system

Abstract

The system according to this embodiment aims to continuously learn through interaction with the user and provide more appropriate responses. [Solution] The system according to the embodiment comprises a reception unit, an analysis unit, a generation unit, a provision unit, and a learning unit. The reception unit receives questions and instructions from the user. The analysis unit analyzes the information received by the reception unit. The generation unit generates a response based on the information analyzed by the analysis unit. The provision unit provides the response generated by the generation unit to the user. The learning unit learns based on the response provided by the provision unit.

Description

Technical Field

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

Background Art

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

Prior Art Documents

Patent Documents

[0003]

Patent Document 1

Summary of the Invention

Problems to be Solved by the Invention

[0004] In the conventional technology, robots that provide information through interaction with users have not been sufficiently learning continuously to improve the accuracy of responses, and there is room for improvement.

[0005] The system according to the embodiment aims to continuously learn through interaction with users and provide more appropriate responses.

Means for Solving the Problems

[0006] The system according to this embodiment comprises a reception unit, an analysis unit, a generation unit, a provision unit, and a learning unit. The reception unit receives questions and instructions from the user. The analysis unit analyzes the information received by the reception unit. The generation unit generates a response based on the information analyzed by the analysis unit. The provision unit provides the response generated by the generation unit to the user. The learning unit learns based on the response provided by the provision unit. [Effects of the Invention]

[0007] The system according to this embodiment can continuously learn through interaction with the user and provide more appropriate responses. [Brief explanation of the drawing]

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

[0028] (Example of form 1) The robot system according to an embodiment of the present invention is a system that provides information through dialogue with a user and becomes capable of providing more appropriate responses through continuous learning. This robot system begins with the user inputting questions or instructions to the robot in natural language. For example, the user inputs questions such as "What's the weather like today?" or "What time is the next meeting?". This information is input to an AI agent installed in the robot system. Next, the AI ​​agent analyzes the input questions or instructions. The AI ​​agent uses natural language processing technology to understand the user's intent and generate an appropriate response. For example, in response to the question "What's the weather like today?", the AI ​​agent refers to weather forecast data and generates a response such as "It's sunny today." Furthermore, the AI ​​agent learns from the data obtained through the dialogue. Using machine learning technology, it analyzes the user's profile and past dialogue history to improve the accuracy of future responses. For example, by learning the response when the user previously asked "What time is the next meeting?", it can respond more quickly and accurately to similar questions in the future. This mechanism improves user satisfaction. Users can receive immediate information and emotional support through dialogue with the robot. Furthermore, the AI ​​agent's learning function improves the accuracy of its responses, allowing it to respond more appropriately to user needs. For example, in the retail industry, AI agents can improve customer engagement by responding quickly and accurately to customer questions. In the education sector, AI agents can improve learning effectiveness by providing appropriate learning support to students' questions. In the healthcare sector, AI agents can improve patient satisfaction by providing appropriate medical information to patients' questions. In this way, robot systems equipped with AI agents can provide information through dialogue with users and, through continuous learning, become capable of more appropriate responses. This improves user satisfaction and the accuracy of information provided through dialogue. As a result, robot systems can respond quickly and accurately to user questions and instructions.

[0029] The robot system according to this embodiment comprises a reception unit, an analysis unit, a generation unit, a provision unit, and a learning unit. The reception unit receives questions and instructions from the user. Questions and instructions from the user include, but are not limited to, text-based questions and voice instructions. The reception unit can, for example, receive questions and instructions entered by the user in natural language. The analysis unit analyzes the information received by the reception unit. The analysis unit analyzes the user's intent using natural language processing techniques. For example, the analysis unit applies a natural language processing algorithm to analyze the user's input and understand its intent. The generation unit generates a response based on the information analyzed by the analysis unit. For example, the generation unit applies a natural language generation algorithm to generate an appropriate response based on the analyzed information. The provision unit provides the response generated by the generation unit to the user. The provision unit can, for example, provide the generated response to the user in text or voice. The learning unit learns based on the response provided by the provision unit. The learning unit, for example, learns from data obtained through dialogue and applies machine learning algorithms to improve the accuracy of subsequent responses. As a result, the robot system according to this embodiment can efficiently receive, analyze, generate, provide, and learn from user questions and instructions, enabling it to provide more appropriate responses.

[0030] The reception unit receives questions and instructions from the user. These include, but are not limited to, text-based questions and voice instructions. The reception unit can, for example, receive questions and instructions entered by the user in natural language. Specifically, the reception unit has an interface that accepts text input via keyboard or touchscreen. It also includes a microphone and voice recognition software for voice input, allowing users to input instructions by speaking. Furthermore, the reception unit has the capability to process user input in real time and quickly transmit it to the analysis unit. This allows users to interact with the robot system in an intuitive and natural way, and the system can quickly grasp the user's intent. The reception unit can also use noise cancellation technology and input error correction algorithms to accurately receive user input. This ensures that the system accurately understands the user's intent even in noisy environments or with inaccurate input.

[0031] The analysis unit analyzes the information received by the reception unit. The analysis unit analyzes the user's intent using natural language processing technology. For example, the analysis unit applies natural language processing algorithms to analyze the user's input and understand its intent. Specifically, the analysis unit performs morphological and syntactic analysis to grammatically analyze the user's input. Furthermore, it performs semantic analysis, considering the context and related information to accurately grasp the user's intent. For example, if the user inputs "What's the weather like tomorrow?", the analysis unit performs morphological analysis to extract the keywords "tomorrow" and "weather," and then performs syntactic analysis to understand the sentence structure. After that, it performs semantic analysis to understand the user's intent to know tomorrow's weather forecast. Based on these analysis results, the analysis unit accurately understands the user's intent and provides information to the generation unit to generate an appropriate response. The analysis unit can also refer to the user's past input history and dialogue history to perform more accurate analysis. This allows the analysis unit to accurately understand the user's intent and improve the overall response accuracy of the system.

[0032] The generation unit generates responses based on the information analyzed by the analysis unit. For example, the generation unit applies a natural language generation algorithm to generate an appropriate response based on the analyzed information. Specifically, the generation unit can use template-based generation methods or generation methods using generative AI to generate responses that match the user's intent. In template-based generation methods, a pre-prepared response template is used to generate a response corresponding to the user's input. For example, if the user asks, "What's the weather like tomorrow?", the generation unit will generate a response using a template such as "It will be sunny tomorrow." On the other hand, generation methods using generative AI generate more flexible and natural responses based on the user's input. Generative AI has the ability to learn from a large amount of dialogue data and generate appropriate responses to user input. For example, if the user asks, "What's the weather like tomorrow?", the generative AI can generate a detailed response such as, "It's forecast to be sunny tomorrow. The temperature will be around 25 degrees Celsius." By using a combination of these generation methods, the generation unit can generate appropriate responses that match the user's intent.

[0033] The provider unit provides the user with the response generated by the generator unit. The provider unit can provide the generated response to the user in text or voice, for example. Specifically, the provider unit has the function of displaying text-based responses on a screen and the function of playing voice-based responses through a speaker. In text-based responses, the response to the question or instruction entered by the user is displayed on the screen. In voice-based responses, the generated response is converted into voice using speech synthesis technology and provided to the user through a speaker. This allows the user to receive the response both visually and aurally. The provider unit can also customize the method of providing responses according to the user's preference. For example, if the user prefers voice responses, the provider unit can be set to prioritize providing voice-based responses. This allows the provider unit to provide responses to the user in the most optimal way and improve user convenience.

[0034] The learning unit learns based on the responses provided by the providing unit. For example, the learning unit learns from data obtained through dialogue and applies machine learning algorithms to improve the accuracy of subsequent responses. Specifically, the learning unit collects user dialogue history and response evaluation data, and updates the machine learning model based on this data. For example, if a user provides feedback on a provided response, the learning unit collects that feedback and evaluates the appropriateness of the response. The learning unit uses this evaluation data to adjust the parameters of the response generation algorithm and improve the accuracy of subsequent responses. The learning unit can also update the content and style of responses based on new data and trends. This allows the learning unit to always provide highly accurate responses based on the latest information, improving user satisfaction. Furthermore, the learning unit can use anomaly detection algorithms to detect abnormal patterns and inappropriate responses during dialogue and use this information to improve the system. This allows the learning unit to improve the overall reliability and security of the system.

[0035] The reception desk can analyze the user's past question history and select the optimal reception method. For example, the reception desk may prioritize receiving questions in formats that the user has frequently used in the past. The reception desk may also suggest the optimal reception timing based on the time of day the user has used in the past. The reception desk may also prioritize receiving questions on specific topics based on the user's past question history. This allows the reception desk to select the optimal reception method by analyzing the user's past question history. Some or all of the above processing in the reception desk may be performed using AI, for example, or without AI.

[0036] The reception desk can filter questions and instructions based on the user's current situation and areas of interest. For example, the reception desk can prioritize questions related to the user's current situation. The reception desk can also filter relevant questions and instructions based on the user's areas of interest. The reception desk can also suggest appropriate questions and instructions based on the user's current activities. This allows the reception desk to prioritize receiving highly relevant questions and instructions by filtering based on the user's current situation and areas of interest. Some or all of the above processing in the reception desk may be performed using AI, for example, or without AI.

[0037] The reception desk can prioritize receiving questions and instructions that are highly relevant, taking into account the user's geographical location. For example, if the user is in a specific location, the reception desk will prioritize receiving questions and instructions related to that location. For example, if the user is traveling, the reception desk can also prioritize receiving questions and instructions related to the travel destination. For example, if the user is at home, the reception desk can also prioritize receiving questions and instructions related to home. In this way, by taking into account the user's geographical location, it is possible to prioritize receiving questions and instructions that are highly relevant. Some or all of the above processing in the reception desk may be performed using AI, for example, or without using AI.

[0038] The reception desk can analyze the user's social media activity when receiving questions or instructions and receive relevant questions or instructions. For example, the reception desk can receive relevant questions or instructions based on information the user has shared on social media. For example, the reception desk can analyze the content of the user's social media posts and suggest relevant questions or instructions. For example, the reception desk can receive relevant questions or instructions based on the activity of the user's social media followers and friends. This allows the reception desk to prioritize receiving relevant questions and instructions by analyzing the user's social media activity. Some or all of the above processing in the reception desk may be performed using AI, for example, or not using AI.

[0039] The analysis unit can adjust the level of detail of the analysis based on the importance of the questions and instructions during the analysis. For example, the analysis unit can perform a detailed analysis for questions and instructions of high importance. For example, the analysis unit can also perform a simplified analysis for questions and instructions of low importance. The analysis unit can also determine the priority of the analysis according to the importance of the questions and instructions. This allows for more appropriate analysis by adjusting the level of detail of the analysis based on the importance of the questions and instructions. Some or all of the above processing in the analysis unit may be performed using AI, for example, or without using AI.

[0040] The analysis unit can apply different analysis algorithms depending on the category of the question or instruction during analysis. For example, the analysis unit can apply a specialized analysis algorithm to a technical question. For example, the analysis unit can also apply a general-purpose analysis algorithm to a general question. For example, the analysis unit can select and apply the most suitable analysis algorithm for each category. This allows for more appropriate analysis by applying different analysis algorithms depending on the category of the question or instruction. Some or all of the above-described processes in the analysis unit may be performed using AI, for example, or without using AI.

[0041] The analysis unit can determine the priority of analysis based on when questions and instructions were submitted. For example, the analysis unit may prioritize the analysis of recently submitted questions and instructions. The analysis unit may also postpone the analysis of older questions and instructions. The analysis unit may also dynamically adjust the priority of analysis based on the submission date. This allows for analysis in a more appropriate order by determining the priority of analysis based on when questions and instructions were submitted. Some or all of the above processing in the analysis unit may be performed using AI, for example, or without using AI.

[0042] The analysis unit can adjust the order of analysis based on the relevance of questions and instructions during the analysis. For example, the analysis unit may prioritize the analysis of highly relevant questions and instructions. For example, the analysis unit may postpone the analysis of less relevant questions and instructions. The analysis unit can also dynamically adjust the order of analysis according to the relevance of questions and instructions. This allows for analysis in a more appropriate order by adjusting the order of analysis based on the relevance of questions and instructions. Some or all of the above processing in the analysis unit may be performed using AI, for example, or without using AI.

[0043] The generation unit can adjust the level of detail in responses based on the importance of the questions and instructions when generating responses. For example, the generation unit generates detailed responses to high-importance questions and instructions. The generation unit can also generate simplified responses to low-importance questions and instructions. The generation unit can also determine the priority of responses based on the importance of the questions and instructions. This allows for more appropriate responses by adjusting the level of detail in responses based on the importance of the questions and instructions. Some or all of the above processing in the generation unit may be performed using AI, for example, or without using AI.

[0044] The generation unit can apply different response algorithms depending on the category of the question or instruction when generating a response. For example, the generation unit can apply a specialized response algorithm to a technical question. For example, the generation unit can also apply a general-purpose response algorithm to a general question. For example, the generation unit can select and apply the most appropriate response algorithm for each category. This makes it possible to provide a more appropriate response by applying different response algorithms depending on the category of the question or instruction. Some or all of the above processing in the generation unit may be performed using AI, for example, or without using AI.

[0045] The generation unit can determine the priority of responses based on when the questions and instructions were submitted. For example, the generation unit can prioritize generating responses to recently submitted questions and instructions. The generation unit can also postpone generating responses to older questions and instructions. The generation unit can also dynamically adjust the priority of responses according to the submission date. This allows for responses to be sent in a more appropriate order by determining the priority of responses based on when the questions and instructions were submitted. Some or all of the above processing in the generation unit may be performed using AI, for example, or without AI.

[0046] The generation unit can adjust the order of responses based on the relevance of the questions and instructions when generating responses. For example, the generation unit can prioritize generating responses for highly relevant questions and instructions. The generation unit can also postpone generating responses for less relevant questions and instructions. The generation unit can also dynamically adjust the order of responses according to the relevance of the questions and instructions. This allows for responses in a more appropriate order by adjusting the order of responses based on the relevance of the questions and instructions. Some or all of the above processing in the generation unit may be performed using AI, for example, or without using AI.

[0047] The service provider can select the optimal service provider method by referring to the user's past dialogue history when providing a response. For example, the service provider may prioritize providing a response method that the user has previously preferred. The service provider may also select the optimal response method from the user's past dialogue history. For example, the service provider may analyze the user's past dialogue history and propose the optimal response method. This allows the service provider to select the optimal service provider method by referring to the user's past dialogue history. Some or all of the above processing in the service provider may be performed using AI, for example, or without using AI.

[0048] The service provider can customize the means of providing a response based on the user's current situation when providing a response. For example, if the user is on the move, the service provider may provide a voice response. For example, if the user is in a quiet place, the service provider may provide a text response. For example, if the user is in a meeting, the service provider may provide a notification response. By customizing the means of providing a response based on the user's current situation, a more appropriate response becomes possible. Some or all of the processing described above in the service provider may be performed using AI, for example, or not using AI.

[0049] The service provider can select the optimal service delivery method when providing a response, taking into account the user's geographical location. For example, if the user is in a specific location, the service provider can prioritize providing information related to that location. For example, if the user is traveling, the service provider can prioritize providing information related to the travel destination. For example, if the user is at home, the service provider can prioritize providing information related to home. This allows the service provider to select the optimal service delivery method by taking into account the user's geographical location. Some or all of the processing described above in the service provider may be performed using AI, for example, or without using AI.

[0050] The service provider can analyze the user's social media activity and propose a means of providing a response when providing a response. For example, the service provider can provide a relevant response based on information shared by the user on social media. The service provider can also analyze the content of the user's social media posts and propose a relevant response. The service provider can also provide a relevant response based on the activity of the user's social media followers and friends. In this way, a relevant response can be provided by analyzing the user's social media activity. Some or all of the above processing in the service provider may be performed using AI, for example, or without using AI.

[0051] The learning unit can optimize the learning algorithm by referring to past learning data during the learning process. For example, the learning unit can analyze past learning data and select the optimal learning algorithm. The learning unit can also adjust parameters to improve learning accuracy based on past learning data. For example, the learning unit can identify areas for improvement in the learning algorithm based on past learning data and optimize it. In this way, the learning algorithm can be optimized by referring to past learning data. Some or all of the above processes in the learning unit may be performed using AI, for example, or without using AI.

[0052] The learning unit can improve the accuracy of learning by considering the user's profile information during the learning process. For example, the learning unit can select personalized learning data based on the user's profile information. The learning unit can also adjust the learning algorithm by considering the user's profile information. For example, the learning unit can select data to improve the accuracy of learning based on the user's profile information. In this way, the accuracy of learning can be improved by considering the user's profile information. Some or all of the above processes in the learning unit may be performed using AI, for example, or without using AI.

[0053] The learning unit can weight the training data based on the submission date of the dialogue history during training. For example, the learning unit prioritizes learning recent dialogue histories. The learning unit can also reduce the weight of older dialogue histories, for example. The learning unit can also dynamically adjust the weighting of the training data according to the submission date. This allows for more appropriate training by weighting the training data based on the submission date of the dialogue history. Some or all of the above processing in the learning unit may be performed using AI, for example, or without using AI.

[0054] The learning unit can improve the accuracy of learning by referring to the user's relevant literature during the learning process. For example, the learning unit selects learning data based on the relevant literature provided by the user. The learning unit can also adjust the learning algorithm by referring to the user's relevant literature. For example, the learning unit can select data to improve the accuracy of learning based on the user's relevant literature. In this way, the accuracy of learning can be improved by referring to the user's relevant literature. Some or all of the above processes in the learning unit may be performed using AI, for example, or without using AI.

[0055] The system according to the embodiment is not limited to the example described above, and various modifications are possible, for example, as follows.

[0056] The reception desk can analyze a user's past question history and select the optimal reception method. For example, it can prioritize receiving questions in formats frequently used by the user in the past. It can also suggest the optimal reception timing based on the time of day the user has used it in the past. Furthermore, it can prioritize receiving questions on specific topics based on the user's past question history. In this way, the optimal reception method can be selected by analyzing the user's past question history.

[0057] The reception desk can filter questions and instructions based on the user's current situation and areas of interest. For example, it can prioritize questions related to the user's current situation. It can also filter relevant questions and instructions based on the user's areas of interest. Furthermore, it can suggest appropriate questions and instructions based on the user's current activities. In this way, by filtering based on the user's current situation and areas of interest, it can prioritize receiving highly relevant questions and instructions.

[0058] The analysis unit can adjust the level of detail in the analysis based on the importance of the questions and instructions. For example, it can perform a detailed analysis on high-importance questions and instructions, and a simplified analysis on low-importance questions and instructions. Furthermore, it can determine the priority of the analysis based on the importance of the questions and instructions. By adjusting the level of detail in the analysis based on the importance of the questions and instructions, more appropriate analysis becomes possible.

[0059] The generation unit can adjust the level of detail in responses based on the importance of the questions and instructions during response generation. For example, it can generate detailed responses to high-importance questions and instructions, and simplified responses to low-importance questions and instructions. Furthermore, it can determine the priority of responses based on the importance of the questions and instructions. This allows for more appropriate responses by adjusting the level of detail based on the importance of the questions and instructions.

[0060] The response system can select the optimal response method by referring to the user's past dialogue history when providing a response. For example, it can prioritize providing a response method that the user has preferred in the past. It can also select the optimal response method from the user's past dialogue history. Furthermore, it can analyze the user's past dialogue history and suggest the optimal response method. In this way, the optimal response method can be selected by referring to the user's past dialogue history.

[0061] The following briefly describes the processing flow for example form 1.

[0062] Step 1: The reception desk receives questions and instructions from users. These include text-based questions and voice instructions. For example, it can accept questions and instructions entered by users in natural language. Step 2: The analysis unit analyzes the information received by the reception unit. The analysis unit uses natural language processing technology to analyze the user's intent. For example, it analyzes the user's input and applies a natural language processing algorithm to understand their intent. Step 3: The generation unit generates a response based on the information analyzed by the analysis unit. The generation unit applies a natural language generation algorithm to generate an appropriate response based on the analyzed information. Step 4: The providing unit provides the user with the response generated by the generating unit. The providing unit can provide the generated response to the user in text or voice. Step 5: The learning unit learns based on the responses provided by the providing unit. The learning unit learns from the data obtained through the interaction and applies machine learning algorithms to improve the accuracy of subsequent responses.

[0063] (Example of form 2) The robot system according to an embodiment of the present invention is a system that provides information through dialogue with a user and becomes capable of providing more appropriate responses through continuous learning. This robot system begins with the user inputting questions or instructions to the robot in natural language. For example, the user inputs questions such as "What's the weather like today?" or "What time is the next meeting?". This information is input to an AI agent installed in the robot system. Next, the AI ​​agent analyzes the input questions or instructions. The AI ​​agent uses natural language processing technology to understand the user's intent and generate an appropriate response. For example, in response to the question "What's the weather like today?", the AI ​​agent refers to weather forecast data and generates a response such as "It's sunny today." Furthermore, the AI ​​agent learns from the data obtained through the dialogue. Using machine learning technology, it analyzes the user's profile and past dialogue history to improve the accuracy of future responses. For example, by learning the response when the user previously asked "What time is the next meeting?", it can respond more quickly and accurately to similar questions in the future. This mechanism improves user satisfaction. Users can receive immediate information and emotional support through dialogue with the robot. Furthermore, the AI ​​agent's learning function improves the accuracy of its responses, allowing it to respond more appropriately to user needs. For example, in the retail industry, AI agents can improve customer engagement by responding quickly and accurately to customer questions. In the education sector, AI agents can improve learning effectiveness by providing appropriate learning support to students' questions. In the healthcare sector, AI agents can improve patient satisfaction by providing appropriate medical information to patients' questions. In this way, robot systems equipped with AI agents can provide information through dialogue with users and, through continuous learning, become capable of more appropriate responses. This improves user satisfaction and the accuracy of information provided through dialogue. As a result, robot systems can respond quickly and accurately to user questions and instructions.

[0064] The robot system according to this embodiment comprises a reception unit, an analysis unit, a generation unit, a provision unit, and a learning unit. The reception unit receives questions and instructions from the user. Questions and instructions from the user include, but are not limited to, text-based questions and voice instructions. The reception unit can, for example, receive questions and instructions entered by the user in natural language. The analysis unit analyzes the information received by the reception unit. The analysis unit analyzes the user's intent using natural language processing techniques. For example, the analysis unit applies a natural language processing algorithm to analyze the user's input and understand its intent. The generation unit generates a response based on the information analyzed by the analysis unit. For example, the generation unit applies a natural language generation algorithm to generate an appropriate response based on the analyzed information. The provision unit provides the response generated by the generation unit to the user. The provision unit can, for example, provide the generated response to the user in text or voice. The learning unit learns based on the response provided by the provision unit. The learning unit, for example, learns from data obtained through dialogue and applies machine learning algorithms to improve the accuracy of subsequent responses. As a result, the robot system according to this embodiment can efficiently receive, analyze, generate, provide, and learn from user questions and instructions, enabling it to provide more appropriate responses.

[0065] The reception unit receives questions and instructions from the user. These include, but are not limited to, text-based questions and voice instructions. The reception unit can, for example, receive questions and instructions entered by the user in natural language. Specifically, the reception unit has an interface that accepts text input via keyboard or touchscreen. It also includes a microphone and voice recognition software for voice input, allowing users to input instructions by speaking. Furthermore, the reception unit has the capability to process user input in real time and quickly transmit it to the analysis unit. This allows users to interact with the robot system in an intuitive and natural way, and the system can quickly grasp the user's intent. The reception unit can also use noise cancellation technology and input error correction algorithms to accurately receive user input. This ensures that the system accurately understands the user's intent even in noisy environments or with inaccurate input.

[0066] The analysis unit analyzes the information received by the reception unit. The analysis unit analyzes the user's intent using natural language processing technology. For example, the analysis unit applies natural language processing algorithms to analyze the user's input and understand its intent. Specifically, the analysis unit performs morphological and syntactic analysis to grammatically analyze the user's input. Furthermore, it performs semantic analysis, considering the context and related information to accurately grasp the user's intent. For example, if the user inputs "What's the weather like tomorrow?", the analysis unit performs morphological analysis to extract the keywords "tomorrow" and "weather," and then performs syntactic analysis to understand the sentence structure. After that, it performs semantic analysis to understand the user's intent to know tomorrow's weather forecast. Based on these analysis results, the analysis unit accurately understands the user's intent and provides information to the generation unit to generate an appropriate response. The analysis unit can also refer to the user's past input history and dialogue history to perform more accurate analysis. This allows the analysis unit to accurately understand the user's intent and improve the overall response accuracy of the system.

[0067] The generation unit generates responses based on the information analyzed by the analysis unit. For example, the generation unit applies a natural language generation algorithm to generate an appropriate response based on the analyzed information. Specifically, the generation unit can use template-based generation methods or generation methods using generative AI to generate responses that match the user's intent. In template-based generation methods, a pre-prepared response template is used to generate a response corresponding to the user's input. For example, if the user asks, "What's the weather like tomorrow?", the generation unit will generate a response using a template such as "It will be sunny tomorrow." On the other hand, generation methods using generative AI generate more flexible and natural responses based on the user's input. Generative AI has the ability to learn from a large amount of dialogue data and generate appropriate responses to user input. For example, if the user asks, "What's the weather like tomorrow?", the generative AI can generate a detailed response such as, "It's forecast to be sunny tomorrow. The temperature will be around 25 degrees Celsius." By using a combination of these generation methods, the generation unit can generate appropriate responses that match the user's intent.

[0068] The provider unit provides the user with the response generated by the generator unit. The provider unit can provide the generated response to the user in text or voice, for example. Specifically, the provider unit has the function of displaying text-based responses on a screen and the function of playing voice-based responses through a speaker. In text-based responses, the response to the question or instruction entered by the user is displayed on the screen. In voice-based responses, the generated response is converted into voice using speech synthesis technology and provided to the user through a speaker. This allows the user to receive the response both visually and aurally. The provider unit can also customize the method of providing responses according to the user's preference. For example, if the user prefers voice responses, the provider unit can be set to prioritize providing voice-based responses. This allows the provider unit to provide responses to the user in the most optimal way and improve user convenience.

[0069] The learning unit learns based on the responses provided by the providing unit. For example, the learning unit learns from data obtained through dialogue and applies machine learning algorithms to improve the accuracy of subsequent responses. Specifically, the learning unit collects user dialogue history and response evaluation data, and updates the machine learning model based on this data. For example, if a user provides feedback on a provided response, the learning unit collects that feedback and evaluates the appropriateness of the response. The learning unit uses this evaluation data to adjust the parameters of the response generation algorithm and improve the accuracy of subsequent responses. The learning unit can also update the content and style of responses based on new data and trends. This allows the learning unit to always provide highly accurate responses based on the latest information, improving user satisfaction. Furthermore, the learning unit can use anomaly detection algorithms to detect abnormal patterns and inappropriate responses during dialogue and use this information to improve the system. This allows the learning unit to improve the overall reliability and security of the system.

[0070] The reception desk can estimate the user's emotions and adjust the timing of receiving questions and instructions based on the estimated emotions. For example, if the user is stressed, the reception desk can temporarily delay receiving questions and instructions to give the user time to relax. For example, if the user is excited, the reception desk can also quickly receive questions and instructions and start responding immediately. For example, if the user is tired, the reception desk can simplify the process of receiving questions and instructions to complete them in a short time. This allows for more appropriate timing of receiving questions and instructions by adjusting the timing according to the user's emotions. Emotion estimation is achieved using emotion estimation functions, such as emotion engines or generative AI. Generative AI includes, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI.

[0071] The reception desk can analyze the user's past question history and select the optimal reception method. For example, the reception desk may prioritize receiving questions in formats that the user has frequently used in the past. The reception desk may also suggest the optimal reception timing based on the time of day the user has used in the past. The reception desk may also prioritize receiving questions on specific topics based on the user's past question history. This allows the reception desk to select the optimal reception method by analyzing the user's past question history. Some or all of the above processing in the reception desk may be performed using AI, for example, or without AI.

[0072] The reception desk can filter questions and instructions based on the user's current situation and areas of interest. For example, the reception desk can prioritize questions related to the user's current situation. The reception desk can also filter relevant questions and instructions based on the user's areas of interest. The reception desk can also suggest appropriate questions and instructions based on the user's current activities. This allows the reception desk to prioritize receiving highly relevant questions and instructions by filtering based on the user's current situation and areas of interest. Some or all of the above processing in the reception desk may be performed using AI, for example, or without AI.

[0073] The reception desk can estimate the user's emotions and determine the priority of questions and instructions to be received based on those estimated emotions. For example, if the user is stressed, the reception desk may postpone less important questions and instructions. For example, if the user is relaxed, the reception desk may prioritize more important questions and instructions. For example, if the user is in a hurry, the reception desk may prioritize questions and instructions that require a quick response. This allows for more appropriate processing by prioritizing questions and instructions according to the user's emotions. Emotion estimation is achieved using emotion estimation functions, such as emotion engines or generative AI. Generative AI includes, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI.

[0074] The reception desk can prioritize receiving questions and instructions that are highly relevant, taking into account the user's geographical location. For example, if the user is in a specific location, the reception desk will prioritize receiving questions and instructions related to that location. For example, if the user is traveling, the reception desk can also prioritize receiving questions and instructions related to the travel destination. For example, if the user is at home, the reception desk can also prioritize receiving questions and instructions related to home. In this way, by taking into account the user's geographical location, it is possible to prioritize receiving questions and instructions that are highly relevant. Some or all of the above processing in the reception desk may be performed using AI, for example, or without using AI.

[0075] The reception desk can analyze the user's social media activity when receiving questions or instructions and receive relevant questions or instructions. For example, the reception desk can receive relevant questions or instructions based on information the user has shared on social media. For example, the reception desk can analyze the content of the user's social media posts and suggest relevant questions or instructions. For example, the reception desk can receive relevant questions or instructions based on the activity of the user's social media followers and friends. This allows the reception desk to prioritize receiving relevant questions and instructions by analyzing the user's social media activity. Some or all of the above processing in the reception desk may be performed using AI, for example, or not using AI.

[0076] The analysis unit can estimate the user's emotions and adjust the analysis method based on the estimated emotions. For example, if the user is stressed, the analysis unit can simplify the level of detail in the analysis. For example, if the user is relaxed, the analysis unit can perform a detailed analysis. For example, if the user is in a hurry, the analysis unit can perform a rapid analysis. This allows for more appropriate analysis by adjusting the analysis method according to the user's emotions. Emotion estimation is achieved using an emotion estimation function, for example, using an emotion engine or generative AI. Generative AI includes, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI.

[0077] The analysis unit can adjust the level of detail of the analysis based on the importance of the questions and instructions during the analysis. For example, the analysis unit can perform a detailed analysis for questions and instructions of high importance. For example, the analysis unit can also perform a simplified analysis for questions and instructions of low importance. The analysis unit can also determine the priority of the analysis according to the importance of the questions and instructions. This allows for more appropriate analysis by adjusting the level of detail of the analysis based on the importance of the questions and instructions. Some or all of the above processing in the analysis unit may be performed using AI, for example, or without using AI.

[0078] The analysis unit can apply different analysis algorithms depending on the category of the question or instruction during analysis. For example, the analysis unit can apply a specialized analysis algorithm to a technical question. For example, the analysis unit can also apply a general-purpose analysis algorithm to a general question. For example, the analysis unit can select and apply the most suitable analysis algorithm for each category. This allows for more appropriate analysis by applying different analysis algorithms depending on the category of the question or instruction. Some or all of the above-described processes in the analysis unit may be performed using AI, for example, or without using AI.

[0079] The analysis unit can estimate the user's emotions and determine the priority of analyses based on the estimated emotions. For example, if the user is stressed, the analysis unit may postpone less important analyses. For example, if the user is relaxed, the analysis unit may prioritize more important analyses. For example, if the user is in a hurry, the analysis unit may prioritize analyses that require a quick response. This allows for analyses to be performed in a more appropriate order by determining the priority of analyses according to the user's emotions. Emotion estimation is achieved using an emotion estimation function, for example, using an emotion engine or generative AI. Generative AI includes, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI.

[0080] The analysis unit can determine the priority of analysis based on when questions and instructions were submitted. For example, the analysis unit may prioritize the analysis of recently submitted questions and instructions. The analysis unit may also postpone the analysis of older questions and instructions. The analysis unit may also dynamically adjust the priority of analysis based on the submission date. This allows for analysis in a more appropriate order by determining the priority of analysis based on when questions and instructions were submitted. Some or all of the above processing in the analysis unit may be performed using AI, for example, or without using AI.

[0081] The analysis unit can adjust the order of analysis based on the relevance of questions and instructions during the analysis. For example, the analysis unit may prioritize the analysis of highly relevant questions and instructions. For example, the analysis unit may postpone the analysis of less relevant questions and instructions. The analysis unit can also dynamically adjust the order of analysis according to the relevance of questions and instructions. This allows for analysis in a more appropriate order by adjusting the order of analysis based on the relevance of questions and instructions. Some or all of the above processing in the analysis unit may be performed using AI, for example, or without using AI.

[0082] The generation unit can estimate the user's emotions and adjust the way it expresses its response based on those emotions. For example, if the user is stressed, the generation unit will generate a concise and clear response. If the user is relaxed, the generation unit can also generate a response that includes detailed explanations. If the user is in a hurry, the generation unit can also generate a quick and concise response. By adjusting the way the response is expressed according to the user's emotions, a more appropriate response becomes possible. Emotion estimation is achieved using an emotion estimation function, such as an emotion engine or a generative AI. Generative AI may include, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI.

[0083] The generation unit can adjust the level of detail in responses based on the importance of the questions and instructions when generating responses. For example, the generation unit generates detailed responses to high-importance questions and instructions. The generation unit can also generate simplified responses to low-importance questions and instructions. The generation unit can also determine the priority of responses based on the importance of the questions and instructions. This allows for more appropriate responses by adjusting the level of detail in responses based on the importance of the questions and instructions. Some or all of the above processing in the generation unit may be performed using AI, for example, or without using AI.

[0084] The generation unit can apply different response algorithms depending on the category of the question or instruction when generating a response. For example, the generation unit can apply a specialized response algorithm to a technical question. For example, the generation unit can also apply a general-purpose response algorithm to a general question. For example, the generation unit can select and apply the most appropriate response algorithm for each category. This makes it possible to provide a more appropriate response by applying different response algorithms depending on the category of the question or instruction. Some or all of the above processing in the generation unit may be performed using AI, for example, or without using AI.

[0085] The generation unit can estimate the user's emotions and adjust the length of the response based on the estimated emotions. For example, if the user is stressed, the generation unit will generate a short, to-the-point response. If the user is relaxed, for example, the generation unit can also generate a longer response that includes detailed explanations. If the user is in a hurry, for example, the generation unit can generate a quick and concise response. By adjusting the length of the response according to the user's emotions, a more appropriate response becomes possible. Emotion estimation is achieved using emotion estimation functions, such as emotion engines or generative AI. Generative AI includes, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI.

[0086] The generation unit can determine the priority of responses based on when the questions and instructions were submitted. For example, the generation unit can prioritize generating responses to recently submitted questions and instructions. The generation unit can also postpone generating responses to older questions and instructions. The generation unit can also dynamically adjust the priority of responses according to the submission date. This allows for responses to be sent in a more appropriate order by determining the priority of responses based on when the questions and instructions were submitted. Some or all of the above processing in the generation unit may be performed using AI, for example, or without AI.

[0087] The generation unit can adjust the order of responses based on the relevance of the questions and instructions when generating responses. For example, the generation unit can prioritize generating responses for highly relevant questions and instructions. The generation unit can also postpone generating responses for less relevant questions and instructions. The generation unit can also dynamically adjust the order of responses according to the relevance of the questions and instructions. This allows for responses in a more appropriate order by adjusting the order of responses based on the relevance of the questions and instructions. Some or all of the above processing in the generation unit may be performed using AI, for example, or without using AI.

[0088] The service provider can estimate the user's emotions and adjust the way it delivers responses based on those emotions. For example, if the user is stressed, the service provider will deliver a response in a calm voice. If the user is relaxed, the service provider may deliver a response in a cheerful voice. If the user is in a hurry, the service provider may deliver a quick and concise response. By adjusting the way responses are delivered according to the user's emotions, more appropriate responses become possible. Emotion estimation is achieved using an emotion estimation function, such as an emotion engine or generative AI. Generative AI includes, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI.

[0089] The service provider can select the optimal service provider method by referring to the user's past dialogue history when providing a response. For example, the service provider may prioritize providing a response method that the user has previously preferred. The service provider may also select the optimal response method from the user's past dialogue history. For example, the service provider may analyze the user's past dialogue history and propose the optimal response method. This allows the service provider to select the optimal service provider method by referring to the user's past dialogue history. Some or all of the above processing in the service provider may be performed using AI, for example, or without using AI.

[0090] The service provider can customize the means of providing a response based on the user's current situation when providing a response. For example, if the user is on the move, the service provider may provide a voice response. For example, if the user is in a quiet place, the service provider may provide a text response. For example, if the user is in a meeting, the service provider may provide a notification response. By customizing the means of providing a response based on the user's current situation, a more appropriate response becomes possible. Some or all of the processing described above in the service provider may be performed using AI, for example, or not using AI.

[0091] The service provider can estimate the user's emotions and determine the priority of responses based on the estimated emotions. For example, if the user is stressed, the service provider may postpone less important responses. For example, if the user is relaxed, the service provider may prioritize providing more important responses. For example, if the user is in a hurry, the service provider may prioritize providing responses that require a quick response. This allows for responses to be delivered in a more appropriate order by determining the priority of responses according to the user's emotions. Emotion estimation is achieved using an emotion estimation function, for example, using an emotion engine or generative AI. Generative AI includes, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI.

[0092] The service provider can select the optimal service delivery method when providing a response, taking into account the user's geographical location. For example, if the user is in a specific location, the service provider can prioritize providing information related to that location. For example, if the user is traveling, the service provider can prioritize providing information related to the travel destination. For example, if the user is at home, the service provider can prioritize providing information related to home. This allows the service provider to select the optimal service delivery method by taking into account the user's geographical location. Some or all of the processing described above in the service provider may be performed using AI, for example, or without using AI.

[0093] The service provider can analyze the user's social media activity and propose a means of providing a response when providing a response. For example, the service provider can provide a relevant response based on information shared by the user on social media. The service provider can also analyze the content of the user's social media posts and propose a relevant response. The service provider can also provide a relevant response based on the activity of the user's social media followers and friends. In this way, a relevant response can be provided by analyzing the user's social media activity. Some or all of the above processing in the service provider may be performed using AI, for example, or without using AI.

[0094] The learning unit can estimate the user's emotions and select training data based on the estimated emotions. For example, if the user is stressed, the learning unit will prioritize learning data related to stress reduction. For example, if the user is relaxed, the learning unit can also prioritize learning data related to relaxation. For example, if the user is in a hurry, the learning unit can also prioritize learning data related to quick responses. This allows for more appropriate learning by selecting training data according to the user's emotions. Emotion estimation is achieved using an emotion estimation function, for example, using an emotion engine or generative AI. Generative AI includes, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI.

[0095] The learning unit can optimize the learning algorithm by referring to past learning data during the learning process. For example, the learning unit can analyze past learning data and select the optimal learning algorithm. The learning unit can also adjust parameters to improve learning accuracy based on past learning data. For example, the learning unit can identify areas for improvement in the learning algorithm based on past learning data and optimize it. In this way, the learning algorithm can be optimized by referring to past learning data. Some or all of the above processes in the learning unit may be performed using AI, for example, or without using AI.

[0096] The learning unit can improve the accuracy of learning by considering the user's profile information during the learning process. For example, the learning unit can select personalized learning data based on the user's profile information. The learning unit can also adjust the learning algorithm by considering the user's profile information. For example, the learning unit can select data to improve the accuracy of learning based on the user's profile information. In this way, the accuracy of learning can be improved by considering the user's profile information. Some or all of the above processes in the learning unit may be performed using AI, for example, or without using AI.

[0097] The learning unit can estimate the user's emotions and adjust the learning frequency based on the estimated emotions. For example, if the user is stressed, the learning unit can reduce the learning frequency. For example, if the user is relaxed, the learning unit can increase the learning frequency. For example, if the user is in a hurry, the learning unit can adjust the learning frequency to enable a quick response. This allows for more appropriate learning by adjusting the learning frequency according to the user's emotions. Emotion estimation is achieved using an emotion estimation function, for example, using an emotion engine or generative AI. Generative AI is, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI.

[0098] The learning unit can weight the training data based on the submission date of the dialogue history during training. For example, the learning unit prioritizes learning recent dialogue histories. The learning unit can also reduce the weight of older dialogue histories, for example. The learning unit can also dynamically adjust the weighting of the training data according to the submission date. This allows for more appropriate training by weighting the training data based on the submission date of the dialogue history. Some or all of the above processing in the learning unit may be performed using AI, for example, or without using AI.

[0099] The learning unit can improve the accuracy of learning by referring to the user's relevant literature during the learning process. For example, the learning unit selects learning data based on the relevant literature provided by the user. The learning unit can also adjust the learning algorithm by referring to the user's relevant literature. For example, the learning unit can select data to improve the accuracy of learning based on the user's relevant literature. In this way, the accuracy of learning can be improved by referring to the user's relevant literature. Some or all of the above processes in the learning unit may be performed using AI, for example, or without using AI.

[0100] The system according to the embodiment is not limited to the example described above, and various modifications are possible, for example, as follows.

[0101] The reception desk can estimate the user's emotions and adjust how questions and instructions are received based on those estimates. For example, if the user is stressed, the reception desk can temporarily delay receiving questions and instructions to give them time to relax. Conversely, if the user is agitated, the reception desk can quickly receive questions and instructions and begin responding immediately. Furthermore, if the user is tired, the reception desk can simplify the process of receiving questions and instructions to complete them in a short amount of time. By adjusting how questions and instructions are received according to the user's emotions, reception can be conducted at a more appropriate time.

[0102] The analysis unit can estimate the user's emotions and adjust the analysis method based on those emotions. For example, if the user is stressed, the analysis unit can simplify the level of detail in the analysis. Conversely, if the user is relaxed, the analysis unit can perform a detailed analysis. Furthermore, if the user is in a hurry, the analysis unit can perform a rapid analysis. By adjusting the analysis method according to the user's emotions, a more appropriate analysis becomes possible.

[0103] The generation unit can estimate the user's emotions and adjust the way it expresses its response based on those emotions. For example, if the user is stressed, the generation unit can generate a concise and clear response. If the user is relaxed, the generation unit can generate a response that includes detailed explanations. Furthermore, if the user is in a hurry, the generation unit can generate a quick and concise response. By adjusting the way the response is expressed according to the user's emotions, a more appropriate response becomes possible.

[0104] The system can estimate the user's emotions and adjust its response based on those estimates. For example, if the user is stressed, the system can respond in a calm voice. If the user is relaxed, the system can respond in a cheerful voice. Furthermore, if the user is in a hurry, the system can provide a quick and concise response. By adjusting the response method according to the user's emotions, a more appropriate response becomes possible.

[0105] The learning unit can estimate the user's emotions and select training data based on those estimated emotions. For example, if the user is stressed, the learning unit can prioritize learning data related to stress reduction. Similarly, if the user is relaxed, the learning unit can prioritize learning data related to relaxation. Furthermore, if the user is in a hurry, the learning unit can prioritize learning data related to quick responses. This allows for more appropriate learning by selecting training data according to the user's emotions.

[0106] The reception desk can analyze a user's past question history and select the optimal reception method. For example, it can prioritize receiving questions in formats frequently used by the user in the past. It can also suggest the optimal reception timing based on the time of day the user has used it in the past. Furthermore, it can prioritize receiving questions on specific topics based on the user's past question history. In this way, the optimal reception method can be selected by analyzing the user's past question history.

[0107] The reception desk can filter questions and instructions based on the user's current situation and areas of interest. For example, it can prioritize questions related to the user's current situation. It can also filter relevant questions and instructions based on the user's areas of interest. Furthermore, it can suggest appropriate questions and instructions based on the user's current activities. In this way, by filtering based on the user's current situation and areas of interest, it can prioritize receiving highly relevant questions and instructions.

[0108] The analysis unit can adjust the level of detail in the analysis based on the importance of the questions and instructions. For example, it can perform a detailed analysis on high-importance questions and instructions, and a simplified analysis on low-importance questions and instructions. Furthermore, it can determine the priority of the analysis based on the importance of the questions and instructions. By adjusting the level of detail in the analysis based on the importance of the questions and instructions, more appropriate analysis becomes possible.

[0109] The generation unit can adjust the level of detail in responses based on the importance of the questions and instructions during response generation. For example, it can generate detailed responses to high-importance questions and instructions, and simplified responses to low-importance questions and instructions. Furthermore, it can determine the priority of responses based on the importance of the questions and instructions. This allows for more appropriate responses by adjusting the level of detail based on the importance of the questions and instructions.

[0110] The response system can select the optimal response method by referring to the user's past dialogue history when providing a response. For example, it can prioritize providing a response method that the user has preferred in the past. It can also select the optimal response method from the user's past dialogue history. Furthermore, it can analyze the user's past dialogue history and suggest the optimal response method. In this way, the optimal response method can be selected by referring to the user's past dialogue history.

[0111] The following briefly describes the processing flow for example form 2.

[0112] Step 1: The reception desk receives questions and instructions from users. These include text-based questions and voice instructions. For example, it can accept questions and instructions entered by users in natural language. Step 2: The analysis unit analyzes the information received by the reception unit. The analysis unit uses natural language processing technology to analyze the user's intent. For example, it analyzes the user's input and applies a natural language processing algorithm to understand their intent. Step 3: The generation unit generates a response based on the information analyzed by the analysis unit. The generation unit applies a natural language generation algorithm to generate an appropriate response based on the analyzed information. Step 4: The providing unit provides the user with the response generated by the generating unit. The providing unit can provide the generated response to the user in text or voice. Step 5: The learning unit learns based on the responses provided by the providing unit. The learning unit learns from the data obtained through the interaction and applies machine learning algorithms to improve the accuracy of subsequent responses.

[0113] The specific processing unit 290 transmits the result of the specific processing to the smart device 14. In the smart device 14, the control unit 46A causes the output device 40 to output the result of the specific processing. The microphone 38B acquires audio indicating user input for the result of the specific processing. The control unit 46A transmits the audio data indicating user input acquired by the microphone 38B to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the audio data.

[0114] Data generation model 58 is a form of so-called generative AI (Artificial Intelligence). An example of data generation model 58 is ChatGPT (registered trademark) (Internet search).<URL: https: / / openai.com / blog / chatgpt> Examples of generative AI include text generation AI, image generation AI, and multimodal generation AI. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 is input with prompts containing instructions, and with inference data such as audio data representing speech, text data representing text, and image data representing images (e.g., still image data or video data). The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference result in one or more data formats from audio data, text data, and image data. The data generation model 58 includes, for example, text generation AI, image generation AI, and multimodal generation AI. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The specific processing unit 290 performs the specific processing described above using the data generation model 58. The data generation model 58 may be a fine-tuned model that outputs inference results from prompts that do not contain instructions, in which case the data generation model 58 can output inference results from prompts that do not contain instructions. In the data processing device 12, etc., there are multiple types of data generation models 58, and the data generation model 58 includes AI other than generative AI. AI other than generative AI includes, for example, linear regression, logistic regression, decision trees, random forests, support vector machines (SVMs), k-means clustering, convolutional neural networks (CNNs), recurrent neural networks (RNNs), generative adversarial networks (GANs), or naive Bayes, and can perform various processes, but is not limited to these examples. Also, the AI ​​may be an AI agent. Furthermore, when the processing of each of the above parts is performed by the AI, the processing may be performed by the AI ​​in part or in whole, but is not limited to this example.Furthermore, processing performed by AI, including generative AI, may be replaced with rule-based processing, and rule-based processing may be replaced with processing performed by AI, including generative AI.

[0115] Furthermore, the processing performed by the data processing system 10 described above is carried out by the specific processing unit 290 of the data processing device 12 or the control unit 46A of the smart device 14, but it may also be carried out by the specific processing unit 290 of the data processing device 12 and the control unit 46A of the smart device 14. In addition, the specific processing unit 290 of the data processing device 12 acquires or collects information necessary for processing from the smart device 14 or an external device, and the smart device 14 acquires or collects information necessary for processing from the data processing device 12 or an external device.

[0116] Each of the multiple elements described above, including the reception unit, analysis unit, generation unit, provision unit, and learning unit, is implemented in at least one of the smart device 14 and the data processing unit 12. For example, the reception unit is implemented by the reception device 38 of the smart device 14 and receives questions and instructions from the user. The analysis unit is implemented by the specific processing unit 290 of the data processing unit 12 and analyzes the received information. The generation unit is implemented by the specific processing unit 290 of the data processing unit 12 and generates a response based on the analyzed information. The provision unit is implemented by the output device 40 of the smart device 14 and provides the generated response to the user. The learning unit is implemented by the specific processing unit 290 of the data processing unit 12 and learns based on the provided response. The correspondence between each unit and the device or control unit is not limited to the example described above and can be changed in various ways.

[0117] [Second Embodiment] Figure 3 shows an example of the configuration of the data processing system 210 according to the second embodiment.

[0118] As shown in Figure 3, the data processing system 210 includes a data processing device 12 and smart glasses 214. An example of the data processing device 12 is a server.

[0119] The data processing device 12 comprises a computer 22, a database 24, and a communication interface 26. The computer 22 comprises a processor 28, RAM 30, and storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication interface 26 are also connected to the bus 34. The communication interface 26 is connected to a network 54. An example of the network 54 is a WAN and / or LAN.

[0120] The smart glasses 214 include a computer 36, a microphone 238, a speaker 240, a camera 42, and a communication interface 44. The computer 36 includes a processor 46, RAM 48, and storage 50. The processor 46, RAM 48, and storage 50 are connected to a bus 52. The microphone 238, speaker 240, and camera 42 are also connected to the bus 52.

[0121] The microphone 238 receives voice signals from the user and accepts instructions from the user. The microphone 238 captures the voice signals from the user, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to the instructions from the processor 46.

[0122] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an image sensor such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, which captures images of the area around the user (for example, an imaging range defined by a field of view equivalent to the field of vision of a typical healthy person).

[0123] Communication interface 44 is connected to network 54. Communication interfaces 44 and 26 are responsible for the exchange of various information between processor 46 and processor 28 via network 54. The exchange of various information between processor 46 and processor 28 using communication interfaces 44 and 26 is performed in a secure manner.

[0124] Figure 4 shows an example of the main functions of the data processing device 12 and the smart glasses 214. As shown in Figure 4, the data processing device 12 performs specific processing by the processor 28. The storage 32 stores the specific processing program 56.

[0125] The processor 28 reads a specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 acting as a specific processing unit 290 according to the specific processing program 56 executed on the RAM 30.

[0126] Storage 32 stores the data generation model 58 and the emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290. The identification processing unit 290 can estimate the user's emotions using the emotion identification model 59 and perform identification processing using the user's emotions. The emotion estimation function (emotion identification function) using the emotion identification model 59 performs various estimations and predictions regarding the user's emotions, including but not limited to these examples. Furthermore, emotion estimation and prediction also include, for example, emotion analysis.

[0127] In the smart glasses 214, specific processing is performed by the processor 46. The storage 50 stores a specific processing program 60. The processor 46 reads the specific processing program 60 from the storage 50 and executes the read specific processing program 60 on the RAM 48. The specific processing is realized by the processor 46 acting as a control unit 46A according to the specific processing program 60 executed on the RAM 48. The smart glasses 214 also have a data generation model 58 and an emotion identification model 59, similar to the data generation model and emotion identification model 59, and can perform processing similar to that of the specific processing unit 290 using these models.

[0128] Furthermore, other devices besides the data processing device 12 may also have the data generation model 58. For example, a server device may have the data generation model 58. In this case, the data processing device 12 obtains processing results (such as prediction results) using the data generation model 58 by communicating with the server device that has the data generation model 58. Also, the data processing device 12 may be a server device or a terminal device owned by the user (for example, a mobile phone, robot, home appliance, etc.).

[0129] The specific processing unit 290 transmits the result of the specific processing to the smart glasses 214. In the smart glasses 214, the control unit 46A causes the speaker 240 to output the result of the specific processing. The microphone 238 acquires audio indicating user input for the result of the specific processing. The control unit 46A transmits the audio data indicating user input acquired by the microphone 238 to the data processing unit 12. In the data processing unit 12, the specific processing unit 290 acquires the audio data.

[0130] The data generation model 58 is a so-called generative AI. An example of a data generation model 58 is a generative AI such as ChatGPT. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 is input with prompts containing instructions, and inference data such as audio data representing speech, text data representing text, and image data representing images (e.g., still image data or video data). The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference result in one or more data formats such as audio data, text data, and image data. The data generation model 58 includes, for example, text generation AI, image generation AI, and multimodal generation AI. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The specific processing unit 290 performs the specific processing described above using the data generation model 58. The data generation model 58 may be a fine-tuned model that outputs inference results from prompts that do not contain instructions, in which case the data generation model 58 can output inference results from prompts that do not contain instructions. In the data processing device 12, etc., there are multiple types of data generation models 58, and the data generation model 58 includes AI other than generative AI. AI other than generative AI includes, for example, linear regression, logistic regression, decision trees, random forests, support vector machines (SVM), k-means clustering, convolutional neural networks (CNN), recurrent neural networks (RNN), generative adversarial networks (GAN), or naive Bayes, and can perform various processes, but is not limited to these examples. Also, the AI ​​may be an AI agent. Furthermore, when the processing of each part described above is performed by the AI, the processing may be performed by the AI ​​in part or in whole, but is not limited to this example. Also, processing performed by an AI including a generative AI may be replaced by rule-based processing, and rule-based processing may be replaced by processing performed by an AI including a generative AI.

[0131] The data processing system 210 according to the second embodiment performs the same processing as the data processing system 10 according to the first embodiment. The processing by the data processing system 210 is performed by the specific processing unit 290 of the data processing device 12 or the control unit 46A of the smart glasses 214, but it may also be performed by the specific processing unit 290 of the data processing device 12 and the control unit 46A of the smart glasses 214. In addition, the specific processing unit 290 of the data processing device 12 acquires or collects information necessary for processing from the smart glasses 214 or an external device, and the smart glasses 214 acquires or collects information necessary for processing from the data processing device 12 or an external device.

[0132] Each of the multiple elements described above, including the reception unit, analysis unit, generation unit, provision unit, and learning unit, is implemented in at least one of the smart glasses 214 and the data processing unit 12. For example, the reception unit is implemented by the microphone 238 of the smart glasses 214 and receives questions and instructions from the user. The analysis unit is implemented by the specific processing unit 290 of the data processing unit 12 and analyzes the received information. The generation unit is implemented by the specific processing unit 290 of the data processing unit 12 and generates a response based on the analyzed information. The provision unit is implemented by the speaker 240 of the smart glasses 214 and provides the generated response to the user. The learning unit is implemented by the specific processing unit 290 of the data processing unit 12 and learns based on the provided response. The correspondence between each unit and the device or control unit is not limited to the example described above and can be changed in various ways.

[0133] [Third Embodiment] Figure 5 shows an example of the configuration of the data processing system 310 according to the third embodiment.

[0134] As shown in Figure 5, the data processing system 310 includes a data processing device 12 and a headset terminal 314. An example of the data processing device 12 is a server.

[0135] The data processing device 12 comprises a computer 22, a database 24, and a communication interface 26. The computer 22 comprises a processor 28, RAM 30, and storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication interface 26 are also connected to the bus 34. The communication interface 26 is connected to a network 54. An example of the network 54 is a WAN and / or LAN.

[0136] The headset terminal 314 includes a computer 36, a microphone 238, a speaker 240, a camera 42, a communication interface 44, and a display 343. The computer 36 includes a processor 46, RAM 48, and storage 50. The processor 46, RAM 48, and storage 50 are connected to a bus 52. The microphone 238, speaker 240, camera 42, and display 343 are also connected to the bus 52.

[0137] The microphone 238 receives voice signals from the user and accepts instructions from the user. The microphone 238 captures the voice signals from the user, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to the instructions from the processor 46.

[0138] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an image sensor such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, which captures images of the area around the user (for example, an imaging range defined by a field of view equivalent to the field of vision of a typical healthy person).

[0139] Communication interface 44 is connected to network 54. Communication interfaces 44 and 26 are responsible for the exchange of various information between processor 46 and processor 28 via network 54. The exchange of various information between processor 46 and processor 28 using communication interfaces 44 and 26 is performed in a secure manner.

[0140] Figure 6 shows an example of the main functions of the data processing device 12 and the headset terminal 314. As shown in Figure 6, the data processing device 12 performs specific processing using the processor 28. The storage 32 stores the specific processing program 56.

[0141] The processor 28 reads a specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 acting as a specific processing unit 290 according to the specific processing program 56 executed on the RAM 30.

[0142] Storage 32 stores the data generation model 58 and the emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290. The identification processing unit 290 can estimate the user's emotions using the emotion identification model 59 and perform identification processing using the user's emotions. The emotion estimation function (emotion identification function) using the emotion identification model 59 performs various estimations and predictions regarding the user's emotions, including but not limited to these examples. Furthermore, emotion estimation and prediction also include, for example, emotion analysis.

[0143] In the headset terminal 314, specific processing is performed by the processor 46. The storage 50 stores a specific program 60. The processor 46 reads the specific program 60 from the storage 50 and executes the read specific program 60 on the RAM 48. The specific processing is realized by the processor 46 acting as a control unit 46A according to the specific program 60 executed on the RAM 48. The headset terminal 314 also has a data generation model 58 and an emotion identification model 59, similar to the data generation model and emotion identification model 59, and can perform processing similar to that of the specific processing unit 290 using these models.

[0144] Furthermore, other devices besides the data processing device 12 may also have the data generation model 58. For example, a server device may have the data generation model 58. In this case, the data processing device 12 obtains processing results (such as prediction results) using the data generation model 58 by communicating with the server device that has the data generation model 58. Also, the data processing device 12 may be a server device or a terminal device owned by the user (for example, a mobile phone, robot, home appliance, etc.).

[0145] The specific processing unit 290 transmits the result of the specific processing to the headset terminal 314. In the headset terminal 314, the control unit 46A causes the speaker 240 and display 343 to output the result of the specific processing. The microphone 238 acquires audio indicating user input for the result of the specific processing. The control unit 46A transmits the audio data indicating user input acquired by the microphone 238 to the data processing unit 12. In the data processing unit 12, the specific processing unit 290 acquires the audio data.

[0146] The data generation model 58 is a so-called generative AI. An example of a data generation model 58 is a generative AI such as ChatGPT. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 is input with prompts containing instructions, and inference data such as audio data representing speech, text data representing text, and image data representing images (e.g., still image data or video data). The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference result in one or more data formats such as audio data, text data, and image data. The data generation model 58 includes, for example, text generation AI, image generation AI, and multimodal generation AI. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The specific processing unit 290 performs the specific processing described above using the data generation model 58. The data generation model 58 may be a fine-tuned model that outputs inference results from prompts that do not contain instructions, in which case the data generation model 58 can output inference results from prompts that do not contain instructions. In the data processing device 12, etc., there are multiple types of data generation models 58, and the data generation model 58 includes AI other than generative AI. AI other than generative AI includes, for example, linear regression, logistic regression, decision trees, random forests, support vector machines (SVM), k-means clustering, convolutional neural networks (CNN), recurrent neural networks (RNN), generative adversarial networks (GAN), or naive Bayes, and can perform various processes, but is not limited to these examples. Also, the AI ​​may be an AI agent. Furthermore, when the processing of each part described above is performed by the AI, the processing may be performed by the AI ​​in part or in whole, but is not limited to this example. Also, processing performed by an AI including a generative AI may be replaced by rule-based processing, and rule-based processing may be replaced by processing performed by an AI including a generative AI.

[0147] The data processing system 310 according to the third embodiment performs the same processing as the data processing system 10 according to the first embodiment. The processing by the data processing system 310 is performed by the specific processing unit 290 of the data processing device 12 or the control unit 46A of the headset terminal 314, but may also be performed by the specific processing unit 290 of the data processing device 12 and the control unit 46A of the headset terminal 314. In addition, the specific processing unit 290 of the data processing device 12 acquires or collects information necessary for processing from the headset terminal 314 or an external device, and the headset terminal 314 acquires or collects information necessary for processing from the data processing device 12 or an external device.

[0148] Each of the multiple elements described above, including the reception unit, analysis unit, generation unit, provision unit, and learning unit, is implemented in at least one of the headset terminal 314 and the data processing unit 12. For example, the reception unit is implemented by the microphone 238 of the headset terminal 314 and receives questions and instructions from the user. The analysis unit is implemented by the specific processing unit 290 of the data processing unit 12 and analyzes the received information. The generation unit is implemented by the specific processing unit 290 of the data processing unit 12 and generates a response based on the analyzed information. The provision unit is implemented by the speaker 240 of the headset terminal 314 and provides the generated response to the user. The learning unit is implemented by the specific processing unit 290 of the data processing unit 12 and learns based on the provided response. The correspondence between each unit and the device or control unit is not limited to the example described above and can be modified in various ways.

[0149] [Fourth Embodiment] Figure 7 shows an example of the configuration of the data processing system 410 according to the fourth embodiment.

[0150] As shown in Figure 7, the data processing system 410 includes a data processing device 12 and a robot 414. An example of the data processing device 12 is a server.

[0151] The data processing device 12 comprises a computer 22, a database 24, and a communication interface 26. The computer 22 comprises a processor 28, RAM 30, and storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication interface 26 are also connected to the bus 34. The communication interface 26 is connected to a network 54. An example of the network 54 is a WAN and / or LAN.

[0152] The robot 414 includes a computer 36, a microphone 238, a speaker 240, a camera 42, a communication interface 44, and a controlled object 443. The computer 36 includes a processor 46, RAM 48, and storage 50. The processor 46, RAM 48, and storage 50 are connected to a bus 52. The microphone 238, speaker 240, camera 42, and controlled object 443 are also connected to the bus 52.

[0153] The microphone 238 receives voice signals from the user and accepts instructions from the user. The microphone 238 captures the voice signals from the user, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to the instructions from the processor 46.

[0154] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an image sensor such as a CMOS image sensor or CCD image sensor, which captures images of the area around the user (for example, an imaging range defined by a field of view equivalent to the field of vision of a typical healthy person).

[0155] Communication interface 44 is connected to network 54. Communication interfaces 44 and 26 are responsible for the exchange of various information between processor 46 and processor 28 via network 54. The exchange of various information between processor 46 and processor 28 using communication interfaces 44 and 26 is performed in a secure manner.

[0156] The controlled object 443 includes a display device, LEDs in the eyes, and motors that drive the arms, hands, and feet. The posture and gestures of the robot 414 are controlled by controlling the motors of the arms, hands, and feet. Some of the robot 414's emotions can be expressed by controlling these motors. The robot 414's facial expressions can also be expressed by controlling the illumination state of the LEDs in its eyes.

[0157] Figure 8 shows an example of the main functions of the data processing device 12 and the robot 414. As shown in Figure 8, the data processing device 12 performs specific processing using the processor 28. The storage 32 stores the specific processing program 56.

[0158] The processor 28 reads a specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 acting as a specific processing unit 290 according to the specific processing program 56 executed on the RAM 30.

[0159] Storage 32 stores the data generation model 58 and the emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290. The identification processing unit 290 can estimate the user's emotions using the emotion identification model 59 and perform identification processing using the user's emotions. The emotion estimation function (emotion identification function) using the emotion identification model 59 performs various estimations and predictions regarding the user's emotions, including but not limited to these examples. Furthermore, emotion estimation and prediction also include, for example, emotion analysis.

[0160] In robot 414, specific processing is performed by processor 46. A specific program 60 is stored in storage 50. Processor 46 reads the specific program 60 from storage 50 and executes it on RAM 48. The specific processing is achieved by processor 46 acting as a control unit 46A according to the specific program 60 executed on RAM 48. Robot 414 also has data generation model 58 and emotion identification model 59, similar to those of the robot, and can perform processing similar to that of the specific processing unit 290 using these models.

[0161] Furthermore, other devices besides the data processing device 12 may also have the data generation model 58. For example, a server device may have the data generation model 58. In this case, the data processing device 12 obtains processing results (such as prediction results) using the data generation model 58 by communicating with the server device that has the data generation model 58. Also, the data processing device 12 may be a server device or a terminal device owned by the user (for example, a mobile phone, robot, home appliance, etc.).

[0162] The specific processing unit 290 transmits the result of the specific processing to the robot 414. In the robot 414, the control unit 46A causes the speaker 240 and the controlled object 443 to output the result of the specific processing. The microphone 238 acquires audio indicating user input for the result of the specific processing. The control unit 46A transmits the audio data indicating user input acquired by the microphone 238 to the data processing unit 12. In the data processing unit 12, the specific processing unit 290 acquires the audio data.

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

[0164] The data processing system 410 according to the fourth embodiment performs the same processing as the data processing system 10 according to the first embodiment. The processing by the data processing system 410 is performed by the specific processing unit 290 of the data processing device 12 or the control unit 46A of the robot 414, but it may also be performed by the specific processing unit 290 of the data processing device 12 and the control unit 46A of the robot 414. In addition, the specific processing unit 290 of the data processing device 12 acquires or collects information necessary for processing from the robot 414 or an external device, and the robot 414 acquires or collects information necessary for processing from the data processing device 12 or an external device.

[0165] Each of the multiple elements described above, including the reception unit, analysis unit, generation unit, provision unit, and learning unit, is implemented in at least one of the following: the robot 414 and the data processing unit 12. For example, the reception unit is implemented by the microphone 238 of the robot 414 and receives questions and instructions from the user. The analysis unit is implemented by the specific processing unit 290 of the data processing unit 12 and analyzes the received information. The generation unit is implemented by the specific processing unit 290 of the data processing unit 12 and generates a response based on the analyzed information. The provision unit is implemented by the speaker 240 of the robot 414 and provides the generated response to the user. The learning unit is implemented by the specific processing unit 290 of the data processing unit 12 and learns based on the provided response. The correspondence between each unit and the device or control unit is not limited to the example described above and can be modified in various ways.

[0166] Furthermore, the emotion identification model 59, acting as an emotion engine, may determine the user's emotion according to a specific mapping. Specifically, the emotion identification model 59 may determine the user's emotion according to a specific mapping, which is an emotion map (see Figure 9). Similarly, the emotion identification model 59 may also determine the robot's emotion, and the identification processing unit 290 may perform identification processing using the robot's emotion.

[0167] Figure 9 shows the emotion map 400, in which multiple emotions are mapped. In the emotion map 400, emotions are arranged in concentric circles radiating from the center. The closer to the center of the concentric circles, the more primitive the emotions are located. Further out of the concentric circles, emotions representing states and actions arising from mental states are located. Emotion is a concept that includes feelings and mental states. On the left side of the concentric circles, emotions that are generally generated from reactions occurring in the brain are located. On the right side of the concentric circles, emotions that are generally induced by situational judgment are located. Above and below the concentric circles, emotions that are generally generated from reactions occurring in the brain and induced by situational judgment are located. In addition, the emotion of "pleasure" is located on the upper side of the concentric circles, and the emotion of "displeasure" is located on the lower side. Thus, in the emotion map 400, multiple emotions are mapped based on the structure in which emotions arise, and emotions that are likely to occur simultaneously are mapped close together.

[0168] These emotions are distributed at the 3 o'clock position on the Emotion Map 400, and usually fluctuate between feelings of security and anxiety. In the right half of the Emotion Map 400, situational awareness takes precedence over internal feelings, resulting in a calm impression.

[0169] The inside of the Emotion Map 400 represents inner thoughts, while the outside represents actions. Therefore, the further you go from the outside of the Emotion Map 400, the more visible (expressed in actions) your emotions become.

[0170] Here, human emotions are based on various balances, such as posture and blood sugar levels. When these balances deviate from the ideal, it results in discomfort, and when they approach the ideal, it results in pleasure. Similarly, in robots, cars, and motorcycles, emotions can be created based on various balances, such as posture and battery level. When these balances deviate from the ideal, it results in discomfort, and when they approach the ideal, it results in pleasure. The emotion map can be generated based, for example, on Dr. Mitsuyoshi's emotion map (Research on a system for analyzing brain physiological signals of speech emotion recognition and emotion, Tokushima University, doctoral dissertation: https: / / ci.nii.ac.jp / naid / 500000375379). The left half of the emotion map contains emotions belonging to a region called "response," where sensation is dominant. The right half of the emotion map contains emotions belonging to a region called "situation," where situational awareness is dominant.

[0171] The emotion map defines two emotions that promote learning. One is the emotion around the middle of the negative "repentance" and "reflection" on the situation side. In other words, it is when the robot experiences negative emotions such as "I never want to feel this way again" or "I don't want to be scolded again." The other is the emotion around the positive "desire" on the reaction side. In other words, it is when the robot has positive feelings such as "I want more" or "I want to know more."

[0172] The emotion identification model 59 inputs user input into a pre-trained neural network, obtains emotion values ​​representing each emotion shown in the emotion map 400, and determines the user's emotion. This neural network is pre-trained based on multiple training data sets, which are combinations of user input and emotion values ​​representing each emotion shown in the emotion map 400. Furthermore, this neural network is trained so that emotions located close together have similar values, as shown in the emotion map 900 in Figure 10. Figure 10 shows an example where multiple emotions such as "reassured," "calm," and "confident" have similar emotion values.

[0173] In the above embodiment, an example was given in which a specific process is performed by a single computer 22. However, the technology of this disclosure is not limited thereto, and a distributed processing method for the specific process may be used, which includes computer 22 and multiple other computers.

[0174] In the above embodiment, an example was given in which the specific processing program 56 is stored in the storage 32, but the technology of this disclosure is not limited thereto. For example, the specific processing program 56 may be stored in a portable, computer-readable, non-temporary storage medium such as a USB (Universal Serial Bus) memory. The specific processing program 56 stored in the non-temporary storage medium is installed in the computer 22 of the data processing device 12. The processor 28 executes specific processing according to the specific processing program 56.

[0175] 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.

[0176] Furthermore, it is not necessary to store the entirety of the specific processing program 56 in a storage device such as a server connected to the data processing device 12 via the network 54, or to store the entirety of the specific processing program 56 in the storage 32; it is acceptable to store only a portion of the specific processing program 56.

[0177] The following types of processors can be used as hardware resources to perform specific processing. Examples of processors include a CPU, a general-purpose processor that functions as a hardware resource to perform specific processing by executing software, i.e., a program. Other examples of processors include dedicated electrical circuits, such as FPGAs (Field-Programmable Gate Arrays), PLDs (Programmable Logic Devices), or ASICs (Application Specific Integrated Circuits), which have circuit configurations specifically designed to perform specific processing. All of these processors have built-in or connected memory, and all of them perform specific processing by using memory.

[0178] The hardware resource that performs a specific process may consist of one of these various processors, or it may consist of a combination of two or more processors of the same or different types (for example, a combination of multiple FPGAs, or a combination of a CPU and an FPGA). Alternatively, the hardware resource that performs a specific process may consist of a single processor.

[0179] Examples of configurations using a single processor include, firstly, a configuration in which one or more CPUs and software are combined to form a single processor, and this processor functions as a hardware resource that performs a specific process. Secondly, there is a configuration using a processor that realizes the functions of the entire system, including multiple hardware resources that perform a specific process, on a single IC chip, as exemplified by SoCs (System-on-a-chip). In this way, a specific process is realized using one or more of the above types of processors as hardware resources.

[0180] Furthermore, the hardware structure of these various processors can more specifically utilize electrical circuits that combine circuit elements such as semiconductor devices. Also, the specific processing described above is merely an example. Therefore, it goes without saying that unnecessary steps can be deleted, new steps added, or the processing order rearranged, as long as it does not deviate from the main purpose.

[0181] Furthermore, although the above-described examples were divided into four embodiments, some or all of these embodiments may be combined. Also, the smart device 14, smart glasses 214, headset terminal 314, and robot 414 are just examples, and they may be combined, or other devices may be used. Also, although the above-described examples were divided into two embodiments, Embodiment 1 and Embodiment 2, these may be combined.

[0182] The descriptions and illustrations presented above are detailed explanations of the technical aspects of this disclosure and are merely examples of the technical aspects. For example, the above descriptions of the structure, function, operation, and effect are examples of the structure, function, operation, and effect of the technical aspects of this disclosure. Therefore, it goes without saying that you may delete unnecessary parts, add new elements, or replace elements in the descriptions and illustrations presented above, as long as you do not deviate from the essence of the technical aspects of this disclosure. Furthermore, in order to avoid confusion and facilitate understanding of the technical aspects of this disclosure, explanations of common technical knowledge and other things that do not require special explanation to enable the implementation of the technical aspects of this disclosure have been omitted from the descriptions and illustrations presented above.

[0183] All documents, patent applications, and technical standards described herein are incorporated by reference to the same extent as if each individual document, patent application, and technical standard were specifically and individually noted to be incorporated by reference.

[0184] (Note 1) A reception desk that receives questions and instructions from users, An analysis unit that analyzes the information received by the reception unit, A generation unit that generates a response based on the information analyzed by the analysis unit, A providing unit that provides the response generated by the generation unit to the user, The system includes a learning unit that learns based on the response provided by the aforementioned providing unit. A system characterized by the following features. (Note 2) The aforementioned reception unit is It estimates the user's emotions and adjusts the timing of receiving questions and instructions based on the estimated user emotions. The system described in Appendix 1, characterized by the features described herein. (Note 3) The aforementioned reception unit is Analyze the user's past question history and select the most suitable method of handling inquiries. The system described in Appendix 1, characterized by the features described herein. (Note 4) The aforementioned reception unit is When receiving questions or instructions, filtering is performed based on the user's current situation and areas of interest. The system described in Appendix 1, characterized by the features described herein. (Note 5) The aforementioned reception unit is It estimates the user's emotions and determines the priority of questions and instructions to accept based on those estimated emotions. The system described in Appendix 1, characterized by the features described herein. (Note 6) The aforementioned reception unit is When receiving questions or instructions, the system prioritizes receiving questions and instructions that are highly relevant, taking into account the user's geographical location. The system described in Appendix 1, characterized by the features described herein. (Note 7) The aforementioned reception unit is When receiving questions or instructions, the system analyzes the user's social media activity and accepts relevant questions or instructions. The system described in Appendix 1, characterized by the features described herein. (Note 8) The aforementioned analysis unit, It estimates the user's emotions and adjusts the analysis method based on the estimated user emotions. The system described in Appendix 1, characterized by the features described herein. (Note 9) The aforementioned analysis unit, During analysis, adjust the level of detail based on the importance of the questions and instructions. The system described in Appendix 1, characterized by the features described herein. (Note 10) The aforementioned analysis unit, During analysis, different analysis algorithms are applied depending on the category of the question or instruction. The system described in Appendix 1, characterized by the features described herein. (Note 11) The aforementioned analysis unit, The system estimates the user's emotions and determines the priority of analysis based on the estimated emotions. The system described in Appendix 1, characterized by the features described herein. (Note 12) The aforementioned analysis unit, During the analysis, the priority of the analysis will be determined based on when questions and instructions were submitted. The system described in Appendix 1, characterized by the features described herein. (Note 13) The aforementioned analysis unit, During analysis, the order of analysis is adjusted based on the relevance of the questions and instructions. The system described in Appendix 1, characterized by the features described herein. (Note 14) The generating unit is It estimates the user's emotions and adjusts the way responses are expressed based on those estimated emotions. The system described in Appendix 1, characterized by the features described herein. (Note 15) The generating unit is When generating a response, adjust the level of detail in the response based on the importance of the question or instruction. The system described in Appendix 1, characterized by the features described herein. (Note 16) The generating unit is When generating responses, different response algorithms are applied depending on the category of the question or instruction. The system described in Appendix 1, characterized by the features described herein. (Note 17) The generating unit is It estimates the user's emotions and adjusts the length of the response based on the estimated emotions. The system described in Appendix 1, characterized by the features described herein. (Note 18) The generating unit is When generating responses, the system prioritizes responses based on when the questions or instructions were submitted. The system described in Appendix 1, characterized by the features described herein. (Note 19) The generating unit is When generating responses, the order of responses is adjusted based on the relevance of the questions and instructions. The system described in Appendix 1, characterized by the features described herein. (Note 20) The aforementioned supply unit is, It estimates the user's emotions and adjusts the way responses are delivered based on those estimated emotions. The system described in Appendix 1, characterized by the features described herein. (Note 21) The aforementioned supply unit is, When providing a response, the system selects the optimal method of delivery by referring to the user's past conversation history. The system described in Appendix 1, characterized by the features described herein. (Note 22) The aforementioned supply unit is, When providing a response, customize the method of providing the response based on the user's current situation. The system described in Appendix 1, characterized by the features described herein. (Note 23) The aforementioned supply unit is, It estimates the user's emotions and determines the priority of response delivery based on the estimated user emotions. The system described in Appendix 1, characterized by the features described herein. (Note 24) The aforementioned supply unit is, When providing a response, the optimal delivery method is selected considering the user's geographical location. The system described in Appendix 1, characterized by the features described herein. (Note 25) The aforementioned supply unit is, When providing a response, we analyze the user's social media activity and suggest a method for providing the response. The system described in Appendix 1, characterized by the features described herein. (Note 26) The aforementioned learning unit, The system estimates the user's emotions and selects training data based on those estimated emotions. The system described in Appendix 1, characterized by the features described herein. (Note 27) The aforementioned learning unit, During training, the learning algorithm is optimized by referring to past training data. The system described in Appendix 1, characterized by the features described herein. (Note 28) The aforementioned learning unit, During training, the accuracy of the learning process is improved by considering the user's profile information. The system described in Appendix 1, characterized by the features described herein. (Note 29) The aforementioned learning unit, It estimates the user's emotions and adjusts the learning frequency based on the estimated user emotions. The system described in Appendix 1, characterized by the features described herein. (Note 30) The aforementioned learning unit, During training, the training data is weighted based on when the dialogue history was submitted. The system described in Appendix 1, characterized by the features described herein. (Note 31) The aforementioned learning unit, During training, the system improves the accuracy of learning by referencing relevant literature from the user. The system described in Appendix 1, characterized by the features described herein. [Explanation of symbols]

[0185] 10, 210, 310, 410 Data Processing Systems 12 Data Processing Devices 14 Smart Devices 214 Smart Glasses 314 Headset-type terminal 414 Robots

Claims

1. A reception desk that receives questions and instructions from users, An analysis unit that analyzes the information received by the reception unit, A generation unit that generates a response based on the information analyzed by the analysis unit, A providing unit that provides the response generated by the generation unit to the user, The system includes a learning unit that learns based on the response provided by the aforementioned providing unit. A system characterized by the following features.

2. The aforementioned reception unit is It estimates the user's emotions and adjusts the timing of receiving questions and instructions based on the estimated user emotions. The system according to feature 1.

3. The aforementioned reception unit is Analyze the user's past question history and select the most suitable method of handling inquiries. The system according to feature 1.

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

5. The aforementioned reception unit is It estimates the user's emotions and determines the priority of questions and instructions to accept based on those estimated emotions. The system according to feature 1.

6. The aforementioned reception unit is When receiving questions or instructions, the system prioritizes receiving questions and instructions that are highly relevant, taking into account the user's geographical location. The system according to feature 1.

7. The aforementioned reception unit is When receiving questions or instructions, the system analyzes the user's social media activity and accepts relevant questions or instructions. The system according to feature 1.

8. The aforementioned analysis unit, It estimates the user's emotions and adjusts the analysis method based on the estimated user emotions. The system according to feature 1.

9. The aforementioned analysis unit, During analysis, adjust the level of detail based on the importance of the questions and instructions. The system according to feature 1.

10. The aforementioned analysis unit, During analysis, different analysis algorithms are applied depending on the category of the question or instruction. The system according to feature 1.

Images