjusts the action determination method based on the user's past feedback. The determination unit can also improve the accuracy of action determination by reflecting the user's feedback. The determination unit can also select the optimal action determination method by taking the user's past feedback into consideration. In this way, the action determination method can be customized and accuracy can be improved by reflecting the past feedback.

[0091] The control unit can estimate the user's emotions and adjust the control method based on the estimated user's emotions. For example, if the user is feeling stressed, the control unit causes the generation AI to select a simple and quick control method. The control unit can also cause the generation AI to select a detailed control method if the user is relaxed. The control unit can also cause the generation AI to select the quickest control method if the user is in a hurry. This allows for more appropriate control by adjusting the control method according to the user's emotions. Emotion estimation is achieved using an emotion estimation function, for example, using an emotion engine or generation AI. The generation AI can be a text generation AI (e.g., LLM) or a multimodal generation AI, but is not limited to these examples.

[0092] When controlling, the control unit can select a control method by referring to the user's past control history. For example, the control unit allows the generation AI to select the optimal control method based on the user's past control history. The control unit can also identify frequently used control methods from the user's past control history, and the generation AI can prioritize them. The control unit can also analyze the user's past control history, and the generation AI can select the most efficient control method. In this way, the optimal control method can be selected by referring to the past control history.

[0093] The control unit can base control on the user's current environmental information. For example, the control unit obtains the user's current environmental information in real time, and the generation AI reflects this information in the control. The control unit can also have the generation AI select the optimal control method based on the user's environmental information. The control unit can also have the generation AI adjust the control method by taking the user's environmental information into account. This makes it possible to provide the optimal control method by taking the current environmental information into account.

[0094] During control, the control unit can select a control method taking into account the user's health data. The control unit allows the generation AI to select the optimal control method based on the user's heart rate, for example. The control unit can also allow the generation AI to select a control method taking into account the user's sleep data. The control unit can also allow the generation AI to select the optimal control method based on the user's health data. This makes it possible to provide the optimal control method by taking into account the health data.

[0095] The control unit can estimate the user's emotions and determine the priority of control based on the estimated user's emotions. For example, if the user is feeling stressed, the control unit can cause the generation AI to prioritize the most important control. Also, if the user is relaxed, the control unit can cause the generation AI to prioritize detailed control. Also, if the user is in a hurry, the control unit can cause the generation AI to prioritize control that can be executed quickly. This allows for more appropriate control to be provided by determining the priority of control according to the user's emotions. Emotion estimation is achieved using an emotion estimation function, for example, using an emotion engine or generation AI. The generation AI can be, but is not limited to, a text generation AI (e.g., LLM) or a multimodal generation AI.

[0096] During control, the control unit can select a control method taking into account the user's geographical location information. In the control unit, for example, the generation AI selects the optimal control method based on the user's current location. The control unit can also select a control method taking into account the user's geographical location information. The control unit can also select a control method taking into account the user's location information. In this way, the optimal control method can be provided by taking into account the geographical location information.

[0097] During control, the control unit can analyze the user's social media activity and select a relevant control method. For example, the control unit analyzes the content of the user's social media posts, and the generation AI selects a relevant control method. The control unit can also have the generation AI select a control method based on the activity of the user's friends on social media. The control unit can also have the generation AI select a control method based on the user's check-in information on social media. In this way, a relevant control method can be provided by analyzing social media activity.

[0098] The control unit can customize the control method by reflecting the user's past feedback during control. For example, the control unit has the generation AI adjust the control method based on the user's past feedback. The control unit can also improve control accuracy by reflecting the user's feedback. The control unit can also have the generation AI select the optimal control method by taking the user's past feedback into consideration. In this way, the control method can be customized and accuracy can be improved by reflecting past feedback.

[0099] The health management unit can estimate the user's emotions and adjust health management advice based on the estimated user emotions. For example, if the user is feeling stressed, the generation AI can provide advice to relax. Furthermore, if the user is relaxed, the health management unit can also provide advice to maintain health. Furthermore, if the user is tired, the generation AI can provide advice to encourage rest. In this way, by adjusting the health management advice according to the user's emotions, more appropriate advice can be provided. Emotion estimation is realized using an emotion estimation function, for example, using an emotion engine or generation AI. The generation AI can be a text generation AI (e.g., LLM) or a multimodal generation AI, but is not limited to these examples.

[0100] The health management unit can provide advice by referring to the user's past health data during health management. For example, the health management unit allows the generation AI to provide optimal advice based on the user's past health data. The health management unit can also identify common health problems from the user's past health data, and the generation AI can provide advice for those problems. The health management unit can also analyze the user's past health data, and the generation AI can provide the most effective advice. This makes it possible to provide optimal advice by referring to past health data.

[0101] The health management unit can take into account the user's current living situation when managing health. For example, the health management unit obtains the user's current living situation in real time, and the generation AI reflects this in the advice. The health management unit can also have the generation AI select the most appropriate advice based on the user's living situation. The health management unit can also have the generation AI adjust the priority of advice by taking the user's living situation into consideration. This makes it possible to provide the most appropriate advice by taking the user's current living situation into consideration.

[0102] The health management unit can provide advice taking into account the user's dietary data during health management. For example, the health management unit allows the generation AI to provide optimal advice based on the user's dietary data. The health management unit can also allow the generation AI to provide advice for maintaining health taking into account the user's dietary data. The health management unit can also allow the generation AI to suggest nutritionally balanced meals based on the user's dietary data. This makes it possible to provide optimal advice by taking into account dietary data.

[0103] The health management unit can estimate the user's emotions and determine health management priorities based on the estimated user emotions. For example, if the user is feeling stressed, the generation AI can prioritize providing advice to relax. Furthermore, if the user is relaxed, the health management unit can also prioritize advice to maintain health. Furthermore, if the user is tired, the health management unit can also prioritize advice encouraging rest. In this way, by determining health management priorities according to the user's emotions, more appropriate advice can be provided. Emotion estimation is realized using an emotion estimation function, for example, using an emotion engine or generation AI. The generation AI can be a text generation AI (e.g., LLM) or a multimodal generation AI, but is not limited to these examples.

[0104] The health management unit can provide advice taking into account the user's geographical location information during health management. For example, the health management unit allows the generation AI to provide optimal advice based on the user's current location. The health management unit can also allow the generation AI to select advice taking into account the user's geographical location information. The health management unit can also allow the generation AI to provide optimal advice based on the user's location information. In this way, optimal advice can be provided by taking into account the geographical location information.

[0105] The health management unit can analyze the user's social media activity during health management and provide relevant advice. For example, the health management unit analyzes the content posted by the user on social media, and the generation AI provides relevant advice. The health management unit can also provide advice by referring to the activities of the user's friends on social media. The health management unit can also provide advice by referring to the check-in information of the user on social media. In this way, relevant advice can be provided by analyzing social media activity.

[0106] The health management unit can customize the advice method by reflecting the user's past feedback during health management. In the health management unit, for example, the generation AI adjusts the advice method based on the user's past feedback. The health management unit can also improve the accuracy of the advice by reflecting the user's feedback. The health management unit can also have the generation AI select the optimal advice method by taking the user's past feedback into consideration. In this way, the advice method can be customized and accuracy can be improved by reflecting past feedback.

[0107] The schedule management unit can estimate the user's emotions and adjust schedule management advice based on the estimated user emotions. For example, if the user is feeling stressed, the schedule management unit allows the generation AI to suggest a schedule for relaxation. Furthermore, if the user is relaxed, the schedule management unit can also allow the generation AI to suggest an efficient schedule. Furthermore, if the user is in a hurry, the schedule management unit can also allow the generation AI to suggest a schedule that can be implemented quickly. This allows the schedule management advice to be adjusted according to the user's emotions, making it possible to provide more appropriate advice. Emotion estimation is achieved using an emotion estimation function, for example, using an emotion engine or generation AI. The generation AI can be a text generation AI (e.g., LLM) or a multimodal generation AI, but is not limited to these examples.

[0108] When managing a schedule, the schedule management unit can provide advice by referring to the user's past schedule history. For example, the schedule management unit allows the generation AI to provide optimal advice based on the user's past schedule history. The schedule management unit can also identify frequently used schedule patterns from the user's past schedule history, and the generation AI can prioritize them. The schedule management unit can also analyze the user's past schedule history and allow the generation AI to provide the most efficient advice. This makes it possible to provide optimal advice by referring to the past schedule history.

[0109] The schedule management unit can take into account the user's current activity status when managing the schedule. For example, the schedule management unit obtains the user's current activity status in real time, and the generation AI reflects this in the advice. The schedule management unit can also have the generation AI select the most appropriate advice based on the user's activity status. The schedule management unit can also have the generation AI adjust the priority of advice by taking the user's activity status into consideration. This makes it possible to provide the most appropriate advice by taking the current activity status into consideration.

[0110] The schedule management unit can provide advice taking into account the user's health data when managing the schedule. For example, the schedule management unit allows the generation AI to provide optimal advice based on the user's heart rate. The schedule management unit can also allow the generation AI to provide advice taking into account the user's sleep data. The schedule management unit can also allow the generation AI to provide optimal advice based on the user's health data. This makes it possible to provide optimal advice by taking into account the health data.

[0111] The schedule management unit can estimate the user's emotions and determine schedule management priorities based on the estimated user emotions. For example, if the user is feeling stressed, the schedule management unit can cause the generation AI to prioritize a schedule that allows relaxation. Furthermore, if the user is relaxed, the schedule management unit can cause the generation AI to prioritize an efficient schedule. Furthermore, if the user is in a hurry, the schedule management unit can cause the generation AI to prioritize a schedule that can be executed quickly. In this way, by determining schedule management priorities according to the user's emotions, more appropriate advice can be provided. Emotion estimation is realized using an emotion estimation function, for example, using an emotion engine or generation AI. The generation AI can be, but is not limited to, a text generation AI (e.g., LLM) or a multimodal generation AI.

[0112] The schedule management unit can provide advice taking into account the user's geographical location information when managing the schedule. For example, the schedule management unit allows the generation AI to provide optimal advice based on the user's current location. The schedule management unit can also allow the generation AI to select advice taking into account the user's geographical location information. The schedule management unit can also allow the generation AI to provide optimal advice based on the user's location information. In this way, optimal advice can be provided by taking into account the geographical location information.

[0113] The schedule management unit can analyze the user's social media activity and provide relevant advice when managing the schedule. For example, the schedule management unit analyzes the content posted by the user on social media, and the generation AI provides relevant advice. The schedule management unit can also have the generation AI provide advice by referring to the activity of the user's friends on social media. The schedule management unit can also have the generation AI provide advice based on the user's check-in information on social media. In this way, relevant advice can be provided by analyzing social media activity.

[0114] The schedule management unit can customize the advice method by reflecting the user's past feedback when managing the schedule. In the schedule management unit, for example, the generation AI adjusts the advice method based on the user's past feedback. The schedule management unit can also improve the accuracy of the advice by reflecting the user's feedback. The schedule management unit can also have the generation AI select the optimal advice method by taking the user's past feedback into consideration. In this way, the advice method can be customized and accuracy can be improved by reflecting past feedback. === Hard Collateral 1-1 === Each of the multiple elements, including the above-described analysis unit, determination unit, control unit, health management unit, and schedule management unit, is realized, for example, by at least one of the smart device 14 and the data processing device 12. For example, the analysis unit is realized by the processor 46 of the smart device 14 and analyzes the user's ambiguous instructions using voice recognition technology. The determination unit is realized, for example, by the specific processing unit 290 of the data processing device 12 and determines an appropriate action based on the analysis result. The control unit is realized, for example, by the control unit 46A of the smart device 14 and executes the determined action. For example, the health management unit collects health data using a sensor of the smart device 14 and analyzes it using the specific processing unit 290 of the data processing device 12. For example, the schedule management unit works in conjunction with a calendar app of the smart device 14 to manage the user's schedule. === Hard Collateral 1-2 === Each of the multiple elements, including the above-described analysis unit, determination unit, control unit, health management unit, and schedule management unit, is realized, for example, by at least one of the smart glasses 214 and the data processing device 12. For example, the analysis unit is realized by the processor 46 of the smart glasses 214 and analyzes the user's ambiguous instructions using voice recognition technology. The determination unit is realized, for example, by the specific processing unit 290 of the data processing device 12 and determines an appropriate action based on the analysis result. The control unit is realized, for example, by the control unit 46A of the smart glasses 214 and executes the determined action. For example, the health management unit collects health data using a sensor of the smart glasses 214 and analyzes it using the specific processing unit 290 of the data processing device 12. For example, the schedule management unit works in conjunction with a calendar app of the smart glasses 214 to manage the user's schedule. === Hard Collateral 1-3 === Each of the multiple elements including the above-mentioned analysis unit, determination unit, control unit, health management unit, and schedule management unit is realized, for example, by at least one of the headset type terminal 314 and the data processing device 12. For example, the analysis unit is realized by the processor 46 of the headset type terminal 314 and analyzes the user's ambiguous instructions using voice recognition technology. The determination unit is realized, for example, by the specific processing unit 290 of the data processing device 12 and determines an appropriate action based on the analysis results. The control unit is realized, for example, by the control unit 46A of the headset type terminal 314 and executes the determined action. For example, the health management unit collects health data using a sensor of the headset type terminal 314 and analyzes the data using the specific processing unit 290 of the data processing device 12. For example, the schedule management unit works in conjunction with a calendar app of the headset type terminal 314 to manage the user's schedule. === Hard Collateral 1-4 === Each of the multiple elements including the above-mentioned analysis unit, determination unit, control unit, health management unit, and schedule management unit is realized, for example, by at least one of the robot 414 and the data processing device 12. For example, the analysis unit is realized by the processor 46 of the robot 414 and analyzes the user's ambiguous instructions using voice recognition technology. The determination unit is realized, for example, by the specific processing unit 290 of the data processing device 12 and determines an appropriate action based on the analysis results. The control unit is realized, for example, by the control unit 46A of the robot 414 and executes the determined action. For example, the health management unit collects health data using a sensor of the robot 414 and analyzes it using the specific processing unit 290 of the data processing device 12. For example, the schedule management unit works in conjunction with a calendar app of the robot 414 to manage the user's schedule.

[0115] The system according to the embodiment is not limited to the above-described example, and various modifications are possible, for example, as follows.

[0116] The analysis unit can take into account the user's past purchase history when analyzing the user's ambiguous instruction. For example, the analysis unit infers the intention of the ambiguous instruction based on data on products and services purchased by the user in the past. The analysis unit can also identify frequently purchased products and services from the user's purchase history to improve the accuracy of the analysis. Furthermore, the analysis unit can select the optimal analysis method for the ambiguous instruction based on the user's purchase history. In this way, by taking into account the past purchase history, the accuracy of the analysis of the ambiguous instruction can be improved.

[0117] The health management unit can estimate the user's emotions and adjust health management advice based on the estimated user emotions. For example, if the user is feeling stressed, the generation AI can provide advice to relax. Also, if the user is relaxed, the generation AI can provide advice to maintain health. Furthermore, if the user is tired, the generation AI can provide advice encouraging rest. In this way, health management advice can be adjusted according to the user's emotions, making it possible to provide more appropriate advice.

[0118] The schedule management unit can estimate the user's emotions and adjust schedule management advice based on the estimated user emotions. For example, if the user is feeling stressed, the generation AI can suggest a schedule for relaxation. Also, if the user is relaxed, the generation AI can suggest an efficient schedule. Furthermore, if the user is in a hurry, the generation AI can suggest a schedule that can be carried out quickly. This makes it possible to provide more appropriate advice by adjusting schedule management advice according to the user's emotions.

[0119] The analysis unit can base its analysis of ambiguous instructions on the user's current activity status. For example, the analysis unit acquires the user's current activity status in real time, and the generation AI reflects this in the analysis. The analysis unit can also perform analysis to more accurately understand the intention of ambiguous instructions based on the user's activity status. Furthermore, the analysis unit can select the optimal analysis method taking the user's activity status into consideration. This makes it possible to more accurately understand the intention of ambiguous instructions by taking the current activity status into consideration.

[0120] The determination unit can estimate the user's emotions and adjust the action determination method based on the estimated user emotions. For example, if the user is feeling stressed, the generation AI can determine a simple and quick action. Also, if the user is relaxed, the generation AI can determine a detailed action. Furthermore, if the user is in a hurry, the generation AI can determine the quickest action. In this way, by adjusting the action determination method according to the user's emotions, more appropriate actions can be provided.

[0121] The control unit can estimate the user's emotions and adjust the control method based on the estimated user emotions. For example, if the user is feeling stressed, the generation AI can select a simple and quick control method. Alternatively, if the user is relaxed, the generation AI can select a detailed control method. Furthermore, if the user is in a hurry, the generation AI can select the quickest control method. This makes it possible to provide more appropriate control by adjusting the control method according to the user's emotions.

[0122] When analyzing ambiguous instructions, the analysis unit can prioritize highly relevant analysis results by taking into account the user's geographical location information. For example, the analysis unit uses a generation AI to prioritize highly relevant analysis results based on the user's current location. The analysis unit can also select the optimal analysis result by taking into account the user's geographical location information. Furthermore, the analysis unit can perform analysis to more accurately understand the intention of ambiguous instructions based on the user's location information. This makes it possible to provide highly relevant analysis results by taking into account the geographical location information.

[0123] The health management unit can provide advice by referring to the user's past health data when managing their health. For example, the health management unit allows the generation AI to provide optimal advice based on the user's past health data. The health management unit can also identify common health problems from the user's past health data, and the generation AI can provide advice for those problems. Furthermore, the health management unit can analyze the user's past health data and allow the generation AI to provide the most effective advice. This allows the optimal advice to be provided by referring to past health data.

[0124] The schedule management unit can analyze the user's social media activity and provide relevant advice when managing the schedule. For example, the schedule management unit analyzes the content of the user's posts on social media, and the generation AI provides relevant advice. The schedule management unit can also have the generation AI provide advice based on the activity of the user's friends on social media. Furthermore, the schedule management unit can have the generation AI provide advice based on the user's check-in information on social media. This makes it possible to provide relevant advice by analyzing social media activity.

[0125] When controlling, the control unit can select a control method by referring to the user's past control history. For example, the control unit allows the generation AI to select the optimal control method based on the user's past control history. The control unit can also identify frequently used control methods from the user's past control history, and the generation AI can prioritize them. Furthermore, the control unit can analyze the user's past control history, and the generation AI can select the most efficient control method. In this way, the optimal control method can be selected by referring to the past control history.

[0126] The processing flow of the second embodiment will be briefly explained below.

[0127] Step 1: The analysis unit analyzes the ambiguous instruction given by the user. For example, the analysis unit uses generative AI to analyze the ambiguous instruction by natural language processing technology. The analysis unit can also use a machine learning algorithm to infer the intention of the ambiguous instruction. The analysis unit can also use voice recognition technology to analyze the voice instruction. For example, the analysis unit converts the voice instruction into text and analyzes the text. Step 2: The decision unit determines an action based on the results of the analysis by the analysis unit. For example, the decision unit uses a generation AI to determine an appropriate action, such as adjusting the temperature of the air conditioner or the brightness of the lights. The decision unit can also determine an action based on the user's past data. The decision unit can also determine an action taking into account the user's current situation. For example, the decision unit determines an action based on the user's current environmental information (temperature, humidity, illuminance, etc.). Step 3: The control unit executes the operation determined by the determination unit. For example, the control unit uses the generation AI to adjust the temperature of the air conditioner or the brightness of the lights. The control unit can also provide an interface for controlling the smart device. The control unit can also adjust the control method based on user feedback. For example, the control unit customizes the control method by reflecting the user feedback.

[0128] The specific processing unit 290 transmits the result of the specific processing to the smart device 14. In the smart device 14, the control unit 46A causes the output device 40 to output the result of the specific processing. The microphone 38B acquires audio indicating a user input regarding the result of the specific processing. The control unit 46A transmits audio data indicating the user input acquired by the microphone 38B to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the audio data.

[0129] 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 engine).<URL: https: / / openai.com / blog / chatgpt> Examples of generative AIs include the data generation model 58, such as a neural network model (e.g., a neural network model), and a neural network model (e.g., a neural network model). The data generation model 58 is obtained by performing deep learning on a neural network. A prompt including an instruction is input to the data generation model 58, and inference data such as voice data indicating speech, text data indicating text, and image data indicating an image is also input to the data generation model 58. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The specification processing unit 290 performs the above-mentioned specification processing using the data generation model 58. The data generation model 58 may be a fine-tuned model so as to output an inference result from a prompt that does not include an instruction. In this case, the data generation model 58 can output an inference result from a prompt that does not include an instruction. The data processing device 12 and the like include multiple types of data generation models 58, and the data generation model 58 includes AIs other than the generative AI. The AI ​​other than the generative AI may be, for example, linear regression, logistic regression, decision tree, random forest, support vector machine (SVM), k-means clustering, convolutional neural network (CNN), recurrent neural network (RNN), generative adversarial network (GAN), or naive Bayes, and can perform various processes, but is not limited to these examples. The AI ​​may also be an AI agent. When the processes of each of the above-mentioned parts are performed by AI, the processes may be performed in part or entirely by AI, but are not limited to these examples. The processes performed by AI, including the generative AI, may be replaced with rule-based processes.

[0130] Furthermore, the processing by the data processing system 10 described above is executed by the specific processing unit 290 of the data processing device 12 or the control unit 46A of the smart device 14, but may also be executed by the specific processing unit 290 of the data processing device 12 and the control unit 46A of the smart device 14. Furthermore, the specific processing unit 290 of the data processing device 12 acquires or collects information necessary for processing from the smart device 14 or an external device, and the smart device 14 acquires or collects information necessary for processing from the data processing device 12 or an external device.

[0131] The correspondence between each part and the device or control part is not limited to the example described above, and various modifications are possible.

[0132] [Second embodiment] FIG. 3 shows an example of the configuration of a data processing system 210 according to the second embodiment.

[0133] 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.

[0134] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN and / or a LAN.

[0135] 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.

[0136] The microphone 238 receives instructions and the like from the user by receiving voice uttered by the user. The microphone 238 captures the voice uttered by the user, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to instructions from the processor 46.

[0137] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an imaging element such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the user's surroundings (for example, an imaging range defined by an angle of view equivalent to the field of vision of a typical healthy person).

[0138] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 are responsible for the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is carried out in a secure state.

[0139] Fig. 4 shows an example of the main functions of the data processing device 12 and the smart glasses 214. As shown in Fig. 4, in the data processing device 12, a specific process is performed by the processor 28. A specific process program 56 is stored in the storage 32.

[0140] 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.

[0141] 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 a user's emotion using the emotion identification model 59 and perform identification processing using the user's emotion. The emotion estimation function (emotion identification function) using the emotion identification model 59 performs various estimations and predictions regarding the user's emotion, including estimation and prediction of the user's emotion, but is not limited to these examples. Furthermore, the estimation and prediction of emotion also includes, for example, emotion analysis.

[0142] In the smart glasses 214, the specific processing is performed by the processor 46. A specific processing program 60 is stored in the storage 50. The processor 46 reads the specific processing program 60 from the storage 50 and executes the read specific processing program 60 on the RAM 48. The specific processing is realized by the processor 46 operating as the control unit 46A in accordance with the specific processing program 60 executed on the RAM 48. The smart glasses 214 also 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 perform processing similar to that of the specific processing unit 290 using these models.

[0143] Note that a device other than the data processing device 12 may have the data generation model 58. For example, a server device may have the data generation model 58. In this case, the data processing device 12 communicates with the server device having the data generation model 58 to obtain a processing result (such as a prediction result) using the data generation model 58. Furthermore, the data processing device 12 may be a server device, or may be a terminal device (for example, a mobile phone, a robot, a home appliance, etc.) owned by a user.

[0144] The specific processing unit 290 transmits the result of the specific processing to the smart glasses 214. In the smart glasses 214, the control unit 46A causes the speaker 240 to output the result of the specific processing. The microphone 238 acquires audio indicating a user input regarding the result of the specific processing. The control unit 46A transmits audio data indicating the user input acquired by the microphone 238 to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the audio data.

[0145] The data generation model 58 is a so-called generative AI. An example of the data generation model 58 is a generative AI such as ChatGPT. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 receives a prompt containing an instruction, as well as inference data such as voice data representing speech, text data representing text, and image data representing an image. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The identification processing unit 290 performs the above-mentioned identification processing using the data generation model 58. The data generation model 58 may be a fine-tuned model so as to output an inference result from a prompt that does not include an instruction. In this case, the data generation model 58 can output an inference result from a prompt that does not include an instruction. The data processing device 12 and the like include multiple types of data generation models 58, and the data generation model 58 includes AIs other than the generative AI. The AI ​​other than the generative AI may be, for example, linear regression, logistic regression, decision tree, random forest, support vector machine (SVM), k-means clustering, convolutional neural network (CNN), recurrent neural network (RNN), generative adversarial network (GAN), or naive Bayes, and can perform various processes, but is not limited to these examples. The AI ​​may also be an AI agent. When the processes of each of the above-mentioned parts are performed by AI, the processes may be performed in part or entirely by AI, but are not limited to these examples. The processes performed by AI, including the generative AI, may be replaced with rule-based processes.

[0146] The data processing system 210 according to the second embodiment performs the same processing as the data processing system 10 according to the first embodiment. The processing by the data processing system 210 is executed by the specific processing unit 290 of the data processing device 12 or the control unit 46A of the smart glasses 214, but may also be executed by the specific processing unit 290 of the data processing device 12 and the control unit 46A of the smart glasses 214. Furthermore, the specific processing unit 290 of the data processing device 12 acquires or collects information required for processing from the smart glasses 214 or an external device, etc., and the smart glasses 214 acquires or collects information required for processing from the data processing device 12 or an external device, etc.

[0147] The correspondence between each part and the device or control part is not limited to the example described above, and various modifications are possible.

[0148] [Third embodiment] FIG. 5 shows an example of the configuration of a data processing system 310 according to the third embodiment.

[0149] 5, the data processing system 310 includes the data processing device 12 and a headset terminal 314. An example of the data processing device 12 is a server.

[0150] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN and / or a LAN.

[0151] 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.

[0152] The microphone 238 receives instructions and the like from the user by receiving voice uttered by the user. The microphone 238 captures the voice uttered by the user, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to instructions from the processor 46.

[0153] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an imaging element such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the user's surroundings (for example, an imaging range defined by an angle of view equivalent to the field of vision of a typical healthy person).

[0154] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 are responsible for the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is carried out in a secure state.

[0155] 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.

[0156] 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.

[0157] 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 a user's emotion using the emotion identification model 59 and perform identification processing using the user's emotion. The emotion estimation function (emotion identification function) using the emotion identification model 59 performs various estimations and predictions regarding the user's emotion, including estimation and prediction of the user's emotion, but is not limited to these examples. Furthermore, the estimation and prediction of emotion also includes, for example, emotion analysis.

[0158] In the headset type terminal 314, the identification process is performed by the processor 46. A identification program 60 is stored in the storage 50. The processor 46 reads the identification program 60 from the storage 50 and executes the read identification program 60 on the RAM 48. The identification process is realized by the processor 46 operating as a control unit 46A in accordance with the identification program 60 executed on the RAM 48. Note that the headset type terminal 314 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.

[0159] Note that a device other than the data processing device 12 may have the data generation model 58. For example, a server device may have the data generation model 58. In this case, the data processing device 12 communicates with the server device having the data generation model 58 to obtain a processing result (such as a prediction result) using the data generation model 58. Furthermore, the data processing device 12 may be a server device, or may be a terminal device (for example, a mobile phone, a robot, a home appliance, etc.) owned by a user.

[0160] The specific processing unit 290 transmits the result of the specific processing to the headset type terminal 314. In the headset type terminal 314, the control unit 46A causes the speaker 240 and the display 343 to output the result of the specific processing. The microphone 238 acquires audio indicating a user input regarding the result of the specific processing. The control unit 46A transmits audio data indicating the user input acquired by the microphone 238 to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the audio data.

[0161] The data generation model 58 is a so-called generative AI. An example of the data generation model 58 is a generative AI such as ChatGPT. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 receives a prompt containing an instruction, as well as inference data such as voice data representing speech, text data representing text, and image data representing an image. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The identification processing unit 290 performs the above-mentioned identification processing using the data generation model 58. The data generation model 58 may be a fine-tuned model so as to output an inference result from a prompt that does not include an instruction. In this case, the data generation model 58 can output an inference result from a prompt that does not include an instruction. The data processing device 12 and the like include multiple types of data generation models 58, and the data generation model 58 includes AIs other than the generative AI. The AI ​​other than the generative AI may be, for example, linear regression, logistic regression, decision tree, random forest, support vector machine (SVM), k-means clustering, convolutional neural network (CNN), recurrent neural network (RNN), generative adversarial network (GAN), or naive Bayes, and can perform various processes, but is not limited to these examples. The AI ​​may also be an AI agent. When the processes of each of the above-mentioned parts are performed by AI, the processes may be performed in part or entirely by AI, but are not limited to these examples. The processes performed by AI, including the generative AI, may be replaced with rule-based processes.

[0162] The data processing system 310 according to the third embodiment performs the same processing as the data processing system 10 according to the first embodiment. The processing by the data processing system 310 is executed by the specific processing unit 290 of the data processing device 12 or the control unit 46A of the headset type terminal 314, but may also be executed by the specific processing unit 290 of the data processing device 12 and the control unit 46A of the headset type terminal 314. Furthermore, the specific processing unit 290 of the data processing device 12 acquires or collects information required for processing from the headset type terminal 314 or an external device, etc., and the headset type terminal 314 acquires or collects information required for processing from the data processing device 12 or an external device, etc.

[0163] The correspondence between each part and the device or control part is not limited to the example described above, and various modifications are possible.

[0164] [Fourth embodiment] FIG. 7 shows an example of the configuration of a data processing system 410 according to the fourth embodiment.

[0165] 7, the data processing system 410 includes a data processing device 12 and a robot 414. An example of the data processing device 12 is a server.

[0166] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN and / or a LAN.

[0167] 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.

[0168] The microphone 238 receives instructions and the like from the user by receiving voice uttered by the user. The microphone 238 captures the voice uttered by the user, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to instructions from the processor 46.

[0169] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an imaging element such as a CMOS image sensor or a CCD image sensor, and captures images of the user's surroundings (for example, an imaging range defined by an angle of view equivalent to the field of vision of a typical healthy person).

[0170] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 are responsible for the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is carried out in a secure state.

[0171] The control object 443 includes a display device, LEDs in the eyes, and motors that drive the arms, hands, and feet. The posture and gestures of the robot 414 are controlled by controlling the motors of the arms, hands, and feet. Some of the emotions of the robot 414 can be expressed by controlling these motors. In addition, the facial expressions of the robot 414 can also be expressed by controlling the light emission state of the LEDs in the eyes of the robot 414.

[0172] 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.

[0173] 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.

[0174] 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 a user's emotion using the emotion identification model 59 and perform identification processing using the user's emotion. The emotion estimation function (emotion identification function) using the emotion identification model 59 performs various estimations and predictions regarding the user's emotion, including estimation and prediction of the user's emotion, but is not limited to these examples. Furthermore, the estimation and prediction of emotion also includes, for example, emotion analysis.

[0175] In the robot 414, the processor 46 performs the identification process. The storage 50 stores the identification program 60. The processor 46 reads the identification program 60 from the storage 50 and executes the read identification program 60 on the RAM 48. The identification process is realized by the processor 46 operating as the control unit 46A in accordance with the identification program 60 executed on the RAM 48. The robot 414 also 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 perform the same process as the identification processing unit 290 using these models.

[0176] Note that a device other than the data processing device 12 may have the data generation model 58. For example, a server device may have the data generation model 58. In this case, the data processing device 12 communicates with the server device having the data generation model 58 to obtain a processing result (such as a prediction result) using the data generation model 58. Furthermore, the data processing device 12 may be a server device, or may be a terminal device (for example, a mobile phone, a robot, a home appliance, etc.) owned by a user.

[0177] The specific processing unit 290 transmits the result of the specific processing to the robot 414. In the robot 414, the control unit 46A causes the speaker 240 and the control target 443 to output the result of the specific processing. The microphone 238 acquires voice indicating a user input regarding the result of the specific processing. The control unit 46A transmits voice data indicating the user input acquired by the microphone 238 to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the voice data.

[0178] The data generation model 58 is a so-called generative AI. An example of the data generation model 58 is a generative AI such as ChatGPT. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 receives a prompt containing an instruction, as well as inference data such as voice data representing speech, text data representing text, and image data representing an image. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The identification processing unit 290 performs the above-mentioned identification processing using the data generation model 58. The data generation model 58 may be a fine-tuned model so as to output an inference result from a prompt that does not include an instruction. In this case, the data generation model 58 can output an inference result from a prompt that does not include an instruction. The data processing device 12 and the like include multiple types of data generation models 58, and the data generation model 58 includes AIs other than the generative AI. The AI ​​other than the generative AI may be, for example, linear regression, logistic regression, decision tree, random forest, support vector machine (SVM), k-means clustering, convolutional neural network (CNN), recurrent neural network (RNN), generative adversarial network (GAN), or naive Bayes, and can perform various processes, but is not limited to these examples. The AI ​​may also be an AI agent. When the processes of each of the above-mentioned parts are performed by AI, the processes may be performed in part or entirely by AI, but are not limited to these examples. The processes performed by AI, including the generative AI, may be replaced with rule-based processes.

[0179] The data processing system 410 according to the fourth embodiment performs the same processing as the data processing system 10 according to the first embodiment. The processing by the data processing system 410 is executed by the specific processing unit 290 of the data processing device 12 or the control unit 46A of the robot 414, but may also be executed by the specific processing unit 290 of the data processing device 12 and the control unit 46A of the robot 414. Furthermore, the specific processing unit 290 of the data processing device 12 acquires or collects information required for processing from the robot 414 or an external device, etc., and the robot 414 acquires or collects information required for processing from the data processing device 12 or an external device, etc.

[0180] The correspondence between each part and the device or control part is not limited to the example described above, and various modifications are possible.

[0181] The emotion identification model 59 as an emotion engine may determine the user's emotion according to a specific mapping. Specifically, the emotion identification model 59 may determine the user's emotion according to an emotion map (see FIG. 9), which is a specific mapping. Similarly, the emotion identification model 59 may determine the robot's emotion, and the identification processing unit 290 may perform identification processing using the robot's emotion.

[0182] FIG. 9 illustrates an emotion map 400 on which multiple emotions are mapped. In the emotion map 400, emotions are arranged in concentric circles radiating from the center. Emotions closer to the center of the concentric circles are more primitive. Emotions representing states and behaviors arising from a state of mind are arranged on the outer edges of the concentric circles. The concept of emotion encompasses both emotions and mental states. Emotions generally generated from reactions occurring in the brain are arranged on the left side of the concentric circles. Emotions generally induced by situational judgment are arranged on the right side of the concentric circles. Emotions generally generated from reactions occurring in the brain and induced by situational judgment are arranged on the upper and lower sides of the concentric circles. Furthermore, the emotion of "pleasure" is arranged on the upper side of the concentric circles, and the emotion of "discomfort" is arranged on the lower side. In this way, in the emotion map 400, multiple emotions are mapped based on the structure by which emotions are generated, and emotions that tend to occur simultaneously are mapped close to each other.

[0183] These emotions are distributed in the 3 o'clock direction on emotion map 400, and typically fluctuate between relief and anxiety. In the right half of emotion map 400, situational awareness dominates over internal sensations, resulting in a sense of calm.

[0184] The inside of emotion map 400 represents what is going on in the mind, and the outside of emotion map 400 represents behavior, so the further you go outside emotion map 400, the more visible the emotions become (the more they are expressed in behavior).

[0185] Human emotions are based on various balances, such as posture and blood sugar levels. When these balances deviate from the ideal, a state of discomfort is expressed, and when they approach the ideal, a state of pleasure is expressed. Emotions can also be created for robots, cars, and motorcycles, based on various balances, such as posture and remaining battery life. When these balances deviate from the ideal, a state of discomfort is expressed, and when they approach the ideal, a state of pleasure is expressed. An emotion map can be generated, for example, based on Dr. Mitsuyoshi's emotion map (Research on speech emotion recognition and brain physiological signal analysis systems for emotions, Tokushima University, doctoral dissertation: https: / / ci.nii.ac.jp / naid / 500000375379). The left half of the emotion map lists emotions belonging to the area called "reaction," where sensation is dominant. The right half of the emotion map lists emotions belonging to the area called "situation," where situational awareness is dominant.

[0186] The emotion map defines two emotions that promote learning. One is a negative emotion on the situation side, around the middle of "repentance" or "reflection." In other words, this occurs when the robot experiences negative emotions such as "I never want to feel this way again" or "I don't want to be scolded again." The other is a positive emotion on the response side, around "desire." In other words, this occurs when the robot experiences positive feelings such as "I want more" or "I want to know more."

[0187] The emotion identification model 59 inputs user input into a pre-trained neural network, obtains emotion values ​​indicating each emotion shown in the emotion map 400, and determines the user's emotion. This neural network is pre-trained based on multiple pieces of training data that are combinations of user input and emotion values ​​indicating each emotion shown in the emotion map 400. Furthermore, this neural network is trained so that emotions that are located close to each other have similar values, as in the emotion map 900 shown in FIG. 10. FIG. 10 shows an example in which multiple emotions, "relieved," "calm," and "reassuring," have similar emotion values.

[0188] 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.

[0189] In the above embodiment, an example in which the specific processing program 56 is stored in the storage 32 has been described, but the technology of the present disclosure is not limited to this. For example, the specific processing program 56 may be stored in a portable, computer-readable, non-transitory storage medium such as a USB (Universal Serial Bus) memory. The specific processing program 56 stored in the non-transitory storage medium is installed in the computer 22 of the data processing device 12. The processor 28 executes the specific processing in accordance with the specific processing program 56.

[0190] Alternatively, the specific processing program 56 may be stored in a storage device such as a server connected to the data processing device 12 via the network 54, and the specific processing program 56 may be downloaded and installed on the computer 22 in response to a request from the data processing device 12.

[0191] 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.

[0192] The hardware resource for executing a specific process can be any of the following types of processors: A processor, for example, is a CPU, which is a general-purpose processor that functions as a hardware resource for executing a specific process by executing software, i.e., a program. A processor also includes a dedicated electrical circuit, such as an FPGA (Field-Programmable Gate Array), a PLD (Programmable Logic Device), or an ASIC (Application Specific Integrated Circuit), which is a processor with a circuit configuration designed specifically for executing a specific process. Each processor has built-in or connected memory, and each processor uses the memory to execute the specific process.

[0193] The hardware resource that executes the specific process may be configured with one of these various processors, or may be configured with a combination of two or more processors of the same or different types (for example, a combination of multiple FPGAs, or a combination of a CPU and an FPGA). Also, the hardware resource that executes the specific process may be a single processor.

[0194] As an example of a system configured with a single processor, first, one processor is configured by combining one or more CPUs and software, and this processor functions as a hardware resource that executes a specific process. Second, there is a system that uses a processor that realizes the functions of an entire system including multiple hardware resources that execute a specific process on a single IC chip, as typified by SoC (System-on-a-chip). In this way, a specific process is realized using one or more of the above-mentioned various processors as hardware resources.

[0195] Furthermore, the hardware structure of these various processors can be, more specifically, an electric circuit that combines circuit elements such as semiconductor devices. The specific processing described above is merely an example. Therefore, it goes without saying that unnecessary steps may be deleted, new steps may be added, or the processing order may be rearranged, without departing from the spirit of the invention.

[0196] In the above example, the first to fourth embodiments have been described separately, but some or all of these embodiments may be combined. The smart device 14, smart glasses 214, headset terminal 314, and robot 414 are merely examples, and they may be combined, or other devices may be used. In the above example, the first and second embodiments have been described separately, but they may be combined.

[0197] The above-described description and illustrations are a detailed explanation of the parts related to the technology of the present disclosure and are merely an example of the technology of the present disclosure. For example, the above description of the configuration, functions, actions, and effects is an explanation of an example of the configuration, functions, actions, and effects of the parts related to the technology of the present disclosure. Therefore, it goes without saying that unnecessary parts may be deleted, new elements may be added, or replacements may be made to the above-described description and illustrations within the scope of the gist of the technology of the present disclosure. Furthermore, to avoid confusion and facilitate understanding of the parts related to the technology of the present disclosure, the above-described description and illustrations omit explanations of common technical knowledge that do not require particular explanation to enable the implementation of the technology of the present disclosure.

[0198] All publications, patent applications, and technical standards mentioned in this specification are herein incorporated by reference to the same extent as if each individual publication, patent application, or technical standard was specifically and individually indicated to be incorporated by reference.

[0199] [Explanation of symbols]

[0200] 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. an analysis unit that analyzes ambiguous instructions; a decision unit that decides an action based on the analysis result by the unit; a control unit that executes the operation determined by the determination unit A system characterized by:

2. Equipped with a health management section that monitors the user's health status and provides advice 2. The system of claim 1.

3. A schedule management section is provided to manage the user's schedule and provide necessary information.

2. The system of claim 1.

4. The analysis unit Estimate the user's emotions and adjust the analysis method for ambiguous instructions based on the estimated user emotions.

2. The system of claim 1.

5. The analysis unit Analyze the user's past instruction history to improve the accuracy of analyzing ambiguous instructions 2. The system of claim 1.

6. The analysis unit Relying on information about the user's current environment when parsing ambiguous instructions 2. The system of claim 1.

7. The analysis unit When parsing ambiguous instructions, the system analyzes the user's tone and speed of speech to more accurately understand the intent of the instruction.

2. The system of claim 1.

8. The analysis unit Estimate the user's emotions and prioritize the analysis results based on the estimated user emotions.

2. The system of claim 1.

9. The analysis unit Prioritize relevant results when parsing ambiguous instructions by taking into account the user's geographic location 2. The system of claim 1.

10. The analysis unit Analyze users' social media activities and provide relevant analysis results when parsing ambiguous instructions 2. The system of claim 1.

Images