system

Abstract

The system according to this embodiment aims to allow the user to choose whether or not to refer to past interactions. [Solution] The system according to the embodiment comprises a reception unit, a selection unit, a generation unit, and a citation unit. The reception unit receives instructions from the user. The selection unit selects whether to refer to past interactions based on the instructions received by the reception unit. The generation unit generates a response based on the information selected by the selection unit. The citation unit cites past interactions in the response generated by the generation 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 in response to the user utterance.

Prior Art Documents

Patent Documents

[0003]

Patent Document 1

Summary of the Invention

Problems to be Solved by the Invention

[0004] In the prior art, there is a problem that since the generative AI resets the past conversation and answers new questions, it cannot handle the case where a consistent answer is required.

[0005] The system according to the embodiment aims to enable a user to select whether to refer to past conversations.

Means for Solving the Problems

[0006] The system according to this embodiment comprises a reception unit, a selection unit, a generation unit, and a citation unit. The reception unit receives instructions from the user. The selection unit selects whether to refer to past interactions based on the instructions received by the reception unit. The generation unit generates a response based on the information selected by the selection unit. The citation unit cites past interactions in the response generated by the generation unit. [Effects of the Invention]

[0007] The system according to this embodiment can allow the user to choose whether or not to refer to past interactions. [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 labeled communication I / F (Interface) is an interface including a communication processor, an antenna, and the like. The communication I / F controls communication between a plurality of computers. Examples of communication standards applied to the communication I / F include wireless communication standards including 5G (5th Generation Mobile Communication System), Wi-Fi (registered trademark), or Bluetooth (registered trademark).

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

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

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

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

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

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

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

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

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

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

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

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

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

[0028] (Example of form 1) The generation AI system according to an embodiment of the present invention provides a function that allows the user to choose whether or not to refer to past interactions for each instruction, and allows the user to arbitrarily switch between "answer mode based on past interactions." The generation AI system provides a function that allows the user to choose whether or not to refer to past interactions for each instruction, and allows the user to arbitrarily switch between "answer mode based on past interactions." In addition, the generation AI system adds a quoting function, like a communication tool, so that other interactions can be quoted. If the user wants to reset past interactions and get an answer, they can simply open a new chat as before. For example, when a user enters a question to the generation AI, the user can choose whether or not to refer to past interactions. For example, if the user enters "Based on our last conversation, please tell me the next step," the generation AI will refer to past interactions and generate an answer. On the other hand, if the user enters "I have a new question," the generation AI will reset past interactions and answer a new question. Next, the generation AI will decide whether or not to refer to past interactions based on the user's selection. If past interactions are to be referred to, the generation AI will analyze the past conversation history and extract relevant information. For example, if a user inputs "Please tell me the progress of the last project," the generating AI extracts information about the project's progress from past conversation history and generates an answer. Furthermore, the generating AI provides a quoting function. Users can reuse specific information by quoting past interactions. For example, if a user inputs "Please quote the points mentioned in our last conversation," the generating AI quotes the relevant parts from past conversation history and includes them in the answer. This mechanism allows users to obtain consistent answers and efficiently utilize past interactions. In addition, by using the quoting function, users can easily reuse necessary information and reduce the effort required for input. For example, business professionals can obtain consistent answers by referring to past interactions when checking project progress. Also, educators and researchers can maintain the necessary past context when conducting long-term interactions.Furthermore, creative writers and content creators can efficiently reuse information when creating new content by referencing past ideas. In this way, generative AI systems are expected to be used in various fields by improving user convenience and providing consistent answers. This allows generative AI systems to refer to past interactions based on user instructions and generate consistent answers.

[0029] The generation AI system according to the embodiment comprises a reception unit, a selection unit, a generation unit, and a citation unit. The reception unit receives user instructions. User instructions include, but are not limited to, voice instructions, text instructions, and gesture instructions. The reception unit receives voice instructions using, for example, voice recognition technology. The reception unit can also receive text instructions using a text input interface. Furthermore, the reception unit can also receive gesture instructions using gesture recognition technology. For example, the reception unit converts the user's voice instructions into text using voice recognition technology and inputs them into the system. The text input interface allows the user to input text instructions using a keyboard or touchscreen. Gesture recognition technology analyzes the user's hand movements and facial expressions and recognizes them as instructions. The selection unit selects whether to refer to past interactions based on the instructions received by the reception unit. The selection unit decides whether to refer to past interactions based, for example, the user's past selection history and current situation. For example, if the user previously instructed "based on our previous conversation," the selection unit will refer to past interactions. Furthermore, the selection unit resets past interactions when the user instructs "I will ask a new question." The selection unit saves the user's selection history to a database, which can be used as a reference for future selections. The generation unit generates answers based on the information selected by the selection unit. The generation unit generates answers using, for example, a generative AI. The generative AI can generate answers in natural language using a text generation AI (e.g., LLM). The generation unit can also generate answers based on user instructions using the generative AI. For example, the generation unit inputs the prompt "Based on our last conversation, please tell me the next step," and the generative AI generates an answer. The generation unit provides the user with the answer generated by the generative AI. The quoting unit quotes past interactions in the answers generated by the generation unit. The quoting unit, for example, analyzes past conversation history, extracts relevant information, and includes it in the answer. If the user instructs "Please quote the points mentioned in the last conversation," the quoting unit quotes the relevant parts from the past conversation history.The citation section allows you to set criteria for selecting quoted sections and the format of the citation. For example, the citation section extracts keywords from past conversation history and quotes relevant information. The citation section highlights the quoted sections so that users can easily identify the quoted parts. As a result, the generation AI system according to the embodiment can refer to past interactions based on user instructions and generate consistent responses.

[0030] The reception unit receives user instructions. User instructions include, but are not limited to, voice instructions, text instructions, and gesture instructions. The reception unit can receive voice instructions using, for example, speech recognition technology. Specifically, speech recognition technology analyzes the speech signal and identifies phonemes and words in order to convert the user's voice into text. This ensures that what the user says is accurately transcribed and entered into the system. The reception unit can also receive text instructions using a text input interface. A text input interface allows the user to input text instructions using a keyboard or touchscreen. For example, if the user types a question using a keyboard, the reception unit receives the text and sends it to the system. Furthermore, the reception unit can also receive gesture instructions using gesture recognition technology. Gesture recognition technology analyzes the user's hand movements and facial expressions and recognizes them as instructions. For example, if the user waves their hand, the reception unit recognizes the movement as a specific instruction and enters it into the system. This allows the reception unit to support a variety of input methods, including voice, text, and gestures, enabling users to input instructions in the way that is most convenient for them. Furthermore, the reception unit can combine these input methods; for example, by simultaneously accepting voice and gesture instructions, it can achieve more intuitive and efficient operation.

[0031] The selection unit chooses whether to refer to past interactions based on the instructions received by the reception unit. For example, the selection unit decides whether to refer to past interactions based on the user's past selection history and current situation. Specifically, the selection unit stores the user's past instructions and selection history in a database for reference during future selections. For example, if the user previously instructed "Based on our previous conversation," the selection unit will refer to that history and generate an answer based on the past interaction. Also, if the user instructed "I have a new question," the selection unit will reset the past interactions and generate an answer based on the new information. The selection unit analyzes the user's selection history and uses algorithms to accurately understand the user's intent. For example, the selection unit can learn the user's past selection patterns and predict in what situations the user prefers to refer to past interactions. This allows the selection unit to make the optimal choice according to the user's intent and improve the system's response accuracy. Furthermore, the selection unit can dynamically decide whether to refer to past interactions, taking into account the user's current situation and context. For example, if the user is asking a question about a specific project, the selection unit will prioritize referring to past interactions related to that project. This allows the selection unit to respond flexibly to user needs, thereby improving the usability of the system.

[0032] The generation unit generates responses based on the information selected by the selection unit. The generation unit generates responses using, for example, a generative AI. The generative AI can generate responses in natural language using a text generation AI (e.g., LLM). Specifically, the generation unit inputs a prompt to the generative AI, and the generative AI generates a response based on that prompt. For example, the generation unit inputs the prompt, "Based on our previous conversation, please tell me the next step," to the generative AI, and the generative AI generates an appropriate response based on that prompt. Because the generative AI has learned from a large amount of text data and excels at generating responses in natural language, it can provide high-quality responses to user instructions. Before providing the response generated by the generative AI to the user, the generation unit can review the content of the response and make corrections as needed. For example, the generation unit checks whether the response generated by the generative AI matches the user's intent and checks whether it contains misleading expressions or inappropriate content. This allows the generation unit to provide accurate and reliable responses to the user. Furthermore, the generation unit regularly updates the generative AI's training data so that it can generate responses based on the latest information and trends. This allows the generation unit to consistently provide high-quality answers based on the latest information, thereby improving user satisfaction.

[0033] The quoting section quotes past conversations in the response generated by the generating section. For example, the quoting section analyzes past conversation history, extracts relevant information, and includes it in the response. Specifically, the quoting section extracts keywords from past conversation history and quotes relevant information. For example, if a user instructs, "Please quote the points mentioned in the previous conversation," the quoting section searches the past conversation history for the relevant portion and includes it in the response. The quoting section can set criteria for selecting quoted sections and the format of the quotations. For example, the quoting section extracts important keywords and phrases from past conversation history and highlights them, making it easy for users to identify quoted sections. The quoting section also standardizes the format of quoted sections, ensuring that users receive consistent information. This allows the quoting section to refer to past conversations based on user instructions and generate consistent responses. Furthermore, the quoting section uses algorithms to efficiently search past conversations. For example, the quoting section can use natural language processing techniques to analyze past conversation history and quickly extract relevant information. This allows the quoting section to respond quickly and accurately to user instructions, improving the system's response speed. Furthermore, the quoted section can continuously improve its selection criteria and format based on user feedback. This allows the quoted section to provide users with more appropriate and satisfying answers.

[0034] The generation unit includes an analysis unit that analyzes past conversation history and extracts relevant information. The analysis unit analyzes past conversation history using, for example, text mining technology. The analysis unit extracts relevant information from past conversation history and provides it to the generation unit. For example, the analysis unit extracts frequently occurring keywords from past conversation history and identifies relevant information. The analysis unit can also analyze past conversation history and extract relevant information using machine learning algorithms. For example, the analysis unit clusters past conversation history using machine learning algorithms and identifies relevant information. The analysis unit provides the extracted information to the generation unit, which generates a response based on that information. In this way, the generation unit can extract relevant information and generate a more appropriate response by analyzing past conversation history. Some or all of the above processing in the analysis unit may be performed using, for example, a generation AI, or without a generation AI. For example, the analysis unit can input past conversation history into a generation AI and have the generation AI perform the extraction of relevant information.

[0035] The quoting section includes an identification section that identifies information to quote from past exchanges. The identification section analyzes past exchanges using, for example, keyword matching technology to identify information to quote. The identification section extracts relevant information from past exchanges and provides it to the quoting section. For example, the identification section extracts portions containing specific keywords from past exchanges and provides them to the quoting section. The identification section can also analyze past exchanges using context analysis technology to identify information to quote. For example, the identification section analyzes the context of past exchanges and identifies relevant information. The identification section provides the extracted information to the quoting section, and the quoting section includes the quote in its response based on that information. This improves the accuracy of the quote by allowing the quoting section to identify information to quote from past exchanges. Some or all of the above processing in the identification section may be performed using, for example, a generative AI, or without a generative AI. For example, the identification section can input past exchanges into a generative AI and have the generative AI perform the identification of information to quote.

[0036] The selection unit allows the user to choose whether or not to refer to past interactions. The selection unit makes this decision based, for example, on the user's past selection history and current situation. The selection unit can save the user's selection history to a database and refer to it for future selections. For example, if the user has previously instructed the selection unit to "consider our previous conversation," the selection unit will refer to past interactions. Also, if the user instructs the selection unit to "ask a new question," the selection unit will reset past interactions. The selection unit analyzes the user's selection history and decides whether or not to refer to past interactions. This allows the selection unit to maintain consistency in its responses by allowing the user to choose whether or not to refer to past interactions. Some or all of the above processing in the selection unit may be performed using, for example, a generative AI, or not. For example, the selection unit can input the user's selection history into a generative AI and have the generative AI make the decision on whether or not to refer to past interactions.

[0037] The generation unit generates a response based on user instructions. The generation unit generates a response using, for example, a generation AI. The generation AI can generate a response in natural language using a text generation AI (e.g., LLM). The generation unit uses the generation AI to generate a response based on user instructions. For example, the generation unit inputs the prompt "Based on our previous conversation, please tell me the next step" to the generation AI, and the generation AI generates a response. The generation unit provides the user with the response generated by the generation AI. In this way, the generation unit can provide a response that meets the user's request by generating a response based on the user's instructions. Some or all of the above processing in the generation unit may be performed using, for example, a generation AI, or without using a generation AI. For example, the generation unit can input user instructions to the generation AI and have the generation AI perform the generation of a response.

[0038] The quoted section includes quotes from past conversations in its responses. For example, the quoted section analyzes past conversation history, extracts relevant information, and includes it in its responses. If a user instructs the quoted section to "quote points mentioned in the previous conversation," the quoted section will quote the relevant parts from the past conversation history. The quoted section can set criteria for selecting quotes and formatting the quotes. For example, the quoted section can extract keywords from past conversation history and quote relevant information. The quoted section highlights the quoted sections to make them easily identifiable to the user. This allows the quoted section to maintain consistency in its responses by including quotes from past conversations. Some or all of the above processing in the quoted section may be performed using, for example, a generative AI, or not. For example, the quoted section can input past conversation history into a generative AI and have the generative AI extract the information to be quoted.

[0039] The reception desk analyzes the user's past instruction history and proposes the optimal reception method. For example, the reception desk saves past instruction history to a database for reference during subsequent reception. The reception desk automatically displays instructions that the user has frequently entered in the past as suggestions. For example, the reception desk prioritizes suggesting input methods (voice, text, etc.) that the user has used in the past. The reception desk can also predict and suggest instructions to be used during specific time periods based on the user's past instruction history. In this way, the reception desk can propose the optimal reception method by analyzing the user's past instruction history. Some or all of the above processing in the reception desk may be performed using, for example, a generative AI, or not using a generative AI. For example, the reception desk can input the user's past instruction history into a generative AI and have the generative AI propose the optimal reception method.

[0040] The reception unit filters the user's current situation and areas of interest upon receiving the request. For example, when the user enters their current situation, the reception unit prioritizes displaying relevant instructions. The reception unit filters and displays relevant instructions based on the user's areas of interest. For example, the reception unit suggests the most appropriate instructions according to the user's current situation. In this way, the reception unit can prioritize receiving highly relevant instructions by filtering based on the user's current situation and areas of interest. Some or all of the above processing in the reception unit may be performed using, for example, a generative AI, or without a generative AI. For example, the reception unit can input the user's current situation and areas of interest into a generative AI and have the generative AI perform the filtering.

[0041] The reception unit, upon receiving a request, prioritizes receiving 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 unit prioritizes receiving instructions related to that location. The reception unit proposes the most appropriate instructions based on the user's current location. For example, the reception unit prioritizes receiving instructions that are highly relevant, taking into account the user's geographical location. This allows the reception unit to prioritize receiving instructions that are highly relevant by considering the user's geographical location. Some or all of the above processing in the reception unit may be performed using, for example, a generative AI, or without a generative AI. For example, the reception unit can input the user's geographical location information into a generative AI and have the generative AI prioritize highly relevant instructions.

[0042] The reception unit analyzes the user's social media activity upon receiving a request and receives relevant instructions. For example, the reception unit extracts and receives relevant instructions from the user's social media activity. The reception unit analyzes the user's social media activity and proposes the most appropriate instructions. For example, the reception unit prioritizes receiving relevant instructions based on the user's social media activity. This allows the reception unit to prioritize receiving relevant instructions by analyzing the user's social media activity. Some or all of the above processing in the reception unit may be performed using, for example, a generative AI, or without a generative AI. For example, the reception unit can input the user's social media activity into a generative AI and have the generative AI extract relevant instructions.

[0043] The selection unit, when making a selection, refers to the user's past selection history to present the most suitable options. For example, the selection unit can save the past selection history to a database and refer to it for future selections. The selection unit presents the most suitable options based on the options the user has previously selected. For example, the selection unit can prioritize presenting relevant options from the user's past selection history. The selection unit can also analyze the user's past selection history and present the most suitable options. In this way, the selection unit can present the most suitable options by referring to the past selection history. Some or all of the above processing in the selection unit may be performed using, for example, a generative AI, or without a generative AI. For example, the selection unit can input the user's past selection history into a generative AI and have the generative AI perform the task of presenting the most suitable options.

[0044] The selection unit customizes the options based on the user's current situation when an option is selected. For example, the selection unit customizes and presents the optimal option according to the user's current situation. The selection unit prioritizes presenting relevant options, taking into account the user's current situation. For example, the selection unit customizes and presents options based on the user's current situation. In this way, the selection unit can provide the optimal option by customizing the options based on the user's current situation. Some or all of the above processing in the selection unit may be performed using, for example, a generative AI, or without a generative AI. For example, the selection unit can input the user's current situation into a generative AI and have the generative AI perform the customization of the options.

[0045] The selection unit presents the optimal options when a selection is made, taking into account the user's geographical location information. For example, the selection unit presents the optimal options based on the user's current location. The selection unit prioritizes presenting relevant options, taking into account the user's geographical location information. For example, the selection unit presents the optimal options according to the user's current location. In this way, the selection unit can present the optimal options by taking into account the user's geographical location information. Some or all of the above processing in the selection unit may be performed using, for example, a generative AI, or without a generative AI. For example, the selection unit can input the user's geographical location information into a generative AI and have the generative AI perform the task of presenting the optimal options.

[0046] The selection unit analyzes the user's social media activity and presents options when a selection is made. For example, the selection unit extracts and presents relevant options from the user's social media activity. The selection unit analyzes the user's social media activity and presents the optimal option. For example, the selection unit prioritizes presenting relevant options based on the user's social media activity. In this way, the selection unit can prioritize presenting relevant options by analyzing the user's social media activity. Some or all of the above processing in the selection unit may be performed using, for example, a generative AI, or without a generative AI. For example, the selection unit can input the user's social media activity into a generative AI and have the generative AI extract relevant options.

[0047] The generation unit extracts relevant information by referring to past conversation history during generation. For example, the generation unit saves past conversation history to a database for reference during the next generation. The generation unit generates the optimal answer based on information the user has used in the past. For example, the generation unit prioritizes extracting relevant information from the user's past conversation history. The generation unit can also analyze the user's past conversation history, extract the most appropriate information, and generate an answer. In this way, the generation unit can extract relevant information by referring to past conversation history and generate a more appropriate answer. Some or all of the above processing in the generation unit may be performed using, for example, a generation AI, or without a generation AI. For example, the generation unit can input the user's past conversation history into a generation AI and have the generation AI perform the extraction of relevant information.

[0048] The generation unit adjusts the level of detail in the response based on user instructions during generation. The generation unit generates the response using, for example, a generation AI. The generation AI can generate the response in natural language using a text generation AI (e.g., LLM). The generation unit uses the generation AI to adjust the level of detail in the response based on user instructions. For example, the generation unit can input the prompt "Please provide detailed information" to the generation AI, and the generation AI will generate a detailed response. Alternatively, the generation unit can input the prompt "Please provide concise information" to the generation AI, and the generation AI will generate a concise response. In this way, the generation unit can provide a response that meets the user's request by adjusting the level of detail in the response based on user instructions. Some or all of the above processing in the generation unit may be performed using, for example, a generation AI, or without using a generation AI. For example, the generation unit can input user instructions to the generation AI and have the generation AI adjust the level of detail in the response.

[0049] The generation unit determines the priority of answers based on the user's past instruction history during generation. For example, the generation unit saves the past instruction history to a database and uses it as a reference during the next generation. The generation unit generates the optimal answer based on the instructions the user has used in the past. For example, the generation unit prioritizes extracting relevant information from the user's past instruction history. The generation unit can also analyze the user's past instruction history, extract the most appropriate information, and generate an answer. In this way, the generation unit can prioritize important answers by determining the priority of answers based on the user's past instruction history. Some or all of the above processing in the generation unit may be performed using a generation AI, for example, or without a generation AI. For example, the generation unit can input the user's past instruction history into a generation AI and have the generation AI perform the determination of answer priorities.

[0050] The generation unit generates answers by referring to the user's relevant activity history during the generation process. For example, the generation unit saves past activity history to a database for reference during the next generation. The generation unit generates the optimal answer based on the user's past activities. For example, the generation unit prioritizes extracting relevant information from the user's past activity history. The generation unit can also analyze the user's past activity history, extract the most appropriate information, and generate an answer. This allows the generation unit to generate more appropriate answers by referring to the user's relevant activity history. Some or all of the above processing in the generation unit may be performed using, for example, a generation AI, or without a generation AI. For example, the generation unit can input the user's past activity history into a generation AI and have the generation AI extract relevant information.

[0051] The citation function analyzes past interactions to identify the optimal citation location when quoting. For example, it can save past interactions to a database for reference during future citations. The citation function identifies the optimal citation location based on information previously used by the user. For example, it prioritizes extracting relevant information from the user's past interactions. It can also analyze the user's past interactions to identify the most appropriate citation location. In this way, the citation function can identify the optimal citation location and improve the accuracy of citations by analyzing past interactions. Some or all of the above processing in the citation function may be performed using, for example, a generative AI, or without a generative AI. For example, the citation function can input the user's past interactions into a generative AI and have the generative AI identify the optimal citation location.

[0052] The citation function adjusts the level of detail of a citation based on user instructions when citing. For example, the citation function can store user instructions in a database for reference the next time a citation is made. If the user requests a detailed citation, the citation function provides a detailed citation. For example, if the user requests a concise citation, the citation function provides a concise citation. The citation function can also adjust the level of detail of a citation based on user instructions. In this way, the citation function can provide citations that meet user requests by adjusting the level of detail of citations based on user instructions. Some or all of the above processing in the citation function may be performed using, for example, a generative AI, or not using a generative AI. For example, the citation function can input user instructions into a generative AI and have the generative AI perform the adjustment of the level of detail of the citation.

[0053] The citation function identifies the optimal citation location by considering the user's geographical location information at the time of citation. For example, the citation function stores the user's geographical location information in a database and refers to it the next time a citation is made. If the user is in a specific location, the citation function prioritizes citing information related to that location. For example, the citation function identifies the optimal citation location based on the user's current location. The citation function can also prioritize citing relevant information by considering the user's geographical location information. In this way, the citation function can identify the optimal citation location and improve the accuracy of citations by considering the user's geographical location information. Some or all of the above processing in the citation function may be performed using, for example, a generative AI, or without a generative AI. For example, the citation function can input the user's geographical location information into a generative AI and have the generative AI identify the optimal citation location.

[0054] The citation function analyzes the user's social media activity to identify the appropriate citation location. For example, the citation function can save the user's social media activity to a database for reference during future citations. The citation function extracts relevant information from the user's social media activity and cites it. For example, the citation function analyzes the user's social media activity to identify the most appropriate citation location. The citation function can also prioritize citing relevant information based on the user's social media activity. This allows the citation function to identify the most appropriate citation location and improve the accuracy of citations by analyzing the user's social media activity. Some or all of the above processing in the citation function may be performed using, for example, a generative AI, or without a generative AI. For example, the citation function can input the user's social media activity into a generative AI and have the generative AI identify the most appropriate citation location.

[0055] The analysis unit extracts relevant information by referring to past conversation history during analysis. For example, the analysis unit saves past conversation history to a database for reference during subsequent analyses. The analysis unit performs optimal analysis based on information previously used by the user. For example, the analysis unit prioritizes extracting relevant information from the user's past conversation history. The analysis unit can also analyze the user's past conversation history and extract the most appropriate information for analysis. This allows the analysis unit to extract relevant information by referring to past conversation history and perform more appropriate analysis. Some or all of the above processing in the analysis unit may be performed using, for example, a generative AI, or without a generative AI. For example, the analysis unit can input the user's past conversation history into a generative AI and have the generative AI extract relevant information.

[0056] The analysis unit adjusts the level of detail of the analysis based on user instructions during the analysis. The analysis unit performs the analysis using, for example, a generative AI. The generative AI can perform analysis in natural language using a text generation AI (e.g., LLM). The analysis unit uses the generative AI to adjust the level of detail of the analysis based on user instructions. For example, the analysis unit inputs a prompt to the generative AI saying, "Please perform a detailed analysis," and the generative AI performs a detailed analysis. Alternatively, the analysis unit can input a prompt to the generative AI saying, "Please perform a concise analysis," and the generative AI performs a concise analysis. In this way, the analysis unit can perform analysis according to user requests by adjusting the level of detail of the analysis based on user instructions. Some or all of the above processing in the analysis unit may be performed using, for example, a generative AI, or without using a generative AI. For example, the analysis unit can input user instructions to the generative AI and have the generative AI adjust the level of detail of the analysis.

[0057] The analysis unit selects the optimal analysis method during analysis, taking into account the user's geographical location information. For example, the analysis unit saves the user's geographical location information to a database for reference during subsequent analyses. If the user is in a specific location, the analysis unit prioritizes analyzing information related to that location. For example, the analysis unit selects the optimal analysis method based on the user's current location. The analysis unit can also prioritize the analysis of relevant information by taking into account the user's geographical location information. This allows the analysis unit to select the optimal analysis method and improve the accuracy of the analysis by considering the user's geographical location information. Some or all of the above processing in the analysis unit may be performed using, for example, a generative AI, or without a generative AI. For example, the analysis unit can input the user's geographical location information into a generative AI and have the generative AI select the optimal analysis method.

[0058] The analysis unit analyzes the user's social media activity during analysis and selects an analysis method. For example, the analysis unit saves the user's social media activity to a database for reference during subsequent analyses. The analysis unit extracts relevant information from the user's social media activity and performs analysis. For example, the analysis unit analyzes the user's social media activity and selects the optimal analysis method. The analysis unit can also prioritize the analysis of relevant information based on the user's social media activity. This allows the analysis unit to select the optimal analysis method by analyzing the user's social media activity and improve the accuracy of the analysis. Some or all of the above processes in the analysis unit may be performed using, for example, a generative AI, or without a generative AI. For example, the analysis unit can input the user's social media activity into a generative AI and have the generative AI select the optimal analysis method.

[0059] The identification unit, at the time of identification, analyzes past interactions to select the optimal identification location. The identification unit, for example, saves past interactions to a database for reference during the next identification. The identification unit selects the optimal identification location based on information previously used by the user. For example, the identification unit prioritizes extracting relevant information from the user's past interactions. The identification unit can also analyze the user's past interactions and select the most suitable identification location. In this way, the identification unit can improve the accuracy of identification by selecting the optimal identification location through analysis of past interactions. Some or all of the above processing in the identification unit may be performed using, for example, a generative AI, or without a generative AI. For example, the identification unit can input the user's past interactions into a generative AI and have the generative AI select the optimal identification location.

[0060] The identification unit adjusts the level of detail of the identification based on the user's instructions during the identification process. For example, the identification unit saves the user's instructions to a database for reference during subsequent identifications. If the user requests detailed identification, the identification unit performs detailed identification. For example, if the user requests concise identification, the identification unit performs concise identification. The identification unit can also adjust the level of detail of the identification based on the user's instructions. In this way, the identification unit can perform identification that meets the user's requirements by adjusting the level of detail of the identification based on the user's instructions. Some or all of the above-described processes in the identification unit may be performed using, for example, a generating AI, or not using a generating AI. For example, the identification unit can input the user's instructions into a generating AI and have the generating AI perform the adjustment of the level of detail of the identification.

[0061] The identification unit selects the optimal location by considering the user's geographical location information during identification. For example, the identification unit stores the user's geographical location information in a database for reference during subsequent identification. If the user is in a specific location, the identification unit prioritizes identifying information related to that location. For example, the identification unit selects the optimal location based on the user's current location. The identification unit can also prioritize identifying related information by considering the user's geographical location information. This allows the identification unit to select the optimal location and improve the accuracy of identification by considering the user's geographical location information. Some or all of the above processing in the identification unit may be performed using, for example, a generation AI, or without a generation AI. For example, the identification unit can input the user's geographical location information into a generation AI and have the generation AI select the optimal location.

[0062] The identification unit analyzes the user's social media activity at the time of identification to select a location to identify. The identification unit, for example, saves the user's social media activity to a database for reference during subsequent identification. The identification unit extracts relevant information from the user's social media activity and identifies it. For example, the identification unit analyzes the user's social media activity and selects the optimal location to identify. The identification unit can also prioritize the identification of relevant information based on the user's social media activity. This allows the identification unit to select the optimal location by analyzing the user's social media activity and improve the accuracy of identification. Some or all of the above processing in the identification unit may be performed using, for example, a generative AI, or without a generative AI. For example, the identification unit can input the user's social media activity into a generative AI and have the generative AI select the optimal location to identify.

[0063] The identification unit, at the time of identification, refers to the user's calendar information to perform identification based on the schedule. The identification unit, for example, saves the user's calendar information to a database for reference during the next identification. The identification unit refers to the schedule registered in the user's calendar and identifies relevant information. For example, the identification unit prioritizes identifying information related to a specific event from the user's calendar information. The identification unit can also select the optimal identification location based on the schedule based on the user's calendar information. In this way, the identification unit can improve the accuracy of identification by selecting the optimal identification location based on the schedule by referring to the user's calendar information. Some or all of the above processing in the identification unit may be performed using, for example, a generation AI, or without a generation AI. For example, the identification unit can input the user's calendar information into a generation AI and have the generation AI perform identification based on the schedule.

[0064] The system according to the embodiment is not limited to the example described above, and various modifications are possible, for example, as follows.

[0065] Generative AI systems can further analyze a user's past behavior history and be equipped with the ability to customize answers based on the user's interests. For example, if a user has asked many questions on a particular topic in the past, the generative AI can prioritize providing information related to that topic. Also, if a user tends to ask certain types of questions at certain times of the day, the generative AI can provide answers appropriate for that time of day. Furthermore, based on the user's past behavior history, the generative AI can suggest new information that the user might be interested in. In this way, generative AI systems can provide personalized answers that match the user's interests, thereby improving user satisfaction.

[0066] The generative AI system can also be equipped with the ability to customize responses by taking into account the user's geographical location. For example, if the user is in a specific location, it can prioritize providing information relevant to that location. If the user is traveling, the generative AI can also provide information about their travel destination. Furthermore, based on the user's current location, the generative AI can provide information about nearby events and facilities. This allows the generative AI system to provide appropriate information tailored to the user's geographical location, thereby improving user convenience.

[0067] The generative AI system can further analyze the user's social media activity and customize responses based on the user's interests. For example, if a user frequently posts about a particular topic on social media, the generative AI can prioritize providing information related to that topic. Similarly, if a user participates in a specific event, the generative AI can provide information related to that event. Furthermore, based on the user's social media activity, the generative AI can suggest new information that the user might be interested in. This allows the generative AI system to provide personalized responses tailored to the user's social media activity, thereby improving user satisfaction.

[0068] The generative AI system can also be equipped with the ability to customize its responses by referencing the user's calendar information. For example, based on appointments registered in the user's calendar, the generative AI can provide relevant information. Furthermore, if the user has plans to attend a specific event, the generative AI can provide information related to that event. In addition, based on the user's calendar information, the generative AI can suggest new events and activities that the user might be interested in. This allows the generative AI system to provide personalized responses tailored to the user's calendar information, thereby improving user satisfaction.

[0069] The generative AI system can further analyze the user's past instruction history and have the ability to prioritize answers based on the user's instructions. For example, if a user has asked many questions on a particular topic in the past, the generative AI can prioritize providing information related to that topic. Also, if a user tends to ask certain types of questions at certain times of the day, the generative AI can provide answers appropriate for that time of day. Furthermore, based on the user's past instruction history, the generative AI can suggest new information that the user might be interested in. In this way, the generative AI system can provide personalized answers that are tailored to the user's past instruction history, thereby improving user satisfaction.

[0070] The following briefly describes the processing flow for example form 1.

[0071] Step 1: The reception desk receives user instructions. User instructions include voice instructions, text instructions, and gesture instructions. For example, the reception desk receives voice instructions using voice recognition technology, text instructions using a text input interface, and gesture instructions using gesture recognition technology. Step 2: The selection unit chooses whether to refer to past interactions based on the instructions received by the reception unit. The selection unit makes this decision based on the user's past selection history and current situation. For example, if the user instructs "Considering our previous conversation," the selection unit will refer to past interactions; if the user instructs "I will ask a new question," the selection unit will reset past interactions. Step 3: The generation unit generates an answer based on the information selected by the selection unit. The generation unit generates the answer in natural language using a generation AI. For example, the generation unit inputs the prompt "Based on our previous conversation, please tell me the next step" into the generation AI and provides the generated answer to the user. Step 4: The quoting section quotes past conversations in the response generated by the generating section. The quoting section analyzes the past conversation history, extracts relevant information, and includes it in the response. For example, if the user instructs, "Please quote the points mentioned in the previous conversation," the quoting section will quote the relevant parts from the past conversation history.

[0072] (Example of form 2) The generation AI system according to an embodiment of the present invention provides a function that allows the user to choose whether or not to refer to past interactions for each instruction, and allows the user to arbitrarily switch between "answer mode based on past interactions." The generation AI system provides a function that allows the user to choose whether or not to refer to past interactions for each instruction, and allows the user to arbitrarily switch between "answer mode based on past interactions." In addition, the generation AI system adds a quoting function, like a communication tool, so that other interactions can be quoted. If the user wants to reset past interactions and get an answer, they can simply open a new chat as before. For example, when a user enters a question to the generation AI, the user can choose whether or not to refer to past interactions. For example, if the user enters "Based on our last conversation, please tell me the next step," the generation AI will refer to past interactions and generate an answer. On the other hand, if the user enters "I have a new question," the generation AI will reset past interactions and answer a new question. Next, the generation AI will decide whether or not to refer to past interactions based on the user's selection. If past interactions are to be referred to, the generation AI will analyze the past conversation history and extract relevant information. For example, if a user inputs "Please tell me the progress of the last project," the generating AI extracts information about the project's progress from past conversation history and generates an answer. Furthermore, the generating AI provides a quoting function. Users can reuse specific information by quoting past interactions. For example, if a user inputs "Please quote the points mentioned in our last conversation," the generating AI quotes the relevant parts from past conversation history and includes them in the answer. This mechanism allows users to obtain consistent answers and efficiently utilize past interactions. In addition, by using the quoting function, users can easily reuse necessary information and reduce the effort required for input. For example, business professionals can obtain consistent answers by referring to past interactions when checking project progress. Also, educators and researchers can maintain the necessary past context when conducting long-term interactions.Furthermore, creative writers and content creators can efficiently reuse information when creating new content by referencing past ideas. In this way, generative AI systems are expected to be used in various fields by improving user convenience and providing consistent answers. This allows generative AI systems to refer to past interactions based on user instructions and generate consistent answers.

[0073] The generation AI system according to the embodiment comprises a reception unit, a selection unit, a generation unit, and a citation unit. The reception unit receives user instructions. User instructions include, but are not limited to, voice instructions, text instructions, and gesture instructions. The reception unit receives voice instructions using, for example, voice recognition technology. The reception unit can also receive text instructions using a text input interface. Furthermore, the reception unit can also receive gesture instructions using gesture recognition technology. For example, the reception unit converts the user's voice instructions into text using voice recognition technology and inputs them into the system. The text input interface allows the user to input text instructions using a keyboard or touchscreen. Gesture recognition technology analyzes the user's hand movements and facial expressions and recognizes them as instructions. The selection unit selects whether to refer to past interactions based on the instructions received by the reception unit. The selection unit decides whether to refer to past interactions based, for example, the user's past selection history and current situation. For example, if the user previously instructed "based on our previous conversation," the selection unit will refer to past interactions. Furthermore, the selection unit resets past interactions when the user instructs "I will ask a new question." The selection unit saves the user's selection history to a database, which can be used as a reference for future selections. The generation unit generates answers based on the information selected by the selection unit. The generation unit generates answers using, for example, a generative AI. The generative AI can generate answers in natural language using a text generation AI (e.g., LLM). The generation unit can also generate answers based on user instructions using the generative AI. For example, the generation unit inputs the prompt "Based on our last conversation, please tell me the next step," and the generative AI generates an answer. The generation unit provides the user with the answer generated by the generative AI. The quoting unit quotes past interactions in the answers generated by the generation unit. The quoting unit, for example, analyzes past conversation history, extracts relevant information, and includes it in the answer. If the user instructs "Please quote the points mentioned in the last conversation," the quoting unit quotes the relevant parts from the past conversation history.The citation section allows you to set criteria for selecting quoted sections and the format of the citation. For example, the citation section extracts keywords from past conversation history and quotes relevant information. The citation section highlights the quoted sections so that users can easily identify the quoted parts. As a result, the generation AI system according to the embodiment can refer to past interactions based on user instructions and generate consistent responses.

[0074] The reception unit receives user instructions. User instructions include, but are not limited to, voice instructions, text instructions, and gesture instructions. The reception unit can receive voice instructions using, for example, speech recognition technology. Specifically, speech recognition technology analyzes the speech signal and identifies phonemes and words in order to convert the user's voice into text. This ensures that what the user says is accurately transcribed and entered into the system. The reception unit can also receive text instructions using a text input interface. A text input interface allows the user to input text instructions using a keyboard or touchscreen. For example, if the user types a question using a keyboard, the reception unit receives the text and sends it to the system. Furthermore, the reception unit can also receive gesture instructions using gesture recognition technology. Gesture recognition technology analyzes the user's hand movements and facial expressions and recognizes them as instructions. For example, if the user waves their hand, the reception unit recognizes the movement as a specific instruction and enters it into the system. This allows the reception unit to support a variety of input methods, including voice, text, and gestures, enabling users to input instructions in the way that is most convenient for them. Furthermore, the reception unit can combine these input methods; for example, by simultaneously accepting voice and gesture instructions, it can achieve more intuitive and efficient operation.

[0075] The selection unit chooses whether to refer to past interactions based on the instructions received by the reception unit. For example, the selection unit decides whether to refer to past interactions based on the user's past selection history and current situation. Specifically, the selection unit stores the user's past instructions and selection history in a database for reference during future selections. For example, if the user previously instructed "Based on our previous conversation," the selection unit will refer to that history and generate an answer based on the past interaction. Also, if the user instructed "I have a new question," the selection unit will reset the past interactions and generate an answer based on the new information. The selection unit analyzes the user's selection history and uses algorithms to accurately understand the user's intent. For example, the selection unit can learn the user's past selection patterns and predict in what situations the user prefers to refer to past interactions. This allows the selection unit to make the optimal choice according to the user's intent and improve the system's response accuracy. Furthermore, the selection unit can dynamically decide whether to refer to past interactions, taking into account the user's current situation and context. For example, if the user is asking a question about a specific project, the selection unit will prioritize referring to past interactions related to that project. This allows the selection unit to respond flexibly to user needs, thereby improving the usability of the system.

[0076] The generation unit generates responses based on the information selected by the selection unit. The generation unit generates responses using, for example, a generative AI. The generative AI can generate responses in natural language using a text generation AI (e.g., LLM). Specifically, the generation unit inputs a prompt to the generative AI, and the generative AI generates a response based on that prompt. For example, the generation unit inputs the prompt, "Based on our previous conversation, please tell me the next step," to the generative AI, and the generative AI generates an appropriate response based on that prompt. Because the generative AI has learned from a large amount of text data and excels at generating responses in natural language, it can provide high-quality responses to user instructions. Before providing the response generated by the generative AI to the user, the generation unit can review the content of the response and make corrections as needed. For example, the generation unit checks whether the response generated by the generative AI matches the user's intent and checks whether it contains misleading expressions or inappropriate content. This allows the generation unit to provide accurate and reliable responses to the user. Furthermore, the generation unit regularly updates the generative AI's training data so that it can generate responses based on the latest information and trends. This allows the generation unit to consistently provide high-quality answers based on the latest information, thereby improving user satisfaction.

[0077] The quoting section quotes past conversations in the response generated by the generating section. For example, the quoting section analyzes past conversation history, extracts relevant information, and includes it in the response. Specifically, the quoting section extracts keywords from past conversation history and quotes relevant information. For example, if a user instructs, "Please quote the points mentioned in the previous conversation," the quoting section searches the past conversation history for the relevant portion and includes it in the response. The quoting section can set criteria for selecting quoted sections and the format of the quotations. For example, the quoting section extracts important keywords and phrases from past conversation history and highlights them, making it easy for users to identify quoted sections. The quoting section also standardizes the format of quoted sections, ensuring that users receive consistent information. This allows the quoting section to refer to past conversations based on user instructions and generate consistent responses. Furthermore, the quoting section uses algorithms to efficiently search past conversations. For example, the quoting section can use natural language processing techniques to analyze past conversation history and quickly extract relevant information. This allows the quoting section to respond quickly and accurately to user instructions, improving the system's response speed. Furthermore, the quoted section can continuously improve its selection criteria and format based on user feedback. This allows the quoted section to provide users with more appropriate and satisfying answers.

[0078] The generation unit includes an analysis unit that analyzes past conversation history and extracts relevant information. The analysis unit analyzes past conversation history using, for example, text mining technology. The analysis unit extracts relevant information from past conversation history and provides it to the generation unit. For example, the analysis unit extracts frequently occurring keywords from past conversation history and identifies relevant information. The analysis unit can also analyze past conversation history and extract relevant information using machine learning algorithms. For example, the analysis unit clusters past conversation history using machine learning algorithms and identifies relevant information. The analysis unit provides the extracted information to the generation unit, which generates a response based on that information. In this way, the generation unit can extract relevant information and generate a more appropriate response by analyzing past conversation history. Some or all of the above processing in the analysis unit may be performed using, for example, a generation AI, or without a generation AI. For example, the analysis unit can input past conversation history into a generation AI and have the generation AI perform the extraction of relevant information.

[0079] The quoting section includes an identification section that identifies information to quote from past exchanges. The identification section analyzes past exchanges using, for example, keyword matching technology to identify information to quote. The identification section extracts relevant information from past exchanges and provides it to the quoting section. For example, the identification section extracts portions containing specific keywords from past exchanges and provides them to the quoting section. The identification section can also analyze past exchanges using context analysis technology to identify information to quote. For example, the identification section analyzes the context of past exchanges and identifies relevant information. The identification section provides the extracted information to the quoting section, and the quoting section includes the quote in its response based on that information. This improves the accuracy of the quote by allowing the quoting section to identify information to quote from past exchanges. Some or all of the above processing in the identification section may be performed using, for example, a generative AI, or without a generative AI. For example, the identification section can input past exchanges into a generative AI and have the generative AI perform the identification of information to quote.

[0080] The selection unit allows the user to choose whether or not to refer to past interactions. The selection unit makes this decision based, for example, on the user's past selection history and current situation. The selection unit can save the user's selection history to a database and refer to it for future selections. For example, if the user has previously instructed the selection unit to "consider our previous conversation," the selection unit will refer to past interactions. Also, if the user instructs the selection unit to "ask a new question," the selection unit will reset past interactions. The selection unit analyzes the user's selection history and decides whether or not to refer to past interactions. This allows the selection unit to maintain consistency in its responses by allowing the user to choose whether or not to refer to past interactions. Some or all of the above processing in the selection unit may be performed using, for example, a generative AI, or not. For example, the selection unit can input the user's selection history into a generative AI and have the generative AI make the decision on whether or not to refer to past interactions.

[0081] The generation unit generates a response based on user instructions. The generation unit generates a response using, for example, a generation AI. The generation AI can generate a response in natural language using a text generation AI (e.g., LLM). The generation unit uses the generation AI to generate a response based on user instructions. For example, the generation unit inputs the prompt "Based on our previous conversation, please tell me the next step" to the generation AI, and the generation AI generates a response. The generation unit provides the user with the response generated by the generation AI. In this way, the generation unit can provide a response that meets the user's request by generating a response based on the user's instructions. Some or all of the above processing in the generation unit may be performed using, for example, a generation AI, or without using a generation AI. For example, the generation unit can input user instructions to the generation AI and have the generation AI perform the generation of a response.

[0082] The quoted section includes quotes from past conversations in its responses. For example, the quoted section analyzes past conversation history, extracts relevant information, and includes it in its responses. If a user instructs the quoted section to "quote points mentioned in the previous conversation," the quoted section will quote the relevant parts from the past conversation history. The quoted section can set criteria for selecting quotes and formatting the quotes. For example, the quoted section can extract keywords from past conversation history and quote relevant information. The quoted section highlights the quoted sections to make them easily identifiable to the user. This allows the quoted section to maintain consistency in its responses by including quotes from past conversations. Some or all of the above processing in the quoted section may be performed using, for example, a generative AI, or not. For example, the quoted section can input past conversation history into a generative AI and have the generative AI extract the information to be quoted.

[0083] The reception unit estimates the user's emotions and adjusts the method of receiving instructions based on the estimated emotions. The reception unit estimates emotions from the user's voice, for example, using voice analysis technology. The reception unit analyzes the tone and speed of the user's voice and calculates an emotion score. For example, if the user is stressed, the reception unit provides a simple interface and minimizes the input steps. If the user is relaxed, the reception unit can also provide detailed input options and suggest customizable input methods. Furthermore, if the user is in a hurry, the reception unit prioritizes voice input to allow for quick instruction input. In this way, the reception unit can improve user convenience by adjusting the method of receiving instructions 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. Some or all of the above processing in the reception unit may be performed using, for example, generative AI, or not using generative AI. For example, the reception desk can input the user's voice data into a generating AI and have the AI ​​perform emotion estimation.

[0084] The reception desk analyzes the user's past instruction history and proposes the optimal reception method. For example, the reception desk saves past instruction history to a database for reference during subsequent reception. The reception desk automatically displays instructions that the user has frequently entered in the past as suggestions. For example, the reception desk prioritizes suggesting input methods (voice, text, etc.) that the user has used in the past. The reception desk can also predict and suggest instructions to be used during specific time periods based on the user's past instruction history. In this way, the reception desk can propose the optimal reception method by analyzing the user's past instruction history. Some or all of the above processing in the reception desk may be performed using, for example, a generative AI, or not using a generative AI. For example, the reception desk can input the user's past instruction history into a generative AI and have the generative AI propose the optimal reception method.

[0085] The reception unit filters the user's current situation and areas of interest upon receiving the request. For example, when the user enters their current situation, the reception unit prioritizes displaying relevant instructions. The reception unit filters and displays relevant instructions based on the user's areas of interest. For example, the reception unit suggests the most appropriate instructions according to the user's current situation. In this way, the reception unit can prioritize receiving highly relevant instructions by filtering based on the user's current situation and areas of interest. Some or all of the above processing in the reception unit may be performed using, for example, a generative AI, or without a generative AI. For example, the reception unit can input the user's current situation and areas of interest into a generative AI and have the generative AI perform the filtering.

[0086] The reception unit estimates the user's emotions and determines the priority of instructions to be received based on the estimated emotions. The reception unit estimates emotions from the user's voice using, for example, voice analysis technology. The reception unit analyzes the tone and speed of the user's voice and calculates an emotion score. For example, if the user is tense, the reception unit will prioritize receiving important instructions. Also, if the user is relaxed, the reception unit may prioritize receiving detailed instructions. Furthermore, if the user is in a hurry, the reception unit will prioritize receiving instructions that require quick processing. In this way, the reception unit can prioritize receiving important instructions by determining the priority of instructions 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. Some or all of the above processing in the reception unit may be performed using, for example, generative AI, or not using generative AI. For example, the reception desk can input the user's voice data into a generating AI and have the AI ​​perform emotion estimation.

[0087] The reception unit, upon receiving a request, prioritizes receiving 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 unit prioritizes receiving instructions related to that location. The reception unit proposes the most appropriate instructions based on the user's current location. For example, the reception unit prioritizes receiving instructions that are highly relevant, taking into account the user's geographical location. This allows the reception unit to prioritize receiving instructions that are highly relevant by considering the user's geographical location. Some or all of the above processing in the reception unit may be performed using, for example, a generative AI, or without a generative AI. For example, the reception unit can input the user's geographical location information into a generative AI and have the generative AI prioritize highly relevant instructions.

[0088] The reception unit analyzes the user's social media activity upon receiving a request and receives relevant instructions. For example, the reception unit extracts and receives relevant instructions from the user's social media activity. The reception unit analyzes the user's social media activity and proposes the most appropriate instructions. For example, the reception unit prioritizes receiving relevant instructions based on the user's social media activity. This allows the reception unit to prioritize receiving relevant instructions by analyzing the user's social media activity. Some or all of the above processing in the reception unit may be performed using, for example, a generative AI, or without a generative AI. For example, the reception unit can input the user's social media activity into a generative AI and have the generative AI extract relevant instructions.

[0089] The selection unit estimates the user's emotions and adjusts the way choices are presented based on the estimated emotions. The selection unit estimates emotions from the user's voice using, for example, speech analysis technology. The selection unit analyzes the tone and speed of the user's voice and calculates an emotion score. For example, if the user is nervous, the selection unit presents simple and highly visible choices. If the user is relaxed, the selection unit can also present more detailed choices. Furthermore, if the user is in a hurry, the selection unit presents choices that can be selected quickly. In this way, the selection unit can improve user convenience by adjusting the way choices are presented 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. Some or all of the above processing in the selection unit may be performed using, for example, a generative AI, or not using a generative AI. For example, the selection unit can input the user's voice data into a generative AI and have the generative AI perform emotion estimation.

[0090] The selection unit, when making a selection, refers to the user's past selection history to present the most suitable options. For example, the selection unit can save the past selection history to a database and refer to it for future selections. The selection unit presents the most suitable options based on the options the user has previously selected. For example, the selection unit can prioritize presenting relevant options from the user's past selection history. The selection unit can also analyze the user's past selection history and present the most suitable options. In this way, the selection unit can present the most suitable options by referring to the past selection history. Some or all of the above processing in the selection unit may be performed using, for example, a generative AI, or without a generative AI. For example, the selection unit can input the user's past selection history into a generative AI and have the generative AI perform the task of presenting the most suitable options.

[0091] The selection unit customizes the options based on the user's current situation when an option is selected. For example, the selection unit customizes and presents the optimal option according to the user's current situation. The selection unit prioritizes presenting relevant options, taking into account the user's current situation. For example, the selection unit customizes and presents options based on the user's current situation. In this way, the selection unit can provide the optimal option by customizing the options based on the user's current situation. Some or all of the above processing in the selection unit may be performed using, for example, a generative AI, or without a generative AI. For example, the selection unit can input the user's current situation into a generative AI and have the generative AI perform the customization of the options.

[0092] The selection unit estimates the user's emotions and determines the priority of the options based on the estimated emotions. The selection unit estimates emotions from the user's voice using, for example, speech analysis technology. The selection unit analyzes the tone and speed of the user's voice and calculates an emotion score. For example, if the user is nervous, the selection unit will prioritize presenting important options. Also, if the user is relaxed, the selection unit may prioritize presenting detailed options. Furthermore, if the user is in a hurry, the selection unit will prioritize presenting options that can be selected quickly. In this way, the selection unit can prioritize presenting important options by determining the priority of options according to the user's emotions. Emotion estimation is implemented 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. Some or all of the above processing in the selection unit may be performed using, for example, generative AI, or not using generative AI. For example, the selection unit can input the user's voice data into a generating AI and have the generating AI perform emotion estimation.

[0093] The selection unit presents the optimal options when a selection is made, taking into account the user's geographical location information. For example, the selection unit presents the optimal options based on the user's current location. The selection unit prioritizes presenting relevant options, taking into account the user's geographical location information. For example, the selection unit presents the optimal options according to the user's current location. In this way, the selection unit can present the optimal options by taking into account the user's geographical location information. Some or all of the above processing in the selection unit may be performed using, for example, a generative AI, or without a generative AI. For example, the selection unit can input the user's geographical location information into a generative AI and have the generative AI perform the task of presenting the optimal options.

[0094] The selection unit analyzes the user's social media activity and presents options when a selection is made. For example, the selection unit extracts and presents relevant options from the user's social media activity. The selection unit analyzes the user's social media activity and presents the optimal option. For example, the selection unit prioritizes presenting relevant options based on the user's social media activity. In this way, the selection unit can prioritize presenting relevant options by analyzing the user's social media activity. Some or all of the above processing in the selection unit may be performed using, for example, a generative AI, or without a generative AI. For example, the selection unit can input the user's social media activity into a generative AI and have the generative AI extract relevant options.

[0095] The generation unit estimates the user's emotions and adjusts the expression of the generated responses based on the estimated emotions. The generation unit estimates emotions from the user's voice using, for example, speech analysis technology. The generation unit analyzes the tone and speed of the user's voice and calculates an emotion score. For example, if the user is relaxed, the generation unit generates responses that proceed at a leisurely pace. The generation unit can also generate responses that emphasize the shortest route if the user is in a hurry. Furthermore, if the user is excited, the generation unit generates responses with visually stimulating effects. In this way, the generation unit can improve user convenience by adjusting the expression of responses according to the user's emotions. Emotion estimation is achieved using an emotion estimation function, for example, using an emotion engine or a generation AI. The generation AI is, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI. Some or all of the above processing in the generation unit may be performed using, for example, a generation AI, or not using a generation AI. For example, the generation unit can input user voice data into the generation AI and have the generation AI perform emotion estimation.

[0096] The generation unit extracts relevant information by referring to past conversation history during generation. For example, the generation unit saves past conversation history to a database for reference during the next generation. The generation unit generates the optimal answer based on information the user has used in the past. For example, the generation unit prioritizes extracting relevant information from the user's past conversation history. The generation unit can also analyze the user's past conversation history, extract the most appropriate information, and generate an answer. In this way, the generation unit can extract relevant information by referring to past conversation history and generate a more appropriate answer. Some or all of the above processing in the generation unit may be performed using, for example, a generation AI, or without a generation AI. For example, the generation unit can input the user's past conversation history into a generation AI and have the generation AI perform the extraction of relevant information.

[0097] The generation unit adjusts the level of detail in the response based on user instructions during generation. The generation unit generates the response using, for example, a generation AI. The generation AI can generate the response in natural language using a text generation AI (e.g., LLM). The generation unit uses the generation AI to adjust the level of detail in the response based on user instructions. For example, the generation unit can input the prompt "Please provide detailed information" to the generation AI, and the generation AI will generate a detailed response. Alternatively, the generation unit can input the prompt "Please provide concise information" to the generation AI, and the generation AI will generate a concise response. In this way, the generation unit can provide a response that meets the user's request by adjusting the level of detail in the response based on user instructions. Some or all of the above processing in the generation unit may be performed using, for example, a generation AI, or without using a generation AI. For example, the generation unit can input user instructions to the generation AI and have the generation AI adjust the level of detail in the response.

[0098] The generation unit estimates the user's emotions and adjusts the length of the generated response based on the estimated emotions. The generation unit estimates emotions from the user's voice using, for example, speech analysis technology. The generation unit analyzes the tone and speed of the user's voice and calculates an emotion score. For example, if the user is in a hurry, the generation unit generates a short, to-the-point response. The generation unit can also generate a longer response with detailed explanations if the user is relaxed. Furthermore, if the user is excited, the generation unit generates a response with visually stimulating effects. In this way, the generation unit can improve user convenience by adjusting the length of the response according to the user's emotions. Emotion estimation is achieved using an emotion estimation function, for example, using an emotion engine or a generation AI. The generation AI is, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI. Some or all of the above processing in the generation unit may be performed using, for example, a generation AI, or not using a generation AI. For example, the generation unit can input user voice data into the generation AI and have the generation AI perform emotion estimation.

[0099] The generation unit determines the priority of answers based on the user's past instruction history during generation. For example, the generation unit saves the past instruction history to a database and uses it as a reference during the next generation. The generation unit generates the optimal answer based on the instructions the user has used in the past. For example, the generation unit prioritizes extracting relevant information from the user's past instruction history. The generation unit can also analyze the user's past instruction history, extract the most appropriate information, and generate an answer. In this way, the generation unit can prioritize important answers by determining the priority of answers based on the user's past instruction history. Some or all of the above processing in the generation unit may be performed using a generation AI, for example, or without a generation AI. For example, the generation unit can input the user's past instruction history into a generation AI and have the generation AI perform the determination of answer priorities.

[0100] The generation unit generates answers by referring to the user's relevant activity history during the generation process. For example, the generation unit saves past activity history to a database for reference during the next generation. The generation unit generates the optimal answer based on the user's past activities. For example, the generation unit prioritizes extracting relevant information from the user's past activity history. The generation unit can also analyze the user's past activity history, extract the most appropriate information, and generate an answer. This allows the generation unit to generate more appropriate answers by referring to the user's relevant activity history. Some or all of the above processing in the generation unit may be performed using, for example, a generation AI, or without a generation AI. For example, the generation unit can input the user's past activity history into a generation AI and have the generation AI extract relevant information.

[0101] The quoting function estimates the user's emotions and adjusts its quoting method based on the estimated emotions. For example, the quoting function estimates emotions from the user's voice using speech analysis technology. The quoting function analyzes the tone and speed of the user's voice and calculates an emotion score. For example, if the user is relaxed, the quoting function provides a detailed quote. If the user is in a hurry, the quoting function can also provide a concise quote. Furthermore, if the user is excited, the quoting function provides a visually stimulating quote. In this way, the quoting function can improve user convenience by adjusting its quoting 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 is, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI. Some or all of the above processing in the quoting function may be performed using a generative AI, or not. For example, the quoting function can input the user's voice data into a generative AI and have the generative AI perform emotion estimation.

[0102] The citation function analyzes past interactions to identify the optimal citation location when quoting. For example, it can save past interactions to a database for reference during future citations. The citation function identifies the optimal citation location based on information previously used by the user. For example, it prioritizes extracting relevant information from the user's past interactions. It can also analyze the user's past interactions to identify the most appropriate citation location. In this way, the citation function can identify the optimal citation location and improve the accuracy of citations by analyzing past interactions. Some or all of the above processing in the citation function may be performed using, for example, a generative AI, or without a generative AI. For example, the citation function can input the user's past interactions into a generative AI and have the generative AI identify the optimal citation location.

[0103] The citation function adjusts the level of detail of a citation based on user instructions when citing. For example, the citation function can store user instructions in a database for reference the next time a citation is made. If the user requests a detailed citation, the citation function provides a detailed citation. For example, if the user requests a concise citation, the citation function provides a concise citation. The citation function can also adjust the level of detail of a citation based on user instructions. In this way, the citation function can provide citations that meet user requests by adjusting the level of detail of citations based on user instructions. Some or all of the above processing in the citation function may be performed using, for example, a generative AI, or not using a generative AI. For example, the citation function can input user instructions into a generative AI and have the generative AI perform the adjustment of the level of detail of the citation.

[0104] The citation function estimates the user's emotions and prioritizes the information to quote based on the estimated emotions. For example, the citation function estimates emotions from the user's voice using speech analysis technology. It analyzes the tone and speed of the user's voice and calculates an emotion score. For example, if the user is tense, the citation function prioritizes quoting important information. Similarly, if the user is relaxed, it may prioritize quoting detailed information. Furthermore, if the user is in a hurry, it prioritizes quoting information that can be quickly quoted. This allows the citation function to prioritize important information by prioritizing the information to quote according to the user's emotions. Emotion estimation is achieved using an emotion estimation function, such as an emotion engine or generative AI. Generative AI may be, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI. Some or all of the above-described processes in the citation function may be performed using, for example, a generative AI, or not. For example, the citation function can input the user's voice data into a generative AI and have the generative AI perform emotion estimation.

[0105] The citation function identifies the optimal citation location by considering the user's geographical location information at the time of citation. For example, the citation function stores the user's geographical location information in a database and refers to it the next time a citation is made. If the user is in a specific location, the citation function prioritizes citing information related to that location. For example, the citation function identifies the optimal citation location based on the user's current location. The citation function can also prioritize citing relevant information by considering the user's geographical location information. In this way, the citation function can identify the optimal citation location and improve the accuracy of citations by considering the user's geographical location information. Some or all of the above processing in the citation function may be performed using, for example, a generative AI, or without a generative AI. For example, the citation function can input the user's geographical location information into a generative AI and have the generative AI identify the optimal citation location.

[0106] The citation function analyzes the user's social media activity to identify the appropriate citation location. For example, the citation function can save the user's social media activity to a database for reference during future citations. The citation function extracts relevant information from the user's social media activity and cites it. For example, the citation function analyzes the user's social media activity to identify the most appropriate citation location. The citation function can also prioritize citing relevant information based on the user's social media activity. This allows the citation function to identify the most appropriate citation location and improve the accuracy of citations by analyzing the user's social media activity. Some or all of the above processing in the citation function may be performed using, for example, a generative AI, or without a generative AI. For example, the citation function can input the user's social media activity into a generative AI and have the generative AI identify the most appropriate citation location.

[0107] The analysis unit estimates the user's emotions and adjusts the analysis method based on the estimated emotions. The analysis unit estimates emotions from the user's voice using, for example, speech analysis technology. The analysis unit analyzes the tone and speed of the user's voice and calculates an emotion score. For example, the analysis unit performs a detailed analysis when the user is relaxed. The analysis unit can also perform a rapid analysis when the user is in a hurry. Furthermore, if the user is excited, the analysis unit provides visually stimulating analysis results. In this way, the analysis unit can improve user convenience 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 is, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI. Some or all of the above processing in the analysis unit may be performed using, for example, a generative AI, or not using a generative AI. For example, the analysis unit can input the user's voice data into a generative AI and have the generative AI perform emotion estimation.

[0108] The analysis unit extracts relevant information by referring to past conversation history during analysis. For example, the analysis unit saves past conversation history to a database for reference during subsequent analyses. The analysis unit performs optimal analysis based on information previously used by the user. For example, the analysis unit prioritizes extracting relevant information from the user's past conversation history. The analysis unit can also analyze the user's past conversation history and extract the most appropriate information for analysis. This allows the analysis unit to extract relevant information by referring to past conversation history and perform more appropriate analysis. Some or all of the above processing in the analysis unit may be performed using, for example, a generative AI, or without a generative AI. For example, the analysis unit can input the user's past conversation history into a generative AI and have the generative AI extract relevant information.

[0109] The analysis unit adjusts the level of detail of the analysis based on user instructions during the analysis. The analysis unit performs the analysis using, for example, a generative AI. The generative AI can perform analysis in natural language using a text generation AI (e.g., LLM). The analysis unit uses the generative AI to adjust the level of detail of the analysis based on user instructions. For example, the analysis unit inputs a prompt to the generative AI saying, "Please perform a detailed analysis," and the generative AI performs a detailed analysis. Alternatively, the analysis unit can input a prompt to the generative AI saying, "Please perform a concise analysis," and the generative AI performs a concise analysis. In this way, the analysis unit can perform analysis according to user requests by adjusting the level of detail of the analysis based on user instructions. Some or all of the above processing in the analysis unit may be performed using, for example, a generative AI, or without using a generative AI. For example, the analysis unit can input user instructions to the generative AI and have the generative AI adjust the level of detail of the analysis.

[0110] The analysis unit estimates the user's emotions and determines the priority of information to analyze based on the estimated emotions. The analysis unit estimates emotions from the user's voice using, for example, speech analysis technology. The analysis unit analyzes the tone and speed of the user's voice and calculates an emotion score. For example, if the user is tense, the analysis unit prioritizes analyzing important information. The analysis unit can also prioritize analyzing detailed information if the user is relaxed. Furthermore, if the user is in a hurry, the analysis unit prioritizes analyzing information that can be analyzed quickly. In this way, the analysis unit can prioritize the analysis of important information by determining the priority of information to analyze 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. Some or all of the above processing in the analysis unit may be performed using, for example, a generative AI, or not using a generative AI. For example, the analysis unit can input the user's voice data into a generative AI and have the generative AI perform emotion estimation.

[0111] The analysis unit selects the optimal analysis method during analysis, taking into account the user's geographical location information. For example, the analysis unit saves the user's geographical location information to a database for reference during subsequent analyses. If the user is in a specific location, the analysis unit prioritizes analyzing information related to that location. For example, the analysis unit selects the optimal analysis method based on the user's current location. The analysis unit can also prioritize the analysis of relevant information by taking into account the user's geographical location information. This allows the analysis unit to select the optimal analysis method and improve the accuracy of the analysis by considering the user's geographical location information. Some or all of the above processing in the analysis unit may be performed using, for example, a generative AI, or without a generative AI. For example, the analysis unit can input the user's geographical location information into a generative AI and have the generative AI select the optimal analysis method.

[0112] The analysis unit analyzes the user's social media activity during analysis and selects an analysis method. For example, the analysis unit saves the user's social media activity to a database for reference during subsequent analyses. The analysis unit extracts relevant information from the user's social media activity and performs analysis. For example, the analysis unit analyzes the user's social media activity and selects the optimal analysis method. The analysis unit can also prioritize the analysis of relevant information based on the user's social media activity. This allows the analysis unit to select the optimal analysis method by analyzing the user's social media activity and improve the accuracy of the analysis. Some or all of the above processes in the analysis unit may be performed using, for example, a generative AI, or without a generative AI. For example, the analysis unit can input the user's social media activity into a generative AI and have the generative AI select the optimal analysis method.

[0113] The identification unit estimates the user's emotions and adjusts specific methods based on the estimated emotions. The identification unit estimates emotions from the user's voice using, for example, voice analysis technology. The identification unit analyzes the tone and speed of the user's voice and calculates an emotion score. For example, if the user is relaxed, the identification unit performs detailed identification. The identification unit can also perform rapid identification if the user is in a hurry. Furthermore, if the user is excited, the identification unit provides visually stimulating identification results. In this way, the identification unit can improve user convenience by adjusting specific methods 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. Some or all of the above processing in the identification unit may be performed using, for example, a generative AI, or not using a generative AI. For example, the identification unit can input the user's voice data into a generative AI and have the generative AI perform emotion estimation.

[0114] The identification unit, at the time of identification, analyzes past interactions to select the optimal identification location. The identification unit, for example, saves past interactions to a database for reference during the next identification. The identification unit selects the optimal identification location based on information previously used by the user. For example, the identification unit prioritizes extracting relevant information from the user's past interactions. The identification unit can also analyze the user's past interactions and select the most suitable identification location. In this way, the identification unit can improve the accuracy of identification by selecting the optimal identification location through analysis of past interactions. Some or all of the above processing in the identification unit may be performed using, for example, a generative AI, or without a generative AI. For example, the identification unit can input the user's past interactions into a generative AI and have the generative AI select the optimal identification location.

[0115] The identification unit adjusts the level of detail of the identification based on the user's instructions during the identification process. For example, the identification unit saves the user's instructions to a database for reference during subsequent identifications. If the user requests detailed identification, the identification unit performs detailed identification. For example, if the user requests concise identification, the identification unit performs concise identification. The identification unit can also adjust the level of detail of the identification based on the user's instructions. In this way, the identification unit can perform identification that meets the user's requirements by adjusting the level of detail of the identification based on the user's instructions. Some or all of the above-described processes in the identification unit may be performed using, for example, a generating AI, or not using a generating AI. For example, the identification unit can input the user's instructions into a generating AI and have the generating AI perform the adjustment of the level of detail of the identification.

[0116] The identification unit estimates the user's emotions and determines the priority of information to identify based on the estimated emotions. The identification unit estimates emotions from the user's voice using, for example, speech analysis technology. The identification unit analyzes the tone and speed of the user's voice and calculates an emotion score. For example, if the user is tense, the identification unit prioritizes identifying important information. The identification unit can also prioritize identifying detailed information if the user is relaxed. Furthermore, if the user is in a hurry, the identification unit prioritizes identifying information that can be identified quickly. In this way, the identification unit can prioritize identifying important information by determining the priority of information to identify according to the user's emotions. Emotion estimation is implemented 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. Some or all of the above processing in the identification unit may be performed using, for example, a generative AI, or not using a generative AI. For example, the identification unit can input the user's voice data into a generative AI and have the generative AI perform emotion estimation.

[0117] The identification unit selects the optimal location by considering the user's geographical location information during identification. For example, the identification unit stores the user's geographical location information in a database for reference during subsequent identification. If the user is in a specific location, the identification unit prioritizes identifying information related to that location. For example, the identification unit selects the optimal location based on the user's current location. The identification unit can also prioritize identifying related information by considering the user's geographical location information. This allows the identification unit to select the optimal location and improve the accuracy of identification by considering the user's geographical location information. Some or all of the above processing in the identification unit may be performed using, for example, a generation AI, or without a generation AI. For example, the identification unit can input the user's geographical location information into a generation AI and have the generation AI select the optimal location.

[0118] The identification unit analyzes the user's social media activity at the time of identification to select a location to identify. The identification unit, for example, saves the user's social media activity to a database for reference during subsequent identification. The identification unit extracts relevant information from the user's social media activity and identifies it. For example, the identification unit analyzes the user's social media activity and selects the optimal location to identify. The identification unit can also prioritize the identification of relevant information based on the user's social media activity. This allows the identification unit to select the optimal location by analyzing the user's social media activity and improve the accuracy of identification. Some or all of the above processing in the identification unit may be performed using, for example, a generative AI, or without a generative AI. For example, the identification unit can input the user's social media activity into a generative AI and have the generative AI select the optimal location to identify.

[0119] The identification unit, at the time of identification, refers to the user's calendar information to perform identification based on the schedule. The identification unit, for example, saves the user's calendar information to a database for reference during the next identification. The identification unit refers to the schedule registered in the user's calendar and identifies relevant information. For example, the identification unit prioritizes identifying information related to a specific event from the user's calendar information. The identification unit can also select the optimal identification location based on the schedule based on the user's calendar information. In this way, the identification unit can improve the accuracy of identification by selecting the optimal identification location based on the schedule by referring to the user's calendar information. Some or all of the above processing in the identification unit may be performed using, for example, a generation AI, or without a generation AI. For example, the identification unit can input the user's calendar information into a generation AI and have the generation AI perform identification based on the schedule.

[0120] The system according to the embodiment is not limited to the example described above, and various modifications are possible, for example, as follows.

[0121] The generative AI system can also be equipped with the ability to estimate the user's emotions and adjust the tone of its response based on those emotions. For example, if the user is stressed, the generative AI can generate a response in a gentle tone. If the user is excited, the generative AI can generate a response in an energetic tone. Furthermore, if the user is relaxed, the generative AI can generate a response in a calm tone. This allows the generative AI system to provide responses in an appropriate tone according to the user's emotions, thereby improving user satisfaction.

[0122] Generative AI systems can further analyze a user's past behavior history and be equipped with the ability to customize answers based on the user's interests. For example, if a user has asked many questions on a particular topic in the past, the generative AI can prioritize providing information related to that topic. Also, if a user tends to ask certain types of questions at certain times of the day, the generative AI can provide answers appropriate for that time of day. Furthermore, based on the user's past behavior history, the generative AI can suggest new information that the user might be interested in. In this way, generative AI systems can provide personalized answers that match the user's interests, thereby improving user satisfaction.

[0123] The generative AI system can also be equipped with the ability to estimate the user's emotions and adjust the level of detail in the response based on those emotions. For example, if the user is in a hurry, the generative AI can provide a concise and to-the-point response. If the user is relaxed, the generative AI can provide a response that includes detailed explanations. Furthermore, if the user is excited, the generative AI can provide a response with visually stimulating effects. This allows the generative AI system to provide responses with the appropriate level of detail according to the user's emotions, thereby improving user convenience.

[0124] The generative AI system can also be equipped with the ability to customize responses by taking into account the user's geographical location. For example, if the user is in a specific location, it can prioritize providing information relevant to that location. If the user is traveling, the generative AI can also provide information about their travel destination. Furthermore, based on the user's current location, the generative AI can provide information about nearby events and facilities. This allows the generative AI system to provide appropriate information tailored to the user's geographical location, thereby improving user convenience.

[0125] The generative AI system can also be equipped with the ability to estimate the user's emotions and prioritize responses based on those emotions. For example, if the user is stressed, the generative AI can prioritize providing important information. If the user is relaxed, the generative AI can prioritize providing detailed information. Furthermore, if the user is in a hurry, the generative AI can prioritize providing information that needs to be processed quickly. In this way, the generative AI system can provide information with appropriate priorities according to the user's emotions, thereby improving user convenience.

[0126] The generative AI system can further analyze the user's social media activity and customize responses based on the user's interests. For example, if a user frequently posts about a particular topic on social media, the generative AI can prioritize providing information related to that topic. Similarly, if a user participates in a specific event, the generative AI can provide information related to that event. Furthermore, based on the user's social media activity, the generative AI can suggest new information that the user might be interested in. This allows the generative AI system to provide personalized responses tailored to the user's social media activity, thereby improving user satisfaction.

[0127] The generative AI system can also be equipped with the ability to estimate the user's emotions and adjust the way the response is expressed based on those emotions. For example, if the user is relaxed, the generative AI can provide a response that proceeds at a leisurely pace. If the user is in a hurry, the generative AI can provide a response that emphasizes the shortest route. Furthermore, if the user is excited, the generative AI can provide a response with visually stimulating effects. In this way, the generative AI system can provide responses in an appropriate manner according to the user's emotions, thereby improving user convenience.

[0128] The generative AI system can also be equipped with the ability to customize its responses by referencing the user's calendar information. For example, based on appointments registered in the user's calendar, the generative AI can provide relevant information. Furthermore, if the user has plans to attend a specific event, the generative AI can provide information related to that event. In addition, based on the user's calendar information, the generative AI can suggest new events and activities that the user might be interested in. This allows the generative AI system to provide personalized responses tailored to the user's calendar information, thereby improving user satisfaction.

[0129] The generative AI system can also be equipped with the ability to estimate the user's emotions and adjust the length of the response based on those emotions. For example, if the user is in a hurry, the generative AI can provide a short, to-the-point response. If the user is relaxed, the generative AI can provide a longer response that includes detailed explanations. Furthermore, if the user is excited, the generative AI can provide a response with visually stimulating effects. This allows the generative AI system to provide responses of appropriate length according to the user's emotions, thereby improving user convenience.

[0130] The generative AI system can further analyze the user's past instruction history and have the ability to prioritize answers based on the user's instructions. For example, if a user has asked many questions on a particular topic in the past, the generative AI can prioritize providing information related to that topic. Also, if a user tends to ask certain types of questions at certain times of the day, the generative AI can provide answers appropriate for that time of day. Furthermore, based on the user's past instruction history, the generative AI can suggest new information that the user might be interested in. In this way, the generative AI system can provide personalized answers that are tailored to the user's past instruction history, thereby improving user satisfaction.

[0131] The following briefly describes the processing flow for example form 2.

[0132] Step 1: The reception desk receives user instructions. User instructions include voice instructions, text instructions, and gesture instructions. For example, the reception desk receives voice instructions using voice recognition technology, text instructions using a text input interface, and gesture instructions using gesture recognition technology. Step 2: The selection unit chooses whether to refer to past interactions based on the instructions received by the reception unit. The selection unit makes this decision based on the user's past selection history and current situation. For example, if the user instructs "Considering our previous conversation," the selection unit will refer to past interactions; if the user instructs "I will ask a new question," the selection unit will reset past interactions. Step 3: The generation unit generates an answer based on the information selected by the selection unit. The generation unit generates the answer in natural language using a generation AI. For example, the generation unit inputs the prompt "Based on our previous conversation, please tell me the next step" into the generation AI and provides the generated answer to the user. Step 4: The quoting section quotes past conversations in the response generated by the generating section. The quoting section analyzes the past conversation history, extracts relevant information, and includes it in the response. For example, if the user instructs, "Please quote the points mentioned in the previous conversation," the quoting section will quote the relevant parts from the past conversation history.

[0133] 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.

[0134] 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.

[0135] 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.

[0136] Each of the multiple elements described above, including the reception unit, selection unit, generation unit, and citation 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 voice or text instructions from the user. The selection unit is implemented by the identification processing unit 290 of the data processing unit 12 and determines whether to refer to past interactions. The generation unit is implemented by the identification processing unit 290 of the data processing unit 12 and generates a response using a generation AI. The citation unit is implemented by the identification processing unit 290 of the data processing unit 12 and includes past interactions in the response by quoting them. 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.

[0137] [Second Embodiment] Figure 3 shows an example of the configuration of the data processing system 210 according to the second embodiment.

[0138] 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.

[0139] 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.

[0140] 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.

[0141] 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.

[0142] 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).

[0143] 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.

[0144] 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.

[0145] 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.

[0146] 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.

[0147] 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.

[0148] 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.).

[0149] 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.

[0150] 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.

[0151] 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.

[0152] Each of the multiple elements described above, including the reception unit, selection unit, generation unit, and citation 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 voice instructions from the user. The selection unit is implemented by the identification processing unit 290 of the data processing unit 12 and determines whether to refer to past interactions. The generation unit is implemented by the identification processing unit 290 of the data processing unit 12 and generates an answer using a generation AI. The citation unit is implemented by the identification processing unit 290 of the data processing unit 12 and includes past interactions in the answer by citing them. 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.

[0153] [Third Embodiment] Figure 5 shows an example of the configuration of the data processing system 310 according to the third embodiment.

[0154] 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.

[0155] 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.

[0156] 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.

[0157] 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.

[0158] 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).

[0159] 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.

[0160] 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.

[0161] 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.

[0162] 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.

[0163] 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.

[0164] 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.).

[0165] 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.

[0166] 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.

[0167] 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.

[0168] Each of the multiple elements described above, including the reception unit, selection unit, generation unit, and citation 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 voice instructions from the user. The selection unit is implemented by the identification processing unit 290 of the data processing unit 12 and determines whether to refer to past interactions. The generation unit is implemented by the identification processing unit 290 of the data processing unit 12 and generates a response using a generation AI. The citation unit is implemented by the identification processing unit 290 of the data processing unit 12 and includes past interactions in the response by referencing them. 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.

[0169] [Fourth Embodiment] Figure 7 shows an example of the configuration of the data processing system 410 according to the fourth embodiment.

[0170] 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.

[0171] 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.

[0172] 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.

[0173] 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.

[0174] 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).

[0175] 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.

[0176] 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.

[0177] 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.

[0178] 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.

[0179] 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.

[0180] 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.

[0181] 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.).

[0182] 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.

[0183] 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.

[0184] 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.

[0185] Each of the multiple elements described above, including the reception unit, selection unit, generation unit, and citation unit, is implemented in at least one of 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 voice instructions from the user. The selection unit is implemented by the identification processing unit 290 of the data processing unit 12 and determines whether to refer to past interactions. The generation unit is implemented by the identification processing unit 290 of the data processing unit 12 and generates a response using a generation AI. The citation unit is implemented by the identification processing unit 290 of the data processing unit 12 and includes past interactions in the response by referencing them. 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.

[0186] 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.

[0187] 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.

[0188] 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.

[0189] 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.

[0190] 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.

[0191] 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."

[0192] 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.

[0193] 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.

[0194] 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.

[0195] 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.

[0196] 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.

[0197] 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.

[0198] 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.

[0199] 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.

[0200] 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.

[0201] 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.

[0202] 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.

[0203] 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.

[0204] (Note 1) A reception desk that takes user instructions, A selection unit that selects whether to refer to past exchanges based on instructions received by the reception unit, A generation unit that generates an answer based on the information selected by the selection unit, The generated response includes a section that quotes past exchanges. A system characterized by the following features. (Note 2) The generating unit is It includes an analysis unit that analyzes past conversation history and extracts relevant information. The system described in Appendix 1, characterized by the features described herein. (Note 3) The aforementioned quoted section is, It includes a special unit that identifies information that quotes past exchanges. The system described in Appendix 1, characterized by the features described herein. (Note 4) The aforementioned selection unit is Users can choose whether to refer to past interactions. The system described in Appendix 1, characterized by the features described herein. (Note 5) The generating unit is Generates answers based on user instructions. The system described in Appendix 1, characterized by the features described herein. (Note 6) The aforementioned quoted section is, Include quotes from past exchanges in your response. The system described in Appendix 1, characterized by the features described herein. (Note 7) The aforementioned reception unit is It estimates the user's emotions and adjusts how instructions are received based on those estimated emotions. The system described in Appendix 1, characterized by the features described herein. (Note 8) The aforementioned reception unit is We analyze the user's past instruction history and propose the optimal reception method. The system described in Appendix 1, characterized by the features described herein. (Note 9) The aforementioned reception unit is During registration, 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 10) The aforementioned reception unit is It estimates the user's emotions and determines the priority of instructions to accept based on the estimated user emotions. The system described in Appendix 1, characterized by the features described herein. (Note 11) The aforementioned reception unit is When receiving a request, the system prioritizes processing requests based on the user's geographical location, ensuring that the most relevant instructions are processed. The system described in Appendix 1, characterized by the features described herein. (Note 12) The aforementioned reception unit is Upon registration, the system analyzes the user's social media activity and receives relevant instructions. The system described in Appendix 1, characterized by the features described herein. (Note 13) The aforementioned selection unit is It estimates the user's emotions and adjusts how choices are presented based on those estimated emotions. The system described in Appendix 1, characterized by the features described herein. (Note 14) The aforementioned selection unit is When making a selection, the system will refer to past selection history to suggest the most suitable option. The system described in Appendix 1, characterized by the features described herein. (Note 15) The aforementioned selection unit is When selecting an option, customize the choices based on the user's current situation. The system described in Appendix 1, characterized by the features described herein. (Note 16) The aforementioned selection unit is It estimates the user's emotions and determines the priority of choices based on the estimated user emotions. The system described in Appendix 1, characterized by the features described herein. (Note 17) The aforementioned selection unit is When making a selection, the system will consider the user's geographical location to present the most suitable options. The system described in Appendix 1, characterized by the features described herein. (Note 18) The aforementioned selection unit is When making a selection, the system analyzes the user's social media activity to present options. The system described in Appendix 1, characterized by the features described herein. (Note 19) The generating unit is It estimates the user's emotions and adjusts how the generated responses are expressed based on those estimated emotions. The system described in Appendix 1, characterized by the features described herein. (Note 20) The generating unit is During generation, relevant information is extracted by referring to past conversation history. The system described in Appendix 1, characterized by the features described herein. (Note 21) The generating unit is During generation, the level of detail in the response is adjusted based on user instructions. The system described in Appendix 1, characterized by the features described herein. (Note 22) The generating unit is It estimates the user's emotions and adjusts the length of the response generated based on the estimated user emotions. The system described in Appendix 1, characterized by the features described herein. (Note 23) The generating unit is During generation, the priority of responses is determined based on the user's past instruction history. The system described in Appendix 1, characterized by the features described herein. (Note 24) The generating unit is During generation, the system references the user's relevant activity history to generate the response. The system described in Appendix 1, characterized by the features described herein. (Note 25) The aforementioned quoted section is, It estimates the user's sentiment and adjusts the quoting method based on the estimated user sentiment. The system described in Appendix 1, characterized by the features described herein. (Note 26) The aforementioned quoted section is, When quoting, past exchanges are analyzed to identify the most appropriate citation. The system described in Appendix 1, characterized by the features described herein. (Note 27) The aforementioned quoted section is, When quoting, adjust the level of detail of the quote based on the user's instructions. The system described in Appendix 1, characterized by the features described herein. (Note 28) The aforementioned quoted section is, It estimates the user's emotions and determines the priority of information to quote based on the estimated user emotions. The system described in Appendix 1, characterized by the features described herein. (Note 29) The aforementioned quoted section is, When quoting, the system takes the user's geographical location into consideration to identify the optimal citation location. The system described in Appendix 1, characterized by the features described herein. (Note 30) The aforementioned quoted section is, When quoting, the system analyzes the user's social media activity to identify the quoted portion. The system described in Appendix 1, characterized by the features described herein. (Note 31) 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 2, characterized by the features described herein. (Note 32) The aforementioned analysis unit, During analysis, relevant information is extracted by referring to past conversation history. The system described in Appendix 2, characterized by the features described herein. (Note 33) The aforementioned analysis unit, During analysis, the level of detail of the analysis is adjusted based on user instructions. The system described in Appendix 2, characterized by the features described herein. (Note 34) The aforementioned analysis unit, It estimates the user's emotions and determines the priority of information to analyze based on the estimated user emotions. The system described in Appendix 2, characterized by the features described herein. (Note 35) The aforementioned analysis unit, During analysis, the optimal analysis method is selected considering the user's geographical location information. The system described in Appendix 2, characterized by the features described herein. (Note 36) The aforementioned analysis unit, During the analysis, the analysis method is selected by analyzing the user's social media activity. The system described in Appendix 2, characterized by the features described herein. (Note 37) The specified part is, It estimates the user's emotions and adjusts specific methods based on those estimated emotions. The system described in Appendix 3, characterized by the features described herein. (Note 38) The specified part is, At a specific point in time, past interactions are analyzed to select the most appropriate location. The system described in Appendix 3, characterized by the features described herein. (Note 39) The specified part is, At specific times, adjust the level of detail based on user instructions. The system described in Appendix 3, characterized by the features described herein. (Note 40) The specified part is, It estimates the user's emotions and prioritizes the information to identify based on those estimated emotions. The system described in Appendix 3, characterized by the features described herein. (Note 41) The specified part is, When a location is identified, the optimal location is selected considering the user's geographical location information. The system described in Appendix 3, characterized by the features described herein. (Note 42) The specified part is, At specific times, analyze the user's social media activity to select specific locations. The system described in Appendix 3, characterized by the features described herein. (Note 43) The specified part is, When a user is identified, their calendar information is referenced to identify them based on their schedule. The system described in Appendix 3, characterized by the features described herein. [Explanation of Symbols]

[0205] 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 takes user instructions, A selection unit that selects whether to refer to past exchanges based on instructions received by the reception unit, A generation unit that generates an answer based on the information selected by the selection unit, The generated response includes a section that quotes past exchanges. A system characterized by the following features.

2. The generating unit is It includes an analysis unit that analyzes past conversation history and extracts relevant information. The system according to feature 1.

3. The aforementioned quoted section is, It includes a special unit that identifies information that quotes past exchanges. The system according to feature 1.

4. The aforementioned selection unit is Users can choose whether to refer to past interactions. The system according to feature 1.

5. The generating unit is Generates answers based on user instructions. The system according to feature 1.

6. The aforementioned quoted section is, Include quotes from past exchanges in your response. The system according to feature 1.

7. The aforementioned reception unit is It estimates the user's emotions and adjusts how instructions are received based on those estimated emotions. The system according to feature 1.

8. The aforementioned reception unit is We analyze the user's past instruction history and propose the optimal reception method. The system according to feature 1.

9. The aforementioned reception unit is During registration, filtering is performed based on the user's current situation and areas of interest. The system according to feature 1.

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

Images