system

Abstract

The system according to this embodiment aims to enable a privately owned AI agent to efficiently interact with multiple corporate AIs and acquire information. [Solution] The system according to this embodiment comprises a reception unit, an inquiry unit, a receiving unit, a provision unit, and a management unit. The reception unit receives instructions from the user. The inquiry unit makes inquiries to the corporate AI based on the instructions received by the reception unit. The receiving unit receives responses from the corporate AI. The provision unit analyzes the responses received by the receiving unit and provides them to the user. The management unit manages the dialogue with the corporate AI.

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, 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 it is difficult for a personally-owned AI agent to efficiently interact with multiple enterprise AIs and obtain information.

[0005] The system according to the embodiment aims to enable a personally-owned AI agent to efficiently interact with multiple enterprise AIs and obtain information.

Means for Solving the Problems

[0006] The system according to this embodiment comprises a reception unit, an inquiry unit, a receiving unit, a provision unit, and a management unit. The reception unit receives instructions from the user. The inquiry unit makes inquiries to the corporate AI based on the instructions received by the reception unit. The receiving unit receives responses from the corporate AI. The provision unit analyzes the responses received by the receiving unit and provides them to the user. The management unit manages the dialogue with the corporate AI. [Effects of the Invention]

[0007] The system according to this embodiment allows a privately owned AI agent to efficiently interact with multiple corporate AIs and acquire information. [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 manages 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 interactive multi-agent system according to an embodiment of the present invention is a system in which a privately owned AI agent and a corporate AI agent conduct multi-dialogue on a virtual platform. This system enables a private AI to interact with multiple corporate AIs, achieving immediate problem resolution, service comparison, and fluid mutual proposals and interactions. First, a privately owned AI agent (hereinafter referred to as "private AI") connects to the virtual platform. Next, based on user instructions, the private AI begins interacting with multiple corporate AI agents (hereinafter referred to as "corporate AIs"). For example, if a user instructs "I want to book a trip," the private AI queries travel-related corporate AIs for information. The corporate AIs respond to the inquiry from the private AI based on the data they hold. For example, a travel agent's corporate AI might propose the optimal travel plan based on travel data and provide discount information and booking procedures. Furthermore, multiple corporate AIs can collaborate to provide the optimal service tailored to the user's needs. This system allows users to interact with multiple corporate AIs through their private AI, efficiently acquire information, and utilize services. For example, if a user is looking for a specific product, the private AI queries corporate AIs of multiple e-commerce sites to provide optimal product information. Furthermore, if a user wishes to book a trip, the personal AI will contact corporate AIs of multiple travel agencies to propose the optimal travel plan. Moreover, since the interaction between the personal AI and corporate AI takes place in real time, users can obtain information immediately and resolve their issues quickly. The interaction between the personal AI and corporate AI can also be flexibly adapted to the user's requests, allowing users to receive the best possible service tailored to their needs. This system is an interactive multi-agent system where personal AI and corporate AI work together in the background, enabling users to experience diverse services by interacting with multiple corporate AIs through the personal AI. For example, if a user is looking for a specific product, the personal AI will contact corporate AIs of multiple e-commerce sites to provide the best product information. Similarly, if a user wishes to book a trip, the personal AI will contact corporate AIs of multiple travel agencies to propose the optimal travel plan.This system allows users to interact with multiple corporate AIs through their personal AI, efficiently acquiring information and utilizing services. Furthermore, since the interaction between the personal AI and corporate AIs takes place in real time, users can obtain information immediately and quickly resolve their issues. As a result, the conversational multi-agent system can quickly resolve user issues and efficiently provide information.

[0029] The interactive multi-agent system according to this embodiment comprises a reception unit, an inquiry unit, a receiving unit, a provision unit, and a management 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 the user's voice instructions using, for example, speech recognition technology. The reception unit can also receive the user's text instructions using a text input interface. Furthermore, the reception unit can also receive the user's gesture instructions using gesture recognition technology. For example, the reception unit analyzes the user's voice instructions using speech recognition technology and understands the content of the instructions. The text input interface receives text instructions entered by the user using a keyboard or touchscreen. Gesture recognition technology captures the user's hand movements and body movements with a camera and analyzes the content of the instructions. The inquiry unit makes inquiries to the enterprise AI based on the instructions received by the reception unit. The enterprise AI includes, but is not limited to, a customer support AI and a sales support AI. The inquiry unit sends the user's inquiry to, for example, the customer support AI. Furthermore, the inquiry unit can communicate user requests to the sales support AI. In addition, the inquiry unit can simultaneously submit inquiries to multiple company AIs. For example, the inquiry unit can send a user inquiry to the customer support AI, requesting a prompt response. It can also communicate the user's requests to the sales support AI, requesting the best possible proposal. By simultaneously submitting inquiries to multiple company AIs, information is collected efficiently. The receiving unit receives responses from the company AIs. Responses include, but are not limited to, text responses, voice responses, and image responses. For example, the receiving unit receives a text-based response and analyzes its content. It can also receive a voice-based response and convert it to text using speech recognition technology. Furthermore, it can receive an image-based response and understand its content using image analysis technology. For example, the receiving unit receives a text-based response and analyzes its content using natural language processing technology.Voice responses are converted to text using speech recognition technology, and their content is understood. Image responses are analyzed using image analysis technology and provided to the user. The delivery unit analyzes the responses received by the receiving unit and provides them to the user. The delivery unit, for example, displays text responses to the user. The delivery unit can also play voice responses to the user. Furthermore, the delivery unit can also display image responses to the user. For example, the delivery unit displays text responses on the user's device for confirmation. Voice responses are played on the user's device to convey the content. Image responses are displayed on the user's device to provide information visually. The management unit manages the dialogue between the personal AI and the enterprise AI. For example, the management unit monitors the progress of the dialogue and adjusts it as needed. The management unit can also record the history of the dialogue for later reference. Furthermore, the management unit can analyze the content of the dialogue and find areas for improvement. For example, the management unit monitors the progress of the dialogue in real time and adjusts the dialogue if problems occur. The history of the conversation is recorded in a database and can be referenced later. The content of the conversation is analyzed to find areas for improvement that meet the user's needs. As a result, the conversational multi-agent system according to this embodiment can immediately solve the user's problems by receiving user instructions, querying the enterprise AI, receiving responses, analyzing them, and providing them.

[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, for example, receive voice instructions using speech recognition technology. Specifically, speech recognition technology collects the user's speech with a microphone and converts the voice signal into digital data. Then, a speech recognition engine analyzes the voice data and converts the spoken content into text. This allows the system to understand the user's voice instructions. The reception unit can also receive text instructions from the user using a text input interface. The text input interface receives text data entered by the user using a keyboard or touchscreen and transmits it to the system. Furthermore, the reception unit can also receive gesture instructions from the user using gesture recognition technology. Gesture recognition technology captures the user's hand and body movements using cameras and sensors, analyzes those movements, and understands the instructions. For example, if a user waves their hand, that movement is recognized as a specific instruction. This allows the reception unit to flexibly receive user instructions through various input methods, including voice, text, and gestures. Furthermore, the reception desk can combine these input methods to improve user convenience. For example, voice and gesture instructions can be combined to provide more complex instructions. This allows the reception desk to meet the diverse needs of users and enable intuitive and efficient operation.

[0031] The inquiry department makes inquiries to the corporate AI based on instructions received by the reception department. The corporate AI includes, but is not limited to, customer support AI and sales support AI. For example, the inquiry department sends user inquiries to the customer support AI. Specifically, if a user inquires about a product defect, the inquiry department sends the details to the customer support AI and requests an appropriate response. The inquiry department can also communicate user requests to the sales support AI. For example, if a user requests a proposal for a new product, the inquiry department sends the request to the sales support AI and requests the best possible proposal. Furthermore, the inquiry department can make inquiries to multiple corporate AIs simultaneously. For example, if a user requests information about multiple products, the inquiry department will contact both the customer support AI and the sales support AI to collect information quickly and efficiently. This allows the inquiry department to respond to diverse user needs and provide information promptly. Additionally, the inquiry department can appropriately format the inquiry content and include necessary information to optimize communication with the corporate AI. For example, including past conversation history and user profile information related to the inquiry allows the corporate AI to respond more accurately and quickly. This will enable the inquiry department to effectively integrate with corporate AI and improve user satisfaction.

[0032] The receiving unit receives responses from the enterprise AI. These responses include, but are not limited to, text responses, voice responses, and image responses. For example, the receiving unit receives a text-based response and analyzes its content. Specifically, text-based responses are analyzed using natural language processing techniques to extract answers to user inquiries. The receiving unit can also receive voice-based responses and convert them to text using speech recognition technology. For voice-based responses, the receiving unit receives voice data generated by the enterprise AI, and a speech recognition engine converts this data into text. This allows the content of the voice response to be understood as text. Furthermore, the receiving unit can receive image-based responses and understand their content using image analysis technology. For image-based responses, the receiving unit receives image data generated by the enterprise AI, and an image analysis engine analyzes the image data to understand its content. For example, if product manuals or diagrams are provided in image format, the receiving unit analyzes their content and provides it to the user. This allows the receiving unit to receive and appropriately analyze responses in various formats from the enterprise AI. Additionally, the receiving unit can evaluate the reliability and accuracy of the responses and re-query as needed. For example, if the received response is incomplete, the receiving unit requests additional information from the enterprise AI to ensure the quality of the information provided to the user. This allows the receiving unit to provide high-quality information to the user and improve the overall reliability of the system.

[0033] The delivery unit analyzes the response received by the receiving unit and provides it to the user. For example, the delivery unit displays the response to the user in text format. Specifically, the text response is displayed on the user's device, allowing the user to review the content. The delivery unit can also play an audio response to the user. The audio response is played on the user's device, allowing the user to listen to the content. Furthermore, the delivery unit can display an image response to the user. The image response is displayed on the user's device, providing information visually. For example, if a product manual or diagram is provided in image format, the delivery unit displays the image on the user's device, allowing the user to understand the content. This allows the delivery unit to provide the response received from the receiving unit in an appropriate format, improving user convenience. Furthermore, the delivery unit can collect user feedback and continuously improve the accuracy and effectiveness of the provided content. For example, by having users evaluate and comment on the provided information, the delivery unit can review and improve the content based on that feedback. The delivery unit can also reliably transmit information using multiple communication methods. For example, by using a combination of methods such as text messages, voice calls, and email, important information can be reliably delivered to users. This allows the service provider to deliver information quickly and reliably to users, thereby improving user satisfaction.

[0034] The management department manages the interactions between personal AI and enterprise AI. For example, the management department monitors the progress of the interactions and adjusts them as needed. Specifically, the management department monitors each step of the interaction in real time and adjusts the interaction if problems arise. For example, if a user's instructions are not properly understood, the management department reconfirms the instructions and takes appropriate action. The management department can also record the history of the interactions for later reference. The history of the interactions is recorded in a database, allowing users to review past inquiries and responses received. Furthermore, the management department can analyze the content of the interactions and identify areas for improvement. For example, by analyzing the content of the interactions and identifying areas for improvement based on user requests, the accuracy and efficiency of the system can be improved. This allows the management department to effectively manage the interactions between personal AI and enterprise AI, improving the overall reliability of the system and user satisfaction. Additionally, the management department can perform analysis based on the interaction data to evaluate the system's performance. For example, they can analyze the success rate of the interactions and the response time to identify areas for system improvement. The management department can also collect user feedback to help improve the system. This allows the management department to continuously improve the system and provide high-quality services to users.

[0035] The reception desk can analyze the user's past instruction history and select the optimal reception method. For example, the reception desk can automatically display instructions that the user has frequently entered in the past as suggestions. The reception desk can also prioritize suggesting input methods (voice, text, etc.) that the user has used in the past. Furthermore, the reception desk can predict and suggest instructions to be used during specific time periods based on the user's past instruction history. For example, the reception desk can store the user's past instruction history in a database and automatically display frequently entered instructions as suggestions. It improves user convenience by prioritizing and suggesting input methods that the user has used in the past. It enables efficient instruction input by predicting and suggesting instructions to be used during specific time periods. In this way, by analyzing the user's past instruction history, the reception desk can provide the user with the optimal reception method. Some or all of the above processes in the reception desk may be performed using AI, for example, or not using AI. For example, the reception desk can input the user's past instruction history into AI and have the AI ​​select the optimal reception method.

[0036] The reception unit can filter instructions based on the user's current situation or areas of interest when receiving them. For example, the reception unit can prioritize receiving relevant instructions based on the user's current situation. The reception unit can also filter and receive relevant instructions based on the user's areas of interest. Furthermore, the reception unit can suggest the most appropriate instructions based on the user's current situation and areas of interest. For example, the reception unit can prioritize receiving relevant instructions based on the user's location and time of day. It can filter and receive relevant instructions based on the user's areas of interest. It can suggest the most appropriate instructions based on the user's current situation and areas of interest. This allows for the priority of receiving highly relevant instructions by filtering instructions 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 AI, for example, or not. For example, the reception unit can input the user's location and areas of interest into the AI ​​and have the AI ​​perform the filtering of the most appropriate instructions.

[0037] The reception unit can prioritize receiving instructions that are highly relevant, taking into account the user's geographical location information. For example, if the user is in a specific location, the reception unit will prioritize receiving instructions related to that location. The reception unit can also suggest the most appropriate instructions based on the user's geographical location information. Furthermore, if the user is on the move, the reception unit can prioritize receiving relevant instructions based on their current location. For example, the reception unit can obtain the user's location information from GPS data and prioritize receiving instructions related to that location. It will suggest the most appropriate instructions based on the user's geographical location information. If the user is on the move, it will prioritize receiving relevant instructions based on their current location. This allows the reception unit to provide the user with the most appropriate instructions by prioritizing the receipt of highly relevant instructions based on the user's geographical location information. Some or all of the above processing in the reception unit may be performed using AI, for example, or not. For example, the reception unit can input the user's geographical location information into the AI ​​and have the AI ​​prioritize receiving highly relevant instructions.

[0038] The reception unit can analyze the user's social media activity when receiving instructions and receive relevant instructions. For example, the reception unit can prioritize receiving relevant instructions based on the user's social media activity. The reception unit can also analyze the user's social media activity and suggest the most appropriate instructions. Furthermore, the reception unit can also receive instructions related to the user's current areas of interest based on the user's social media activity. For example, the reception unit can analyze the user's social media activity using data mining techniques and prioritize receiving relevant instructions. It analyzes the user's social media activity and suggests the most appropriate instructions. It receives instructions related to the user's current areas of interest based on the user's social media activity. This allows the reception unit to provide the user with the most appropriate instructions by receiving relevant instructions based on the user's social media activity. Some or all of the above processing in the reception unit may be performed using AI, for example, or not using AI. For example, the reception unit can input the user's social media activity into AI and have AI perform the task of receiving relevant instructions.

[0039] The inquiry unit can adjust the level of detail of an inquiry based on the importance of the corporate AI. For example, the inquiry unit will make a detailed inquiry to important corporate AIs. It can also make a concise inquiry to less important corporate AIs. Furthermore, the inquiry unit can select the optimal inquiry method based on the importance of the corporate AI. For example, the inquiry unit will make a detailed inquiry to important corporate AIs based on the size of the company and the urgency of the inquiry. It will make a concise inquiry to less important corporate AIs. It will select the optimal inquiry method based on the importance of the corporate AI. In this way, by adjusting the level of detail of the inquiry based on the importance of the corporate AI, the most optimal inquiry can be made. Some or all of the above processing in the inquiry unit may be performed using AI, for example, or not using AI. For example, the inquiry unit can input the importance of the corporate AI into the AI ​​and have the AI ​​perform the adjustment of the level of detail of the inquiry.

[0040] The inquiry unit can apply different inquiry algorithms depending on the category of the corporate AI when an inquiry is made. For example, the inquiry unit can make detailed inquiries about travel to corporate AIs related to travel. It can also make detailed inquiries about products to corporate AIs related to e-commerce sites. Furthermore, it can make detailed inquiries about financial products to corporate AIs related to finance. For example, the inquiry unit can make detailed inquiries about travel plans and discount information to corporate AIs related to travel. It can make detailed inquiries about product availability and prices to corporate AIs related to e-commerce sites. It can make detailed inquiries about interest rates and conditions of financial products to corporate AIs related to finance. In this way, by applying different inquiry algorithms depending on the category of the corporate AI, the most optimal inquiry can be made. Some or all of the above processing in the inquiry unit may be performed using AI, for example, or not using AI. For example, the inquiry unit can input the category of the corporate AI into the AI ​​and have the AI ​​execute the application of different inquiry algorithms.

[0041] The inquiry unit can determine the priority of inquiries based on the response speed of the corporate AI. For example, the inquiry unit will prioritize inquiries to corporate AIs with fast response speeds. It can also postpone inquiries to corporate AIs with slow response speeds. Furthermore, the inquiry unit can determine the optimal inquiry order based on the response speed of the corporate AIs. For example, the inquiry unit can monitor the response speed of corporate AIs in real time and prioritize inquiries to corporate AIs with fast response speeds. It will postpone inquiries to corporate AIs with slow response speeds. It will determine the optimal inquiry order based on the response speed of the corporate AIs. This allows inquiries requiring a quick response to be prioritized by determining the priority of inquiries based on the response speed of the corporate AIs. Some or all of the above processing in the inquiry unit may be performed using AI, or not using AI. For example, the inquiry unit can input the response speed of corporate AIs into the AI ​​and have the AI ​​determine the priority of inquiries.

[0042] The inquiry unit can adjust the order of inquiries based on the relevance of the corporate AIs. For example, the inquiry unit can prioritize inquiries to corporate AIs with high relevance. It can also postpone inquiries to corporate AIs with low relevance. Furthermore, the inquiry unit can determine the optimal inquiry order based on the relevance of the corporate AIs. For example, the inquiry unit can evaluate the relevance of the corporate AIs and prioritize inquiries to corporate AIs with high relevance. It can postpone inquiries to corporate AIs with low relevance. It determines the optimal inquiry order based on the relevance of the corporate AIs. In this way, by adjusting the order of inquiries based on the relevance of the corporate AIs, it is possible to prioritize inquiries to corporate AIs with high relevance. Some or all of the above processing in the inquiry unit may be performed using AI, or not using AI. For example, the inquiry unit can input the relevance of the corporate AIs into the AI ​​and have the AI ​​perform the adjustment of the inquiry order.

[0043] The receiving unit can adjust the level of detail of the received data based on the content of the corporate AI's response. For example, the receiving unit can receive detailed information for important responses. It can also receive concise information for less important responses. Furthermore, the receiving unit can select the optimal receiving method based on the content of the corporate AI's response. For example, the receiving unit analyzes the content of the corporate AI's response and receives detailed information for important responses. It receives concise information for less important responses. It selects the optimal receiving method based on the content of the corporate AI's response. This allows important responses to be received in detail by adjusting the level of detail based on the content of the corporate AI's response. Some or all of the above processing in the receiving unit may be performed using AI, for example, or without AI. For example, the receiving unit can input the content of the corporate AI's response into the AI ​​and have the AI ​​perform the adjustment of the level of detail of the received data.

[0044] The receiving unit can apply different receiving algorithms depending on the category of the corporate AI upon receiving data. For example, the receiving unit can receive detailed information about travel in response to a response from a travel-related corporate AI. It can also receive detailed information about products in response to a response from an e-commerce site corporate AI. Furthermore, it can receive detailed information about financial products in response to a response from a financial-related corporate AI. For example, the receiving unit can receive detailed information about travel plans and discounts in response to a travel-related corporate AI. It can receive detailed information about product availability and pricing in response to a response from an e-commerce site corporate AI. It can receive detailed information about interest rates and conditions for financial products in response to a response from a financial-related corporate AI. This allows the receiving unit to provide the optimal receiving method by applying different receiving algorithms depending on the category of the corporate AI. Some or all of the processing described above in the receiving unit may be performed using AI, for example, or without AI. For example, the receiving unit can input the category of the corporate AI into the AI ​​and have the AI ​​apply different receiving algorithms.

[0045] The receiving unit can determine the priority of reception based on the response speed of the corporate AIs. For example, the receiving unit may prioritize receiving responses from corporate AIs with fast response speeds. It can also postpone receiving responses from corporate AIs with slow response speeds. Furthermore, the receiving unit can determine the optimal reception order based on the response speed of the corporate AIs. For example, the receiving unit may monitor the response speed of the corporate AIs in real time and prioritize receiving responses from corporate AIs with fast response speeds, postpone receiving responses from corporate AIs with slow response speeds, and determine the optimal reception order based on the response speed of the corporate AIs. This allows for the priority of receiving responses that require a quick response, by determining the priority of reception based on the response speed of the corporate AIs. Some or all of the above processing in the receiving unit may be performed using AI, or not using AI. For example, the receiving unit may input the response speed of the corporate AIs into the AI ​​and have the AI ​​perform the determination of the reception priority.

[0046] The receiving unit can adjust the order of reception based on the relevance of the corporate AIs. For example, the receiving unit can prioritize receiving responses from corporate AIs with high relevance. It can also postpone receiving responses from corporate AIs with low relevance. Furthermore, the receiving unit can determine the optimal reception order based on the relevance of the corporate AIs. For example, the receiving unit can evaluate the relevance of the corporate AIs and prioritize receiving responses from corporate AIs with high relevance, postpone receiving responses from corporate AIs with low relevance, and determine the optimal reception order based on the relevance of the corporate AIs. This allows the receiving unit to prioritize receiving responses from corporate AIs with high relevance by adjusting the reception order based on the relevance of the corporate AIs. Some or all of the above processing in the receiving unit may be performed using AI, for example, or without AI. For example, the receiving unit can input the relevance of the corporate AIs into an AI and have the AI ​​perform the adjustment of the reception order.

[0047] The receiving unit can adjust the order of reception based on the relevance of the corporate AIs. For example, the receiving unit can prioritize receiving responses from corporate AIs with high relevance. It can also postpone receiving responses from corporate AIs with low relevance. Furthermore, the receiving unit can determine the optimal reception order based on the relevance of the corporate AIs. For example, the receiving unit can evaluate the relevance of the corporate AIs and prioritize receiving responses from corporate AIs with high relevance, postpone receiving responses from corporate AIs with low relevance, and determine the optimal reception order based on the relevance of the corporate AIs. This allows the receiving unit to prioritize receiving responses from corporate AIs with high relevance by adjusting the reception order based on the relevance of the corporate AIs. Some or all of the above processing in the receiving unit may be performed using AI, for example, or without AI. For example, the receiving unit can input the relevance of the corporate AIs into an AI and have the AI ​​perform the adjustment of the reception order.

[0048] The delivery unit can adjust the level of detail provided based on the importance of the response at the time of delivery. For example, the delivery unit can provide detailed information for important responses. It can also provide concise information for less important responses. Furthermore, the delivery unit can select the optimal delivery method based on the importance of the response. For example, the delivery unit can analyze the content of the response and provide detailed information for important responses. It can provide concise information for less important responses. It can select the optimal delivery method based on the importance of the response. In this way, by adjusting the level of detail provided based on the importance of the response, important responses can be provided in detail. Some or all of the above processing in the delivery unit may be performed using AI, for example, or not using AI. For example, the delivery unit can input the importance of the response into the AI ​​and have the AI ​​perform the adjustment of the level of detail provided.

[0049] The service provider can apply different service provision algorithms depending on the category of the response at the time of provision. For example, for travel-related responses, the service provider can provide detailed information about travel. It can also provide detailed information about products for e-commerce site responses. Furthermore, it can provide detailed information about financial products for financial-related responses. For example, for travel-related responses, the service provider can provide detailed information about travel plans and discounts. For e-commerce site responses, it can provide detailed information about product availability and pricing. For financial-related responses, it can provide detailed information about interest rates and conditions for financial products. This allows the service provider to provide the optimal service method by applying different service provision algorithms depending on the category of the response. Some or all of the above processing in the service provider may be performed using AI, for example, or without AI. For example, the service provider can input the response category into the AI ​​and have the AI ​​apply different service provision algorithms.

[0050] The service provider can determine the priority of responses based on their submission timing at the time of delivery. For example, the service provider may prioritize responses submitted earlier. It may also postpone the delivery of responses submitted later. Furthermore, the service provider can determine the optimal delivery order based on the submission timing of responses. For example, the service provider may evaluate the submission dates and times of responses and prioritize responses submitted earlier, postpone the delivery of responses submitted later, or determine the optimal delivery order based on the submission timing of responses. This allows the service provider to prioritize responses submitted earlier by determining the priority of deliveries based on their submission timing. Some or all of the above processing in the service provider may be performed using AI, for example, or not. For example, the service provider can input the submission timing of responses into an AI and have the AI ​​determine the priority of deliveries.

[0051] The service provider can adjust the order of service delivery based on the relevance of the responses. For example, the service provider may prioritize providing highly relevant responses. It may also postpone providing less relevant responses. Furthermore, the service provider can determine the optimal order of service delivery based on the relevance of the responses. For example, the service provider may evaluate the relevance of the responses and prioritize providing highly relevant responses, postpone providing less relevant responses, and determine the optimal order of service delivery based on the relevance of the responses. This allows the service provider to prioritize providing highly relevant responses by adjusting the order of service delivery based on the relevance of the responses. Some or all of the above processing in the service provider may be performed using AI, for example, or without AI. For example, the service provider can input the relevance of the responses into the AI ​​and have the AI ​​perform the adjustment of the order of service delivery.

[0052] The management department can analyze the dialogue history between individual AI and corporate AI during management to select the optimal management method. For example, the management department can select the optimal management method based on the past dialogue history between individual AI and corporate AI. The management department can also identify frequently occurring problems from the dialogue history and propose the optimal management method. Furthermore, the management department can analyze the dialogue history and select an efficient management method. For example, the management department can store the past dialogue history between individual AI and corporate AI in a database and select the optimal management method. It can identify frequently occurring problems from the dialogue history and propose the optimal management method. It can analyze the dialogue history and select an efficient management method. In this way, the optimal management method can be selected by analyzing the dialogue history between individual AI and corporate AI. Some or all of the above processes in the management department may be performed using AI, for example, or not using AI. For example, the management department can input the dialogue history into AI and have the AI ​​select the optimal management method.

[0053] The management department can apply different management algorithms depending on the category of individual AI and corporate AI during management. For example, the management department can apply a travel-related management algorithm to travel-related conversations. It can also apply a product-related management algorithm to conversations on e-commerce sites. Furthermore, it can apply a financial product-related management algorithm to conversations on finance. For example, the management department can apply a management algorithm regarding travel plans and discount information to travel-related conversations. For conversations on e-commerce sites, it can apply a management algorithm regarding product inventory status and pricing. For financial conversations, it can apply a management algorithm regarding interest rates and conditions of financial products. In this way, by applying different management algorithms depending on the category of individual AI and corporate AI, the optimal management method can be provided. Some or all of the above processing in the management department may be performed using AI, for example, or not using AI. For example, the management department can input the categories of individual AI and corporate AI into the AI ​​and have the AI ​​execute the application of different management algorithms.

[0054] The management department can determine the priority of conversations based on the response speed of the individual AI and the corporate AI during management. For example, the management department can prioritize conversations with fast response speeds. It can also postpone the management of conversations with slow response speeds. Furthermore, the management department can determine the optimal order of conversations based on the response speeds of the individual AI and the corporate AI. For example, the management department can monitor the response speeds of the individual AI and the corporate AI in real time and prioritize the management of conversations with fast response speeds. It can postpone the management of conversations with slow response speeds. It can determine the optimal order of conversations based on the response speeds of the individual AI and the corporate AI. In this way, by determining the priority of conversations based on the response speeds of the individual AI and the corporate AI, it is possible to prioritize the management of conversations that require a quick response. Some or all of the above processing in the management department may be performed using AI, for example, or not using AI. For example, the management department can input the response speeds of the individual AI and the corporate AI into the AI ​​and have the AI ​​perform the task of determining the priority of conversations.

[0055] The management department can adjust the order of conversations based on the relationship between the individual AI and the corporate AI during management. For example, the management department can prioritize managing conversations that are highly relevant. It can also postpone managing conversations that are less relevant. Furthermore, the management department can determine the optimal order of conversations based on the relationship between the individual AI and the corporate AI. For example, the management department can evaluate the relationship between the individual AI and the corporate AI and prioritize managing conversations that are highly relevant. It can postpone managing conversations that are less relevant. It can determine the optimal order of conversations based on the relationship between the individual AI and the corporate AI. In this way, by adjusting the order of conversations based on the relationship between the individual AI and the corporate AI, it is possible to prioritize managing conversations that are highly relevant. Some or all of the above processes in the management department may be performed using AI, for example, or not using AI. For example, the management department can input the relationship between the individual AI and the corporate AI into the AI ​​and have the AI ​​perform the adjustment of the order of conversations.

[0056] The system according to the embodiment is not limited to the example described above, and various modifications are possible, for example, as follows.

[0057] The reception desk can analyze a user's past instruction history and select the optimal reception method. For example, it can automatically display instructions that the user has frequently entered in the past as suggestions. It can also prioritize suggesting input methods (voice, text, etc.) that the user has used in the past. Furthermore, it can predict and suggest instructions that the user will use during specific time periods based on their past instruction history. In this way, by analyzing a user's past instruction history, the reception desk can provide the most suitable reception method for the user.

[0058] The reception unit can filter instructions based on the user's current situation or areas of interest. For example, it can prioritize receiving instructions relevant to the user's current situation. It can also filter and receive relevant instructions based on the user's areas of interest. Furthermore, it can suggest the most appropriate instructions based on the user's current situation and areas of interest. This allows for the priority of receiving highly relevant instructions by filtering them based on the user's current situation and areas of interest.

[0059] The inquiry department can adjust the level of detail in inquiries based on the importance of the corporate AI. For example, it can send detailed inquiries to important corporate AIs and concise inquiries to less important ones. Furthermore, it can select the optimal inquiry method based on the importance of the corporate AI. This allows for optimal inquiries by adjusting the level of detail based on the importance of the corporate AI.

[0060] The receiving unit can adjust the level of detail received based on the content of the enterprise AI's response. For example, it can receive detailed information for important responses, and concise information for less important responses. Furthermore, it can select the optimal receiving method based on the content of the enterprise AI's response. This allows for detailed reception of important responses by adjusting the level of detail based on the content of the enterprise AI's response.

[0061] The management department can analyze the dialogue history between individual AI and corporate AI during management to select the optimal management method. For example, it can select the optimal management method based on the past dialogue history of individual AI and corporate AI. It can also identify frequently occurring problems from the dialogue history and propose the optimal management method. Furthermore, it can analyze the dialogue history to select an efficient management method. In this way, the optimal management method can be selected by analyzing the dialogue history of individual AI and corporate AI.

[0062] The following briefly describes the processing flow for example form 1.

[0063] Step 1: The reception desk receives user instructions. User instructions include voice instructions, text instructions, and gesture instructions. The reception desk can receive the user's voice instructions using voice recognition technology, the user's text instructions using a text input interface, and the user's gesture instructions using gesture recognition technology. Step 2: The inquiry department makes inquiries to the corporate AI based on the instructions received by the reception department. The corporate AI includes customer support AI and sales support AI. The inquiry department can send the user's inquiry to the corporate AI and can also make inquiries to multiple corporate AIs simultaneously. Step 3: The receiving unit receives responses from the enterprise AI. These responses include text responses, voice responses, and image responses. The receiving unit receives text-based responses, converts voice-based responses to text using speech recognition technology, and understands the content of image-based responses using image analysis technology. Step 4: The providing unit analyzes the response received by the receiving unit and provides it to the user. The providing unit can display the response in text format to the user, play the response in audio format to the user, or display the response in image format to the user. Step 5: The management department manages the conversations between the personal AI and the enterprise AI. The management department monitors the progress of the conversations, adjusts them as needed, records the conversation history for later reference, and analyzes the content of the conversations to identify areas for improvement.

[0064] (Example of form 2) The interactive multi-agent system according to an embodiment of the present invention is a system in which a privately owned AI agent and a corporate AI agent conduct multi-dialogue on a virtual platform. This system enables a private AI to interact with multiple corporate AIs, achieving immediate problem resolution, service comparison, and fluid mutual proposals and interactions. First, a privately owned AI agent (hereinafter referred to as "private AI") connects to the virtual platform. Next, based on user instructions, the private AI begins interacting with multiple corporate AI agents (hereinafter referred to as "corporate AIs"). For example, if a user instructs "I want to book a trip," the private AI queries travel-related corporate AIs for information. The corporate AIs respond to the inquiry from the private AI based on the data they hold. For example, a travel agent's corporate AI might propose the optimal travel plan based on travel data and provide discount information and booking procedures. Furthermore, multiple corporate AIs can collaborate to provide the optimal service tailored to the user's needs. This system allows users to interact with multiple corporate AIs through their private AI, efficiently acquire information, and utilize services. For example, if a user is looking for a specific product, the private AI queries corporate AIs of multiple e-commerce sites to provide optimal product information. Furthermore, if a user wishes to book a trip, the personal AI will contact corporate AIs of multiple travel agencies to propose the optimal travel plan. Moreover, since the interaction between the personal AI and corporate AI takes place in real time, users can obtain information immediately and resolve their issues quickly. The interaction between the personal AI and corporate AI can also be flexibly adapted to the user's requests, allowing users to receive the best possible service tailored to their needs. This system is an interactive multi-agent system where personal AI and corporate AI work together in the background, enabling users to experience diverse services by interacting with multiple corporate AIs through the personal AI. For example, if a user is looking for a specific product, the personal AI will contact corporate AIs of multiple e-commerce sites to provide the best product information. Similarly, if a user wishes to book a trip, the personal AI will contact corporate AIs of multiple travel agencies to propose the optimal travel plan.This system allows users to interact with multiple corporate AIs through their personal AI, efficiently acquiring information and utilizing services. Furthermore, since the interaction between the personal AI and corporate AIs takes place in real time, users can obtain information immediately and quickly resolve their issues. As a result, the conversational multi-agent system can quickly resolve user issues and efficiently provide information.

[0065] The interactive multi-agent system according to this embodiment comprises a reception unit, an inquiry unit, a receiving unit, a provision unit, and a management 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 the user's voice instructions using, for example, speech recognition technology. The reception unit can also receive the user's text instructions using a text input interface. Furthermore, the reception unit can also receive the user's gesture instructions using gesture recognition technology. For example, the reception unit analyzes the user's voice instructions using speech recognition technology and understands the content of the instructions. The text input interface receives text instructions entered by the user using a keyboard or touchscreen. Gesture recognition technology captures the user's hand movements and body movements with a camera and analyzes the content of the instructions. The inquiry unit makes inquiries to the enterprise AI based on the instructions received by the reception unit. The enterprise AI includes, but is not limited to, a customer support AI and a sales support AI. The inquiry unit sends the user's inquiry to, for example, the customer support AI. Furthermore, the inquiry unit can communicate user requests to the sales support AI. In addition, the inquiry unit can simultaneously submit inquiries to multiple company AIs. For example, the inquiry unit can send a user inquiry to the customer support AI, requesting a prompt response. It can also communicate the user's requests to the sales support AI, requesting the best possible proposal. By simultaneously submitting inquiries to multiple company AIs, information is collected efficiently. The receiving unit receives responses from the company AIs. Responses include, but are not limited to, text responses, voice responses, and image responses. For example, the receiving unit receives a text-based response and analyzes its content. It can also receive a voice-based response and convert it to text using speech recognition technology. Furthermore, it can receive an image-based response and understand its content using image analysis technology. For example, the receiving unit receives a text-based response and analyzes its content using natural language processing technology.Voice responses are converted to text using speech recognition technology, and their content is understood. Image responses are analyzed using image analysis technology and provided to the user. The delivery unit analyzes the responses received by the receiving unit and provides them to the user. The delivery unit, for example, displays text responses to the user. The delivery unit can also play voice responses to the user. Furthermore, the delivery unit can also display image responses to the user. For example, the delivery unit displays text responses on the user's device for confirmation. Voice responses are played on the user's device to convey the content. Image responses are displayed on the user's device to provide information visually. The management unit manages the dialogue between the personal AI and the enterprise AI. For example, the management unit monitors the progress of the dialogue and adjusts it as needed. The management unit can also record the history of the dialogue for later reference. Furthermore, the management unit can analyze the content of the dialogue and find areas for improvement. For example, the management unit monitors the progress of the dialogue in real time and adjusts the dialogue if problems occur. The history of the conversation is recorded in a database and can be referenced later. The content of the conversation is analyzed to find areas for improvement that meet the user's needs. As a result, the conversational multi-agent system according to this embodiment can immediately solve the user's problems by receiving user instructions, querying the enterprise AI, receiving responses, analyzing them, and providing them.

[0066] 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, for example, receive voice instructions using speech recognition technology. Specifically, speech recognition technology collects the user's speech with a microphone and converts the voice signal into digital data. Then, a speech recognition engine analyzes the voice data and converts the spoken content into text. This allows the system to understand the user's voice instructions. The reception unit can also receive text instructions from the user using a text input interface. The text input interface receives text data entered by the user using a keyboard or touchscreen and transmits it to the system. Furthermore, the reception unit can also receive gesture instructions from the user using gesture recognition technology. Gesture recognition technology captures the user's hand and body movements using cameras and sensors, analyzes those movements, and understands the instructions. For example, if a user waves their hand, that movement is recognized as a specific instruction. This allows the reception unit to flexibly receive user instructions through various input methods, including voice, text, and gestures. Furthermore, the reception desk can combine these input methods to improve user convenience. For example, voice and gesture instructions can be combined to provide more complex instructions. This allows the reception desk to meet the diverse needs of users and enable intuitive and efficient operation.

[0067] The inquiry department makes inquiries to the corporate AI based on instructions received by the reception department. The corporate AI includes, but is not limited to, customer support AI and sales support AI. For example, the inquiry department sends user inquiries to the customer support AI. Specifically, if a user inquires about a product defect, the inquiry department sends the details to the customer support AI and requests an appropriate response. The inquiry department can also communicate user requests to the sales support AI. For example, if a user requests a proposal for a new product, the inquiry department sends the request to the sales support AI and requests the best possible proposal. Furthermore, the inquiry department can make inquiries to multiple corporate AIs simultaneously. For example, if a user requests information about multiple products, the inquiry department will contact both the customer support AI and the sales support AI to collect information quickly and efficiently. This allows the inquiry department to respond to diverse user needs and provide information promptly. Additionally, the inquiry department can appropriately format the inquiry content and include necessary information to optimize communication with the corporate AI. For example, including past conversation history and user profile information related to the inquiry allows the corporate AI to respond more accurately and quickly. This will enable the inquiry department to effectively integrate with corporate AI and improve user satisfaction.

[0068] The receiving unit receives responses from the enterprise AI. These responses include, but are not limited to, text responses, voice responses, and image responses. For example, the receiving unit receives a text-based response and analyzes its content. Specifically, text-based responses are analyzed using natural language processing techniques to extract answers to user inquiries. The receiving unit can also receive voice-based responses and convert them to text using speech recognition technology. For voice-based responses, the receiving unit receives voice data generated by the enterprise AI, and a speech recognition engine converts this data into text. This allows the content of the voice response to be understood as text. Furthermore, the receiving unit can receive image-based responses and understand their content using image analysis technology. For image-based responses, the receiving unit receives image data generated by the enterprise AI, and an image analysis engine analyzes the image data to understand its content. For example, if product manuals or diagrams are provided in image format, the receiving unit analyzes their content and provides it to the user. This allows the receiving unit to receive and appropriately analyze responses in various formats from the enterprise AI. Additionally, the receiving unit can evaluate the reliability and accuracy of the responses and re-query as needed. For example, if the received response is incomplete, the receiving unit requests additional information from the enterprise AI to ensure the quality of the information provided to the user. This allows the receiving unit to provide high-quality information to the user and improve the overall reliability of the system.

[0069] The delivery unit analyzes the response received by the receiving unit and provides it to the user. For example, the delivery unit displays the response to the user in text format. Specifically, the text response is displayed on the user's device, allowing the user to review the content. The delivery unit can also play an audio response to the user. The audio response is played on the user's device, allowing the user to listen to the content. Furthermore, the delivery unit can display an image response to the user. The image response is displayed on the user's device, providing information visually. For example, if a product manual or diagram is provided in image format, the delivery unit displays the image on the user's device, allowing the user to understand the content. This allows the delivery unit to provide the response received from the receiving unit in an appropriate format, improving user convenience. Furthermore, the delivery unit can collect user feedback and continuously improve the accuracy and effectiveness of the provided content. For example, by having users evaluate and comment on the provided information, the delivery unit can review and improve the content based on that feedback. The delivery unit can also reliably transmit information using multiple communication methods. For example, by using a combination of methods such as text messages, voice calls, and email, important information can be reliably delivered to users. This allows the service provider to deliver information quickly and reliably to users, thereby improving user satisfaction.

[0070] The management department manages the interactions between personal AI and enterprise AI. For example, the management department monitors the progress of the interactions and adjusts them as needed. Specifically, the management department monitors each step of the interaction in real time and adjusts the interaction if problems arise. For example, if a user's instructions are not properly understood, the management department reconfirms the instructions and takes appropriate action. The management department can also record the history of the interactions for later reference. The history of the interactions is recorded in a database, allowing users to review past inquiries and responses received. Furthermore, the management department can analyze the content of the interactions and identify areas for improvement. For example, by analyzing the content of the interactions and identifying areas for improvement based on user requests, the accuracy and efficiency of the system can be improved. This allows the management department to effectively manage the interactions between personal AI and enterprise AI, improving the overall reliability of the system and user satisfaction. Additionally, the management department can perform analysis based on the interaction data to evaluate the system's performance. For example, they can analyze the success rate of the interactions and the response time to identify areas for system improvement. The management department can also collect user feedback to help improve the system. This allows the management department to continuously improve the system and provide high-quality services to users.

[0071] The reception system can estimate the user's emotions and adjust how instructions are received based on those emotions. For example, if the user is stressed, the reception system can provide a simple interface and minimize the input steps. If the user is relaxed, the reception system can also provide detailed input options and suggest customizable input methods. Furthermore, if the user is in a hurry, the reception system can prioritize voice input to allow for quick instruction input. For example, the reception system can capture the user's facial expressions with a camera and estimate their emotions using an emotion estimation algorithm. If the user is stressed, it provides a simple interface and minimizes the input steps. If the user is relaxed, it provides detailed input options and suggests customizable input methods. If the user is in a hurry, it prioritizes voice input to allow for quick instruction input. This allows the system to provide the optimal interface for the user by adjusting how instructions are received according to their emotions. Emotion estimation is achieved using emotion estimation functions, such as an emotion engine or generative AI. Generative AI includes, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI.

[0072] The reception desk can analyze the user's past instruction history and select the optimal reception method. For example, the reception desk can automatically display instructions that the user has frequently entered in the past as suggestions. The reception desk can also prioritize suggesting input methods (voice, text, etc.) that the user has used in the past. Furthermore, the reception desk can predict and suggest instructions to be used during specific time periods based on the user's past instruction history. For example, the reception desk can store the user's past instruction history in a database and automatically display frequently entered instructions as suggestions. It improves user convenience by prioritizing and suggesting input methods that the user has used in the past. It enables efficient instruction input by predicting and suggesting instructions to be used during specific time periods. In this way, by analyzing the user's past instruction history, the reception desk can provide the user with the optimal reception method. Some or all of the above processes in the reception desk may be performed using AI, for example, or not using AI. For example, the reception desk can input the user's past instruction history into AI and have the AI ​​select the optimal reception method.

[0073] The reception unit can filter instructions based on the user's current situation or areas of interest when receiving them. For example, the reception unit can prioritize receiving relevant instructions based on the user's current situation. The reception unit can also filter and receive relevant instructions based on the user's areas of interest. Furthermore, the reception unit can suggest the most appropriate instructions based on the user's current situation and areas of interest. For example, the reception unit can prioritize receiving relevant instructions based on the user's location and time of day. It can filter and receive relevant instructions based on the user's areas of interest. It can suggest the most appropriate instructions based on the user's current situation and areas of interest. This allows for the priority of receiving highly relevant instructions by filtering instructions 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 AI, for example, or not. For example, the reception unit can input the user's location and areas of interest into the AI ​​and have the AI ​​perform the filtering of the most appropriate instructions.

[0074] The reception system can estimate the user's emotions and determine the priority of instructions to receive based on the estimated emotions. For example, if the user is stressed, the reception system will prioritize important instructions. If the user is relaxed, the reception system can also prioritize detailed instructions. Furthermore, if the user is in a hurry, the reception system can prioritize instructions that require quick processing. For example, the reception system can capture the user's facial expression with a camera and estimate their emotions using an emotion estimation algorithm. If the user is stressed, important instructions will be prioritized. If the user is relaxed, detailed instructions will be prioritized. If the user is in a hurry, instructions that require quick processing will be prioritized. This allows for prioritizing instructions according to the user's emotions, ensuring that important instructions are received first. Emotion estimation is achieved using an emotion estimation function, such as an emotion engine or generative AI. Generative AI includes, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI.

[0075] The reception unit can prioritize receiving instructions that are highly relevant, taking into account the user's geographical location information. For example, if the user is in a specific location, the reception unit will prioritize receiving instructions related to that location. The reception unit can also suggest the most appropriate instructions based on the user's geographical location information. Furthermore, if the user is on the move, the reception unit can prioritize receiving relevant instructions based on their current location. For example, the reception unit can obtain the user's location information from GPS data and prioritize receiving instructions related to that location. It will suggest the most appropriate instructions based on the user's geographical location information. If the user is on the move, it will prioritize receiving relevant instructions based on their current location. This allows the reception unit to provide the user with the most appropriate instructions by prioritizing the receipt of highly relevant instructions based on the user's geographical location information. Some or all of the above processing in the reception unit may be performed using AI, for example, or not. For example, the reception unit can input the user's geographical location information into the AI ​​and have the AI ​​prioritize receiving highly relevant instructions.

[0076] The reception unit can analyze the user's social media activity when receiving instructions and receive relevant instructions. For example, the reception unit can prioritize receiving relevant instructions based on the user's social media activity. The reception unit can also analyze the user's social media activity and suggest the most appropriate instructions. Furthermore, the reception unit can also receive instructions related to the user's current areas of interest based on the user's social media activity. For example, the reception unit can analyze the user's social media activity using data mining techniques and prioritize receiving relevant instructions. It analyzes the user's social media activity and suggests the most appropriate instructions. It receives instructions related to the user's current areas of interest based on the user's social media activity. This allows the reception unit to provide the user with the most appropriate instructions by receiving relevant instructions based on the user's social media activity. Some or all of the above processing in the reception unit may be performed using AI, for example, or not using AI. For example, the reception unit can input the user's social media activity into AI and have AI perform the task of receiving relevant instructions.

[0077] The inquiry unit can estimate the user's emotions and adjust the way the inquiry is phrased based on the estimated emotions. For example, if the user is nervous, the inquiry unit will provide a simple and easy-to-understand expression. If the user is relaxed, the inquiry unit can also provide an expression that includes detailed information. Furthermore, if the user is in a hurry, the inquiry unit can provide an expression that can be quickly understood. For example, the inquiry unit can capture the user's facial expression with a camera and estimate their emotions using an emotion estimation algorithm. If the user is nervous, it will provide a simple and easy-to-understand expression. If the user is relaxed, it will provide an expression that includes detailed information. If the user is in a hurry, it will provide an expression that can be quickly understood. This allows the inquiry to be phrased in a way that is optimal for the user by adjusting the way the inquiry is phrased 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.

[0078] The inquiry unit can adjust the level of detail of an inquiry based on the importance of the corporate AI. For example, the inquiry unit will make a detailed inquiry to important corporate AIs. It can also make a concise inquiry to less important corporate AIs. Furthermore, the inquiry unit can select the optimal inquiry method based on the importance of the corporate AI. For example, the inquiry unit will make a detailed inquiry to important corporate AIs based on the size of the company and the urgency of the inquiry. It will make a concise inquiry to less important corporate AIs. It will select the optimal inquiry method based on the importance of the corporate AI. In this way, by adjusting the level of detail of the inquiry based on the importance of the corporate AI, the most optimal inquiry can be made. Some or all of the above processing in the inquiry unit may be performed using AI, for example, or not using AI. For example, the inquiry unit can input the importance of the corporate AI into the AI ​​and have the AI ​​perform the adjustment of the level of detail of the inquiry.

[0079] The inquiry unit can apply different inquiry algorithms depending on the category of the corporate AI when an inquiry is made. For example, the inquiry unit can make detailed inquiries about travel to corporate AIs related to travel. It can also make detailed inquiries about products to corporate AIs related to e-commerce sites. Furthermore, it can make detailed inquiries about financial products to corporate AIs related to finance. For example, the inquiry unit can make detailed inquiries about travel plans and discount information to corporate AIs related to travel. It can make detailed inquiries about product availability and prices to corporate AIs related to e-commerce sites. It can make detailed inquiries about interest rates and conditions of financial products to corporate AIs related to finance. In this way, by applying different inquiry algorithms depending on the category of the corporate AI, the most optimal inquiry can be made. Some or all of the above processing in the inquiry unit may be performed using AI, for example, or not using AI. For example, the inquiry unit can input the category of the corporate AI into the AI ​​and have the AI ​​execute the application of different inquiry algorithms.

[0080] The inquiry unit can estimate the user's emotions and adjust the length of the inquiry based on the estimated emotions. For example, if the user is nervous, the inquiry unit will make a short, to-the-point inquiry. If the user is relaxed, the inquiry unit can make a longer inquiry that includes more detailed information. Furthermore, if the user is in a hurry, the inquiry unit can make a short inquiry that can be quickly understood. For example, the inquiry unit can capture the user's facial expression with a camera and estimate their emotions using an emotion estimation algorithm. If the user is nervous, it will make a short, to-the-point inquiry. If the user is relaxed, it will make a longer inquiry that includes more detailed information. If the user is in a hurry, it will make a short inquiry that can be quickly understood. In this way, by adjusting the length of the inquiry according to the user's emotions, the inquiry can be made in a way that is optimal for the user. Emotion estimation is achieved using an emotion estimation function, for example, using an emotion engine or generative AI. Generative AI is a text generation AI (e.g., LLM) or a multimodal generation AI, but is not limited to these examples.

[0081] The inquiry unit can determine the priority of inquiries based on the response speed of the corporate AI. For example, the inquiry unit will prioritize inquiries to corporate AIs with fast response speeds. It can also postpone inquiries to corporate AIs with slow response speeds. Furthermore, the inquiry unit can determine the optimal inquiry order based on the response speed of the corporate AIs. For example, the inquiry unit can monitor the response speed of corporate AIs in real time and prioritize inquiries to corporate AIs with fast response speeds. It will postpone inquiries to corporate AIs with slow response speeds. It will determine the optimal inquiry order based on the response speed of the corporate AIs. This allows inquiries requiring a quick response to be prioritized by determining the priority of inquiries based on the response speed of the corporate AIs. Some or all of the above processing in the inquiry unit may be performed using AI, or not using AI. For example, the inquiry unit can input the response speed of corporate AIs into the AI ​​and have the AI ​​determine the priority of inquiries.

[0082] The inquiry unit can adjust the order of inquiries based on the relevance of the corporate AIs. For example, the inquiry unit can prioritize inquiries to corporate AIs with high relevance. It can also postpone inquiries to corporate AIs with low relevance. Furthermore, the inquiry unit can determine the optimal inquiry order based on the relevance of the corporate AIs. For example, the inquiry unit can evaluate the relevance of the corporate AIs and prioritize inquiries to corporate AIs with high relevance. It can postpone inquiries to corporate AIs with low relevance. It determines the optimal inquiry order based on the relevance of the corporate AIs. In this way, by adjusting the order of inquiries based on the relevance of the corporate AIs, it is possible to prioritize inquiries to corporate AIs with high relevance. Some or all of the above processing in the inquiry unit may be performed using AI, or not using AI. For example, the inquiry unit can input the relevance of the corporate AIs into the AI ​​and have the AI ​​perform the adjustment of the inquiry order.

[0083] The receiver can estimate the user's emotions and adjust the response delivery method based on the estimated emotions. For example, if the user is nervous, the receiver provides a simple and easy-to-understand response. If the user is relaxed, the receiver can also provide a response containing detailed information. Furthermore, if the user is in a hurry, the receiver can provide a response that can be quickly understood. For example, the receiver captures the user's facial expression with a camera and estimates the emotion using an emotion estimation algorithm. If the user is nervous, it provides a simple and easy-to-understand response. If the user is relaxed, it provides a response containing detailed information. If the user is in a hurry, it provides a response that can be quickly understood. This allows the user to receive the optimal response by adjusting the response delivery method according to their emotions. Emotion estimation is achieved using an emotion estimation function, for example, using an emotion engine or generative AI. Generative AI includes, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI.

[0084] The receiving unit can adjust the level of detail of the received data based on the content of the corporate AI's response. For example, the receiving unit can receive detailed information for important responses. It can also receive concise information for less important responses. Furthermore, the receiving unit can select the optimal receiving method based on the content of the corporate AI's response. For example, the receiving unit analyzes the content of the corporate AI's response and receives detailed information for important responses. It receives concise information for less important responses. It selects the optimal receiving method based on the content of the corporate AI's response. This allows important responses to be received in detail by adjusting the level of detail based on the content of the corporate AI's response. Some or all of the above processing in the receiving unit may be performed using AI, for example, or without AI. For example, the receiving unit can input the content of the corporate AI's response into the AI ​​and have the AI ​​perform the adjustment of the level of detail of the received data.

[0085] The receiving unit can apply different receiving algorithms depending on the category of the corporate AI upon receiving data. For example, the receiving unit can receive detailed information about travel in response to a response from a travel-related corporate AI. It can also receive detailed information about products in response to a response from an e-commerce site corporate AI. Furthermore, it can receive detailed information about financial products in response to a response from a financial-related corporate AI. For example, the receiving unit can receive detailed information about travel plans and discounts in response to a travel-related corporate AI. It can receive detailed information about product availability and pricing in response to a response from an e-commerce site corporate AI. It can receive detailed information about interest rates and conditions for financial products in response to a response from a financial-related corporate AI. This allows the receiving unit to provide the optimal receiving method by applying different receiving algorithms depending on the category of the corporate AI. Some or all of the processing described above in the receiving unit may be performed using AI, for example, or without AI. For example, the receiving unit can input the category of the corporate AI into the AI ​​and have the AI ​​apply different receiving algorithms.

[0086] The receiving unit can estimate the user's emotions and determine the priority of responses to receive based on the estimated emotions. For example, if the user is stressed, the receiving unit will prioritize receiving important responses. The receiving unit can also prioritize receiving detailed responses if the user is relaxed. Furthermore, if the user is in a hurry, the receiving unit can prioritize receiving responses that require quick processing. For example, the receiving unit captures the user's facial expression with a camera and estimates their emotions using an emotion estimation algorithm. If the user is stressed, it prioritizes receiving important responses. If the user is relaxed, it prioritizes receiving detailed responses. If the user is in a hurry, it prioritizes receiving responses that require quick processing. This allows for the priority of receiving important responses by determining the priority of responses according to the user's emotions. Emotion estimation is achieved using an emotion estimation function, for example, with an emotion engine or generative AI. Generative AI includes, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI.

[0087] The receiving unit can determine the priority of reception based on the response speed of the corporate AIs. For example, the receiving unit may prioritize receiving responses from corporate AIs with fast response speeds. It can also postpone receiving responses from corporate AIs with slow response speeds. Furthermore, the receiving unit can determine the optimal reception order based on the response speed of the corporate AIs. For example, the receiving unit may monitor the response speed of the corporate AIs in real time and prioritize receiving responses from corporate AIs with fast response speeds, postpone receiving responses from corporate AIs with slow response speeds, and determine the optimal reception order based on the response speed of the corporate AIs. This allows for the priority of receiving responses that require a quick response, by determining the priority of reception based on the response speed of the corporate AIs. Some or all of the above processing in the receiving unit may be performed using AI, or not using AI. For example, the receiving unit may input the response speed of the corporate AIs into the AI ​​and have the AI ​​perform the determination of the reception priority.

[0088] The receiving unit can adjust the order of reception based on the relevance of the corporate AIs. For example, the receiving unit can prioritize receiving responses from corporate AIs with high relevance. It can also postpone receiving responses from corporate AIs with low relevance. Furthermore, the receiving unit can determine the optimal reception order based on the relevance of the corporate AIs. For example, the receiving unit can evaluate the relevance of the corporate AIs and prioritize receiving responses from corporate AIs with high relevance, postpone receiving responses from corporate AIs with low relevance, and determine the optimal reception order based on the relevance of the corporate AIs. This allows the receiving unit to prioritize receiving responses from corporate AIs with high relevance by adjusting the reception order based on the relevance of the corporate AIs. Some or all of the above processing in the receiving unit may be performed using AI, for example, or without AI. For example, the receiving unit can input the relevance of the corporate AIs into an AI and have the AI ​​perform the adjustment of the reception order.

[0089] The receiving unit can adjust the order of reception based on the relevance of the corporate AIs. For example, the receiving unit can prioritize receiving responses from corporate AIs with high relevance. It can also postpone receiving responses from corporate AIs with low relevance. Furthermore, the receiving unit can determine the optimal reception order based on the relevance of the corporate AIs. For example, the receiving unit can evaluate the relevance of the corporate AIs and prioritize receiving responses from corporate AIs with high relevance, postpone receiving responses from corporate AIs with low relevance, and determine the optimal reception order based on the relevance of the corporate AIs. This allows the receiving unit to prioritize receiving responses from corporate AIs with high relevance by adjusting the reception order based on the relevance of the corporate AIs. Some or all of the above processing in the receiving unit may be performed using AI, for example, or without AI. For example, the receiving unit can input the relevance of the corporate AIs into an AI and have the AI ​​perform the adjustment of the reception order.

[0090] The service provider can estimate the user's emotions and adjust the response delivery method based on the estimated emotions. For example, if the user is nervous, the service provider will provide a simple and easy-to-understand response. If the user is relaxed, the service provider may also provide a response that includes detailed information. Furthermore, if the user is in a hurry, the service provider may also provide a response that can be quickly understood. For example, the service provider can capture the user's facial expression with a camera and estimate their emotions using an emotion estimation algorithm. If the user is nervous, it will provide a simple and easy-to-understand response. If the user is relaxed, it will provide a response that includes detailed information. If the user is in a hurry, it will provide a response that can be quickly understood. This allows the service provider to provide the optimal response for the user by adjusting the response delivery method according to the user's emotions. Emotion estimation is achieved using an emotion estimation function, for example, using an emotion engine or generative AI. Generative AI includes, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI.

[0091] The delivery unit can adjust the level of detail provided based on the importance of the response at the time of delivery. For example, the delivery unit can provide detailed information for important responses. It can also provide concise information for less important responses. Furthermore, the delivery unit can select the optimal delivery method based on the importance of the response. For example, the delivery unit can analyze the content of the response and provide detailed information for important responses. It can provide concise information for less important responses. It can select the optimal delivery method based on the importance of the response. In this way, by adjusting the level of detail provided based on the importance of the response, important responses can be provided in detail. Some or all of the above processing in the delivery unit may be performed using AI, for example, or not using AI. For example, the delivery unit can input the importance of the response into the AI ​​and have the AI ​​perform the adjustment of the level of detail provided.

[0092] The service provider can apply different service provision algorithms depending on the category of the response at the time of provision. For example, for travel-related responses, the service provider can provide detailed information about travel. It can also provide detailed information about products for e-commerce site responses. Furthermore, it can provide detailed information about financial products for financial-related responses. For example, for travel-related responses, the service provider can provide detailed information about travel plans and discounts. For e-commerce site responses, it can provide detailed information about product availability and pricing. For financial-related responses, it can provide detailed information about interest rates and conditions for financial products. This allows the service provider to provide the optimal service method by applying different service provision algorithms depending on the category of the response. Some or all of the above processing in the service provider may be performed using AI, for example, or without AI. For example, the service provider can input the response category into the AI ​​and have the AI ​​apply different service provision algorithms.

[0093] The service provider can estimate the user's emotions and determine the priority of responses based on the estimated emotions. For example, if the user is stressed, the service provider will prioritize providing important responses. If the user is relaxed, the service provider can also prioritize providing detailed responses. Furthermore, if the user is in a hurry, the service provider can prioritize providing responses that require quick processing. For example, the service provider can capture the user's facial expression with a camera and estimate their emotions using an emotion estimation algorithm. If the user is stressed, important responses will be prioritized. If the user is relaxed, detailed responses will be prioritized. If the user is in a hurry, responses that require quick processing will be prioritized. This allows for the prioritization of important responses by determining the priority of responses 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 includes, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI.

[0094] The service provider can determine the priority of responses based on their submission timing at the time of delivery. For example, the service provider may prioritize responses submitted earlier. It may also postpone the delivery of responses submitted later. Furthermore, the service provider can determine the optimal delivery order based on the submission timing of responses. For example, the service provider may evaluate the submission dates and times of responses and prioritize responses submitted earlier, postpone the delivery of responses submitted later, or determine the optimal delivery order based on the submission timing of responses. This allows the service provider to prioritize responses submitted earlier by determining the priority of deliveries based on their submission timing. Some or all of the above processing in the service provider may be performed using AI, for example, or not. For example, the service provider can input the submission timing of responses into an AI and have the AI ​​determine the priority of deliveries.

[0095] The service provider can adjust the order of service delivery based on the relevance of the responses. For example, the service provider may prioritize providing highly relevant responses. It may also postpone providing less relevant responses. Furthermore, the service provider can determine the optimal order of service delivery based on the relevance of the responses. For example, the service provider may evaluate the relevance of the responses and prioritize providing highly relevant responses, postpone providing less relevant responses, and determine the optimal order of service delivery based on the relevance of the responses. This allows the service provider to prioritize providing highly relevant responses by adjusting the order of service delivery based on the relevance of the responses. Some or all of the above processing in the service provider may be performed using AI, for example, or without AI. For example, the service provider can input the relevance of the responses into the AI ​​and have the AI ​​perform the adjustment of the order of service delivery.

[0096] The management unit can estimate the user's emotions and adjust the dialogue management method based on the estimated emotions. For example, if the user is nervous, the management unit can provide a simple and easy-to-understand management method. If the user is relaxed, the management unit can also provide a management method that includes detailed information. Furthermore, if the user is in a hurry, the management unit can provide a management method that can be quickly understood. For example, the management unit can capture the user's facial expressions with a camera and estimate their emotions using an emotion estimation algorithm. If the user is nervous, a simple and easy-to-understand management method is provided. If the user is relaxed, a management method that includes detailed information is provided. If the user is in a hurry, a management method that can be quickly understood is provided. This allows for optimal dialogue management for the user by adjusting the dialogue management method according to the user's emotions. Emotion estimation is achieved using an emotion estimation function, for example, using an emotion engine or generative AI. Generative AI includes, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI.

[0097] The management department can analyze the dialogue history between individual AI and corporate AI during management to select the optimal management method. For example, the management department can select the optimal management method based on the past dialogue history between individual AI and corporate AI. The management department can also identify frequently occurring problems from the dialogue history and propose the optimal management method. Furthermore, the management department can analyze the dialogue history and select an efficient management method. For example, the management department can store the past dialogue history between individual AI and corporate AI in a database and select the optimal management method. It can identify frequently occurring problems from the dialogue history and propose the optimal management method. It can analyze the dialogue history and select an efficient management method. In this way, the optimal management method can be selected by analyzing the dialogue history between individual AI and corporate AI. Some or all of the above processes in the management department may be performed using AI, for example, or not using AI. For example, the management department can input the dialogue history into AI and have the AI ​​select the optimal management method.

[0098] The management department can apply different management algorithms depending on the category of individual AI and corporate AI during management. For example, the management department can apply a travel-related management algorithm to travel-related conversations. It can also apply a product-related management algorithm to conversations on e-commerce sites. Furthermore, it can apply a financial product-related management algorithm to conversations on finance. For example, the management department can apply a management algorithm regarding travel plans and discount information to travel-related conversations. For conversations on e-commerce sites, it can apply a management algorithm regarding product inventory status and pricing. For financial conversations, it can apply a management algorithm regarding interest rates and conditions of financial products. In this way, by applying different management algorithms depending on the category of individual AI and corporate AI, the optimal management method can be provided. Some or all of the above processing in the management department may be performed using AI, for example, or not using AI. For example, the management department can input the categories of individual AI and corporate AI into the AI ​​and have the AI ​​execute the application of different management algorithms.

[0099] The management unit can estimate the user's emotions and prioritize conversations based on those emotions. For example, if the user is stressed, the management unit will prioritize important conversations. If the user is relaxed, the management unit can also prioritize detailed conversations. Furthermore, if the user is in a hurry, the management unit can prioritize conversations that require quick processing. For example, the management unit can capture the user's facial expressions with a camera and estimate their emotions using an emotion estimation algorithm. If the user is stressed, important conversations will be prioritized. If the user is relaxed, detailed conversations will be prioritized. If the user is in a hurry, conversations that require quick processing will be prioritized. This allows for prioritizing important conversations based on the user's emotions. Emotion estimation is achieved using emotion estimation functions, such as an emotion engine or generative AI. Generative AI includes, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI.

[0100] The management department can determine the priority of conversations based on the response speed of the individual AI and the corporate AI during management. For example, the management department can prioritize conversations with fast response speeds. It can also postpone the management of conversations with slow response speeds. Furthermore, the management department can determine the optimal order of conversations based on the response speeds of the individual AI and the corporate AI. For example, the management department can monitor the response speeds of the individual AI and the corporate AI in real time and prioritize the management of conversations with fast response speeds. It can postpone the management of conversations with slow response speeds. It can determine the optimal order of conversations based on the response speeds of the individual AI and the corporate AI. In this way, by determining the priority of conversations based on the response speeds of the individual AI and the corporate AI, it is possible to prioritize the management of conversations that require a quick response. Some or all of the above processing in the management department may be performed using AI, for example, or not using AI. For example, the management department can input the response speeds of the individual AI and the corporate AI into the AI ​​and have the AI ​​perform the task of determining the priority of conversations.

[0101] The management department can adjust the order of conversations based on the relationship between the individual AI and the corporate AI during management. For example, the management department can prioritize managing conversations that are highly relevant. It can also postpone managing conversations that are less relevant. Furthermore, the management department can determine the optimal order of conversations based on the relationship between the individual AI and the corporate AI. For example, the management department can evaluate the relationship between the individual AI and the corporate AI and prioritize managing conversations that are highly relevant. It can postpone managing conversations that are less relevant. It can determine the optimal order of conversations based on the relationship between the individual AI and the corporate AI. In this way, by adjusting the order of conversations based on the relationship between the individual AI and the corporate AI, it is possible to prioritize managing conversations that are highly relevant. Some or all of the above processes in the management department may be performed using AI, for example, or not using AI. For example, the management department can input the relationship between the individual AI and the corporate AI into the AI ​​and have the AI ​​perform the adjustment of the order of conversations.

[0102] The system according to the embodiment is not limited to the example described above, and various modifications are possible, for example, as follows.

[0103] The reception system can estimate the user's emotions and adjust how instructions are received based on those emotions. For example, if the user is stressed, it can provide a simple interface and minimize the input steps. If the user is relaxed, it can provide detailed input options and suggest customizable input methods. Furthermore, if the user is in a hurry, it can prioritize voice input to allow for quick instruction input. In this way, by adjusting how instructions are received according to the user's emotions, the system can provide the optimal interface for the user.

[0104] The inquiry department can estimate the user's emotions and adjust the wording of the inquiry based on those emotions. For example, if the user is nervous, it can provide a simple and easy-to-understand expression. If the user is relaxed, it can provide an expression that includes detailed information. Furthermore, if the user is in a hurry, it can provide an expression that can be quickly understood. In this way, by adjusting the wording of the inquiry according to the user's emotions, it is possible to provide the most appropriate inquiry for the user.

[0105] The receiving unit can estimate the user's emotions and adjust the response delivery method based on the estimated emotions. For example, if the user is nervous, it can provide a simple and easy-to-understand response. If the user is relaxed, it can provide a response that includes detailed information. Furthermore, if the user is in a hurry, it can provide a response that can be quickly understood. In this way, by adjusting the response delivery method according to the user's emotions, the user can receive the most optimal response.

[0106] The response system can estimate the user's emotions and adjust the response delivery method based on those estimates. For example, if the user is nervous, it can provide a simple and easy-to-understand response. If the user is relaxed, it can provide a response that includes detailed information. Furthermore, if the user is in a hurry, it can provide a response that can be quickly understood. By adjusting the response delivery method according to the user's emotions, the system can provide the optimal response for the user.

[0107] The management department can estimate the user's emotions and adjust the interaction management method based on those estimates. For example, if the user is nervous, it can provide a simple and easy-to-understand management method. If the user is relaxed, it can provide a management method that includes detailed information. Furthermore, if the user is in a hurry, it can provide a management method that can be quickly understood. In this way, by adjusting the interaction management method according to the user's emotions, optimal interaction management can be achieved for the user.

[0108] The reception desk can analyze a user's past instruction history and select the optimal reception method. For example, it can automatically display instructions that the user has frequently entered in the past as suggestions. It can also prioritize suggesting input methods (voice, text, etc.) that the user has used in the past. Furthermore, it can predict and suggest instructions that the user will use during specific time periods based on their past instruction history. In this way, by analyzing a user's past instruction history, the reception desk can provide the most suitable reception method for the user.

[0109] The reception unit can filter instructions based on the user's current situation or areas of interest. For example, it can prioritize receiving instructions relevant to the user's current situation. It can also filter and receive relevant instructions based on the user's areas of interest. Furthermore, it can suggest the most appropriate instructions based on the user's current situation and areas of interest. This allows for the priority of receiving highly relevant instructions by filtering them based on the user's current situation and areas of interest.

[0110] The inquiry department can adjust the level of detail in inquiries based on the importance of the corporate AI. For example, it can send detailed inquiries to important corporate AIs and concise inquiries to less important ones. Furthermore, it can select the optimal inquiry method based on the importance of the corporate AI. This allows for optimal inquiries by adjusting the level of detail based on the importance of the corporate AI.

[0111] The receiving unit can adjust the level of detail received based on the content of the enterprise AI's response. For example, it can receive detailed information for important responses, and concise information for less important responses. Furthermore, it can select the optimal receiving method based on the content of the enterprise AI's response. This allows for detailed reception of important responses by adjusting the level of detail based on the content of the enterprise AI's response.

[0112] The management department can analyze the dialogue history between individual AI and corporate AI during management to select the optimal management method. For example, it can select the optimal management method based on the past dialogue history of individual AI and corporate AI. It can also identify frequently occurring problems from the dialogue history and propose the optimal management method. Furthermore, it can analyze the dialogue history to select an efficient management method. In this way, the optimal management method can be selected by analyzing the dialogue history of individual AI and corporate AI.

[0113] The following briefly describes the processing flow for example form 2.

[0114] Step 1: The reception desk receives user instructions. User instructions include voice instructions, text instructions, and gesture instructions. The reception desk can receive the user's voice instructions using voice recognition technology, the user's text instructions using a text input interface, and the user's gesture instructions using gesture recognition technology. Step 2: The inquiry department makes inquiries to the corporate AI based on the instructions received by the reception department. The corporate AI includes customer support AI and sales support AI. The inquiry department can send the user's inquiry to the corporate AI and can also make inquiries to multiple corporate AIs simultaneously. Step 3: The receiving unit receives responses from the enterprise AI. These responses include text responses, voice responses, and image responses. The receiving unit receives text-based responses, converts voice-based responses to text using speech recognition technology, and understands the content of image-based responses using image analysis technology. Step 4: The providing unit analyzes the response received by the receiving unit and provides it to the user. The providing unit can display the response in text format to the user, play the response in audio format to the user, or display the response in image format to the user. Step 5: The management department manages the conversations between the personal AI and the enterprise AI. The management department monitors the progress of the conversations, adjusts them as needed, records the conversation history for later reference, and analyzes the content of the conversations to identify areas for improvement.

[0115] 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.

[0116] 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.

[0117] 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.

[0118] Each of the multiple elements described above, including the reception unit, inquiry unit, receiving unit, provision unit, and management 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 control unit 46A of the smart device 14 and receives voice and text instructions from the user. The inquiry unit is implemented by the specific processing unit 290 of the data processing unit 12 and makes inquiries to the corporate AI based on the user's instructions. The receiving unit is implemented by the control unit 46A of the smart device 14 and receives responses from the corporate AI. The provision unit is implemented by the control unit 46A of the smart device 14 and provides the user with the responses from the receiving unit. The management unit is implemented by the specific processing unit 290 of the data processing unit 12 and manages the dialogue between the personal AI and the corporate AI. The correspondence between each unit and the device or control unit is not limited to the example described above and can be changed in various ways.

[0119] [Second Embodiment] Figure 3 shows an example of the configuration of the data processing system 210 according to the second embodiment.

[0120] 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.

[0121] 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.

[0122] 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.

[0123] 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.

[0124] 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).

[0125] 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.

[0126] 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.

[0127] 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.

[0128] 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.

[0129] 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.

[0130] 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.).

[0131] 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.

[0132] 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.

[0133] 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.

[0134] Each of the multiple elements described above, including the reception unit, inquiry unit, receiving unit, provision unit, and management 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 control unit 46A of the smart glasses 214 and receives voice and text instructions from the user. The inquiry unit is implemented by the specific processing unit 290 of the data processing unit 12 and makes inquiries to the corporate AI based on the user's instructions. The receiving unit is implemented by the control unit 46A of the smart glasses 214 and receives responses from the corporate AI. The provision unit is implemented by the control unit 46A of the smart glasses 214 and provides the user with the responses from the receiving unit. The management unit is implemented by the specific processing unit 290 of the data processing unit 12 and manages the dialogue between the personal AI and the corporate AI. The correspondence between each unit and the device or control unit is not limited to the example described above and can be changed in various ways.

[0135] [Third Embodiment] Figure 5 shows an example of the configuration of the data processing system 310 according to the third embodiment.

[0136] 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.

[0137] 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.

[0138] 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.

[0139] 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.

[0140] 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).

[0141] 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.

[0142] 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.

[0143] 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.

[0144] 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.

[0145] 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.

[0146] 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.).

[0147] 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.

[0148] 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.

[0149] 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.

[0150] Each of the multiple elements described above, including the reception unit, inquiry unit, receiving unit, provision unit, and management unit, is implemented by, for example, at least one of the headset terminal 314 and the data processing unit 12. For example, the reception unit is implemented by the control unit 46A of the headset terminal 314 and receives voice and text instructions from the user. The inquiry unit is implemented by, for example, the specific processing unit 290 of the data processing unit 12 and makes inquiries to the corporate AI based on the user's instructions. The receiving unit is implemented by, for example, the control unit 46A of the headset terminal 314 and receives responses from the corporate AI. The provision unit is implemented by, for example, the control unit 46A of the headset terminal 314 and provides the user with the responses from the receiving unit. The management unit is implemented by, for example, the specific processing unit 290 of the data processing unit 12 and manages the dialogue between the personal AI and the corporate AI. The correspondence between each unit and the device or control unit is not limited to the example described above and can be changed in various ways.

[0151] [Fourth Embodiment] Figure 7 shows an example of the configuration of the data processing system 410 according to the fourth embodiment.

[0152] 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.

[0153] 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.

[0154] 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.

[0155] 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.

[0156] 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).

[0157] 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.

[0158] 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.

[0159] 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.

[0160] 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.

[0161] 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.

[0162] 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.

[0163] 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.).

[0164] 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.

[0165] 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.

[0166] 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.

[0167] Each of the multiple elements described above, including the reception unit, inquiry unit, receiving unit, provision unit, and management unit, is implemented by, for example, at least one of the robot 414 and the data processing unit 12. For example, the reception unit is implemented by the control unit 46A of the robot 414 and receives voice and text instructions from the user. The inquiry unit is implemented by, for example, the specific processing unit 290 of the data processing unit 12 and makes inquiries to the corporate AI based on the user's instructions. The receiving unit is implemented by, for example, the control unit 46A of the robot 414 and receives responses from the corporate AI. The provision unit is implemented by, for example, the control unit 46A of the robot 414 and provides the user with the responses from the receiving unit. The management unit is implemented by, for example, the specific processing unit 290 of the data processing unit 12 and manages the dialogue between the personal AI and the corporate AI. The correspondence between each unit and the devices and control units is not limited to the example described above and can be changed in various ways.

[0168] 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.

[0169] 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.

[0170] 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.

[0171] 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.

[0172] 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.

[0173] 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."

[0174] 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.

[0175] 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.

[0176] 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.

[0177] 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.

[0178] 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.

[0179] 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.

[0180] 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.

[0181] 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.

[0182] 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.

[0183] 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.

[0184] 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.

[0185] 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.

[0186] (Note 1) A reception desk that takes user instructions, The inquiry department makes inquiries to the corporate AI based on the instructions received by the aforementioned reception department, A receiving unit that receives a response from the aforementioned company's AI, A providing unit analyzes the response received by the receiving unit and provides it to the user, The system comprises a management unit that manages the dialogue of the aforementioned corporate AI. A system characterized by the following features. (Note 2) 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 3) The aforementioned reception unit is Analyze the user's past instruction history and select the appropriate method of receiving the request. The system described in Appendix 1, characterized by the features described herein. (Note 4) The aforementioned reception unit is When receiving instructions, filtering is performed based on the user's current situation or areas of interest. The system described in Appendix 1, characterized by the features described herein. (Note 5) The aforementioned reception unit is It estimates the user's emotions and determines the priority of instructions to accept based on the estimated user emotions. The system described in Appendix 1, characterized by the features described herein. (Note 6) The aforementioned reception unit is When receiving instructions, the system prioritizes receiving instructions that are highly relevant based on the user's geographical location. The system described in Appendix 1, characterized by the features described herein. (Note 7) The aforementioned reception unit is When receiving instructions, the system analyzes the user's social media activity and accepts relevant instructions. The system described in Appendix 1, characterized by the features described herein. (Note 8) The aforementioned inquiry section is, It estimates the user's emotions and adjusts the wording of inquiries based on those estimated emotions. The system described in Appendix 1, characterized by the features described herein. (Note 9) The aforementioned inquiry section is, When an inquiry is made, the level of detail of the inquiry is adjusted based on the importance level of the company's AI. The system described in Appendix 1, characterized by the features described herein. (Note 10) The aforementioned inquiry section is, When an inquiry is made, different inquiry algorithms are applied depending on the category of the company's AI. The system described in Appendix 1, characterized by the features described herein. (Note 11) The aforementioned inquiry section is, It estimates the user's sentiment and adjusts the length of the inquiry based on the estimated user sentiment. The system described in Appendix 1, characterized by the features described herein. (Note 12) The aforementioned inquiry section is, When an inquiry is made, the company's AI determines the priority of the inquiry based on its response speed. The system described in Appendix 1, characterized by the features described herein. (Note 13) The aforementioned inquiry section is, When an inquiry is made, the order of inquiries is adjusted based on the company's AI's relevance. The system described in Appendix 1, characterized by the features described herein. (Note 14) The receiving unit is It estimates the user's emotions and adjusts how responses are received based on those estimated emotions. The system described in Appendix 1, characterized by the features described herein. (Note 15) The receiving unit is Upon receiving data, the level of detail of the received data is adjusted based on the content of the company's AI response. The system described in Appendix 1, characterized by the features described herein. (Note 16) The receiving unit is When receiving data, different receiving algorithms are applied depending on the category of the enterprise AI. The system described in Appendix 1, characterized by the features described herein. (Note 17) The receiving unit is It estimates the user's emotions and determines the priority of the responses it receives based on those estimated emotions. The system described in Appendix 1, characterized by the features described herein. (Note 18) The receiving unit is Upon receiving data, the company's AI determines the priority of receiving data based on its response speed. The system described in Appendix 1, characterized by the features described herein. (Note 19) The receiving unit is Upon receiving data, the company's AI determines the priority of receiving data based on its response speed. The system described in Appendix 1, characterized by the features described herein. (Note 20) The receiving unit is When receiving data, the order of reception is adjusted based on the relevance of the company's AI. The system described in Appendix 1, characterized by the features described herein. (Note 21) The aforementioned supply unit is, It estimates the user's emotions and adjusts the way responses are delivered based on those estimated emotions. The system described in Appendix 1, characterized by the features described herein. (Note 22) The aforementioned supply unit is, When providing the response, adjust the level of detail based on the importance of the response. The system described in Appendix 1, characterized by the features described herein. (Note 23) The aforementioned supply unit is, When providing data, different delivery algorithms are applied depending on the response category. The system described in Appendix 1, characterized by the features described herein. (Note 24) The aforementioned supply unit is, It estimates the user's emotions and determines the priority of the response to provide based on the estimated user emotions. The system described in Appendix 1, characterized by the features described herein. (Note 25) The aforementioned supply unit is, When providing the service, we will prioritize the delivery based on the timing of the response submission. The system described in Appendix 1, characterized by the features described herein. (Note 26) The aforementioned supply unit is, When providing responses, the order of delivery will be adjusted based on the relevance of the responses. The system described in Appendix 1, characterized by the features described herein. (Note 27) The aforementioned management department, It estimates the user's emotions and adjusts how the interaction is managed based on those estimated emotions. The system described in Appendix 1, characterized by the features described herein. (Note 28) The aforementioned management department, During management, the interaction history between personal AI and corporate AI is analyzed to select the appropriate management method. The system described in Appendix 1, characterized by the features described herein. (Note 29) The aforementioned management department, During management, different management algorithms are applied depending on whether the AI ​​is a personal or corporate AI. The system described in Appendix 1, characterized by the features described herein. (Note 30) The aforementioned management department, It estimates the user's emotions and determines the priority of the conversation based on the estimated user emotions. The system described in Appendix 1, characterized by the features described herein. (Note 31) The aforementioned management department, During management, the priority of conversations is determined based on the response speed of personal AI and enterprise AI. The system described in Appendix 1, characterized by the features described herein. (Note 32) The aforementioned management department, During management, the order of conversations is adjusted based on the relationship between personal AI and enterprise AI. The system described in Appendix 1, characterized by the features described herein. [Explanation of Symbols]

[0187] 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 area that takes user instructions, An inquiry department that makes inquiries to the corporate AI based on instructions received by the aforementioned reception department, A receiving unit that receives responses from the aforementioned company's AI, A providing unit analyzes the response received by the receiving unit and provides it to the user, The system comprises a management unit that manages the dialogue of the aforementioned corporate AI. A system characterized by the following features.

2. 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.

3. The aforementioned reception unit is Analyze the user's past instruction history and select the appropriate method of receiving the request. The system according to feature 1.

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

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

6. The aforementioned reception unit is When receiving instructions, the system prioritizes receiving instructions that are highly relevant based on the user's geographical location. The system according to feature 1.

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

8. The aforementioned inquiry section is, It estimates the user's emotions and adjusts the wording of inquiries based on those estimated emotions. The system according to feature 1.

9. The aforementioned inquiry section is, When you make an inquiry, the level of detail in the inquiry will be adjusted based on the importance level determined by the company's AI. The system according to feature 1.

Images