System

Abstract

An object of the system according to the embodiment is to analyze a natural language instruction and execute an appropriate action.SOLUTION: A system includes a reception unit, an analysis unit, and an execution unit. The reception unit receives an instruction in a natural language. The analysis unit analyzes the instruction in the natural language received by the reception unit. The execution unit executes an appropriate action based on the instruction analyzed by the analysis unit.SELECTED DRAWING: Figure 1

Description

[Technical Field]

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

[0002] Patent document 1 discloses a persona chatbot control method performed by at least one processor, the method including the steps of receiving a user utterance, adding the user utterance to a prompt including 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 do not adequately flexibly analyze natural language instructions and execute appropriate actions, and there is room for improvement.

[0005] The system according to the embodiment aims to parse natural language instructions and perform appropriate actions. [Means for solving the problem]

[0006] A system according to an embodiment includes a reception unit, an analysis unit, and an execution unit. The reception unit receives instructions in natural language. The analysis unit analyzes the instructions in natural language received by the reception unit. The execution unit executes an appropriate action based on the instructions analyzed by the analysis unit. [Effects of the Invention]

[0007] An embodiment of the system can parse natural language instructions and take appropriate action. [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 next-generation mobile phone system according to an embodiment of the present invention accepts a user's natural language instructions, analyzes them using a large-scale language model (LLM), and executes the optimal action. In the next-generation mobile phone system, a user inputs instructions in natural language, and the LLM analyzes the instructions and executes the optimal action. For example, if a user says, "Tell me what the weather will be like tomorrow," the LLM automatically obtains weather information and provides it to the user. Similarly, if a user says, "Tell me what my next meeting is," the LLM checks the calendar and provides information about the next meeting. In this way, the next-generation mobile phone system understands the user's intentions and executes the optimal action, enabling more intuitive and efficient operation. Furthermore, the next-generation mobile phone system is equipped with security features to protect the user's privacy and can learn the user's behavioral history to make optimal suggestions. This allows the next-generation mobile phone system to analyze a user's natural language instructions and execute the optimal action, enabling intuitive and efficient operation. For example, if a user says, "Tell me what the weather will be like tomorrow," the LLM automatically obtains weather information and provides it to the user. Similarly, if a user says, "Tell me what my next meeting is," the LLM checks the calendar and provides information about the next meeting. This will enable next-generation mobile phone systems to understand the user's intentions and execute the optimal action, making operation more intuitive and efficient. Furthermore, next-generation mobile phone systems will be equipped with security features to protect the user's privacy, and will be able to learn the user's behavioral history and make optimal suggestions. This will make next-generation mobile phone systems revolutionary devices that set them apart from conventional smartphones.

[0029] A next-generation mobile phone system according to an embodiment includes a reception unit, an analysis unit, and an execution unit. The reception unit receives a user's natural language instruction. The user's natural language instruction includes, but is not limited to, a voice instruction, a text instruction, and the like. The reception unit converts the user's voice instruction into text data using, for example, voice recognition technology. The reception unit also provides a text input interface, allowing the user to directly input text instructions. The reception unit can also receive a user's gesture instruction using gesture recognition technology. For example, the reception unit converts the user's voice instruction into text data with high accuracy using voice recognition technology. The text input interface allows the user to input text instructions using a keyboard or touch screen. The gesture recognition technology recognizes the user's hand movements and facial expressions and accepts them as instructions. The analysis unit uses LLM to analyze the natural language instruction received by the reception unit. The analysis is performed using, for example, morphological analysis, grammatical analysis, semantic analysis, or the like, but is not limited to, these examples. For example, the analysis unit breaks down natural language instructions into words using morphological analysis and analyzes the structure of the sentence using grammatical analysis. The analysis unit can also use semantic analysis to understand the meaning of the instructions and determine the optimal action. The analysis unit can also use LLM to understand the context and accurately grasp the intent of the instructions. For example, morphological analysis breaks down natural language instructions into words and identifies the part of speech of each word. Grammatical analysis analyzes the structure of the sentence and clarifies relationships such as subject, predicate, and object. Semantic analysis understands the meaning of the instructions and determines the optimal action based on the context. The execution unit executes the optimal action based on the instructions analyzed by the analysis unit. Examples of actions include, but are not limited to, operating a device or providing information. For example, the execution unit operates a device based on the instructions analyzed by the analysis unit. The execution unit can also provide information to a user based on the instructions analyzed by the analysis unit. The execution unit can also execute an action in cooperation with an external service based on the instructions analyzed by the analysis unit.For example, the execution unit performs device operations such as adjusting the volume, launching an app, and changing settings. Information provision includes displaying weather information, checking a calendar, and sending messages. Linking with external services includes using cloud services, making purchases at online stores, and posting to social media. As a result, the next-generation mobile phone system according to the embodiment analyzes natural language instructions from the user and executes the most appropriate action, enabling intuitive and efficient operation.

[0030] The next-generation mobile phone system includes a security unit for protecting user privacy. The security unit provides functions for protecting user privacy. Specific privacy protection methods include, but are not limited to, data encryption and access control. For example, the security unit encrypts user data to protect it from unauthorized access. The security unit can also control access to user data to ensure that only authorized users have access. Furthermore, the security unit can anonymize user behavioral history to protect privacy. For example, the security unit uses encryption algorithms such as AES (Advanced Encryption Standard) and RSA (Rivest-Shamir-Adleman) to encrypt data. Access control includes user authentication, password protection, and two-factor authentication. The behavioral history is anonymized by storing and analyzing data in a format that does not identify individuals. This protects user privacy, allowing users to use the next-generation mobile phone system with peace of mind.

[0031] The next-generation mobile phone system includes a learning unit that learns a user's behavioral history and makes appropriate suggestions. The learning unit learns the user's behavioral history and makes appropriate suggestions. The behavioral history includes, but is not limited to, website browsing history and app usage history. For example, the learning unit analyzes the user's website browsing history and suggests related products and services. The learning unit can also analyze the user's app usage history and prioritize frequently used apps. Furthermore, the learning unit can learn the user's behavioral patterns and make suggestions at the optimal time. For example, the learning unit analyzes the user's frequently visited sites and search keywords as the website browsing history. The learning unit records the user's frequently used apps and usage time as the app usage history. The learning of the behavioral patterns involves understanding the user's activity time periods and locations and making suggestions at the appropriate time. This enables more appropriate suggestions to be made by learning the user's behavioral history.

[0032] The reception unit can analyze the user's past instruction history and select an appropriate reception method. For example, the reception unit automatically displays instructions that the user has frequently used in the past as candidates. The reception unit can also preferentially suggest input methods (voice, text, etc.) that the user has used in the past. Furthermore, the reception unit can predict and suggest instructions to be used in a specific time period based on the user's past instruction history. For example, the reception unit analyzes the user's past voice instructions and displays frequently used phrases as candidates. In the case of text instructions, predictive input is performed based on text entered in the past. In order to predict instructions to be used in a specific time period, the reception unit learns the user's behavioral patterns and makes suggestions at appropriate times. In this way, the optimal reception method can be selected by analyzing the past instruction history.

[0033] When receiving instructions, the reception unit can perform filtering based on the user's current situation and environment. For example, if the user is in a meeting, the reception unit can suggest an input method for a quiet environment. Furthermore, if the user is driving, the reception unit can prioritize voice input and minimize visual operations. Furthermore, if the user is in a public place, the reception unit can suggest an input method that takes privacy into consideration. For example, the reception unit can grasp the current situation based on the user's location information and suggest an appropriate input method. In the case of voice input, noise canceling technology can be used to remove ambient noise. To minimize visual operations, audio guidance can be provided, allowing the user to operate without using their hands. This makes it possible to receive appropriate instructions by filtering according to the user's situation and environment.

[0034] When receiving an instruction, the reception unit can select the optimal reception means depending on the user's input method. For example, when the user inputs an instruction by voice, the reception unit prioritizes reception of voice recognition. Furthermore, when the user inputs an instruction by text, the reception unit can also prioritize reception of text input. Furthermore, when the user inputs an instruction by gesture, the reception unit can also prioritize reception of gesture recognition. For example, the reception unit uses voice recognition technology to convert the user's voice instruction into text data with high accuracy. In the case of text input, the user can input text instructions using a keyboard or touch screen. Gesture recognition technology recognizes the user's hand movements and facial expressions and accepts them as instructions. This allows efficient reception of instructions by selecting the optimal reception means depending on the user's input method.

[0035] When receiving instructions, the reception unit can prioritize receiving highly relevant instructions by taking into account the user's geographical location information. For example, when the user is in a specific location, the reception unit prioritizes receiving instructions related to that location. Furthermore, when the user is traveling, the reception unit can also prioritize receiving instructions related to the trip. Furthermore, when the user is at home, the reception unit can also prioritize receiving instructions related to the home. For example, the reception unit prioritizes receiving instructions related to the user's current location based on the user's location information. When the user is traveling, the reception unit prioritizes receiving instructions related to travel destination information and transportation methods. When the user is at home, the reception unit prioritizes receiving instructions related to home facilities and family. In this way, highly relevant instructions can be prioritized by taking into account the user's geographical location information.

[0036] When receiving an instruction, the reception unit can analyze the user's social media activity and receive related instructions. The reception unit can, for example, receive related instructions based on information shared by the user on social media. The reception unit can also analyze the user's social media activity and preferentially receive related instructions. Furthermore, the reception unit can also receive related instructions by referring to the activity of the user's friends on social media. For example, the reception unit analyzes the content of the user's social media posts and receives related instructions. To analyze the social media activity, the reception unit refers to the user's like history and comments. To refer to the friend's activity, the reception unit analyzes the friend's posted content and activity. In this way, it is possible to receive related instructions by analyzing the social media activity.

[0037] When accepting an instruction, the acceptance unit can customize the acceptance method by reflecting the user's past feedback. The acceptance unit adjusts the acceptance method based on, for example, feedback provided by the user in the past. The acceptance unit can also suggest the optimal acceptance method based on the user's past feedback. Furthermore, the acceptance unit can customize the acceptance interface by reflecting the user's feedback. For example, the acceptance unit adjusts the acceptance method based on the user's ratings and comments. Based on the past feedback, the acceptance unit suggests an input method or interface preferred by the user. The feedback is reflected and customization is performed to suit the user's needs. In this way, the acceptance method can be customized by reflecting the past feedback.

[0038] During analysis, the analysis unit can adjust the level of detail of the analysis based on the importance of the instruction. For example, the analysis unit performs a detailed analysis for an important instruction. The analysis unit can also perform a standard analysis for an ordinary instruction. Furthermore, the analysis unit can perform a simplified analysis for an instruction with low priority. For example, the analysis unit evaluates the importance of the instruction and performs a detailed analysis for an important instruction. For an ordinary instruction, the analysis unit performs a standard analysis to provide necessary information. For an instruction with low priority, the analysis unit performs a simplified analysis to quickly provide results. In this way, by adjusting the level of detail of the analysis based on the importance of the instruction, efficient analysis is possible.

[0039] During analysis, the analysis unit can apply different analysis algorithms depending on the category of the instruction. For example, the analysis unit applies a weather data analysis algorithm to an instruction related to weather information. The analysis unit can also apply a schedule analysis algorithm to an instruction related to calendar information. The analysis unit can also apply a natural language analysis algorithm to an instruction related to a message. For example, the analysis unit performs analysis using a weather data analysis algorithm for an instruction related to weather information. The analysis unit performs analysis using a schedule analysis algorithm for an instruction related to calendar information. The analysis unit performs analysis using a natural language analysis algorithm for an instruction related to a message. This makes it possible to perform appropriate analysis by applying different analysis algorithms depending on the category of the instruction.

[0040] During analysis, the analysis unit can improve the accuracy of the analysis by referring to the user's past analysis results. The analysis unit, for example, adjusts the analysis algorithm based on the user's past analysis results. The analysis unit can also suggest an optimal analysis method based on the user's past analysis results. Furthermore, the analysis unit can improve the accuracy of the analysis by referring to the user's past analysis results. For example, the analysis unit adjusts the parameters of the analysis algorithm based on the past analysis results. The optimal analysis method is suggested based on the past analysis results and provided to the user. A feedback loop is constructed to improve the accuracy of the analysis by referring to the past analysis results. In this way, the accuracy of the analysis can be improved by referring to the past analysis results.

[0041] During analysis, the analysis unit can determine the priority of analysis based on the time when the instructions were submitted. For example, the analysis unit performs analysis with the highest priority for urgent instructions. The analysis unit can also perform analysis with standard priority for normal instructions. Furthermore, the analysis unit can postpone analysis for low priority instructions. For example, the analysis unit evaluates the time when the instructions were submitted, and performs analysis with the highest priority for urgent instructions. For normal instructions, the analysis is performed with standard priority and necessary information is provided. For low priority instructions, the analysis is postponed and results are provided quickly. In this way, efficient analysis is possible by determining the priority of analysis based on the time when the instructions were submitted.

[0042] During analysis, the analysis unit can adjust the order of analysis based on the relevance of instructions. For example, the analysis unit prioritizes analysis of highly relevant instructions. The analysis unit can also postpone analysis of less relevant instructions. Furthermore, the analysis unit can determine an optimal analysis order based on the relevance of instructions. For example, the analysis unit evaluates the relevance of instructions and prioritizes analysis of highly relevant instructions. For less relevant instructions, analysis is postponed to provide results quickly. The optimal analysis order is determined based on the relevance of instructions, and efficient analysis is performed. As a result, efficient analysis is possible by adjusting the analysis order based on the relevance of instructions.

[0043] During analysis, the analysis unit can adjust the use of technical terms in the analysis according to the user's level of expertise. For example, if the user has technical expertise, the analysis unit provides analysis results using technical terms. Also, if the user does not have technical expertise, the analysis unit can provide analysis results in easy-to-understand language. Furthermore, the analysis unit can provide optimal analysis results according to the user's level of expertise. For example, the analysis unit evaluates the user's level of expertise, and if the user has technical expertise, provides detailed analysis results using technical terms. If the user does not have technical expertise, provides concise analysis results in easy-to-understand language. The analysis unit provides optimal analysis results according to the user's level of expertise, helping the user understand. In this way, appropriate analysis results can be provided by adjusting the use of technical terms in the analysis according to the user's level of expertise.

[0044] At the time of execution, the execution unit can analyze the user's past behavioral history and select the optimal execution method. The execution unit, for example, suggests the optimal execution method based on the user's past behavioral history. The execution unit can also select an efficient execution method from the user's past behavioral history. Furthermore, the execution unit can customize the execution method by referring to the user's past behavioral history. For example, the execution unit analyzes the user's past behavioral history and suggests the optimal execution method. An efficient execution method is selected from the past behavioral history and provided to the user. Customization is performed to suit the user's needs by referring to the past behavioral history. In this way, the optimal execution method can be selected by analyzing the past behavioral history.

[0045] The execution unit can customize the means of execution based on the user's current situation at the time of execution. For example, if the user is in a meeting, the execution unit executes in a quiet environment. Also, if the user is driving, the execution unit can execute by voice. Furthermore, if the user is in a public place, the execution unit can execute with privacy in mind. For example, the execution unit grasps the current situation based on the user's location information and suggests an appropriate execution method. If the user is in a meeting, the execution is suppressed to execute in a quiet environment. If the user is driving, the execution is suppressed by voice and visual operations are minimized. If the user is in a public place, the execution is suppressed to consider privacy. In this way, appropriate execution is possible by customizing the means of execution based on the current situation.

[0046] The execution unit can improve the execution method by reflecting user feedback during execution. For example, the execution unit adjusts the execution method based on user feedback. The execution unit can also suggest the optimal execution method based on user feedback. Furthermore, the execution unit can customize the execution interface by reflecting user feedback. For example, the execution unit adjusts the execution method based on user ratings and comments. Based on past feedback, the execution unit suggests the execution method and interface that the user prefers. The feedback is reflected and customization is performed to meet the user's needs. In this way, the execution method can be improved by reflecting feedback.

[0047] At the time of execution, the execution unit can select the optimal execution method by taking into account the user's geographical location information. For example, when the user is in a specific location, the execution unit selects an execution method related to that location. Furthermore, when the user is traveling, the execution unit can also select an execution method related to the trip. Furthermore, when the user is at home, the execution unit can also select an execution method related to the home. For example, the execution unit selects an execution method related to the user's current location based on the user's location information. When the user is traveling, the execution unit selects an execution method related to information about the travel destination and transportation. When the user is at home, the execution unit selects an execution method related to the home's facilities and family. In this way, the optimal execution method can be selected by taking into account the geographical location information.

[0048] At the time of execution, the execution unit can analyze the user's social media activity and suggest a means of execution. For example, the execution unit can suggest a relevant method of execution based on information shared by the user on social media. The execution unit can also analyze the user's social media activity and suggest a relevant method of execution. Furthermore, the execution unit can also suggest a relevant method of execution by referring to the activities of the user's friends on social media. For example, the execution unit analyzes the content of the user's social media posts and suggests a relevant method of execution. To analyze the social media activity, the execution unit refers to the user's like history and comments. To refer to the activities of friends, the execution unit analyzes the content of friends' posts and activities. In this way, it is possible to suggest a relevant method of execution by analyzing social media activity.

[0049] The execution unit can customize the execution method at the time of execution by reflecting the user's past feedback. The execution unit adjusts the execution method, for example, based on feedback provided by the user in the past. The execution unit can also suggest the optimal execution method based on the user's past feedback. Furthermore, the execution unit can customize the execution interface by reflecting the user's feedback. For example, the execution unit adjusts the execution method based on the user's ratings and comments. Based on past feedback, the execution unit suggests the user's preferred execution method and interface. The feedback is reflected and customization is performed to meet the user's needs. In this way, the execution method can be customized by reflecting past feedback.

[0050] During security, the security unit can analyze the user's past behavioral history and select the optimal security measure. For example, the security unit proposes the optimal security measure based on the user's past behavioral history. The security unit can also select efficient security measures from the user's past behavioral history. Furthermore, the security unit can customize security measures by referring to the user's past behavioral history. For example, the security unit analyzes the user's past behavioral history and proposes the optimal security measure. It selects efficient security measures from the past behavioral history and provides them to the user. It customizes the measures to suit the user's needs by referring to the past behavioral history. In this way, the optimal security measure can be selected by analyzing the past behavioral history.

[0051] The security unit can customize security measures based on the user's current situation during security. For example, when the user is in a public place, the security unit provides security measures that take privacy into consideration. Furthermore, when the user is at home, the security unit can provide standard security measures. Furthermore, when the user is traveling, the security unit can provide security measures related to travel. For example, the security unit grasps the current situation based on the user's location information and suggests appropriate security measures. When the user is in a public place, data encryption and access control are strengthened to provide security measures that take privacy into consideration. When the user is at home, standard security measures are provided to maintain the user's sense of security. When the user is traveling, security measures related to travel destination information and transportation are provided. This allows appropriate security measures to be implemented by customizing security measures based on the current situation.

[0052] During security, the security unit can select optimal security measures by taking into account the user's geographical location information. For example, when the user is in a specific location, the security unit selects security measures related to that location. Furthermore, when the user is traveling, the security unit can also select security measures related to the trip. Furthermore, when the user is at home, the security unit can also select security measures related to the home. For example, the security unit selects security measures related to the user's current location based on the user's location information. When the user is traveling, the security unit selects security measures related to information about the travel destination and transportation. When the user is at home, the security unit selects security measures related to the home's facilities and family. In this way, optimal security measures can be selected by taking into account the geographical location information.

[0053] During security, the security unit can analyze the user's social media activities to suggest security measures. For example, the security unit can suggest relevant security measures based on information shared by the user on social media. The security unit can also analyze the user's social media activities to suggest relevant security measures. Furthermore, the security unit can also refer to the activities of the user's friends on social media to suggest relevant security measures. For example, the security unit analyzes the content of the user's social media posts to suggest relevant security measures. To analyze social media activities, the security unit refers to the user's like history and comments. To refer to the activities of friends, the security unit analyzes the content of friends' posts and activities. In this way, relevant security measures can be suggested by analyzing social media activities.

[0054] During learning, the learning unit can optimize the learning algorithm by referring to past learning data. The learning unit, for example, adjusts the learning algorithm based on past learning data. The learning unit can also propose an optimal learning method from past learning data. Furthermore, the learning unit can optimize the learning algorithm by referring to past learning data. For example, the learning unit adjusts the parameters of the learning algorithm based on past learning data. The optimal learning method is proposed from past learning data and provided to the user. A feedback loop is constructed to optimize the learning algorithm by referring to past learning data. In this way, the learning algorithm can be optimized by referring to past learning data.

[0055] During learning, the learning unit can analyze fluctuations in the user's behavioral history and adjust the update frequency of the learning data. The learning unit, for example, adjusts the update frequency of the learning data based on fluctuations in the user's behavioral history. The learning unit can also suggest an optimal update frequency from the user's behavioral history. Furthermore, the learning unit can adjust the update frequency of the learning data by referring to the user's behavioral history. For example, the learning unit analyzes fluctuations in the user's behavioral history and suggests an optimal update frequency. The update frequency of the learning data is adjusted based on fluctuations in the behavioral history and provided to the user. The behavioral history is used as a reference to customize the learning data to meet the user's needs. In this way, the update frequency of the learning data can be appropriately adjusted by analyzing fluctuations in the behavioral history.

[0056] During learning, the learning unit can weight the learning data based on the time when the behavioral history was submitted. The learning unit weights the learning data, for example, based on the most recent behavioral history. The learning unit can also weight the learning data based on past behavioral history. Furthermore, the learning unit can perform optimal weighting based on the time when the behavioral history was submitted. For example, the learning unit weights the learning data based on the most recent behavioral history. The learning data is weighted based on past behavioral history and provided to the user. Efficient learning is achieved by performing optimal weighting based on the time when the behavioral history was submitted. As a result, appropriate learning is possible by weighting the learning data based on the time when the behavioral history was submitted.

[0057] The learning unit can adjust the learning algorithm by reflecting user feedback during learning. The learning unit, for example, adjusts the learning algorithm based on user feedback. The learning unit can also suggest an optimal learning method based on user feedback. The learning unit can also adjust the learning algorithm by reflecting user feedback. For example, the learning unit adjusts the learning algorithm based on user ratings and comments. An optimal learning method is suggested based on past feedback and provided to the user. The learning algorithm is adjusted by reflecting feedback, thereby achieving efficient learning. In this way, the learning algorithm can be appropriately adjusted by reflecting feedback.

[0058] The system according to the embodiment is not limited to the above-described example, and various modifications are possible, for example, as follows.

[0059] When accepting a natural language instruction from a user, the acceptance unit can suggest the optimal acceptance method by referring to the user's past behavior history. For example, instructions that the user has frequently used in the past can be automatically displayed as candidates. The acceptance unit can also preferentially suggest input methods (voice, text, etc.) that the user has used in the past. Furthermore, the acceptance unit can predict and suggest instructions to be used in a specific time period based on the user's past behavior history. This makes it possible to select the optimal acceptance method by analyzing the user's past behavior history.

[0060] When receiving instructions, the reception unit can perform filtering based on the user's current situation and environment. For example, if the user is in a meeting, the reception unit can suggest an input method for a quiet environment. Also, if the user is driving, the reception unit can prioritize voice input and minimize visual operations. Furthermore, if the user is in a public place, the reception unit can suggest an input method that takes privacy into consideration. In this way, by performing filtering according to the user's situation and environment, it becomes possible to receive appropriate instructions.

[0061] During analysis, the analysis unit can adjust the level of detail of the analysis based on the importance of the instruction. For example, a detailed analysis can be performed for an important instruction. A standard analysis can also be performed for an ordinary instruction. Furthermore, a simplified analysis can be performed for an instruction with a low priority. In this way, adjusting the level of detail of the analysis based on the importance of the instruction enables efficient analysis.

[0062] At the time of execution, the execution unit can analyze the user's past behavior history and select the optimal execution method. For example, the execution unit can suggest the optimal execution method based on the user's past behavior history. It can also select an efficient execution method from the user's past behavior history. Furthermore, it can also customize the execution method by referring to the user's past behavior history. In this way, the optimal execution method can be selected by analyzing the user's past behavior history.

[0063] During security checks, the security department can analyze the user's past behavioral history and select the most appropriate security measures. For example, it can propose the most appropriate security measures based on the user's past behavioral history. It can also select efficient security measures from the user's past behavioral history. Furthermore, it can customize security measures by referring to the user's past behavioral history. This allows the most appropriate security measures to be selected by analyzing the user's past behavioral history.

[0064] During learning, the learning unit can analyze fluctuations in the user's behavioral history and adjust the update frequency of the learning data. For example, the update frequency of the learning data can be adjusted based on fluctuations in the user's behavioral history. The learning unit can also suggest an optimal update frequency based on the user's behavioral history. Furthermore, the update frequency of the learning data can be adjusted with reference to the user's behavioral history. In this way, the update frequency of the learning data can be appropriately adjusted by analyzing fluctuations in the behavioral history.

[0065] The processing flow of the first embodiment will be briefly explained below.

[0066] Step 1: The reception unit receives a user's natural language instruction. The user's natural language instruction may include a voice instruction, a text instruction, a gesture instruction, etc. The reception unit converts the voice instruction into text data using a voice recognition technology and provides a text input interface so that the user can directly input the text instruction. The reception unit may also receive a user's gesture instruction using a gesture recognition technology. Step 2: The analysis unit uses LLM to analyze the natural language instructions received by the reception unit. Analysis is performed using methods such as morphological analysis, grammatical analysis, and semantic analysis. Morphological analysis breaks down natural language instructions into words, grammatical analysis analyzes the structure of the sentence, and semantic analysis understands the meaning of the instructions and determines the optimal action. It can also understand the context and accurately grasp the intent of the instructions. Step 3: The execution unit executes the optimal action based on the instructions analyzed by the analysis unit. Actions include device operation, information provision, and linking with external services. For example, device operation includes adjusting the volume, launching an app, and changing settings, while information provision includes displaying weather information, checking the calendar, and sending messages. Linking with external services includes using cloud services, making purchases at online stores, and posting to social media.

[0067] (Example 2) A next-generation mobile phone system according to an embodiment of the present invention accepts a user's natural language instructions, analyzes them using a large-scale language model (LLM), and executes the optimal action. In the next-generation mobile phone system, a user inputs instructions in natural language, and the LLM analyzes the instructions and executes the optimal action. For example, if a user says, "Tell me what the weather will be like tomorrow," the LLM automatically obtains weather information and provides it to the user. Similarly, if a user says, "Tell me what my next meeting is," the LLM checks the calendar and provides information about the next meeting. In this way, the next-generation mobile phone system understands the user's intentions and executes the optimal action, enabling more intuitive and efficient operation. Furthermore, the next-generation mobile phone system is equipped with security features to protect the user's privacy and can learn the user's behavioral history to make optimal suggestions. This allows the next-generation mobile phone system to analyze a user's natural language instructions and execute the optimal action, enabling intuitive and efficient operation. For example, if a user says, "Tell me what the weather will be like tomorrow," the LLM automatically obtains weather information and provides it to the user. Similarly, if a user says, "Tell me what my next meeting is," the LLM checks the calendar and provides information about the next meeting. This will enable next-generation mobile phone systems to understand the user's intentions and execute the optimal action, making operation more intuitive and efficient. Furthermore, next-generation mobile phone systems will be equipped with security features to protect the user's privacy, and will be able to learn the user's behavioral history and make optimal suggestions. This will make next-generation mobile phone systems revolutionary devices that set them apart from conventional smartphones.

[0068] A next-generation mobile phone system according to an embodiment includes a reception unit, an analysis unit, and an execution unit. The reception unit receives a user's natural language instruction. The user's natural language instruction includes, but is not limited to, a voice instruction, a text instruction, and the like. The reception unit converts the user's voice instruction into text data using, for example, voice recognition technology. The reception unit also provides a text input interface, allowing the user to directly input text instructions. The reception unit can also receive a user's gesture instruction using gesture recognition technology. For example, the reception unit converts the user's voice instruction into text data with high accuracy using voice recognition technology. The text input interface allows the user to input text instructions using a keyboard or touch screen. The gesture recognition technology recognizes the user's hand movements and facial expressions and accepts them as instructions. The analysis unit uses LLM to analyze the natural language instruction received by the reception unit. The analysis is performed using, for example, morphological analysis, grammatical analysis, semantic analysis, or the like, but is not limited to, these examples. For example, the analysis unit breaks down natural language instructions into words using morphological analysis and analyzes the structure of the sentence using grammatical analysis. The analysis unit can also use semantic analysis to understand the meaning of the instructions and determine the optimal action. The analysis unit can also use LLM to understand the context and accurately grasp the intent of the instructions. For example, morphological analysis breaks down natural language instructions into words and identifies the part of speech of each word. Grammatical analysis analyzes the structure of the sentence and clarifies relationships such as subject, predicate, and object. Semantic analysis understands the meaning of the instructions and determines the optimal action based on the context. The execution unit executes the optimal action based on the instructions analyzed by the analysis unit. Examples of actions include, but are not limited to, operating a device or providing information. For example, the execution unit operates a device based on the instructions analyzed by the analysis unit. The execution unit can also provide information to a user based on the instructions analyzed by the analysis unit. The execution unit can also execute an action in cooperation with an external service based on the instructions analyzed by the analysis unit.For example, the execution unit performs device operations such as adjusting the volume, launching an app, and changing settings. Information provision includes displaying weather information, checking a calendar, and sending messages. Linking with external services includes using cloud services, making purchases at online stores, and posting to social media. As a result, the next-generation mobile phone system according to the embodiment analyzes natural language instructions from the user and executes the most appropriate action, enabling intuitive and efficient operation.

[0069] The next-generation mobile phone system includes a security unit for protecting user privacy. The security unit provides functions for protecting user privacy. Specific privacy protection methods include, but are not limited to, data encryption and access control. For example, the security unit encrypts user data to protect it from unauthorized access. The security unit can also control access to user data to ensure that only authorized users have access. Furthermore, the security unit can anonymize user behavioral history to protect privacy. For example, the security unit uses encryption algorithms such as AES (Advanced Encryption Standard) and RSA (Rivest-Shamir-Adleman) to encrypt data. Access control includes user authentication, password protection, and two-factor authentication. The behavioral history is anonymized by storing and analyzing data in a format that does not identify individuals. This protects user privacy, allowing users to use the next-generation mobile phone system with peace of mind.

[0070] The next-generation mobile phone system includes a learning unit that learns a user's behavioral history and makes appropriate suggestions. The learning unit learns the user's behavioral history and makes appropriate suggestions. The behavioral history includes, but is not limited to, website browsing history and app usage history. For example, the learning unit analyzes the user's website browsing history and suggests related products and services. The learning unit can also analyze the user's app usage history and prioritize frequently used apps. Furthermore, the learning unit can learn the user's behavioral patterns and make suggestions at the optimal time. For example, the learning unit analyzes the user's frequently visited sites and search keywords as the website browsing history. The learning unit records the user's frequently used apps and usage time as the app usage history. The learning of the behavioral patterns involves understanding the user's activity time periods and locations and making suggestions at the appropriate time. This enables more appropriate suggestions to be made by learning the user's behavioral history.

[0071] The reception unit can estimate the user's emotions and adjust the method for accepting natural language instructions based on the estimated user emotions. For example, if the user is feeling stressed, the reception unit can provide a simple interface and minimize input steps. Furthermore, if the user is relaxed, the reception unit can provide detailed input options and suggest customizable input methods. Furthermore, if the user is in a hurry, the reception unit can prioritize voice input and quickly accept natural language instructions. For example, the reception unit analyzes the user's voice and estimates the emotion using an emotion estimation algorithm. The emotion estimation algorithm estimates the emotion based on the tone and speed of the voice, changes in facial expressions, and the like. This allows the reception method to be adjusted according to the user's emotions, enabling more appropriate instruction acceptance. 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.

[0072] The reception unit can analyze the user's past instruction history and select an appropriate reception method. For example, the reception unit automatically displays instructions that the user has frequently used in the past as candidates. The reception unit can also preferentially suggest input methods (voice, text, etc.) that the user has used in the past. Furthermore, the reception unit can predict and suggest instructions to be used in a specific time period based on the user's past instruction history. For example, the reception unit analyzes the user's past voice instructions and displays frequently used phrases as candidates. In the case of text instructions, predictive input is performed based on text entered in the past. In order to predict instructions to be used in a specific time period, the reception unit learns the user's behavioral patterns and makes suggestions at appropriate times. In this way, the optimal reception method can be selected by analyzing the past instruction history.

[0073] When receiving instructions, the reception unit can perform filtering based on the user's current situation and environment. For example, if the user is in a meeting, the reception unit can suggest an input method for a quiet environment. Furthermore, if the user is driving, the reception unit can prioritize voice input and minimize visual operations. Furthermore, if the user is in a public place, the reception unit can suggest an input method that takes privacy into consideration. For example, the reception unit can grasp the current situation based on the user's location information and suggest an appropriate input method. In the case of voice input, noise canceling technology can be used to remove ambient noise. To minimize visual operations, audio guidance can be provided, allowing the user to operate without using their hands. This makes it possible to receive appropriate instructions by filtering according to the user's situation and environment.

[0074] When receiving an instruction, the reception unit can select the optimal reception means depending on the user's input method. For example, when the user inputs an instruction by voice, the reception unit prioritizes reception of voice recognition. Furthermore, when the user inputs an instruction by text, the reception unit can also prioritize reception of text input. Furthermore, when the user inputs an instruction by gesture, the reception unit can also prioritize reception of gesture recognition. For example, the reception unit uses voice recognition technology to convert the user's voice instruction into text data with high accuracy. In the case of text input, the user can input text instructions using a keyboard or touch screen. Gesture recognition technology recognizes the user's hand movements and facial expressions and accepts them as instructions. This allows efficient reception of instructions by selecting the optimal reception means depending on the user's input method.

[0075] The reception unit can estimate the user's emotions and determine the priority of instructions to be received based on the estimated user emotions. For example, if the user inputs an urgent instruction, the reception unit processes it with priority over other instructions. Furthermore, if the user is relaxed, the reception unit can process instructions with normal priority. Furthermore, if the user is stressed, the reception unit can prioritize important instructions. For example, the reception unit analyzes the user's voice and estimates the emotion using an emotion estimation algorithm. The emotion estimation algorithm estimates the emotion based on the tone and speed of the voice, changes in facial expressions, and the like. This allows the priority of instructions to be determined according to the user's emotions, thereby enabling important instructions to be processed preferentially. The emotion estimation is realized using an emotion estimation function, for example, using an emotion engine or a 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] When receiving instructions, the reception unit can prioritize receiving highly relevant instructions by taking into account the user's geographical location information. For example, when the user is in a specific location, the reception unit prioritizes receiving instructions related to that location. Furthermore, when the user is traveling, the reception unit can also prioritize receiving instructions related to the trip. Furthermore, when the user is at home, the reception unit can also prioritize receiving instructions related to the home. For example, the reception unit prioritizes receiving instructions related to the user's current location based on the user's location information. When the user is traveling, the reception unit prioritizes receiving instructions related to travel destination information and transportation methods. When the user is at home, the reception unit prioritizes receiving instructions related to home facilities and family. In this way, highly relevant instructions can be prioritized by taking into account the user's geographical location information.

[0077] When receiving an instruction, the reception unit can analyze the user's social media activity and receive related instructions. The reception unit can, for example, receive related instructions based on information shared by the user on social media. The reception unit can also analyze the user's social media activity and preferentially receive related instructions. Furthermore, the reception unit can also receive related instructions by referring to the activity of the user's friends on social media. For example, the reception unit analyzes the content of the user's social media posts and receives related instructions. To analyze the social media activity, the reception unit refers to the user's like history and comments. To refer to the friend's activity, the reception unit analyzes the friend's posted content and activity. In this way, it is possible to receive related instructions by analyzing the social media activity.

[0078] When accepting an instruction, the acceptance unit can customize the acceptance method by reflecting the user's past feedback. The acceptance unit adjusts the acceptance method based on, for example, feedback provided by the user in the past. The acceptance unit can also suggest the optimal acceptance method based on the user's past feedback. Furthermore, the acceptance unit can customize the acceptance interface by reflecting the user's feedback. For example, the acceptance unit adjusts the acceptance method based on the user's ratings and comments. Based on the past feedback, the acceptance unit suggests an input method or interface preferred by the user. The feedback is reflected and customization is performed to suit the user's needs. In this way, the acceptance method can be customized by reflecting the past feedback.

[0079] The analysis unit can estimate the user's emotions and adjust the way the analysis is presented based on the estimated user emotions. For example, the analysis unit can provide detailed analysis results when the user is relaxed. The analysis unit can also provide concise analysis results when the user is in a hurry. Furthermore, the analysis unit can provide visually easy-to-understand analysis results when the user is stressed. For example, the analysis unit analyzes the user's voice and estimates the emotion using an emotion estimation algorithm. The emotion estimation algorithm estimates the emotion based on the tone and speed of the voice, changes in facial expressions, etc. This allows the analysis to be adjusted according to the user's emotions, thereby providing more appropriate analysis 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] During analysis, the analysis unit can adjust the level of detail of the analysis based on the importance of the instruction. For example, the analysis unit performs a detailed analysis for an important instruction. The analysis unit can also perform a standard analysis for an ordinary instruction. Furthermore, the analysis unit can perform a simplified analysis for an instruction with low priority. For example, the analysis unit evaluates the importance of the instruction and performs a detailed analysis for an important instruction. For an ordinary instruction, the analysis unit performs a standard analysis to provide necessary information. For an instruction with low priority, the analysis unit performs a simplified analysis to quickly provide results. In this way, by adjusting the level of detail of the analysis based on the importance of the instruction, efficient analysis is possible.

[0081] During analysis, the analysis unit can apply different analysis algorithms depending on the category of the instruction. For example, the analysis unit applies a weather data analysis algorithm to an instruction related to weather information. The analysis unit can also apply a schedule analysis algorithm to an instruction related to calendar information. The analysis unit can also apply a natural language analysis algorithm to an instruction related to a message. For example, the analysis unit performs analysis using a weather data analysis algorithm for an instruction related to weather information. The analysis unit performs analysis using a schedule analysis algorithm for an instruction related to calendar information. The analysis unit performs analysis using a natural language analysis algorithm for an instruction related to a message. This makes it possible to perform appropriate analysis by applying different analysis algorithms depending on the category of the instruction.

[0082] During analysis, the analysis unit can improve the accuracy of the analysis by referring to the user's past analysis results. The analysis unit, for example, adjusts the analysis algorithm based on the user's past analysis results. The analysis unit can also suggest an optimal analysis method based on the user's past analysis results. Furthermore, the analysis unit can improve the accuracy of the analysis by referring to the user's past analysis results. For example, the analysis unit adjusts the parameters of the analysis algorithm based on the past analysis results. The optimal analysis method is suggested based on the past analysis results and provided to the user. A feedback loop is constructed to improve the accuracy of the analysis by referring to the past analysis results. In this way, the accuracy of the analysis can be improved by referring to the past analysis results.

[0083] The analysis unit can estimate the user's emotions and adjust the length of the analysis based on the estimated user emotions. For example, if the user is in a hurry, the analysis unit can provide a short and concise analysis result. Furthermore, if the user is relaxed, the analysis unit can provide a detailed analysis result. Furthermore, if the user is stressed, the analysis unit can provide a visually easy-to-understand analysis result. For example, the analysis unit analyzes the user's voice and estimates the emotion using an emotion estimation algorithm. The emotion estimation algorithm estimates the emotion based on the tone and speed of the voice, changes in facial expressions, and the like. This allows the length of the analysis to be adjusted according to the user's emotions, thereby providing appropriate analysis results. Emotion estimation is achieved using an emotion estimation function, for example, using an emotion engine or a generation AI. The generation AI can be, but is not limited to, a text generation AI (e.g., LLM) or a multimodal generation AI.

[0084] During analysis, the analysis unit can determine the priority of analysis based on the time when the instructions were submitted. For example, the analysis unit performs analysis with the highest priority for urgent instructions. The analysis unit can also perform analysis with standard priority for normal instructions. Furthermore, the analysis unit can postpone analysis for low priority instructions. For example, the analysis unit evaluates the time when the instructions were submitted, and performs analysis with the highest priority for urgent instructions. For normal instructions, the analysis is performed with standard priority and necessary information is provided. For low priority instructions, the analysis is postponed and results are provided quickly. In this way, efficient analysis is possible by determining the priority of analysis based on the time when the instructions were submitted.

[0085] During analysis, the analysis unit can adjust the order of analysis based on the relevance of instructions. For example, the analysis unit prioritizes analysis of highly relevant instructions. The analysis unit can also postpone analysis of less relevant instructions. Furthermore, the analysis unit can determine an optimal analysis order based on the relevance of instructions. For example, the analysis unit evaluates the relevance of instructions and prioritizes analysis of highly relevant instructions. For less relevant instructions, analysis is postponed to provide results quickly. The optimal analysis order is determined based on the relevance of instructions, and efficient analysis is performed. As a result, efficient analysis is possible by adjusting the analysis order based on the relevance of instructions.

[0086] During analysis, the analysis unit can adjust the use of technical terms in the analysis according to the user's level of expertise. For example, if the user has technical expertise, the analysis unit provides analysis results using technical terms. Also, if the user does not have technical expertise, the analysis unit can provide analysis results in easy-to-understand language. Furthermore, the analysis unit can provide optimal analysis results according to the user's level of expertise. For example, the analysis unit evaluates the user's level of expertise, and if the user has technical expertise, provides detailed analysis results using technical terms. If the user does not have technical expertise, provides concise analysis results in easy-to-understand language. The analysis unit provides optimal analysis results according to the user's level of expertise, helping the user understand. In this way, appropriate analysis results can be provided by adjusting the use of technical terms in the analysis according to the user's level of expertise.

[0087] The execution unit can estimate the user's emotions and adjust the execution method based on the estimated user emotions. For example, if the user is relaxed, the execution unit can execute at a leisurely pace. Furthermore, if the user is in a hurry, the execution unit can also execute quickly. Furthermore, if the user is stressed, the execution unit can execute in a visually easy-to-understand manner. For example, the execution unit analyzes the user's voice and estimates the emotion using an emotion estimation algorithm. The emotion estimation algorithm estimates the emotion based on the tone and speed of the voice, changes in facial expressions, etc. This enables appropriate execution by adjusting the execution method according to the user's emotions. The 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] At the time of execution, the execution unit can analyze the user's past behavioral history and select the optimal execution method. The execution unit, for example, suggests the optimal execution method based on the user's past behavioral history. The execution unit can also select an efficient execution method from the user's past behavioral history. Furthermore, the execution unit can customize the execution method by referring to the user's past behavioral history. For example, the execution unit analyzes the user's past behavioral history and suggests the optimal execution method. An efficient execution method is selected from the past behavioral history and provided to the user. Customization is performed to suit the user's needs by referring to the past behavioral history. In this way, the optimal execution method can be selected by analyzing the past behavioral history.

[0089] The execution unit can customize the means of execution based on the user's current situation at the time of execution. For example, if the user is in a meeting, the execution unit executes in a quiet environment. Also, if the user is driving, the execution unit can execute by voice. Furthermore, if the user is in a public place, the execution unit can execute with privacy in mind. For example, the execution unit grasps the current situation based on the user's location information and suggests an appropriate execution method. If the user is in a meeting, the execution is suppressed to execute in a quiet environment. If the user is driving, the execution is suppressed by voice and visual operations are minimized. If the user is in a public place, the execution is suppressed to consider privacy. In this way, appropriate execution is possible by customizing the means of execution based on the current situation.

[0090] The execution unit can improve the execution method by reflecting user feedback during execution. For example, the execution unit adjusts the execution method based on user feedback. The execution unit can also suggest the optimal execution method based on user feedback. Furthermore, the execution unit can customize the execution interface by reflecting user feedback. For example, the execution unit adjusts the execution method based on user ratings and comments. Based on past feedback, the execution unit suggests the execution method and interface that the user prefers. The feedback is reflected and customization is performed to meet the user's needs. In this way, the execution method can be improved by reflecting feedback.

[0091] The execution unit can estimate the user's emotions and determine execution priorities based on the estimated user emotions. For example, if the user inputs an urgent instruction, the execution unit executes it with priority over other instructions. Furthermore, if the user is relaxed, the execution unit can execute it with normal priority. Furthermore, if the user is feeling stressed, the execution unit can prioritize execution of important instructions. For example, the execution unit analyzes the user's voice and estimates the emotion using an emotion estimation algorithm. The emotion estimation algorithm estimates the emotion based on the tone and speed of the voice, changes in facial expressions, and the like. Thus, by determining execution priorities according to the user's emotions, important instructions can be executed with priority. The emotion estimation is realized using an emotion estimation function, for example, using an emotion engine or a generation AI. The generation AI can be, but is not limited to, a text generation AI (e.g., LLM) or a multimodal generation AI.

[0092] At the time of execution, the execution unit can select the optimal execution method by taking into account the user's geographical location information. For example, when the user is in a specific location, the execution unit selects an execution method related to that location. Furthermore, when the user is traveling, the execution unit can also select an execution method related to the trip. Furthermore, when the user is at home, the execution unit can also select an execution method related to the home. For example, the execution unit selects an execution method related to the user's current location based on the user's location information. When the user is traveling, the execution unit selects an execution method related to information about the travel destination and transportation. When the user is at home, the execution unit selects an execution method related to the home's facilities and family. In this way, the optimal execution method can be selected by taking into account the geographical location information.

[0093] At the time of execution, the execution unit can analyze the user's social media activity and suggest a means of execution. For example, the execution unit can suggest a relevant method of execution based on information shared by the user on social media. The execution unit can also analyze the user's social media activity and suggest a relevant method of execution. Furthermore, the execution unit can also suggest a relevant method of execution by referring to the activities of the user's friends on social media. For example, the execution unit analyzes the content of the user's social media posts and suggests a relevant method of execution. To analyze the social media activity, the execution unit refers to the user's like history and comments. To refer to the activities of friends, the execution unit analyzes the content of friends' posts and activities. In this way, it is possible to suggest a relevant method of execution by analyzing social media activity.

[0094] The execution unit can customize the execution method at the time of execution by reflecting the user's past feedback. The execution unit adjusts the execution method, for example, based on feedback provided by the user in the past. The execution unit can also suggest the optimal execution method based on the user's past feedback. Furthermore, the execution unit can customize the execution interface by reflecting the user's feedback. For example, the execution unit adjusts the execution method based on the user's ratings and comments. Based on past feedback, the execution unit suggests the user's preferred execution method and interface. The feedback is reflected and customization is performed to meet the user's needs. In this way, the execution method can be customized by reflecting past feedback.

[0095] The security unit can estimate the user's emotions and adjust the security level based on the estimated user emotions. For example, the security unit can increase the security level when the user is nervous. The security unit can also maintain a normal security level when the user is relaxed. Furthermore, the security unit can adjust the security level to provide a sense of security when the user is stressed. For example, the security unit analyzes the user's voice and estimates the user's emotions using an emotion estimation algorithm. The emotion estimation algorithm estimates emotions based on the tone and speed of the voice, changes in facial expressions, etc. This enables appropriate security measures by adjusting the security level 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 security, the security unit can analyze the user's past behavioral history and select the optimal security measure. For example, the security unit proposes the optimal security measure based on the user's past behavioral history. The security unit can also select efficient security measures from the user's past behavioral history. Furthermore, the security unit can customize security measures by referring to the user's past behavioral history. For example, the security unit analyzes the user's past behavioral history and proposes the optimal security measure. It selects efficient security measures from the past behavioral history and provides them to the user. It customizes the measures to suit the user's needs by referring to the past behavioral history. In this way, the optimal security measure can be selected by analyzing the past behavioral history.

[0097] The security unit can customize security measures based on the user's current situation during security. For example, when the user is in a public place, the security unit provides security measures that take privacy into consideration. Furthermore, when the user is at home, the security unit can provide standard security measures. Furthermore, when the user is traveling, the security unit can provide security measures related to travel. For example, the security unit grasps the current situation based on the user's location information and suggests appropriate security measures. When the user is in a public place, data encryption and access control are strengthened to provide security measures that take privacy into consideration. When the user is at home, standard security measures are provided to maintain the user's sense of security. When the user is traveling, security measures related to travel destination information and transportation are provided. This allows appropriate security measures to be implemented by customizing security measures based on the current situation.

[0098] The security unit can estimate the user's emotions and determine security priorities based on the estimated user emotions. For example, if the user requires urgent security measures, the security unit can prioritize those measures over other measures. Furthermore, if the user is relaxed, the security unit can also implement security measures with normal priority. Furthermore, if the user is feeling stressed, the security unit can prioritize important security measures. For example, the security unit analyzes the user's voice and estimates the user's emotions using an emotion estimation algorithm. The emotion estimation algorithm estimates emotions based on the tone and speed of the voice, changes in facial expressions, and the like. This allows security priorities to be determined according to the user's emotions, thereby prioritizing the implementation of important security measures. The emotion estimation is achieved using an emotion estimation function, such as an emotion engine or a generative AI. The generative AI can be, but is not limited to, a text generation AI (e.g., LLM) or a multimodal generation AI.

[0099] During security, the security unit can select optimal security measures by taking into account the user's geographical location information. For example, when the user is in a specific location, the security unit selects security measures related to that location. Furthermore, when the user is traveling, the security unit can also select security measures related to the trip. Furthermore, when the user is at home, the security unit can also select security measures related to the home. For example, the security unit selects security measures related to the user's current location based on the user's location information. When the user is traveling, the security unit selects security measures related to information about the travel destination and transportation. When the user is at home, the security unit selects security measures related to the home's facilities and family. In this way, optimal security measures can be selected by taking into account the geographical location information.

[0100] During security, the security unit can analyze the user's social media activities to suggest security measures. For example, the security unit can suggest relevant security measures based on information shared by the user on social media. The security unit can also analyze the user's social media activities to suggest relevant security measures. Furthermore, the security unit can also refer to the activities of the user's friends on social media to suggest relevant security measures. For example, the security unit analyzes the content of the user's social media posts to suggest relevant security measures. To analyze social media activities, the security unit refers to the user's like history and comments. To refer to the activities of friends, the security unit analyzes the content of friends' posts and activities. In this way, relevant security measures can be suggested by analyzing social media activities.

[0101] The learning unit can estimate the user's emotions and select training data based on the estimated user emotions. For example, if the user is relaxed, the learning unit selects detailed training data. Furthermore, if the user is in a hurry, the learning unit can select concise training data. Furthermore, if the user is stressed, the learning unit can select visually easy-to-understand training data. For example, the learning unit analyzes the user's voice and estimates the emotion using an emotion estimation algorithm. The emotion estimation algorithm estimates the emotion based on the tone and speed of the voice, changes in facial expressions, and the like. This enables appropriate learning by selecting training data according to the user's emotions. The emotion estimation is realized using an emotion estimation function, for example, using an emotion engine or generative AI. The generative AI can be, but is not limited to, a text generation AI (e.g., LLM) or a multimodal generation AI.

[0102] During learning, the learning unit can optimize the learning algorithm by referring to past learning data. The learning unit, for example, adjusts the learning algorithm based on past learning data. The learning unit can also propose an optimal learning method from past learning data. Furthermore, the learning unit can optimize the learning algorithm by referring to past learning data. For example, the learning unit adjusts the parameters of the learning algorithm based on past learning data. The optimal learning method is proposed from past learning data and provided to the user. A feedback loop is constructed to optimize the learning algorithm by referring to past learning data. In this way, the learning algorithm can be optimized by referring to past learning data.

[0103] During learning, the learning unit can analyze fluctuations in the user's behavioral history and adjust the update frequency of the learning data. The learning unit, for example, adjusts the update frequency of the learning data based on fluctuations in the user's behavioral history. The learning unit can also suggest an optimal update frequency from the user's behavioral history. Furthermore, the learning unit can adjust the update frequency of the learning data by referring to the user's behavioral history. For example, the learning unit analyzes fluctuations in the user's behavioral history and suggests an optimal update frequency. The update frequency of the learning data is adjusted based on fluctuations in the behavioral history and provided to the user. The behavioral history is used as a reference to customize the learning data to meet the user's needs. In this way, the update frequency of the learning data can be appropriately adjusted by analyzing fluctuations in the behavioral history.

[0104] The learning unit can estimate the user's emotions and adjust the frequency of learning based on the estimated user emotions. For example, the learning unit can increase the frequency of learning when the user is relaxed. The learning unit can also decrease the frequency of learning when the user is in a hurry. Furthermore, the learning unit can adjust the frequency of learning when the user is stressed. For example, the learning unit analyzes the user's voice and estimates the emotion using an emotion estimation algorithm. The emotion estimation algorithm estimates the emotion based on the tone and speed of the voice, changes in facial expressions, etc. This enables appropriate learning by adjusting the frequency of learning according to the user's emotions. Emotion estimation is realized using an emotion estimation function, for example, using an emotion engine or generative AI. The generative AI can be, but is not limited to, a text generation AI (e.g., LLM) or a multimodal generation AI.

[0105] During learning, the learning unit can weight the learning data based on the time when the behavioral history was submitted. The learning unit weights the learning data, for example, based on the most recent behavioral history. The learning unit can also weight the learning data based on past behavioral history. Furthermore, the learning unit can perform optimal weighting based on the time when the behavioral history was submitted. For example, the learning unit weights the learning data based on the most recent behavioral history. The learning data is weighted based on past behavioral history and provided to the user. Efficient learning is achieved by performing optimal weighting based on the time when the behavioral history was submitted. As a result, appropriate learning is possible by weighting the learning data based on the time when the behavioral history was submitted.

[0106] The learning unit can adjust the learning algorithm by reflecting user feedback during learning. The learning unit, for example, adjusts the learning algorithm based on user feedback. The learning unit can also suggest an optimal learning method based on user feedback. The learning unit can also adjust the learning algorithm by reflecting user feedback. For example, the learning unit adjusts the learning algorithm based on user ratings and comments. An optimal learning method is suggested based on past feedback and provided to the user. The learning algorithm is adjusted by reflecting feedback, thereby achieving efficient learning. In this way, the learning algorithm can be appropriately adjusted by reflecting feedback. === Hard Collateral 1-1 === Each of the multiple elements including the above-mentioned reception unit, analysis unit, execution unit, security unit, and learning unit is realized, for example, by at least one of the smart device 14 and the data processing device 12. For example, the reception unit receives a user's natural language instruction using the microphone 38B or touch panel 38A of the smart device 14. The analysis unit is realized by the specific processing unit 290 of the data processing device 12 and analyzes the instruction using LLM. The execution unit is realized by the control unit 46A of the smart device 14 and executes an optimal action based on the analyzed instruction. The security unit is realized by the specific processing unit 290 of the data processing device 12 and encrypts user data and performs access control. The learning unit is realized by the specific processing unit 290 of the data processing device 12 and learns the user's behavioral history and makes appropriate suggestions. === Hard Collateral 1-2 === Each of the multiple elements including the above-mentioned reception unit, analysis unit, execution unit, security unit, and learning unit is realized, for example, by at least one of the smart glasses 214 and the data processing device 12. For example, the reception unit receives a user's natural language instruction using the microphone 238 or camera 42 of the smart glasses 214. The analysis unit is realized by the specific processing unit 290 of the data processing device 12 and analyzes the instruction using LLM. The execution unit is realized by the control unit 46A of the smart glasses 214 and executes an optimal action based on the analyzed instruction. The security unit is realized by the specific processing unit 290 of the data processing device 12 and encrypts user data and performs access control. The learning unit is realized by the specific processing unit 290 of the data processing device 12 and learns the user's behavioral history and makes appropriate suggestions. === Hard Collateral 1-3 === Each of the multiple elements including the above-mentioned reception unit, analysis unit, execution unit, security unit, and learning unit is realized, for example, by at least one of the headset type terminal 314 and the data processing device 12. For example, the reception unit receives a user's natural language instruction using the microphone 238 or camera 42 of the headset type terminal 314. The analysis unit is realized by the specific processing unit 290 of the data processing device 12 and analyzes the instruction using LLM. The execution unit is realized by the control unit 46A of the headset type terminal 314 and executes an optimal action based on the analyzed instruction. The security unit is realized by the specific processing unit 290 of the data processing device 12 and encrypts user data and performs access control. The learning unit is realized by the specific processing unit 290 of the data processing device 12 and learns the user's behavioral history and makes appropriate suggestions. === Hard Collateral 1-4 === Each of the multiple elements including the above-mentioned reception unit, analysis unit, execution unit, security unit, and learning unit is realized, for example, by at least one of the robot 414 and the data processing device 12. For example, the reception unit receives a user's natural language instruction using the microphone 238 or camera 42 of the robot 414. The analysis unit is realized by the specific processing unit 290 of the data processing device 12 and analyzes the instruction using LLM. The execution unit is realized by the control unit 46A of the robot 414 and executes an optimal action based on the analyzed instruction. The security unit is realized by the specific processing unit 290 of the data processing device 12 and encrypts user data and performs access control. The learning unit is realized by the specific processing unit 290 of the data processing device 12 and learns the user's behavioral history and makes appropriate suggestions.

[0107] The system according to the embodiment is not limited to the above-described example, and various modifications are possible, for example, as follows.

[0108] When accepting a natural language instruction from a user, the acceptance unit can suggest the optimal acceptance method by referring to the user's past behavior history. For example, instructions that the user has frequently used in the past can be automatically displayed as candidates. The acceptance unit can also preferentially suggest input methods (voice, text, etc.) that the user has used in the past. Furthermore, the acceptance unit can predict and suggest instructions to be used in a specific time period based on the user's past behavior history. This makes it possible to select the optimal acceptance method by analyzing the user's past behavior history.

[0109] The security unit can estimate the user's emotions and adjust the security level based on the estimated user's emotions. For example, if the user is nervous, the security level can be increased. Alternatively, if the user is relaxed, the normal security level can be maintained. Furthermore, if the user is feeling stressed, the security level can be adjusted to provide a sense of security. In this way, appropriate security measures can be implemented by adjusting the security level according to the user's emotions.

[0110] When learning the user's behavioral history, the learning unit can estimate the user's emotions and select learning data based on the estimated emotions. For example, if the user is relaxed, detailed learning data can be selected. If the user is in a hurry, concise learning data can be selected. Furthermore, if the user is stressed, visually easy-to-understand learning data can be selected. This allows appropriate learning by selecting learning data according to the user's emotions.

[0111] The analysis unit can estimate the user's emotions and adjust the way the analysis is presented based on the estimated user emotions. For example, if the user is relaxed, detailed analysis results can be provided. If the user is in a hurry, concise analysis results can be provided. Furthermore, if the user is feeling stressed, analysis results that are visually easy to understand can be provided. In this way, by adjusting the way the analysis is presented according to the user's emotions, more appropriate analysis results can be provided.

[0112] The execution unit can estimate the user's emotions and adjust the execution method based on the estimated user's emotions. For example, if the user is relaxed, the execution can be performed at a leisurely pace. If the user is in a hurry, the execution can be performed quickly. Furthermore, if the user is feeling stressed, the execution can be performed in a visually easy-to-understand manner. In this way, appropriate execution can be achieved by adjusting the execution method according to the user's emotions.

[0113] When receiving instructions, the reception unit can perform filtering based on the user's current situation and environment. For example, if the user is in a meeting, the reception unit can suggest an input method for a quiet environment. Also, if the user is driving, the reception unit can prioritize voice input and minimize visual operations. Furthermore, if the user is in a public place, the reception unit can suggest an input method that takes privacy into consideration. In this way, by performing filtering according to the user's situation and environment, it becomes possible to receive appropriate instructions.

[0114] During analysis, the analysis unit can adjust the level of detail of the analysis based on the importance of the instruction. For example, a detailed analysis can be performed for an important instruction. A standard analysis can also be performed for an ordinary instruction. Furthermore, a simplified analysis can be performed for an instruction with a low priority. In this way, adjusting the level of detail of the analysis based on the importance of the instruction enables efficient analysis.

[0115] At the time of execution, the execution unit can analyze the user's past behavior history and select the optimal execution method. For example, the execution unit can suggest the optimal execution method based on the user's past behavior history. It can also select an efficient execution method from the user's past behavior history. Furthermore, it can also customize the execution method by referring to the user's past behavior history. In this way, the optimal execution method can be selected by analyzing the user's past behavior history.

[0116] During security checks, the security department can analyze the user's past behavioral history and select the most appropriate security measures. For example, it can propose the most appropriate security measures based on the user's past behavioral history. It can also select efficient security measures from the user's past behavioral history. Furthermore, it can customize security measures by referring to the user's past behavioral history. This allows the most appropriate security measures to be selected by analyzing the user's past behavioral history.

[0117] During learning, the learning unit can analyze fluctuations in the user's behavioral history and adjust the update frequency of the learning data. For example, the update frequency of the learning data can be adjusted based on fluctuations in the user's behavioral history. The learning unit can also suggest an optimal update frequency based on the user's behavioral history. Furthermore, the update frequency of the learning data can be adjusted with reference to the user's behavioral history. In this way, the update frequency of the learning data can be appropriately adjusted by analyzing fluctuations in the behavioral history.

[0118] The processing flow of the second embodiment will be briefly explained below.

[0119] Step 1: The reception unit receives a user's natural language instruction. The user's natural language instruction may include a voice instruction, a text instruction, a gesture instruction, etc. The reception unit converts the voice instruction into text data using a voice recognition technology and provides a text input interface so that the user can directly input the text instruction. The reception unit may also receive a user's gesture instruction using a gesture recognition technology. Step 2: The analysis unit uses LLM to analyze the natural language instructions received by the reception unit. Analysis is performed using methods such as morphological analysis, grammatical analysis, and semantic analysis. Morphological analysis breaks down natural language instructions into words, grammatical analysis analyzes the structure of the sentence, and semantic analysis understands the meaning of the instructions and determines the optimal action. It can also understand the context and accurately grasp the intent of the instructions. Step 3: The execution unit executes the optimal action based on the instructions analyzed by the analysis unit. Actions include device operation, information provision, and linking with external services. For example, device operation includes adjusting the volume, launching an app, and changing settings, while information provision includes displaying weather information, checking the calendar, and sending messages. Linking with external services includes using cloud services, making purchases at online stores, and posting to social media.

[0120] 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.

[0121] 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.

[0122] 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.

[0123] The correspondence between each part and the device or control part is not limited to the example described above, and various modifications are possible.

[0124] [Second embodiment] FIG. 3 shows an example of the configuration of a data processing system 210 according to the second embodiment.

[0125] 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.

[0126] 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.

[0127] 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.

[0128] 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.

[0129] 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).

[0130] 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.

[0131] 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.

[0132] 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.

[0133] 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.

[0134] 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.

[0135] 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.

[0136] 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.

[0137] 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 AI 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.

[0138] 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.

[0139] The correspondence between each part and the device or control part is not limited to the example described above, and various modifications are possible.

[0140] [Third embodiment] FIG. 5 shows an example of the configuration of a data processing system 310 according to the third embodiment.

[0141] 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.

[0142] 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.

[0143] 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.

[0144] 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.

[0145] 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).

[0146] 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.

[0147] 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.

[0148] 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.

[0149] 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.

[0150] 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.

[0151] 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.

[0152] 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.

[0153] 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 AI 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.

[0154] 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.

[0155] The correspondence between each part and the device or control part is not limited to the example described above, and various modifications are possible.

[0156] [Fourth embodiment] FIG. 7 shows an example of the configuration of a data processing system 410 according to the fourth embodiment.

[0157] 7, a data processing system 410 includes a data processing device 12 and a robot 414. An example of the data processing device 12 is a server.

[0158] 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.

[0159] 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.

[0160] 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.

[0161] 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).

[0162] 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.

[0163] 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.

[0164] 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.

[0165] 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.

[0166] 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.

[0167] 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.

[0168] 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.

[0169] 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.

[0170] 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 AI 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.

[0171] 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.

[0172] The correspondence between each part and the device or control part is not limited to the example described above, and various modifications are possible.

[0173] 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.

[0174] 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.

[0175] 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.

[0176] 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).

[0177] 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 "reaction" domain, where sensation is dominant. The right half of the emotion map lists emotions belonging to the "situation" domain, where situational awareness is dominant.

[0178] 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."

[0179] 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.

[0180] 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.

[0181] 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.

[0182] 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.

[0183] 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.

[0184] 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.

[0185] 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.

[0186] 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.

[0187] 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.

[0188] 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.

[0189] 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.

[0190] 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.

[0191] [Explanation of symbols]

[0192] 10, 210, 310, 410 Data Processing Systems 12 Data Processing Device 14 Smart Devices 214 Smart Glasses 314 Headset-type terminal 414 Robot

Claims

1. a reception unit that receives instructions in natural language; an analysis unit that analyzes the instruction in natural language received by the reception unit; an execution unit that executes an appropriate action based on the instruction analyzed by the analysis unit; Equipped with A system characterized by:

2. Equipped with a security section to protect user privacy 2. The system of claim 1.

3. Equipped with a learning unit that learns user behavior history and makes appropriate suggestions 2. The system of claim 1.

4. The reception unit Inferring a user's emotions and adjusting how natural language instructions are accepted based on the estimated user's emotions 2. The system of claim 1.

5. The reception unit Analyze the user's past instruction history and select the appropriate acceptance method 2. The system of claim 1.

6. The reception unit When receiving instructions, filtering is performed based on the user's current situation and environment.

2. The system of claim 1.

7. The reception unit When accepting instructions, select the most appropriate acceptance method depending on the user's input method.

2. The system of claim 1.

8. The reception unit Estimate the user's emotions and determine the priority of instructions to be accepted based on the estimated user emotions.

2. The system of claim 1.

9. The reception unit When accepting instructions, the system takes into account the user's geographical location information and prioritizes accepting highly relevant instructions.

2. The system of claim 1.

Images